| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
78a76f2f-9a57-478f-917f-177ead939fab |
2026/09/03 12:52:40 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279965.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279965.0 (TID 279965) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fda05241-2687-493b-abb3-bc4c075fa5d1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279965.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279965.0 (TID 279965) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fda05241-2687-493b-abb3-bc4c075fa5d1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fda05241-2687-493b-abb3-bc4c075fa5d1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
d15ddfd2-2085-48a5-acc8-8cb4324ca802 |
2026/09/03 12:52:40 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279966.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279966.0 (TID 279966) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-349ceb2d-768b-45d8-b010-553eed419bb5-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279966.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279966.0 (TID 279966) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-349ceb2d-768b-45d8-b010-553eed419bb5-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-349ceb2d-768b-45d8-b010-553eed419bb5-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
2e313b11-09bc-4d10-9f45-f7f6c8ee5e57 |
2026/09/03 12:52:40 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279967.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279967.0 (TID 279967) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a7229153-c666-4639-9452-83b058abe256-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279967.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279967.0 (TID 279967) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a7229153-c666-4639-9452-83b058abe256-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a7229153-c666-4639-9452-83b058abe256-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
ad626573-5525-4255-bf62-4c5b1d6db98a |
2026/09/03 12:52:40 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279968.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279968.0 (TID 279968) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-06bc79be-3040-4396-a9f5-17dd7d6185ce-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279968.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279968.0 (TID 279968) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-06bc79be-3040-4396-a9f5-17dd7d6185ce-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-06bc79be-3040-4396-a9f5-17dd7d6185ce-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
d765efb2-7e6f-4552-9a8d-eff027fefbcb |
2026/09/03 12:52:40 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279969.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279969.0 (TID 279969) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-34155d33-ad88-4595-8912-3d888c0184ab-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279969.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279969.0 (TID 279969) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-34155d33-ad88-4595-8912-3d888c0184ab-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-34155d33-ad88-4595-8912-3d888c0184ab-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
e0270a8a-27cf-4e1a-956b-012321af0c13 |
2026/09/03 12:52:40 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279970.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279970.0 (TID 279970) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-32f55174-b5b6-461a-841a-ba2413093c20-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279970.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279970.0 (TID 279970) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-32f55174-b5b6-461a-841a-ba2413093c20-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-32f55174-b5b6-461a-841a-ba2413093c20-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
693a8365-cd92-441d-bba2-43a4f5ff47b9 |
2026/09/03 12:52:40 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279971.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279971.0 (TID 279971) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c836fe00-23da-4acb-aa58-b421bf191cb1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279971.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279971.0 (TID 279971) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c836fe00-23da-4acb-aa58-b421bf191cb1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c836fe00-23da-4acb-aa58-b421bf191cb1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
c743829f-4d78-441f-b9ce-bcfd9d13afc3 |
2026/09/03 12:52:40 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279972.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279972.0 (TID 279972) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8f96eb76-477e-481c-9b92-5840133272a6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279972.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279972.0 (TID 279972) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8f96eb76-477e-481c-9b92-5840133272a6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8f96eb76-477e-481c-9b92-5840133272a6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
14868410-4dd5-4957-90d5-000db5416350 |
2026/09/03 12:52:40 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279973.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279973.0 (TID 279973) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9e6a9a77-36f0-45a8-a62f-82071c4b1e1c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279973.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279973.0 (TID 279973) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9e6a9a77-36f0-45a8-a62f-82071c4b1e1c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9e6a9a77-36f0-45a8-a62f-82071c4b1e1c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
b2bbde86-f4a7-4d35-be53-61756bad5f33 |
2026/09/03 12:52:40 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279974.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279974.0 (TID 279974) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-af547d45-d606-46da-b718-a93c7716abae-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279974.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279974.0 (TID 279974) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-af547d45-d606-46da-b718-a93c7716abae-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-af547d45-d606-46da-b718-a93c7716abae-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
2e27e484-6327-48c4-9312-620b8d07b35c |
2026/09/03 12:52:40 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279975.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279975.0 (TID 279975) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3d0b6fb4-9bab-478b-8c4a-c891a5e30a45-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279975.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279975.0 (TID 279975) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3d0b6fb4-9bab-478b-8c4a-c891a5e30a45-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3d0b6fb4-9bab-478b-8c4a-c891a5e30a45-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
ed656470-9c2f-44e7-9dc6-202566dfffd7 |
2026/09/03 12:52:40 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279976.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279976.0 (TID 279976) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-bd6c3089-77ba-4733-8535-4baf6aa1fea2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279976.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279976.0 (TID 279976) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-bd6c3089-77ba-4733-8535-4baf6aa1fea2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-bd6c3089-77ba-4733-8535-4baf6aa1fea2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
9ecc3408-6623-4837-a6cd-58d39a5233fd |
2026/09/03 12:52:40 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279977.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279977.0 (TID 279977) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7f239f05-e27e-4eb2-a7b9-0408bf764b5f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279977.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279977.0 (TID 279977) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7f239f05-e27e-4eb2-a7b9-0408bf764b5f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7f239f05-e27e-4eb2-a7b9-0408bf764b5f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
78557a4b-3b19-46cf-8ee3-645f32156af5 |
