|
424370
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 04eb32d1-1b05-420a-b57d-d4528b9d52fd
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 04eb32d1-1b05-420a-b57d-d4528b9d52fd
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212185.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212185.0 (TID 212185) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d05a48d7-64a7-4111-90b6-70aa785d4f3f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212185.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212185.0 (TID 212185) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d05a48d7-64a7-4111-90b6-70aa785d4f3f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424371
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 04eb32d1-1b05-420a-b57d-d4528b9d52fd
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 04eb32d1-1b05-420a-b57d-d4528b9d52fd
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
10 ms
|
|
[212185]
|
|
|
424372
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 2f7443c5-f6f1-4181-9fe9-415a2355beb6
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 2f7443c5-f6f1-4181-9fe9-415a2355beb6
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212186.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212186.0 (TID 212186) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8c17d454-b0ac-4ccd-a0c6-2135b1d66ce7-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212186.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212186.0 (TID 212186) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8c17d454-b0ac-4ccd-a0c6-2135b1d66ce7-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424373
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 2f7443c5-f6f1-4181-9fe9-415a2355beb6
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 2f7443c5-f6f1-4181-9fe9-415a2355beb6
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
11 ms
|
|
[212186]
|
|
|
424374
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 688756dd-cf48-405f-b18c-f41bc22cef60
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 688756dd-cf48-405f-b18c-f41bc22cef60
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212187.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212187.0 (TID 212187) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-14f7d2ac-6ef4-448f-9382-1d871c12e691-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212187.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212187.0 (TID 212187) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-14f7d2ac-6ef4-448f-9382-1d871c12e691-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424375
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 688756dd-cf48-405f-b18c-f41bc22cef60
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 688756dd-cf48-405f-b18c-f41bc22cef60
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
11 ms
|
|
[212187]
|
|
|
424376
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9343a064-9a98-4af4-ad24-f5f386f975c0
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9343a064-9a98-4af4-ad24-f5f386f975c0
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212188.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212188.0 (TID 212188) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f3d22f51-ddf3-4f75-8da8-bb039b5a3e59-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212188.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212188.0 (TID 212188) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f3d22f51-ddf3-4f75-8da8-bb039b5a3e59-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424377
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9343a064-9a98-4af4-ad24-f5f386f975c0
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9343a064-9a98-4af4-ad24-f5f386f975c0
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
11 ms
|
|
[212188]
|
|
|
424378
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 533efd24-8928-4a6a-bfa2-cc06491baba0
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 533efd24-8928-4a6a-bfa2-cc06491baba0
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212189.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212189.0 (TID 212189) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8057db8d-e733-4003-b90a-ca36a78fe8c6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212189.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212189.0 (TID 212189) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8057db8d-e733-4003-b90a-ca36a78fe8c6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424379
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 533efd24-8928-4a6a-bfa2-cc06491baba0
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 533efd24-8928-4a6a-bfa2-cc06491baba0
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
11 ms
|
|
[212189]
|
|
|
424380
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 21603379-ebbc-4751-9cdf-2812c489a683
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 21603379-ebbc-4751-9cdf-2812c489a683
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212190.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212190.0 (TID 212190) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fb9971ff-7823-4cad-b010-f473d8105f72-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212190.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212190.0 (TID 212190) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fb9971ff-7823-4cad-b010-f473d8105f72-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424381
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 21603379-ebbc-4751-9cdf-2812c489a683
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 21603379-ebbc-4751-9cdf-2812c489a683
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
11 ms
|
|
[212190]
|
|
|
424382
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 26324480-c64c-40de-b40b-dc6e1f5f4ccb
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 26324480-c64c-40de-b40b-dc6e1f5f4ccb
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212191.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212191.0 (TID 212191) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-830acfb6-12e7-484c-97a5-2ad5b6956328-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212191.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212191.0 (TID 212191) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-830acfb6-12e7-484c-97a5-2ad5b6956328-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424383
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 26324480-c64c-40de-b40b-dc6e1f5f4ccb
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 26324480-c64c-40de-b40b-dc6e1f5f4ccb
