| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
14b1f681-cce7-4bc2-842b-6834ffd5a367 |
2026/09/03 13:46:00 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352203.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352203.0 (TID 352203) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-89f04b27-00ec-4115-891d-7d2f1a1a25c8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352203.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352203.0 (TID 352203) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-89f04b27-00ec-4115-891d-7d2f1a1a25c8-1980890413-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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-89f04b27-00ec-4115-891d-7d2f1a1a25c8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
0ddcbcf5-1641-4a9d-88df-1beb8a7899f4 |
2026/09/03 13:46:00 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352202.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352202.0 (TID 352202) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fdfed02c-7958-4c37-9ba9-01631d932bcc-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352202.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352202.0 (TID 352202) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fdfed02c-7958-4c37-9ba9-01631d932bcc-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fdfed02c-7958-4c37-9ba9-01631d932bcc-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
8f1cf3b0-1e29-4f3c-9db2-a5f64d20ec4e |
2026/09/03 13:46:00 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352201.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352201.0 (TID 352201) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0c188dd4-a737-43fe-aa6b-dd81bbe27ed1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352201.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352201.0 (TID 352201) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0c188dd4-a737-43fe-aa6b-dd81bbe27ed1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0c188dd4-a737-43fe-aa6b-dd81bbe27ed1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
0e4593c0-21f1-4187-824e-3a26ee68ba97 |
2026/09/03 13:46:00 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352200.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352200.0 (TID 352200) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1fa580b2-d7b8-40eb-a441-4fd67edac714-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352200.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352200.0 (TID 352200) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1fa580b2-d7b8-40eb-a441-4fd67edac714-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1fa580b2-d7b8-40eb-a441-4fd67edac714-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
000bc9ea-de68-4c42-ba54-20434eb78ccf |
2026/09/03 13:46:00 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352199.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352199.0 (TID 352199) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1289e55f-526e-4b28-b5e3-a51c572acfc6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352199.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352199.0 (TID 352199) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1289e55f-526e-4b28-b5e3-a51c572acfc6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1289e55f-526e-4b28-b5e3-a51c572acfc6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
03ad1903-a48f-4cae-822e-5969a039e797 |
2026/09/03 13:46:00 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352198.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352198.0 (TID 352198) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e679cc4d-ccdf-4a17-9ffa-cab4e75bab25-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352198.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352198.0 (TID 352198) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e679cc4d-ccdf-4a17-9ffa-cab4e75bab25-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e679cc4d-ccdf-4a17-9ffa-cab4e75bab25-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
b358138e-ec06-41c4-80e0-f6d6904d0937 |
2026/09/03 13:46:00 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352197.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352197.0 (TID 352197) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f075533a-e420-4c5b-bdf8-e1d690459e65-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352197.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352197.0 (TID 352197) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f075533a-e420-4c5b-bdf8-e1d690459e65-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f075533a-e420-4c5b-bdf8-e1d690459e65-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
90068e3c-24f3-4c72-a2f2-4c0aba5d74be |
2026/09/03 13:46:00 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352196.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352196.0 (TID 352196) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f3a58121-f97a-4b15-830e-0ae4d2ab7346-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352196.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352196.0 (TID 352196) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f3a58121-f97a-4b15-830e-0ae4d2ab7346-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f3a58121-f97a-4b15-830e-0ae4d2ab7346-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
717d1431-9827-4122-beb9-9b10579ca1c4 |
2026/09/03 13:46:00 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352195.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352195.0 (TID 352195) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b2ea5597-0f7b-4b9e-af45-9e074d75db2c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352195.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352195.0 (TID 352195) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b2ea5597-0f7b-4b9e-af45-9e074d75db2c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b2ea5597-0f7b-4b9e-af45-9e074d75db2c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
4df57787-2224-4a00-9650-eb38d8362f96 |
2026/09/03 13:46:00 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352194.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352194.0 (TID 352194) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e3cf5815-3948-4469-a8ef-e73e4c875ac4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352194.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352194.0 (TID 352194) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e3cf5815-3948-4469-a8ef-e73e4c875ac4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e3cf5815-3948-4469-a8ef-e73e4c875ac4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
4fcddba2-db50-481d-92e4-9c116dff708b |
2026/09/03 13:46:00 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352193.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352193.0 (TID 352193) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9b0e728e-af3e-4a08-bce5-e285ab2f0e23-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352193.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352193.0 (TID 352193) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9b0e728e-af3e-4a08-bce5-e285ab2f0e23-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9b0e728e-af3e-4a08-bce5-e285ab2f0e23-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
efcbca02-89ab-4b02-bedc-d405fe3f9cc6 |
2026/09/03 13:46:00 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352192.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352192.0 (TID 352192) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e0e4d667-cb3e-43c2-9100-fc04446b8f2d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352192.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352192.0 (TID 352192) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e0e4d667-cb3e-43c2-9100-fc04446b8f2d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e0e4d667-cb3e-43c2-9100-fc04446b8f2d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
4402b2c5-dd1f-4622-9887-28ab3381f51f |