2026/09/03 12:52:40 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279978.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279978.0 (TID 279978) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-093c3803-7ff1-4b3e-bf68-2a7265c24324-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279978.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279978.0 (TID 279978) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-093c3803-7ff1-4b3e-bf68-2a7265c24324-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-093c3803-7ff1-4b3e-bf68-2a7265c24324-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
69526c0d-9ec2-4422-aa41-64be8569bfd0 |
2026/09/03 12:52:40 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279979.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279979.0 (TID 279979) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-95c2adb2-1172-4d49-9f78-b5a8f0eacb2d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279979.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279979.0 (TID 279979) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-95c2adb2-1172-4d49-9f78-b5a8f0eacb2d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-95c2adb2-1172-4d49-9f78-b5a8f0eacb2d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
c5722430-cc0e-438a-87ec-000669f3bb04 |
2026/09/03 12:52:40 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279980.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279980.0 (TID 279980) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e7f61440-8e1b-4efd-ac49-01141f91189c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279980.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279980.0 (TID 279980) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e7f61440-8e1b-4efd-ac49-01141f91189c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e7f61440-8e1b-4efd-ac49-01141f91189c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
d4c416d8-117f-419b-bbc1-4427f128420a |
2026/09/03 12:52:40 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279981.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279981.0 (TID 279981) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9b747c53-ee73-4bd4-a2c3-3fe62fd3046e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279981.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279981.0 (TID 279981) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9b747c53-ee73-4bd4-a2c3-3fe62fd3046e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9b747c53-ee73-4bd4-a2c3-3fe62fd3046e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
303663a3-c6af-4811-9628-3cf4795d1887 |
2026/09/03 12:52:40 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279982.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279982.0 (TID 279982) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-601fb6fe-6a9b-416e-8553-2e292d17559d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279982.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279982.0 (TID 279982) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-601fb6fe-6a9b-416e-8553-2e292d17559d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-601fb6fe-6a9b-416e-8553-2e292d17559d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
118d0873-f6c0-4454-9713-062be2126344 |
2026/09/03 12:52:40 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279983.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279983.0 (TID 279983) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a8fdf592-3a7b-4bba-90c4-961263ecddc6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279983.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279983.0 (TID 279983) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a8fdf592-3a7b-4bba-90c4-961263ecddc6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a8fdf592-3a7b-4bba-90c4-961263ecddc6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
ffdeb333-2136-413d-a00d-4427e3c445f0 |
2026/09/03 12:52:40 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279984.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279984.0 (TID 279984) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-af46a0c0-cf98-4c5d-a000-4a792bdb191c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279984.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279984.0 (TID 279984) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-af46a0c0-cf98-4c5d-a000-4a792bdb191c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-af46a0c0-cf98-4c5d-a000-4a792bdb191c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
2f98f9d3-45d8-4911-8982-3ec1b06cddab |
2026/09/03 12:52:40 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279985.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279985.0 (TID 279985) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-871e9c1a-63ec-446a-9819-ffe17ce537d1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279985.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279985.0 (TID 279985) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-871e9c1a-63ec-446a-9819-ffe17ce537d1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-871e9c1a-63ec-446a-9819-ffe17ce537d1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
a726bb71-c67c-4c59-af7d-04fcca6ebfd2 |
2026/09/03 12:52:41 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279986.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279986.0 (TID 279986) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b4e0570f-bfab-4856-801e-e812cef54bae-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279986.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279986.0 (TID 279986) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b4e0570f-bfab-4856-801e-e812cef54bae-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b4e0570f-bfab-4856-801e-e812cef54bae-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
f4c845a6-598b-42ec-9656-6cdc0c48cee9 |
2026/09/03 12:52:41 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279987.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279987.0 (TID 279987) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f632b19c-7314-4618-8f7f-e286f1b93fb7-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279987.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279987.0 (TID 279987) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f632b19c-7314-4618-8f7f-e286f1b93fb7-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f632b19c-7314-4618-8f7f-e286f1b93fb7-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
2da1d770-5248-45ce-a8b8-e02e8a6df13c |
2026/09/03 12:52:41 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279988.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279988.0 (TID 279988) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ee364c98-1151-47e5-bfbb-faf282cd9f15-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279988.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279988.0 (TID 279988) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ee364c98-1151-47e5-bfbb-faf282cd9f15-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ee364c98-1151-47e5-bfbb-faf282cd9f15-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
4f11c294-5502-427f-94d9-b14bad0f78b6 |
2026/09/03 12:52:41 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279989.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279989.0 (TID 279989) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-99e3b262-eb4c-4b51-ba7c-c5d444f68b07-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279989.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279989.0 (TID 279989) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-99e3b262-eb4c-4b51-ba7c-c5d444f68b07-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-99e3b262-eb4c-4b51-ba7c-c5d444f68b07-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
a075b137-43c2-44da-8049-eafab5fdcffe |
2026/09/03 12:52:41 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279990.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279990.0 (TID 279990) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-76815bd7-ddbe-49b0-99cd-1d0dd6d9c7d0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279990.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279990.0 (TID 279990) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-76815bd7-ddbe-49b0-99cd-1d0dd6d9c7d0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-76815bd7-ddbe-49b0-99cd-1d0dd6d9c7d0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
8963b79d-23d7-47c4-a7ea-ef6ea75e8114 |