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
12 ms
|
|
[212191]
|
|
|
424384
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 030375ec-dfc7-4931-b599-c5532863e193
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 030375ec-dfc7-4931-b599-c5532863e193
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212192.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212192.0 (TID 212192) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ad2db132-e662-4977-8821-b562609ad26f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212192.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212192.0 (TID 212192) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ad2db132-e662-4977-8821-b562609ad26f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424385
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 030375ec-dfc7-4931-b599-c5532863e193
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 030375ec-dfc7-4931-b599-c5532863e193
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
12 ms
|
|
[212192]
|
|
|
424386
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 46756671-49e6-4678-9904-f1ecb5cf3a33
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 46756671-49e6-4678-9904-f1ecb5cf3a33
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212193.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212193.0 (TID 212193) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b5ae2097-3607-45a8-a13a-95db1f0588aa-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212193.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212193.0 (TID 212193) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b5ae2097-3607-45a8-a13a-95db1f0588aa-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424387
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 46756671-49e6-4678-9904-f1ecb5cf3a33
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 46756671-49e6-4678-9904-f1ecb5cf3a33
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
11 ms
|
|
[212193]
|
|
|
424388
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 0b629de8-aee3-4f54-8c8f-3b7dcbf47a8b
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 0b629de8-aee3-4f54-8c8f-3b7dcbf47a8b
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
25 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212194.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212194.0 (TID 212194) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2818d2a9-3cda-45f1-8a4f-5b3340c5e667-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212194.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212194.0 (TID 212194) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2818d2a9-3cda-45f1-8a4f-5b3340c5e667-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424389
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 0b629de8-aee3-4f54-8c8f-3b7dcbf47a8b
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 0b629de8-aee3-4f54-8c8f-3b7dcbf47a8b
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
22 ms
|
|
[212194]
|
|
|
424390
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 69c469a8-45cd-43f1-970a-37acc639bfda
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 69c469a8-45cd-43f1-970a-37acc639bfda
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212195.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212195.0 (TID 212195) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-61562a04-500f-403c-a787-2f0daa62a7d1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212195.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212195.0 (TID 212195) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-61562a04-500f-403c-a787-2f0daa62a7d1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424391
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 69c469a8-45cd-43f1-970a-37acc639bfda
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 69c469a8-45cd-43f1-970a-37acc639bfda
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
11 ms
|
|
[212195]
|
|
|
424392
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9e641434-d850-401e-80e8-1d47dab63525
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9e641434-d850-401e-80e8-1d47dab63525
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212196.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212196.0 (TID 212196) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a7fcc5a1-ed7c-4177-8f20-6e8cf14ab1ac-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212196.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212196.0 (TID 212196) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a7fcc5a1-ed7c-4177-8f20-6e8cf14ab1ac-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424393
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9e641434-d850-401e-80e8-1d47dab63525
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9e641434-d850-401e-80e8-1d47dab63525
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
11 ms
|
|
[212196]
|
|
|
424394
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d68f9a5d-c791-4be6-abb1-01ca9d83bc90
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d68f9a5d-c791-4be6-abb1-01ca9d83bc90
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212197.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212197.0 (TID 212197) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-75021193-d491-46ca-b5dd-5c53df2f0485-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212197.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212197.0 (TID 212197) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-75021193-d491-46ca-b5dd-5c53df2f0485-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424395
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d68f9a5d-c791-4be6-abb1-01ca9d83bc90
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d68f9a5d-c791-4be6-abb1-01ca9d83bc90
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
11 ms
|
|
[212197]
|
|
|
424396
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 78a3a8eb-30a7-4768-b385-7b659bd421b1
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 78a3a8eb-30a7-4768-b385-7b659bd421b1
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212198.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212198.0 (TID 212198) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ea6fed8c-7147-43ff-afca-230841fec063-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212198.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212198.0 (TID 212198) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ea6fed8c-7147-43ff-afca-230841fec063-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424397