2026/09/03 13:46:00 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352191.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352191.0 (TID 352191) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5d377df1-3f4c-4bfc-b295-221778b2153b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352191.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352191.0 (TID 352191) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5d377df1-3f4c-4bfc-b295-221778b2153b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5d377df1-3f4c-4bfc-b295-221778b2153b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
2d108f10-070c-447f-88a2-b418fd403dcb |
2026/09/03 13:46:00 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352190.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352190.0 (TID 352190) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d740fbdf-48e8-4d4c-8714-ef3d7dfa0835-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352190.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352190.0 (TID 352190) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d740fbdf-48e8-4d4c-8714-ef3d7dfa0835-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d740fbdf-48e8-4d4c-8714-ef3d7dfa0835-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
7af360e4-721f-4670-b825-d8f22d12e979 |
2026/09/03 13:46:00 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352189.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352189.0 (TID 352189) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6c9e5ecd-a412-4338-90df-fe7d0f1084d6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352189.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352189.0 (TID 352189) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6c9e5ecd-a412-4338-90df-fe7d0f1084d6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6c9e5ecd-a412-4338-90df-fe7d0f1084d6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
9f75467b-e58c-4860-aebf-0626d1abc52e |
2026/09/03 13:46:00 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352188.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352188.0 (TID 352188) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a44f7f83-9416-4c8f-a8b4-d6ff33cd1df4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352188.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352188.0 (TID 352188) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a44f7f83-9416-4c8f-a8b4-d6ff33cd1df4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a44f7f83-9416-4c8f-a8b4-d6ff33cd1df4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
90ecb10a-b8e1-4211-ac5d-a86294178c2c |
2026/09/03 13:46:00 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352187.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352187.0 (TID 352187) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-41dbb65c-6b60-4fe2-b2b8-1e3f65a3cada-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352187.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352187.0 (TID 352187) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-41dbb65c-6b60-4fe2-b2b8-1e3f65a3cada-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-41dbb65c-6b60-4fe2-b2b8-1e3f65a3cada-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
d32d3024-8112-4cd3-83d5-676baee13bfa |
2026/09/03 13:46:00 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352186.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352186.0 (TID 352186) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-daa59cbe-4645-466d-ab28-487df9c9ee05-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352186.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352186.0 (TID 352186) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-daa59cbe-4645-466d-ab28-487df9c9ee05-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-daa59cbe-4645-466d-ab28-487df9c9ee05-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
383a2b6c-fbea-41c8-928a-1ff2eab92af7 |
2026/09/03 13:46:00 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352185.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352185.0 (TID 352185) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d7c48062-0fd2-4fde-b638-02fc4cc9a600-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352185.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352185.0 (TID 352185) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d7c48062-0fd2-4fde-b638-02fc4cc9a600-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d7c48062-0fd2-4fde-b638-02fc4cc9a600-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
3188397a-cad9-42e2-a811-6023b952cfee |
2026/09/03 13:46:00 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352184.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352184.0 (TID 352184) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fda6c2c2-87b9-4f2c-9aa1-3751c8efdbc8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352184.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352184.0 (TID 352184) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fda6c2c2-87b9-4f2c-9aa1-3751c8efdbc8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fda6c2c2-87b9-4f2c-9aa1-3751c8efdbc8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
a98b05a2-3b2c-4abc-bdaf-bbadac9d4300 |
2026/09/03 13:45:59 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352183.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352183.0 (TID 352183) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d2c5a4cc-0f02-44d4-9451-d6fb67d43924-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352183.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352183.0 (TID 352183) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d2c5a4cc-0f02-44d4-9451-d6fb67d43924-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d2c5a4cc-0f02-44d4-9451-d6fb67d43924-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
75c7a498-33ee-4af2-bbd5-da7e16a7bfbc |
2026/09/03 13:45:59 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352182.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352182.0 (TID 352182) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7ae0417e-87d5-4941-af99-27ea0106de69-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352182.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352182.0 (TID 352182) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7ae0417e-87d5-4941-af99-27ea0106de69-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7ae0417e-87d5-4941-af99-27ea0106de69-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
6a8612ca-7256-4701-ba97-fc3791725861 |
2026/09/03 13:45:59 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352181.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352181.0 (TID 352181) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a5c3ffe8-07fb-4bd3-acd0-d645e4e793e0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352181.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352181.0 (TID 352181) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a5c3ffe8-07fb-4bd3-acd0-d645e4e793e0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a5c3ffe8-07fb-4bd3-acd0-d645e4e793e0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
0428f94f-d80d-45a6-a1b7-358e844758c0 |
2026/09/03 13:45:59 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352180.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352180.0 (TID 352180) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-da075902-8946-46cc-a34b-04c8c29036eb-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352180.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352180.0 (TID 352180) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-da075902-8946-46cc-a34b-04c8c29036eb-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-da075902-8946-46cc-a34b-04c8c29036eb-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
78a7a093-55c2-44d5-9889-b7a413fe17d7 |
2026/09/03 13:45:59 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352179.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352179.0 (TID 352179) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8b1d65be-9da7-4a5c-9ef2-195cd1789b42-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352179.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352179.0 (TID 352179) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8b1d65be-9da7-4a5c-9ef2-195cd1789b42-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8b1d65be-9da7-4a5c-9ef2-195cd1789b42-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
3523f9ba-e8c4-4c23-a11e-801874a19a1e |