2026/09/03 12:52:41 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279991.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279991.0 (TID 279991) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f2c69b54-c019-4804-b518-e046cf8cafc6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279991.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279991.0 (TID 279991) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f2c69b54-c019-4804-b518-e046cf8cafc6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f2c69b54-c019-4804-b518-e046cf8cafc6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
726aa691-99f6-4ce1-a55f-221c73ea23e7 |
2026/09/03 12:52:41 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279992.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279992.0 (TID 279992) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-cb7edde0-1ac9-4199-9029-44ffd0dbd954-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279992.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279992.0 (TID 279992) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-cb7edde0-1ac9-4199-9029-44ffd0dbd954-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-cb7edde0-1ac9-4199-9029-44ffd0dbd954-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
6a05fba0-4f74-40e9-98b9-886f11051c15 |
2026/09/03 12:52:41 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279993.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279993.0 (TID 279993) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5ef2f4ad-4dad-4890-aa2d-ee06971174ec-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279993.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279993.0 (TID 279993) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5ef2f4ad-4dad-4890-aa2d-ee06971174ec-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5ef2f4ad-4dad-4890-aa2d-ee06971174ec-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
6ac254d3-f422-4e66-9949-5eceba395f81 |
2026/09/03 12:52:41 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279994.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279994.0 (TID 279994) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-edf2e248-34bd-4c5b-ab1f-88b07d0a3a74-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279994.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279994.0 (TID 279994) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-edf2e248-34bd-4c5b-ab1f-88b07d0a3a74-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-edf2e248-34bd-4c5b-ab1f-88b07d0a3a74-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
c96ea8a3-be5e-4993-9370-401f2aeab085 |
2026/09/03 12:52:41 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279995.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279995.0 (TID 279995) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-49d9a091-c44a-4a13-b8e5-da1294538030-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279995.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279995.0 (TID 279995) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-49d9a091-c44a-4a13-b8e5-da1294538030-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-49d9a091-c44a-4a13-b8e5-da1294538030-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
3bf70705-3465-4c49-87c9-b47628a358b3 |
2026/09/03 12:52:41 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279996.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279996.0 (TID 279996) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2f226fc3-feaa-47ea-9c99-8ac2d2339f62-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279996.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279996.0 (TID 279996) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2f226fc3-feaa-47ea-9c99-8ac2d2339f62-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2f226fc3-feaa-47ea-9c99-8ac2d2339f62-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
f701e6f7-97a3-4bd4-a90b-b7be099e6aa8 |
2026/09/03 12:52:41 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279997.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279997.0 (TID 279997) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ef092cfd-299f-402e-aae8-67a4536592d7-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279997.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279997.0 (TID 279997) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ef092cfd-299f-402e-aae8-67a4536592d7-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ef092cfd-299f-402e-aae8-67a4536592d7-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
2a406b56-30ee-42a7-8481-a5151d89e2cb |
2026/09/03 12:52:41 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279998.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279998.0 (TID 279998) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-aa962413-0c14-4fb3-9073-c94015573319-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279998.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279998.0 (TID 279998) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-aa962413-0c14-4fb3-9073-c94015573319-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-aa962413-0c14-4fb3-9073-c94015573319-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
87c3ffa5-0d55-40e2-b9b0-913f0e5ed5cb |
2026/09/03 12:52:41 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279999.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279999.0 (TID 279999) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e0c8e1be-8060-4e9a-ae69-90aa2bd7da73-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 279999.0 failed 1 times, most recent failure: Lost task 0.0 in stage 279999.0 (TID 279999) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e0c8e1be-8060-4e9a-ae69-90aa2bd7da73-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e0c8e1be-8060-4e9a-ae69-90aa2bd7da73-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
b21db075-f68d-4853-8bc0-3e1dfaa61411 |
2026/09/03 12:52:41 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280000.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280000.0 (TID 280000) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0ccd1c50-55e0-4254-8cfe-eb66a3422579-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280000.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280000.0 (TID 280000) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0ccd1c50-55e0-4254-8cfe-eb66a3422579-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0ccd1c50-55e0-4254-8cfe-eb66a3422579-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
7f5ab3c3-5d58-4fc7-b50b-ec6d401b1841 |
2026/09/03 12:52:41 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280001.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280001.0 (TID 280001) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6c958266-7767-4c63-88d5-692fca6d73a8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280001.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280001.0 (TID 280001) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6c958266-7767-4c63-88d5-692fca6d73a8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6c958266-7767-4c63-88d5-692fca6d73a8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
2ff526bc-38a4-4fc9-8098-6bbbc3197575 |
2026/09/03 12:52:41 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280002.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280002.0 (TID 280002) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8b57070c-e35e-4e7f-8030-5f2c688283b4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280002.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280002.0 (TID 280002) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8b57070c-e35e-4e7f-8030-5f2c688283b4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8b57070c-e35e-4e7f-8030-5f2c688283b4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
12ff2608-4bae-453a-afef-1651783b0371 |
2026/09/03 12:52:41 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280003.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280003.0 (TID 280003) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-02aa3abd-d4ab-4329-af25-c62dfefdb615-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280003.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280003.0 (TID 280003) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-02aa3abd-d4ab-4329-af25-c62dfefdb615-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-02aa3abd-d4ab-4329-af25-c62dfefdb615-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
eaa4c33a-4bf9-422a-a3b8-b7228176c8bc |