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 78a3a8eb-30a7-4768-b385-7b659bd421b1
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 78a3a8eb-30a7-4768-b385-7b659bd421b1
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
10 ms
|
|
[212198]
|
|
|
424398
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1798d7e7-6067-40a6-b2c7-94e2ac614e4d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1798d7e7-6067-40a6-b2c7-94e2ac614e4d
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
21 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212199.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212199.0 (TID 212199) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-87652acf-5ce7-43b4-9a54-76c8e7cb2340-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212199.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212199.0 (TID 212199) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-87652acf-5ce7-43b4-9a54-76c8e7cb2340-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424399
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1798d7e7-6067-40a6-b2c7-94e2ac614e4d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1798d7e7-6067-40a6-b2c7-94e2ac614e4d
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
18 ms
|
|
[212199]
|
|
|
424400
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 0a7016a2-effc-44a5-9b6d-24c181e373c2
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 0a7016a2-effc-44a5-9b6d-24c181e373c2
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
21 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212200.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212200.0 (TID 212200) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7562290a-28ac-4566-b6a6-7658e3cac0d5-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212200.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212200.0 (TID 212200) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7562290a-28ac-4566-b6a6-7658e3cac0d5-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424401
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 0a7016a2-effc-44a5-9b6d-24c181e373c2
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 0a7016a2-effc-44a5-9b6d-24c181e373c2
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
19 ms
|
|
[212200]
|
|
|
424402
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 064b98a9-c5fc-4db8-8bc9-21651ad2e623
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 064b98a9-c5fc-4db8-8bc9-21651ad2e623
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212201.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212201.0 (TID 212201) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-07e28403-1d4c-4b90-9894-43f7aa7ad08a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212201.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212201.0 (TID 212201) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-07e28403-1d4c-4b90-9894-43f7aa7ad08a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424403
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 064b98a9-c5fc-4db8-8bc9-21651ad2e623
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 064b98a9-c5fc-4db8-8bc9-21651ad2e623
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
12 ms
|
|
[212201]
|
|
|
424404
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = f2ca496d-60fe-4e2b-bd24-a06e49d27195
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = f2ca496d-60fe-4e2b-bd24-a06e49d27195
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212202.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212202.0 (TID 212202) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d8a94415-3d66-4515-a23c-80c839053e9f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212202.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212202.0 (TID 212202) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d8a94415-3d66-4515-a23c-80c839053e9f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424405
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = f2ca496d-60fe-4e2b-bd24-a06e49d27195
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = f2ca496d-60fe-4e2b-bd24-a06e49d27195
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:45
|
13 ms
|
|
[212202]
|
|
|
424406
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c5a920f5-ed2b-4191-9fcb-7726ca007fd6
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c5a920f5-ed2b-4191-9fcb-7726ca007fd6
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
23 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212203.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212203.0 (TID 212203) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b8486197-c20f-4a81-befc-c44e14ef2791-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212203.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212203.0 (TID 212203) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b8486197-c20f-4a81-befc-c44e14ef2791-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424407
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c5a920f5-ed2b-4191-9fcb-7726ca007fd6
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c5a920f5-ed2b-4191-9fcb-7726ca007fd6
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
19 ms
|
|
[212203]
|
|
|
424408
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 61a7e72c-5612-4ad3-a8f6-36d6d2ac6e98
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 61a7e72c-5612-4ad3-a8f6-36d6d2ac6e98
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
30 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212204.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212204.0 (TID 212204) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1cad575d-8fcf-4304-8e02-676e3161c1b6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212204.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212204.0 (TID 212204) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1cad575d-8fcf-4304-8e02-676e3161c1b6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424409
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 61a7e72c-5612-4ad3-a8f6-36d6d2ac6e98
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 61a7e72c-5612-4ad3-a8f6-36d6d2ac6e98
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
26 ms
|
|
[212204]
|
|
|
424410
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4e3168fe-1711-47a1-aff1-e9c94220640f
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4e3168fe-1711-47a1-aff1-e9c94220640f
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