2026/09/03 13:45:59 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352178.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352178.0 (TID 352178) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-bd81cada-4f28-41d8-9c6e-d968e00b9f46-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352178.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352178.0 (TID 352178) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-bd81cada-4f28-41d8-9c6e-d968e00b9f46-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-bd81cada-4f28-41d8-9c6e-d968e00b9f46-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
0ea4ee6d-ab4b-4f69-9de3-0b5f8253fe9e |
2026/09/03 13:45:59 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352177.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352177.0 (TID 352177) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-597ff344-bd03-4199-a705-f2d5fd3190a1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352177.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352177.0 (TID 352177) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-597ff344-bd03-4199-a705-f2d5fd3190a1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-597ff344-bd03-4199-a705-f2d5fd3190a1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
76db04dc-827f-4648-917f-02846b687761 |
2026/09/03 13:45:59 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352176.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352176.0 (TID 352176) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-efb9548a-9bb4-4e6e-bb28-f50c8fcf8d09-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352176.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352176.0 (TID 352176) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-efb9548a-9bb4-4e6e-bb28-f50c8fcf8d09-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-efb9548a-9bb4-4e6e-bb28-f50c8fcf8d09-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
3bfe277d-f5be-4b9b-81f2-bee98b03bba2 |
2026/09/03 13:45:59 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352175.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352175.0 (TID 352175) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1439da54-2b79-475d-9e57-37e67a81298c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352175.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352175.0 (TID 352175) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1439da54-2b79-475d-9e57-37e67a81298c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1439da54-2b79-475d-9e57-37e67a81298c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
bf3dce62-ace5-4de0-ba70-c707f78933f1 |
2026/09/03 13:45:59 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352174.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352174.0 (TID 352174) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-eb57493c-0cde-4c62-ba32-114c9ee2741e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352174.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352174.0 (TID 352174) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-eb57493c-0cde-4c62-ba32-114c9ee2741e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-eb57493c-0cde-4c62-ba32-114c9ee2741e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
0deb6b65-0907-45ee-9808-15555447455b |
2026/09/03 13:45:59 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352173.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352173.0 (TID 352173) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6d0415fc-f53c-4fbb-844f-adb711dfde2d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352173.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352173.0 (TID 352173) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6d0415fc-f53c-4fbb-844f-adb711dfde2d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6d0415fc-f53c-4fbb-844f-adb711dfde2d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
43163d22-6ef1-4985-8a90-a97e53ca93ad |
2026/09/03 13:45:59 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352172.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352172.0 (TID 352172) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a4f18576-b20e-45bb-bace-1d1596ddd8d3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352172.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352172.0 (TID 352172) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a4f18576-b20e-45bb-bace-1d1596ddd8d3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a4f18576-b20e-45bb-bace-1d1596ddd8d3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
92edc5d1-e5cd-45a6-ac9e-029cc28df2c3 |
2026/09/03 13:45:59 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352171.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352171.0 (TID 352171) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9084cf85-31db-490b-a612-d3b3b16a6335-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352171.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352171.0 (TID 352171) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9084cf85-31db-490b-a612-d3b3b16a6335-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9084cf85-31db-490b-a612-d3b3b16a6335-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
fdfbc4a7-0fe4-49e7-ab32-9f348659a5ed |
2026/09/03 13:45:59 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352170.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352170.0 (TID 352170) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3606d35b-905f-4f14-aab7-f9fecc42d67b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352170.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352170.0 (TID 352170) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3606d35b-905f-4f14-aab7-f9fecc42d67b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3606d35b-905f-4f14-aab7-f9fecc42d67b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
e9ebffdc-063f-4af3-ac19-15519386058f |
2026/09/03 13:45:59 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352169.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352169.0 (TID 352169) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8c95048a-c93d-4c37-b25e-951d98e3ec50-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352169.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352169.0 (TID 352169) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8c95048a-c93d-4c37-b25e-951d98e3ec50-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8c95048a-c93d-4c37-b25e-951d98e3ec50-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
ce8ef55b-e6f7-4e37-90e4-fa2fb134bf70 |
2026/09/03 13:45:59 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352168.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352168.0 (TID 352168) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-710a6a56-1d1b-4e6b-a347-1263ffd43225-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352168.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352168.0 (TID 352168) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-710a6a56-1d1b-4e6b-a347-1263ffd43225-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-710a6a56-1d1b-4e6b-a347-1263ffd43225-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
c9a613f9-5c62-4dde-8372-d9a55e01c8ca |
2026/09/03 13:45:59 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352167.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352167.0 (TID 352167) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e1c211e5-162b-4f8e-800d-8097f471a73e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352167.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352167.0 (TID 352167) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e1c211e5-162b-4f8e-800d-8097f471a73e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e1c211e5-162b-4f8e-800d-8097f471a73e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
58ab4d1a-21b8-40fd-9fe0-b21d978211ff |
2026/09/03 13:45:59 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352166.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352166.0 (TID 352166) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-16e557f8-f784-4f31-a9a7-44f86156f7d4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352166.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352166.0 (TID 352166) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-16e557f8-f784-4f31-a9a7-44f86156f7d4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-16e557f8-f784-4f31-a9a7-44f86156f7d4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