2026/09/03 12:52:41 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280004.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280004.0 (TID 280004) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-535a15ff-d993-48e6-b639-16fee3dce241-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280004.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280004.0 (TID 280004) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-535a15ff-d993-48e6-b639-16fee3dce241-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-535a15ff-d993-48e6-b639-16fee3dce241-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
6d3608c2-a7cb-4969-8447-624415e36254 |
2026/09/03 12:52:41 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280005.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280005.0 (TID 280005) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f157391d-dc22-4a53-8687-ed6192efc8d8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280005.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280005.0 (TID 280005) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f157391d-dc22-4a53-8687-ed6192efc8d8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f157391d-dc22-4a53-8687-ed6192efc8d8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
4fd37281-c787-4f8b-ac2c-3d2a2f59dfa1 |
2026/09/03 12:52:41 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280006.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280006.0 (TID 280006) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6f246a7d-9fa6-4c2e-ae5b-8a94da824edb-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280006.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280006.0 (TID 280006) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6f246a7d-9fa6-4c2e-ae5b-8a94da824edb-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6f246a7d-9fa6-4c2e-ae5b-8a94da824edb-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
1941d1ab-4575-4d57-a28c-f2fbbdf69758 |
2026/09/03 12:52:42 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280007.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280007.0 (TID 280007) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8f6b731d-8e83-46d3-9c3a-c1a4ec254e62-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280007.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280007.0 (TID 280007) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8f6b731d-8e83-46d3-9c3a-c1a4ec254e62-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8f6b731d-8e83-46d3-9c3a-c1a4ec254e62-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
757ef9f6-c3f8-4244-ada5-0332aabda714 |
2026/09/03 12:52:42 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280008.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280008.0 (TID 280008) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f0707286-9966-45e8-bd30-318718084473-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280008.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280008.0 (TID 280008) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f0707286-9966-45e8-bd30-318718084473-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f0707286-9966-45e8-bd30-318718084473-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
dc779965-bb51-49b6-b5b2-fabd650d0560 |
2026/09/03 12:52:42 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280009.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280009.0 (TID 280009) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-af002c3d-fac4-45b7-9e27-05aa1b3299db-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280009.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280009.0 (TID 280009) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-af002c3d-fac4-45b7-9e27-05aa1b3299db-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-af002c3d-fac4-45b7-9e27-05aa1b3299db-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
efd2e0c7-9aed-441d-b626-6da6bf50eb11 |
2026/09/03 12:52:42 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280010.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280010.0 (TID 280010) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c6cb2042-7da8-476c-beca-fd44282b86e9-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280010.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280010.0 (TID 280010) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c6cb2042-7da8-476c-beca-fd44282b86e9-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c6cb2042-7da8-476c-beca-fd44282b86e9-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
23d8ddb2-421d-4d1a-a2b5-202e9bb45ba1 |
2026/09/03 12:52:42 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280011.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280011.0 (TID 280011) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fb0e85d1-d39c-4ad2-88cf-4aeb2ac30384-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280011.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280011.0 (TID 280011) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fb0e85d1-d39c-4ad2-88cf-4aeb2ac30384-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fb0e85d1-d39c-4ad2-88cf-4aeb2ac30384-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
9105949b-0d51-4e86-bec9-f2f78d750fe5 |
2026/09/03 12:52:42 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280012.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280012.0 (TID 280012) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-83f2701b-5af4-4626-b72f-ede0a7672ac3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280012.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280012.0 (TID 280012) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-83f2701b-5af4-4626-b72f-ede0a7672ac3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-83f2701b-5af4-4626-b72f-ede0a7672ac3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
fca11cc8-f8f1-474d-90ba-982489a1189d |
2026/09/03 12:52:42 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280013.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280013.0 (TID 280013) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-30f295e6-619b-40b0-9664-5ce1ea8ebb22-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280013.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280013.0 (TID 280013) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-30f295e6-619b-40b0-9664-5ce1ea8ebb22-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-30f295e6-619b-40b0-9664-5ce1ea8ebb22-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
f0f85809-bac4-4ec5-b95a-a0f1e4984536 |
2026/09/03 12:52:42 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280014.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280014.0 (TID 280014) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3fa6b071-c468-4420-a622-74a53a7c6113-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280014.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280014.0 (TID 280014) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3fa6b071-c468-4420-a622-74a53a7c6113-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3fa6b071-c468-4420-a622-74a53a7c6113-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
40d015e8-8c62-47f4-9879-512e88ff8bf0 |
2026/09/03 12:52:42 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280015.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280015.0 (TID 280015) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f71ddeba-7e34-4c4d-a362-f855115e6b29-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280015.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280015.0 (TID 280015) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f71ddeba-7e34-4c4d-a362-f855115e6b29-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f71ddeba-7e34-4c4d-a362-f855115e6b29-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
326e456b-1a31-4414-b74b-18018b1f2e20 |
2026/09/03 12:52:42 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280016.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280016.0 (TID 280016) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-42869aea-2746-444c-9c76-269ffd4f4cdd-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280016.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280016.0 (TID 280016) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-42869aea-2746-444c-9c76-269ffd4f4cdd-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-42869aea-2746-444c-9c76-269ffd4f4cdd-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
6ce586d5-1da4-4de7-9287-7a8d9e5a68ec |