17 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212205.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212205.0 (TID 212205) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2ab2465a-bfea-4293-9ad1-1df9e7218b36-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212205.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212205.0 (TID 212205) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2ab2465a-bfea-4293-9ad1-1df9e7218b36-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424411
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4e3168fe-1711-47a1-aff1-e9c94220640f
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4e3168fe-1711-47a1-aff1-e9c94220640f
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
14 ms
|
|
[212205]
|
|
|
424412
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1abb304e-b3c6-4a56-8e7a-8de7e873104b
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1abb304e-b3c6-4a56-8e7a-8de7e873104b
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212206.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212206.0 (TID 212206) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1f203281-92b4-4d9a-a8b6-03a90977c009-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212206.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212206.0 (TID 212206) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1f203281-92b4-4d9a-a8b6-03a90977c009-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424413
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1abb304e-b3c6-4a56-8e7a-8de7e873104b
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1abb304e-b3c6-4a56-8e7a-8de7e873104b
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
12 ms
|
|
[212206]
|
|
|
424414
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = f0da9f5d-54c1-4d35-b038-ee6d9b62f13c
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = f0da9f5d-54c1-4d35-b038-ee6d9b62f13c
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212207.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212207.0 (TID 212207) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-bf8033e7-b61c-44ee-a006-e47290bfec38-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212207.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212207.0 (TID 212207) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-bf8033e7-b61c-44ee-a006-e47290bfec38-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424415
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = f0da9f5d-54c1-4d35-b038-ee6d9b62f13c
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = f0da9f5d-54c1-4d35-b038-ee6d9b62f13c
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
13 ms
|
|
[212207]
|
|
|
424416
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c55765fe-f40b-4488-8707-0a1405123cbd
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c55765fe-f40b-4488-8707-0a1405123cbd
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212208.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212208.0 (TID 212208) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-247c3b5a-3478-4934-9c86-20533ab49b78-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212208.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212208.0 (TID 212208) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-247c3b5a-3478-4934-9c86-20533ab49b78-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424417
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c55765fe-f40b-4488-8707-0a1405123cbd
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c55765fe-f40b-4488-8707-0a1405123cbd
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
13 ms
|
|
[212208]
|
|
|
424418
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = be70987a-87e0-4f5e-9f2b-8f6c8e5323a9
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = be70987a-87e0-4f5e-9f2b-8f6c8e5323a9
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212209.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212209.0 (TID 212209) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-88fd08e9-4b60-4796-82c2-27592c28dd44-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212209.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212209.0 (TID 212209) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-88fd08e9-4b60-4796-82c2-27592c28dd44-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424419
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = be70987a-87e0-4f5e-9f2b-8f6c8e5323a9
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = be70987a-87e0-4f5e-9f2b-8f6c8e5323a9
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
13 ms
|
|
[212209]
|
|
|
424420
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5d8d7331-3fe2-4953-96a9-7e8164231fde
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5d8d7331-3fe2-4953-96a9-7e8164231fde
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
18 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212210.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212210.0 (TID 212210) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-888437b0-1c02-414c-b12c-e2d416062c54-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212210.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212210.0 (TID 212210) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-888437b0-1c02-414c-b12c-e2d416062c54-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424421
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5d8d7331-3fe2-4953-96a9-7e8164231fde
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5d8d7331-3fe2-4953-96a9-7e8164231fde
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
14 ms
|
|
[212210]
|
|
|
424422
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 2eeeea1c-3aa2-45dd-bfe9-2a26742c124f
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 2eeeea1c-3aa2-45dd-bfe9-2a26742c124f
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212211.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212211.0 (TID 212211) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8fe117c9-991b-46b2-8780-91c01ba7c60d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212211.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212211.0 (TID 212211) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8fe117c9-991b-46b2-8780-91c01ba7c60d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424423
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 2eeeea1c-3aa2-45dd-bfe9-2a26742c124f
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 2eeeea1c-3aa2-45dd-bfe9-2a26742c124f
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
13 ms
|
|
[212211]
|
|
|
424424
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a0fb0442-8840-4a77-8ea4-03a2da2c7aff
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a0fb0442-8840-4a77-8ea4-03a2da2c7aff