4138d092-1cf8-4c62-9c86-70e3f9b6ed2c |
2026/09/03 13:45:59 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352165.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352165.0 (TID 352165) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-57989589-181a-43a8-88b0-96e45f4df081-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352165.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352165.0 (TID 352165) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-57989589-181a-43a8-88b0-96e45f4df081-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-57989589-181a-43a8-88b0-96e45f4df081-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
dc112f0c-3077-48f8-906e-11c3c9328c0c |
2026/09/03 13:45:59 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352164.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352164.0 (TID 352164) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-046c7d55-2e7f-4f5f-af10-9fcf24ce418a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352164.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352164.0 (TID 352164) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-046c7d55-2e7f-4f5f-af10-9fcf24ce418a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-046c7d55-2e7f-4f5f-af10-9fcf24ce418a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
f7eeaab2-c801-4dff-b760-7439f0d90752 |
2026/09/03 13:45:59 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352163.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352163.0 (TID 352163) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ddd6c866-541c-425f-bdcf-cf209eb09a9b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352163.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352163.0 (TID 352163) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ddd6c866-541c-425f-bdcf-cf209eb09a9b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ddd6c866-541c-425f-bdcf-cf209eb09a9b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
bb169abb-19c6-402e-a816-d0922e7c4ba4 |
2026/09/03 13:45:59 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352162.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352162.0 (TID 352162) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-57ae3fd6-3857-4924-b182-c1549dba61fe-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352162.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352162.0 (TID 352162) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-57ae3fd6-3857-4924-b182-c1549dba61fe-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-57ae3fd6-3857-4924-b182-c1549dba61fe-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
cbafb7e6-7cf4-4fda-87ec-40c1e2bd3f69 |
2026/09/03 13:45:59 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352161.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352161.0 (TID 352161) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c9e42011-77cc-49e3-a45c-35162df3c7c6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352161.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352161.0 (TID 352161) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c9e42011-77cc-49e3-a45c-35162df3c7c6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c9e42011-77cc-49e3-a45c-35162df3c7c6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
357e9462-9dde-4814-8253-e076d3aa6e9b |
2026/09/03 13:45:58 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352160.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352160.0 (TID 352160) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6425078b-1ffe-4309-a214-f0511ef822d4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352160.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352160.0 (TID 352160) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6425078b-1ffe-4309-a214-f0511ef822d4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6425078b-1ffe-4309-a214-f0511ef822d4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
4c703e24-4115-49ba-8375-a2e5edf123f8 |
2026/09/03 13:45:58 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352159.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352159.0 (TID 352159) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-91a99e43-fa9e-4bf9-b372-b4c2b113b6c8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352159.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352159.0 (TID 352159) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-91a99e43-fa9e-4bf9-b372-b4c2b113b6c8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-91a99e43-fa9e-4bf9-b372-b4c2b113b6c8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
1fbdd5dd-3352-49d8-bc8f-3fe3304aa3ac |
2026/09/03 13:45:58 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352158.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352158.0 (TID 352158) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b367502c-6abe-42e7-bd9f-ccddfcc42af0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352158.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352158.0 (TID 352158) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b367502c-6abe-42e7-bd9f-ccddfcc42af0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b367502c-6abe-42e7-bd9f-ccddfcc42af0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
c0f4e13b-11a3-4af4-88b3-7c3e15f00029 |
2026/09/03 13:45:58 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352157.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352157.0 (TID 352157) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2b56b281-6d14-4726-b05f-88f9057bb907-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352157.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352157.0 (TID 352157) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2b56b281-6d14-4726-b05f-88f9057bb907-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2b56b281-6d14-4726-b05f-88f9057bb907-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
6b4ef132-64b1-405e-a8c7-2893900399aa |
2026/09/03 13:45:58 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352156.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352156.0 (TID 352156) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2e07ca26-e3fe-4685-9405-221dcd950219-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352156.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352156.0 (TID 352156) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2e07ca26-e3fe-4685-9405-221dcd950219-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2e07ca26-e3fe-4685-9405-221dcd950219-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
2fa43609-7ad9-46f3-82fa-db3566d52d75 |
2026/09/03 13:45:58 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352155.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352155.0 (TID 352155) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1ea97400-aa51-4882-ae49-e8fad7dad514-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352155.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352155.0 (TID 352155) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1ea97400-aa51-4882-ae49-e8fad7dad514-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1ea97400-aa51-4882-ae49-e8fad7dad514-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
c87a3a6e-5529-4608-a279-e19e970c4262 |
2026/09/03 13:45:58 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352154.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352154.0 (TID 352154) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f4c92b1d-3223-455f-ae7e-11a1d63da27f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352154.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352154.0 (TID 352154) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f4c92b1d-3223-455f-ae7e-11a1d63da27f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f4c92b1d-3223-455f-ae7e-11a1d63da27f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
d40f3629-5d78-4cd1-b78d-f6cbfefee952 |