2026/09/03 12:52:42 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280017.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280017.0 (TID 280017) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d8bfd1a6-de7b-4c67-a99b-6557e346c6a5-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280017.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280017.0 (TID 280017) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d8bfd1a6-de7b-4c67-a99b-6557e346c6a5-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d8bfd1a6-de7b-4c67-a99b-6557e346c6a5-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
8a307dd2-e5b5-4e57-8ccf-96071de8f8a0 |
2026/09/03 12:52:42 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280018.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280018.0 (TID 280018) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-308451cf-1858-4acc-801d-197ca343e781-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280018.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280018.0 (TID 280018) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-308451cf-1858-4acc-801d-197ca343e781-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-308451cf-1858-4acc-801d-197ca343e781-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
a5c01d95-6f35-4cf3-a4f3-563c3a287e8d |
2026/09/03 12:52:42 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280019.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280019.0 (TID 280019) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2fd03f50-0719-4c9b-973f-a46a96f8c49d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280019.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280019.0 (TID 280019) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2fd03f50-0719-4c9b-973f-a46a96f8c49d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2fd03f50-0719-4c9b-973f-a46a96f8c49d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
70f67df9-b4f9-4d4a-89f9-48834159a307 |
2026/09/03 12:52:42 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280020.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280020.0 (TID 280020) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4f35763d-7953-4fb8-83a2-97bcb5b36608-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280020.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280020.0 (TID 280020) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4f35763d-7953-4fb8-83a2-97bcb5b36608-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4f35763d-7953-4fb8-83a2-97bcb5b36608-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
3e73ff52-44f4-4392-b3c5-449f85faecdc |
2026/09/03 12:52:42 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280021.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280021.0 (TID 280021) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-45acd707-8fce-4f42-bbb2-c2d493219774-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280021.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280021.0 (TID 280021) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-45acd707-8fce-4f42-bbb2-c2d493219774-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-45acd707-8fce-4f42-bbb2-c2d493219774-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
7d57e9ef-0032-471e-96c9-ff881aeb09ef |
2026/09/03 12:52:42 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280022.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280022.0 (TID 280022) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d84a828e-6c67-4d82-aad4-99f0e8c4e477-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280022.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280022.0 (TID 280022) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d84a828e-6c67-4d82-aad4-99f0e8c4e477-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d84a828e-6c67-4d82-aad4-99f0e8c4e477-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
3eff13e4-1e9e-41d4-af13-af7ff7dab71d |
2026/09/03 12:52:42 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280023.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280023.0 (TID 280023) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1bb45d86-ee9d-4b26-a49a-81d5c9682be1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280023.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280023.0 (TID 280023) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1bb45d86-ee9d-4b26-a49a-81d5c9682be1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1bb45d86-ee9d-4b26-a49a-81d5c9682be1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
34ca4501-825d-4768-9075-c973db6b41b8 |
2026/09/03 12:52:42 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280024.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280024.0 (TID 280024) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6f7c1fbb-0884-4ec7-94e9-92be52bb69c7-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280024.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280024.0 (TID 280024) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6f7c1fbb-0884-4ec7-94e9-92be52bb69c7-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6f7c1fbb-0884-4ec7-94e9-92be52bb69c7-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
3ad21355-3a93-4b69-8b04-899b9a1da3eb |
2026/09/03 12:52:42 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280025.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280025.0 (TID 280025) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6a0ecb78-ffb0-465c-a404-02bdfbe1c1f0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280025.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280025.0 (TID 280025) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6a0ecb78-ffb0-465c-a404-02bdfbe1c1f0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6a0ecb78-ffb0-465c-a404-02bdfbe1c1f0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
acbb2f29-c8a6-47c6-93a1-a5b5f867d48c |
2026/09/03 12:52:42 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280026.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280026.0 (TID 280026) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-51f08025-6781-4209-b09b-e3959805ca10-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280026.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280026.0 (TID 280026) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-51f08025-6781-4209-b09b-e3959805ca10-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-51f08025-6781-4209-b09b-e3959805ca10-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
0d471645-3ee6-4684-934e-c9d6776e0b7b |
2026/09/03 12:52:42 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280027.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280027.0 (TID 280027) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c47b89c7-ef54-4715-9a61-e458649420b5-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280027.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280027.0 (TID 280027) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c47b89c7-ef54-4715-9a61-e458649420b5-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c47b89c7-ef54-4715-9a61-e458649420b5-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
f2f3e57d-ab88-4426-860d-29fccdeef30f |
2026/09/03 12:52:42 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280028.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280028.0 (TID 280028) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-82563d34-9a16-4389-81af-6e6f3c17a00e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280028.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280028.0 (TID 280028) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-82563d34-9a16-4389-81af-6e6f3c17a00e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-82563d34-9a16-4389-81af-6e6f3c17a00e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
30fd633d-1ea6-4e51-91c2-2b94d6b5fd76 |
2026/09/03 12:52:42 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280029.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280029.0 (TID 280029) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4099a2e8-2934-4c64-a198-ae4512d93f18-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280029.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280029.0 (TID 280029) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4099a2e8-2934-4c64-a198-ae4512d93f18-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4099a2e8-2934-4c64-a198-ae4512d93f18-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
5c048efe-5832-4a02-937e-fe715e9ee665 |