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212212.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212212.0 (TID 212212) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2cda4918-7fd9-4932-8455-8b970d4464e4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212212.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212212.0 (TID 212212) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2cda4918-7fd9-4932-8455-8b970d4464e4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424425
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a0fb0442-8840-4a77-8ea4-03a2da2c7aff
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a0fb0442-8840-4a77-8ea4-03a2da2c7aff
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
13 ms
|
|
[212212]
|
|
|
424426
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4cd3a236-d136-4622-b21e-001353fd3354
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4cd3a236-d136-4622-b21e-001353fd3354
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
17 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212213.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212213.0 (TID 212213) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b5341890-2f0e-44a2-ba6d-969dac27cf2d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212213.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212213.0 (TID 212213) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b5341890-2f0e-44a2-ba6d-969dac27cf2d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424427
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4cd3a236-d136-4622-b21e-001353fd3354
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4cd3a236-d136-4622-b21e-001353fd3354
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
14 ms
|
|
[212213]
|
|
|
424428
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ffe15349-d829-4823-b627-34580bec4632
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ffe15349-d829-4823-b627-34580bec4632
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
38 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212214.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212214.0 (TID 212214) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fda89414-8cd0-405f-abc4-409a6cb8d2f1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212214.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212214.0 (TID 212214) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fda89414-8cd0-405f-abc4-409a6cb8d2f1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424429
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ffe15349-d829-4823-b627-34580bec4632
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ffe15349-d829-4823-b627-34580bec4632
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
35 ms
|
|
[212214]
|
|
|
424430
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1ba0560a-b298-4cd4-99b6-b9e24406398d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1ba0560a-b298-4cd4-99b6-b9e24406398d
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212215.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212215.0 (TID 212215) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-dec408bb-7681-4f99-bb43-79fe95172c93-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212215.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212215.0 (TID 212215) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-dec408bb-7681-4f99-bb43-79fe95172c93-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424431
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1ba0560a-b298-4cd4-99b6-b9e24406398d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1ba0560a-b298-4cd4-99b6-b9e24406398d
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
12 ms
|
|
[212215]
|
|
|
424432
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 8b37145a-5382-4c3a-a7ce-3e8ee6d978ca
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 8b37145a-5382-4c3a-a7ce-3e8ee6d978ca
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212216.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212216.0 (TID 212216) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b46da9b3-e2f2-4b24-9ce1-e4c335e4a8f0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212216.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212216.0 (TID 212216) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b46da9b3-e2f2-4b24-9ce1-e4c335e4a8f0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424433
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 8b37145a-5382-4c3a-a7ce-3e8ee6d978ca
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 8b37145a-5382-4c3a-a7ce-3e8ee6d978ca
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
12 ms
|
|
[212216]
|
|
|
424434
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 2620d2d9-d514-42e8-ac30-ea486cef39a3
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 2620d2d9-d514-42e8-ac30-ea486cef39a3
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212217.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212217.0 (TID 212217) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1288fde8-4700-4136-ae0c-eed476d96fbd-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212217.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212217.0 (TID 212217) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1288fde8-4700-4136-ae0c-eed476d96fbd-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424435
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 2620d2d9-d514-42e8-ac30-ea486cef39a3
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 2620d2d9-d514-42e8-ac30-ea486cef39a3
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
12 ms
|
|
[212217]
|
|
|
424436
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 7f103a42-31e3-4957-8401-0709124f5e74
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 7f103a42-31e3-4957-8401-0709124f5e74
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212218.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212218.0 (TID 212218) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-04f43c96-75d6-4766-bdaf-c2fa98dafdd1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212218.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212218.0 (TID 212218) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-04f43c96-75d6-4766-bdaf-c2fa98dafdd1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424437
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 7f103a42-31e3-4957-8401-0709124f5e74
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 7f103a42-31e3-4957-8401-0709124f5e74
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
11 ms
|
|
[212218]
|
|
|
424438