2026/09/03 13:45:58 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352153.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352153.0 (TID 352153) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-45112d3e-d837-475e-8200-e8231c8a05c0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352153.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352153.0 (TID 352153) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-45112d3e-d837-475e-8200-e8231c8a05c0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-45112d3e-d837-475e-8200-e8231c8a05c0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
9b9d4555-ccc2-46cd-815b-d8b9d1cb8fa2 |
2026/09/03 13:45:58 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352152.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352152.0 (TID 352152) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4badecb4-2b06-4d55-bfc1-106c3dd2af7f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352152.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352152.0 (TID 352152) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4badecb4-2b06-4d55-bfc1-106c3dd2af7f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4badecb4-2b06-4d55-bfc1-106c3dd2af7f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
db2cc224-c0ec-4d30-acee-ae26ff5a6902 |
2026/09/03 13:45:58 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352151.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352151.0 (TID 352151) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-31a7e0ca-2d7b-4051-b150-16dded30aa15-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352151.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352151.0 (TID 352151) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-31a7e0ca-2d7b-4051-b150-16dded30aa15-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-31a7e0ca-2d7b-4051-b150-16dded30aa15-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
b26311f8-5f0f-4f91-ac71-97c1ca95223b |
2026/09/03 13:45:58 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352150.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352150.0 (TID 352150) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-bc2f8174-83d7-4749-bf3a-f21c1626cdb8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352150.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352150.0 (TID 352150) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-bc2f8174-83d7-4749-bf3a-f21c1626cdb8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-bc2f8174-83d7-4749-bf3a-f21c1626cdb8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
a53b6468-8105-4802-94e7-bff2cf15b411 |
2026/09/03 13:45:58 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352149.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352149.0 (TID 352149) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-67c879be-b879-4305-9777-64ccd68cee8c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352149.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352149.0 (TID 352149) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-67c879be-b879-4305-9777-64ccd68cee8c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-67c879be-b879-4305-9777-64ccd68cee8c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
fa878df8-799b-4572-9f5a-59c1f05c20a4 |
2026/09/03 13:45:58 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352148.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352148.0 (TID 352148) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-07948d83-2e2e-4184-a660-f0e2338e290a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352148.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352148.0 (TID 352148) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-07948d83-2e2e-4184-a660-f0e2338e290a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-07948d83-2e2e-4184-a660-f0e2338e290a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
01ef4334-124c-42d0-ad9b-6571a63271de |
2026/09/03 13:45:58 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352147.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352147.0 (TID 352147) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-33c39a37-d50d-4281-b6f8-fb9f2597a90a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352147.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352147.0 (TID 352147) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-33c39a37-d50d-4281-b6f8-fb9f2597a90a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-33c39a37-d50d-4281-b6f8-fb9f2597a90a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
71122836-72fa-4962-927d-a38531025de1 |
2026/09/03 13:45:58 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352146.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352146.0 (TID 352146) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5591dabf-4988-421b-be86-fd63ff0eac84-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352146.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352146.0 (TID 352146) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5591dabf-4988-421b-be86-fd63ff0eac84-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5591dabf-4988-421b-be86-fd63ff0eac84-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
46df547d-17cf-4826-9c3b-4bc7612a13dc |
2026/09/03 13:45:58 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352145.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352145.0 (TID 352145) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-bae37177-81fd-464e-b266-0567f03bb9da-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352145.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352145.0 (TID 352145) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-bae37177-81fd-464e-b266-0567f03bb9da-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-bae37177-81fd-464e-b266-0567f03bb9da-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
34f4e88e-6688-45d9-aa9a-9133052e0dfd |
2026/09/03 13:45:58 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352144.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352144.0 (TID 352144) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fa252e3b-9539-4b9c-8741-dbc2299b2040-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352144.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352144.0 (TID 352144) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fa252e3b-9539-4b9c-8741-dbc2299b2040-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fa252e3b-9539-4b9c-8741-dbc2299b2040-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
6dca3a5d-e3dd-4a7d-be47-6c6788b03950 |
2026/09/03 13:45:58 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352143.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352143.0 (TID 352143) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1a21b953-f86f-4dc3-90fe-b93620af6baf-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352143.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352143.0 (TID 352143) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1a21b953-f86f-4dc3-90fe-b93620af6baf-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1a21b953-f86f-4dc3-90fe-b93620af6baf-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
a4baa81c-51b2-4711-9584-f6a50ef1c513 |
2026/09/03 13:45:58 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352142.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352142.0 (TID 352142) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-68267138-d872-4ff6-ad6a-232397822be1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352142.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352142.0 (TID 352142) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-68267138-d872-4ff6-ad6a-232397822be1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-68267138-d872-4ff6-ad6a-232397822be1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
1abd61ed-91c5-4ec0-9e9e-426c1b941d09 |
2026/09/03 13:45:58 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352141.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352141.0 (TID 352141) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b1c5a6c4-2189-43ed-a9b2-6cd32697d04a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352141.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352141.0 (TID 352141) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b1c5a6c4-2189-43ed-a9b2-6cd32697d04a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b1c5a6c4-2189-43ed-a9b2-6cd32697d04a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