2026/09/03 12:52:42 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280030.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280030.0 (TID 280030) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-362c0b4f-c4a7-4b9d-bcae-e450763a53f3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280030.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280030.0 (TID 280030) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-362c0b4f-c4a7-4b9d-bcae-e450763a53f3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-362c0b4f-c4a7-4b9d-bcae-e450763a53f3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
82e5c6ca-c523-46eb-b2e4-9e74967eab28 |
2026/09/03 12:52:43 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280031.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280031.0 (TID 280031) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f030b0c5-bfb9-45d5-937c-b81c0d63f9c3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280031.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280031.0 (TID 280031) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f030b0c5-bfb9-45d5-937c-b81c0d63f9c3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f030b0c5-bfb9-45d5-937c-b81c0d63f9c3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
5b979fe1-e430-4cbb-8514-042251ea1b7d |
2026/09/03 12:52:43 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280032.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280032.0 (TID 280032) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a0349eba-de49-4750-b45b-a837ce0007e2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280032.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280032.0 (TID 280032) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a0349eba-de49-4750-b45b-a837ce0007e2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a0349eba-de49-4750-b45b-a837ce0007e2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
11f51373-6fe5-4225-b2ba-a83d0d0c8c0b |
2026/09/03 12:52:43 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280033.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280033.0 (TID 280033) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1bcc7015-ec6c-4b6c-945c-5e5dfcafdb70-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280033.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280033.0 (TID 280033) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1bcc7015-ec6c-4b6c-945c-5e5dfcafdb70-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1bcc7015-ec6c-4b6c-945c-5e5dfcafdb70-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
22fdfc89-a85a-453b-9268-75a38557a823 |
2026/09/03 12:52:43 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280034.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280034.0 (TID 280034) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2b76e80a-5768-4b2c-8845-140c8cf38b92-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280034.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280034.0 (TID 280034) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2b76e80a-5768-4b2c-8845-140c8cf38b92-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2b76e80a-5768-4b2c-8845-140c8cf38b92-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
401479f0-5a7e-4f9c-bd11-3ae8a4af5ed8 |
2026/09/03 12:52:43 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280035.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280035.0 (TID 280035) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-35ce7c15-c3a8-4d35-a72b-426acfe86601-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280035.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280035.0 (TID 280035) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-35ce7c15-c3a8-4d35-a72b-426acfe86601-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-35ce7c15-c3a8-4d35-a72b-426acfe86601-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
b422776e-f67c-456f-87ec-26966cfa3115 |
2026/09/03 12:52:43 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280036.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280036.0 (TID 280036) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-59e2e328-6243-4a08-9f17-6abf8e621aad-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280036.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280036.0 (TID 280036) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-59e2e328-6243-4a08-9f17-6abf8e621aad-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-59e2e328-6243-4a08-9f17-6abf8e621aad-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
b2ade102-778b-48fa-a765-23918876bf91 |
2026/09/03 12:52:43 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280037.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280037.0 (TID 280037) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6985e76f-0c14-458d-b551-08c5bc152715-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280037.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280037.0 (TID 280037) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6985e76f-0c14-458d-b551-08c5bc152715-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6985e76f-0c14-458d-b551-08c5bc152715-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
c4d02a7c-56b2-4e20-b59c-a8d4152552c7 |
2026/09/03 12:52:43 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280038.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280038.0 (TID 280038) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-bb76a536-902e-4970-a3f3-1c07e5a1af7a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280038.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280038.0 (TID 280038) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-bb76a536-902e-4970-a3f3-1c07e5a1af7a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-bb76a536-902e-4970-a3f3-1c07e5a1af7a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
17d0b0a2-ab4a-47a7-a338-e01b4f944e3b |
2026/09/03 12:52:43 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280039.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280039.0 (TID 280039) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a6679891-89c5-426a-8f55-d06645e0b1e3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280039.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280039.0 (TID 280039) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a6679891-89c5-426a-8f55-d06645e0b1e3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a6679891-89c5-426a-8f55-d06645e0b1e3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
70bf9cca-f593-4871-bf5f-2940d6359d44 |
2026/09/03 12:52:43 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280040.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280040.0 (TID 280040) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-adc8c47e-3bd6-4348-8327-9135ab3b4bc4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280040.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280040.0 (TID 280040) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-adc8c47e-3bd6-4348-8327-9135ab3b4bc4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-adc8c47e-3bd6-4348-8327-9135ab3b4bc4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
b86019ac-eb70-49f3-b0f8-d24b42d29bd6 |
2026/09/03 12:52:43 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280041.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280041.0 (TID 280041) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0e87283b-3065-4333-ad50-81561151c721-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280041.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280041.0 (TID 280041) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0e87283b-3065-4333-ad50-81561151c721-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0e87283b-3065-4333-ad50-81561151c721-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
035dd19c-4d1e-4fa3-a471-6dc0c8912d5e |
2026/09/03 12:52:43 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280042.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280042.0 (TID 280042) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-12046516-df58-4e37-832c-d4cf74cfa556-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280042.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280042.0 (TID 280042) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-12046516-df58-4e37-832c-d4cf74cfa556-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-12046516-df58-4e37-832c-d4cf74cfa556-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
6854d68f-ba3f-4c73-bd66-71343d11a591 |
2026/09/03 12:52:43 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280043.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280043.0 (TID 280043) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9adbe13e-0453-4524-b020-c755a4f2eb03-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280043.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280043.0 (TID 280043) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9adbe13e-0453-4524-b020-c755a4f2eb03-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9adbe13e-0453-4524-b020-c755a4f2eb03-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