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = de03facc-5f9b-45d6-b28b-5aafdd60e3ad
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = de03facc-5f9b-45d6-b28b-5aafdd60e3ad
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212219.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212219.0 (TID 212219) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-66be5fc9-a573-4ab1-83e4-2b1e8f42f60d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212219.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212219.0 (TID 212219) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-66be5fc9-a573-4ab1-83e4-2b1e8f42f60d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424439
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = de03facc-5f9b-45d6-b28b-5aafdd60e3ad
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = de03facc-5f9b-45d6-b28b-5aafdd60e3ad
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
11 ms
|
|
[212219]
|
|
|
424440
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 90ca134f-ac7e-4620-9328-cd3fa3039c14
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 90ca134f-ac7e-4620-9328-cd3fa3039c14
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
24 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212220.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212220.0 (TID 212220) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-625899f3-2982-4ba0-8917-b42e3a39dce9-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212220.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212220.0 (TID 212220) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-625899f3-2982-4ba0-8917-b42e3a39dce9-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424441
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 90ca134f-ac7e-4620-9328-cd3fa3039c14
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 90ca134f-ac7e-4620-9328-cd3fa3039c14
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
21 ms
|
|
[212220]
|
|
|
424442
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 94825df4-5a34-4707-9334-19a3f9706a25
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 94825df4-5a34-4707-9334-19a3f9706a25
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212221.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212221.0 (TID 212221) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e33e7e82-4607-49e5-be37-e7176ce12312-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212221.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212221.0 (TID 212221) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e33e7e82-4607-49e5-be37-e7176ce12312-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424443
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 94825df4-5a34-4707-9334-19a3f9706a25
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 94825df4-5a34-4707-9334-19a3f9706a25
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
11 ms
|
|
[212221]
|
|
|
424444
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 114ff21d-db1b-4664-989c-d86fc8a02014
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 114ff21d-db1b-4664-989c-d86fc8a02014
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
23 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212222.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212222.0 (TID 212222) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-98fb9506-b539-4394-ae8e-026345cd491a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212222.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212222.0 (TID 212222) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-98fb9506-b539-4394-ae8e-026345cd491a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424445
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 114ff21d-db1b-4664-989c-d86fc8a02014
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 114ff21d-db1b-4664-989c-d86fc8a02014
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
20 ms
|
|
[212222]
|
|
|
424446
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 61f2d9a9-eba3-44db-8b51-6b17fbd8b2e6
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 61f2d9a9-eba3-44db-8b51-6b17fbd8b2e6
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212223.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212223.0 (TID 212223) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6c4de50b-ec91-4dab-91a0-95662982ed51-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212223.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212223.0 (TID 212223) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6c4de50b-ec91-4dab-91a0-95662982ed51-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424447
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 61f2d9a9-eba3-44db-8b51-6b17fbd8b2e6
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 61f2d9a9-eba3-44db-8b51-6b17fbd8b2e6
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
12 ms
|
|
[212223]
|
|
|
424448
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 25e9df8b-8c75-48a7-a913-d7682390be5f
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 25e9df8b-8c75-48a7-a913-d7682390be5f
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
25 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212224.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212224.0 (TID 212224) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c583f85e-fdd0-4fdc-a58b-acdf7402c200-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212224.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212224.0 (TID 212224) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c583f85e-fdd0-4fdc-a58b-acdf7402c200-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424449
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 25e9df8b-8c75-48a7-a913-d7682390be5f
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 25e9df8b-8c75-48a7-a913-d7682390be5f
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:46
|
22 ms
|
|
[212224]
|
|
|
424450
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6143ea2c-4b66-4838-80c1-8f45edac39d2
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6143ea2c-4b66-4838-80c1-8f45edac39d2
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212225.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212225.0 (TID 212225) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f68bce05-b0a2-4289-8d57-4ccec4ac4b72-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212225.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212225.0 (TID 212225) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f68bce05-b0a2-4289-8d57-4ccec4ac4b72-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424451