db4ceea3-ef34-4e2d-9e04-e45b2f1adca7 |
2026/09/03 13:45:58 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352140.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352140.0 (TID 352140) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-749d4dd1-8aef-4695-b9da-91d7b359a0f9-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352140.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352140.0 (TID 352140) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-749d4dd1-8aef-4695-b9da-91d7b359a0f9-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-749d4dd1-8aef-4695-b9da-91d7b359a0f9-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
025f2150-6766-46cc-896a-717ae2f7f2f1 |
2026/09/03 13:45:58 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352139.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352139.0 (TID 352139) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b6390c0e-474d-47ec-9474-b4802b18f56e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352139.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352139.0 (TID 352139) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b6390c0e-474d-47ec-9474-b4802b18f56e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b6390c0e-474d-47ec-9474-b4802b18f56e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
3d33c267-f5be-41d7-bae7-ae059dad407a |
2026/09/03 13:45:58 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352138.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352138.0 (TID 352138) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-194d1375-7bb8-4848-bf53-0a4ec2e91f9c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352138.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352138.0 (TID 352138) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-194d1375-7bb8-4848-bf53-0a4ec2e91f9c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-194d1375-7bb8-4848-bf53-0a4ec2e91f9c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
38a216a8-7d99-4a96-8841-3202b27ce13f |
2026/09/03 13:45:57 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352137.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352137.0 (TID 352137) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d5e05cec-d510-41b1-893d-7a2add8fedd4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352137.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352137.0 (TID 352137) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d5e05cec-d510-41b1-893d-7a2add8fedd4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d5e05cec-d510-41b1-893d-7a2add8fedd4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
ba7f6f62-3c80-422e-b1cd-44dddc27ed3c |
2026/09/03 13:45:57 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352136.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352136.0 (TID 352136) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6f78fa23-b654-4f51-83e7-7ce481a2c395-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352136.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352136.0 (TID 352136) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6f78fa23-b654-4f51-83e7-7ce481a2c395-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6f78fa23-b654-4f51-83e7-7ce481a2c395-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
86d551b9-501e-43b8-80d4-34cb0d9fd4a8 |
2026/09/03 13:45:57 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352135.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352135.0 (TID 352135) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9b100ba7-e2b5-4df4-91bb-de3dd1587f33-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352135.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352135.0 (TID 352135) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9b100ba7-e2b5-4df4-91bb-de3dd1587f33-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9b100ba7-e2b5-4df4-91bb-de3dd1587f33-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
ce61f93b-440a-4228-9495-bc72568dc073 |
2026/09/03 13:45:57 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352134.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352134.0 (TID 352134) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-abcbf6ca-cb12-497a-8937-1329aee9fb5c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352134.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352134.0 (TID 352134) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-abcbf6ca-cb12-497a-8937-1329aee9fb5c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-abcbf6ca-cb12-497a-8937-1329aee9fb5c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
901156e3-4898-4486-b760-5ecab2c2a853 |
2026/09/03 13:45:57 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352133.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352133.0 (TID 352133) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f3e429e6-9560-4d1e-972e-9c28b0a822db-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352133.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352133.0 (TID 352133) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f3e429e6-9560-4d1e-972e-9c28b0a822db-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f3e429e6-9560-4d1e-972e-9c28b0a822db-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
3160fff9-8cd7-4623-b863-950895590659 |
2026/09/03 13:45:57 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352132.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352132.0 (TID 352132) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3374175b-b9c7-454d-8aa5-e0813ca0e715-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352132.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352132.0 (TID 352132) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3374175b-b9c7-454d-8aa5-e0813ca0e715-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3374175b-b9c7-454d-8aa5-e0813ca0e715-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
316e3ded-6923-457a-95ca-6fdc3b847103 |
2026/09/03 13:45:57 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352131.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352131.0 (TID 352131) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3b672416-d29e-4435-9524-030ef02d9c77-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352131.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352131.0 (TID 352131) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3b672416-d29e-4435-9524-030ef02d9c77-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3b672416-d29e-4435-9524-030ef02d9c77-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
eae0ff9f-9dd4-4995-998c-57f04b42be54 |
2026/09/03 13:45:57 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352130.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352130.0 (TID 352130) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3c416739-abfe-428a-b198-f26d4a774160-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352130.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352130.0 (TID 352130) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3c416739-abfe-428a-b198-f26d4a774160-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3c416739-abfe-428a-b198-f26d4a774160-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
bb43c4e6-c553-4de9-863d-68350e12382a |
2026/09/03 13:45:57 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352129.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352129.0 (TID 352129) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-bed8c0d4-cddd-49e2-9e39-087b05c071f0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352129.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352129.0 (TID 352129) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-bed8c0d4-cddd-49e2-9e39-087b05c071f0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-bed8c0d4-cddd-49e2-9e39-087b05c071f0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
09e84085-bd28-4b41-8d0d-e4d0f44d0555 |