26545522-2ed6-4678-b3db-dc62a6cad64b |
2026/09/03 12:52:43 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280044.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280044.0 (TID 280044) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-22adedb9-33fb-49b2-bad1-d7da16fca9e5-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280044.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280044.0 (TID 280044) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-22adedb9-33fb-49b2-bad1-d7da16fca9e5-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-22adedb9-33fb-49b2-bad1-d7da16fca9e5-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
a7e75102-a188-4ac4-bae9-075572e27670 |
2026/09/03 12:52:43 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280045.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280045.0 (TID 280045) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-13e70639-cdf0-4b39-ac84-179e753a5b3d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280045.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280045.0 (TID 280045) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-13e70639-cdf0-4b39-ac84-179e753a5b3d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-13e70639-cdf0-4b39-ac84-179e753a5b3d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
7662833c-4287-429b-8283-6dbbc69022e7 |
2026/09/03 12:52:43 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280046.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280046.0 (TID 280046) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-39494fe8-0ea0-4530-a41a-84410bc79123-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280046.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280046.0 (TID 280046) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-39494fe8-0ea0-4530-a41a-84410bc79123-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-39494fe8-0ea0-4530-a41a-84410bc79123-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
d61b5ae6-15f1-4964-be5c-dde87fa33c4f |
2026/09/03 12:52:43 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280047.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280047.0 (TID 280047) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6bf92859-e961-48d0-96ef-4d61c96ce184-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280047.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280047.0 (TID 280047) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6bf92859-e961-48d0-96ef-4d61c96ce184-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6bf92859-e961-48d0-96ef-4d61c96ce184-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
0add1fb4-9a55-40d7-adaa-1fa6eab715a7 |
2026/09/03 12:52:43 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280048.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280048.0 (TID 280048) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-66de12e5-b018-4c0a-a6f2-e6496a61d09a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280048.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280048.0 (TID 280048) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-66de12e5-b018-4c0a-a6f2-e6496a61d09a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-66de12e5-b018-4c0a-a6f2-e6496a61d09a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
08e041cc-03eb-42bc-9829-a3be663e962e |
2026/09/03 12:52:43 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280049.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280049.0 (TID 280049) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3e1938da-2bcf-47f4-8d92-85d383bb2554-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280049.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280049.0 (TID 280049) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3e1938da-2bcf-47f4-8d92-85d383bb2554-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3e1938da-2bcf-47f4-8d92-85d383bb2554-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
71a5e1fc-2a08-4340-b913-a31b7dcecabb |
2026/09/03 12:52:43 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280050.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280050.0 (TID 280050) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ac1f9ffe-6a1f-44b5-931f-08a95cd8cbfe-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280050.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280050.0 (TID 280050) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ac1f9ffe-6a1f-44b5-931f-08a95cd8cbfe-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ac1f9ffe-6a1f-44b5-931f-08a95cd8cbfe-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
4a2c3b2b-0a98-4399-a9ce-8886e3b94c43 |
2026/09/03 12:52:43 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280051.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280051.0 (TID 280051) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f81a1959-17fc-43ca-b241-193a38b24c8d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280051.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280051.0 (TID 280051) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f81a1959-17fc-43ca-b241-193a38b24c8d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f81a1959-17fc-43ca-b241-193a38b24c8d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
ee06152a-da6f-4445-8e34-4629ccbf3373 |
2026/09/03 12:52:44 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280052.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280052.0 (TID 280052) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c9b6e793-b8d6-4b41-a183-751801273daa-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280052.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280052.0 (TID 280052) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c9b6e793-b8d6-4b41-a183-751801273daa-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c9b6e793-b8d6-4b41-a183-751801273daa-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
e7f47e5c-156d-4500-b742-a89e55878fb4 |
2026/09/03 12:52:44 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280053.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280053.0 (TID 280053) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-dc5f3d1d-f409-4442-b00c-7efb93a5e641-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280053.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280053.0 (TID 280053) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-dc5f3d1d-f409-4442-b00c-7efb93a5e641-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-dc5f3d1d-f409-4442-b00c-7efb93a5e641-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
19056e91-a839-4e53-9df3-26ce4c6aa97d |
2026/09/03 12:52:44 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280054.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280054.0 (TID 280054) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-50e14458-172a-447d-9905-e88b37d05520-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280054.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280054.0 (TID 280054) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-50e14458-172a-447d-9905-e88b37d05520-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-50e14458-172a-447d-9905-e88b37d05520-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
8010a4ce-2170-40f2-81d6-ba285f399b27 |
2026/09/03 12:52:44 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280055.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280055.0 (TID 280055) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-91e5c583-4029-4f00-b00b-1ca2fa270aeb-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280055.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280055.0 (TID 280055) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-91e5c583-4029-4f00-b00b-1ca2fa270aeb-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-91e5c583-4029-4f00-b00b-1ca2fa270aeb-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
cdf50df4-1693-4846-9b64-483e0832bc20 |
2026/09/03 12:52:44 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280056.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280056.0 (TID 280056) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b0fec09c-83cb-4de4-8993-200b5f4bbf4d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280056.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280056.0 (TID 280056) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b0fec09c-83cb-4de4-8993-200b5f4bbf4d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b0fec09c-83cb-4de4-8993-200b5f4bbf4d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
b76af72f-cfd6-4a35-879b-254029546465 |
2026/09/03 12:52:44 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280057.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280057.0 (TID 280057) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-405e26f1-18b2-435f-8a3e-b301477e476d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280057.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280057.0 (TID 280057) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-405e26f1-18b2-435f-8a3e-b301477e476d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-405e26f1-18b2-435f-8a3e-b301477e476d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
97354308-1418-4dfb-8e5f-44aab537fb81 |
2026/09/03 12:52:44 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280058.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280058.0 (TID 280058) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fc92b202-d9bb-481c-afa2-8f0d43335731-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280058.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280058.0 (TID 280058) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fc92b202-d9bb-481c-afa2-8f0d43335731-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fc92b202-d9bb-481c-afa2-8f0d43335731-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
6bb058cf-9f65-4be8-92cc-25e30ee21a4d |
2026/09/03 12:52:44 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280059.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280059.0 (TID 280059) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-da1c45a3-d289-4add-9eda-b1752f88d1a8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280059.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280059.0 (TID 280059) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-da1c45a3-d289-4add-9eda-b1752f88d1a8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-da1c45a3-d289-4add-9eda-b1752f88d1a8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
5af3cb72-ccf9-473f-99b9-9bf90bded82d |
2026/09/03 12:52:44 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280060.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280060.0 (TID 280060) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d61d35a2-5e72-4676-ac1e-28c30df2ed3e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280060.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280060.0 (TID 280060) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d61d35a2-5e72-4676-ac1e-28c30df2ed3e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d61d35a2-5e72-4676-ac1e-28c30df2ed3e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
021fa620-2c6b-45de-a269-7f04cf68e5d5 |
2026/09/03 12:52:44 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280061.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280061.0 (TID 280061) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a1925994-f08c-480b-905c-1e87c71b3045-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280061.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280061.0 (TID 280061) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a1925994-f08c-480b-905c-1e87c71b3045-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a1925994-f08c-480b-905c-1e87c71b3045-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
8ed78b3a-b5ab-488a-a70c-11c087644006 |
2026/09/03 12:52:44 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280062.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280062.0 (TID 280062) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ee5e8ea5-8c75-4501-a910-a9698446421e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280062.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280062.0 (TID 280062) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ee5e8ea5-8c75-4501-a910-a9698446421e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ee5e8ea5-8c75-4501-a910-a9698446421e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
602eefbe-b28f-444e-8293-aa5c96d93e04 |
2026/09/03 12:52:44 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280063.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280063.0 (TID 280063) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6afd8113-5cbd-43c5-b088-32f49dcc54d0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280063.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280063.0 (TID 280063) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6afd8113-5cbd-43c5-b088-32f49dcc54d0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6afd8113-5cbd-43c5-b088-32f49dcc54d0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
845d7e38-fc4d-4d8d-952d-be571186b3e3 |
2026/09/03 12:52:44 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280064.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280064.0 (TID 280064) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3c8a0bb6-9a19-4e72-ae5f-fb8f56d7daf6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 280064.0 failed 1 times, most recent failure: Lost task 0.0 in stage 280064.0 (TID 280064) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3c8a0bb6-9a19-4e72-ae5f-fb8f56d7daf6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.failJobAndIndependentStages(DAGScheduler.scala:2898)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2(DAGScheduler.scala:2834)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$abortStage$2$adapted(DAGScheduler.scala:2833)
at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:2833)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGScheduler.$anonfun$handleTaskSetFailed$1$adapted(DAGScheduler.scala:1253)
at scala.Option.foreach(Option.scala:407)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:1253)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:3102)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3036)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:3025)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:995)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2393)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2414)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2433)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:530)
at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:483)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1(Dataset.scala:654)
at org.apache.spark.sql.Dataset.$anonfun$isEmpty$1$adapted(Dataset.scala:653)
at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:4323)
at org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:4321)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:4321)
at org.apache.spark.sql.Dataset.isEmpty(Dataset.scala:653)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1(KafkaDataFrameDataSource.scala:47)
at data.kafka.KafkaDataFrameDataSource.$anonfun$monitor$1$adapted(KafkaDataFrameDataSource.scala:46)
at org.apache.spark.sql.execution.streaming.sources.ForeachBatchSink.addBatch(ForeachBatchSink.scala:34)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$17(MicroBatchExecution.scala:732)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:201)
at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:108)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:66)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runBatch$16(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runBatch(MicroBatchExecution.scala:729)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$2(MicroBatchExecution.scala:286)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken(ProgressReporter.scala:427)
at org.apache.spark.sql.execution.streaming.ProgressReporter.reportTimeTaken$(ProgressReporter.scala:425)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.$anonfun$runActivatedStream$1(MicroBatchExecution.scala:249)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:67)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:239)
at org.apache.spark.sql.execution.streaming.StreamExecution.$anonfun$runStream$1(StreamExecution.scala:311)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:289)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.$anonfun$run$1(StreamExecution.scala:211)
at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
at org.apache.spark.JobArtifactSet$.withActiveJobArtifactState(JobArtifactSet.scala:94)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3c8a0bb6-9a19-4e72-ae5f-fb8f56d7daf6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
|