2026/09/03 13:45:57 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352128.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352128.0 (TID 352128) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c36721ea-9b1b-4a27-b27e-28d7578fe2d7-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352128.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352128.0 (TID 352128) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c36721ea-9b1b-4a27-b27e-28d7578fe2d7-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c36721ea-9b1b-4a27-b27e-28d7578fe2d7-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
3d3b40a6-2e3e-4fb2-96c2-e30d4d2c7b25 |
2026/09/03 13:45:57 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352127.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352127.0 (TID 352127) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f74f52de-17d6-4922-93d2-34a64c75e751-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352127.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352127.0 (TID 352127) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f74f52de-17d6-4922-93d2-34a64c75e751-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f74f52de-17d6-4922-93d2-34a64c75e751-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
91120e10-a539-4530-adef-485f910cb026 |
2026/09/03 13:45:57 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352126.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352126.0 (TID 352126) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-dc6fd5d5-0f38-43a9-bf0a-9cef80f28188-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352126.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352126.0 (TID 352126) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-dc6fd5d5-0f38-43a9-bf0a-9cef80f28188-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-dc6fd5d5-0f38-43a9-bf0a-9cef80f28188-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
43cc9499-02d2-4810-ada1-8b160d68cc7c |
2026/09/03 13:45:57 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352125.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352125.0 (TID 352125) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-be7b337e-8c65-43e9-a9c6-f4f4dcac63d3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352125.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352125.0 (TID 352125) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-be7b337e-8c65-43e9-a9c6-f4f4dcac63d3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-be7b337e-8c65-43e9-a9c6-f4f4dcac63d3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
281136c2-376f-4c78-9e3e-0ce533d8e726 |
2026/09/03 13:45:57 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352124.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352124.0 (TID 352124) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-dca0c529-8fef-41ac-853c-1a3f6773b804-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352124.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352124.0 (TID 352124) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-dca0c529-8fef-41ac-853c-1a3f6773b804-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-dca0c529-8fef-41ac-853c-1a3f6773b804-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
ec48cc7d-e724-44ff-b374-b85e51b0be42 |
2026/09/03 13:45:57 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352123.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352123.0 (TID 352123) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7adb5c10-d159-42f0-87e0-f29fad9d5a6f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352123.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352123.0 (TID 352123) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7adb5c10-d159-42f0-87e0-f29fad9d5a6f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7adb5c10-d159-42f0-87e0-f29fad9d5a6f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
a8e657fa-9dc3-479d-a724-83a7d7406576 |
2026/09/03 13:45:57 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352122.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352122.0 (TID 352122) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-adf320b5-f36f-4fb9-84f2-3b36f51282d2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352122.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352122.0 (TID 352122) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-adf320b5-f36f-4fb9-84f2-3b36f51282d2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-adf320b5-f36f-4fb9-84f2-3b36f51282d2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
c9bdb73c-7ae2-4a0b-9abd-2834ebe1077d |
2026/09/03 13:45:57 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352121.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352121.0 (TID 352121) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ebedd773-0bab-46f5-8bb3-496083e84c78-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352121.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352121.0 (TID 352121) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ebedd773-0bab-46f5-8bb3-496083e84c78-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ebedd773-0bab-46f5-8bb3-496083e84c78-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
385931b7-7ab4-49bb-a8c6-4e2d31ac4c80 |
2026/09/03 13:45:57 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352120.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352120.0 (TID 352120) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e620f3f0-1b8d-4bc6-8837-071ddc574f17-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352120.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352120.0 (TID 352120) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e620f3f0-1b8d-4bc6-8837-071ddc574f17-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e620f3f0-1b8d-4bc6-8837-071ddc574f17-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
a57c8dc6-86ad-4725-8e69-fa0653f20c2d |
2026/09/03 13:45:57 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352119.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352119.0 (TID 352119) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7cfc3159-27c9-4444-847b-2eb7d9bee463-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352119.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352119.0 (TID 352119) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7cfc3159-27c9-4444-847b-2eb7d9bee463-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7cfc3159-27c9-4444-847b-2eb7d9bee463-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
1fa2ce3a-94b4-400a-afba-45ff40406f98 |
2026/09/03 13:45:57 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352118.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352118.0 (TID 352118) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-22d7b0aa-42a4-434c-a2c4-a7f5745f4c31-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352118.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352118.0 (TID 352118) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-22d7b0aa-42a4-434c-a2c4-a7f5745f4c31-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-22d7b0aa-42a4-434c-a2c4-a7f5745f4c31-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
db8fbc65-73ab-4dd3-af66-03811c670090 |
2026/09/03 13:45:57 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352117.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352117.0 (TID 352117) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a5bbf159-1866-4f8c-9b64-03799c0fc4ef-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352117.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352117.0 (TID 352117) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a5bbf159-1866-4f8c-9b64-03799c0fc4ef-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a5bbf159-1866-4f8c-9b64-03799c0fc4ef-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
2f180682-54a7-4ed3-bb39-9fb1888b4f38 |
2026/09/03 13:45:57 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352116.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352116.0 (TID 352116) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9e0da310-5b14-4ab7-b419-e6c91d1dd5e0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352116.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352116.0 (TID 352116) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9e0da310-5b14-4ab7-b419-e6c91d1dd5e0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9e0da310-5b14-4ab7-b419-e6c91d1dd5e0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
c355bda4-abda-43ba-8b73-f9c2c381da10 |
2026/09/03 13:45:56 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352115.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352115.0 (TID 352115) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-70f606c4-5889-4a5e-8f1b-140f8d467526-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352115.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352115.0 (TID 352115) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-70f606c4-5889-4a5e-8f1b-140f8d467526-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-70f606c4-5889-4a5e-8f1b-140f8d467526-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
9b34706f-c04a-4554-a918-435a6a863351 |
2026/09/03 13:45:56 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352114.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352114.0 (TID 352114) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-aded00a6-d27c-4645-836d-791bdf3af5d8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352114.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352114.0 (TID 352114) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-aded00a6-d27c-4645-836d-791bdf3af5d8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-aded00a6-d27c-4645-836d-791bdf3af5d8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
044fd48a-6571-4cbf-9d1b-39a8252192f1 |
2026/09/03 13:45:56 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352113.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352113.0 (TID 352113) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-61b9b1ae-2ad5-4ee5-96c5-6bdd8aa18768-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352113.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352113.0 (TID 352113) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-61b9b1ae-2ad5-4ee5-96c5-6bdd8aa18768-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-61b9b1ae-2ad5-4ee5-96c5-6bdd8aa18768-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
e8b12eb0-e065-450b-82f2-ebdd25156114 |
2026/09/03 13:45:56 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352112.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352112.0 (TID 352112) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-eb30c21e-37ed-4f0f-adbf-5a6a34d6eeb9-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352112.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352112.0 (TID 352112) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-eb30c21e-37ed-4f0f-adbf-5a6a34d6eeb9-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-eb30c21e-37ed-4f0f-adbf-5a6a34d6eeb9-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
99851a99-cf8a-4f8a-b786-1ec43f2c28dd |
2026/09/03 13:45:56 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352111.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352111.0 (TID 352111) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b0d7eab5-7188-4059-a471-737cf3dc1ce8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352111.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352111.0 (TID 352111) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b0d7eab5-7188-4059-a471-737cf3dc1ce8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b0d7eab5-7188-4059-a471-737cf3dc1ce8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
0212355f-b6a5-415e-be17-9990b0c2fe7b |
2026/09/03 13:45:56 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352110.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352110.0 (TID 352110) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ee52dda4-ae7d-4b80-8a8d-773cfa4e8bd3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352110.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352110.0 (TID 352110) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ee52dda4-ae7d-4b80-8a8d-773cfa4e8bd3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ee52dda4-ae7d-4b80-8a8d-773cfa4e8bd3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
5bb726a4-7dbb-4701-9e62-47b397003b2a |
2026/09/03 13:45:56 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352109.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352109.0 (TID 352109) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4a9e7083-a198-45bb-83f1-2b5960c1400a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352109.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352109.0 (TID 352109) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4a9e7083-a198-45bb-83f1-2b5960c1400a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4a9e7083-a198-45bb-83f1-2b5960c1400a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
bf3f23f4-438c-45ed-ad1d-39a18909ed56 |
2026/09/03 13:45:56 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352108.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352108.0 (TID 352108) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ad9acfed-673c-4a76-b941-6a0a4c79b124-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352108.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352108.0 (TID 352108) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ad9acfed-673c-4a76-b941-6a0a4c79b124-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ad9acfed-673c-4a76-b941-6a0a4c79b124-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
038860d8-8b41-44e5-a2f6-53be92a53a7a |
2026/09/03 13:45:56 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352107.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352107.0 (TID 352107) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b0c53281-f600-4c23-9039-f7010be309e0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352107.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352107.0 (TID 352107) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b0c53281-f600-4c23-9039-f7010be309e0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b0c53281-f600-4c23-9039-f7010be309e0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
c73f6a13-b63f-4cd6-b5df-db8998c99130 |
2026/09/03 13:45:56 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352106.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352106.0 (TID 352106) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4f61c9e4-fb5c-4423-b6f6-74a9c7539fa9-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352106.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352106.0 (TID 352106) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4f61c9e4-fb5c-4423-b6f6-74a9c7539fa9-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4f61c9e4-fb5c-4423-b6f6-74a9c7539fa9-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
14a1b5f7-726d-4114-a309-9236e3a8e38b |
2026/09/03 13:45:56 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352105.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352105.0 (TID 352105) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-bc2bc0d3-8d24-4bfc-9a19-42b736dde882-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352105.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352105.0 (TID 352105) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-bc2bc0d3-8d24-4bfc-9a19-42b736dde882-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-bc2bc0d3-8d24-4bfc-9a19-42b736dde882-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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$1(KafkaDataConsumer.scala:323)
... 37 more
|
| <no name> |
FAILED |
9848c4f2-c6f1-4b94-a125-6e64ef893aaa |
b95b4bee-45c6-4820-a921-6ca0e00d241d |
2026/09/03 13:45:56 |
0 ms |
NaN |
NaN |
NaN |
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352104.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352104.0 (TID 352104) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5c0b5bf5-1025-46bf-8b8e-d4282fdeb055-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 352104.0 failed 1 times, most recent failure: Lost task 0.0 in stage 352104.0 (TID 352104) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5c0b5bf5-1025-46bf-8b8e-d4282fdeb055-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.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$$anon$1.run(StreamExecution.scala:211)
Caused by: java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5c0b5bf5-1025-46bf-8b8e-d4282fdeb055-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$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
|