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6143ea2c-4b66-4838-80c1-8f45edac39d2
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6143ea2c-4b66-4838-80c1-8f45edac39d2
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
11 ms
|
|
[212225]
|
|
|
424452
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 8e69d23b-b16e-4812-9a40-179974d315d2
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 8e69d23b-b16e-4812-9a40-179974d315d2
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
19 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212226.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212226.0 (TID 212226) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d86954ed-b6a6-4063-89d6-b6e9c698c39b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212226.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212226.0 (TID 212226) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d86954ed-b6a6-4063-89d6-b6e9c698c39b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424453
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 8e69d23b-b16e-4812-9a40-179974d315d2
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 8e69d23b-b16e-4812-9a40-179974d315d2
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
14 ms
|
|
[212226]
|
|
|
424454
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6aa80ab3-1ad4-4a46-bd4d-24b7c7784d75
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6aa80ab3-1ad4-4a46-bd4d-24b7c7784d75
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212227.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212227.0 (TID 212227) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b622b4ea-3eda-4d09-b5c3-84979cdd544a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212227.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212227.0 (TID 212227) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b622b4ea-3eda-4d09-b5c3-84979cdd544a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424455
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6aa80ab3-1ad4-4a46-bd4d-24b7c7784d75
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6aa80ab3-1ad4-4a46-bd4d-24b7c7784d75
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
11 ms
|
|
[212227]
|
|
|
424456
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = eae08e34-d675-428a-9209-3a6744271c6e
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = eae08e34-d675-428a-9209-3a6744271c6e
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212228.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212228.0 (TID 212228) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2975f354-586e-497f-bd93-ee617f8a369c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212228.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212228.0 (TID 212228) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2975f354-586e-497f-bd93-ee617f8a369c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424457
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = eae08e34-d675-428a-9209-3a6744271c6e
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = eae08e34-d675-428a-9209-3a6744271c6e
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
11 ms
|
|
[212228]
|
|
|
424458
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e1999e2e-8700-4cbf-9c6e-3a420e61f23a
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e1999e2e-8700-4cbf-9c6e-3a420e61f23a
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212229.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212229.0 (TID 212229) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-33c5156b-ef3c-47b1-b868-1fcbcd1b8bde-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212229.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212229.0 (TID 212229) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-33c5156b-ef3c-47b1-b868-1fcbcd1b8bde-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424459
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e1999e2e-8700-4cbf-9c6e-3a420e61f23a
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e1999e2e-8700-4cbf-9c6e-3a420e61f23a
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
11 ms
|
|
[212229]
|
|
|
424460
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3c7340b5-6e9c-4e00-a64b-0fb05acba235
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3c7340b5-6e9c-4e00-a64b-0fb05acba235
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212230.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212230.0 (TID 212230) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5397e48f-5eda-4f54-974a-4666bafa2e17-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212230.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212230.0 (TID 212230) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5397e48f-5eda-4f54-974a-4666bafa2e17-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424461
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3c7340b5-6e9c-4e00-a64b-0fb05acba235
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 3c7340b5-6e9c-4e00-a64b-0fb05acba235
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
11 ms
|
|
[212230]
|
|
|
424462
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = f18e2842-2b9f-4fa0-bc26-2c41025bd6f3
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = f18e2842-2b9f-4fa0-bc26-2c41025bd6f3
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212231.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212231.0 (TID 212231) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-94d25253-1831-4606-bb4a-c3848f58abbe-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212231.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212231.0 (TID 212231) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-94d25253-1831-4606-bb4a-c3848f58abbe-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424463
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = f18e2842-2b9f-4fa0-bc26-2c41025bd6f3
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = f18e2842-2b9f-4fa0-bc26-2c41025bd6f3
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
12 ms
|
|
[212231]
|
|
|
424464
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 781ec00c-4864-46e6-9b87-aa821ee46d23
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 781ec00c-4864-46e6-9b87-aa821ee46d23
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212232.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212232.0 (TID 212232) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6e56f9bd-5f2e-4185-8099-5be2ef080b72-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212232.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212232.0 (TID 212232) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6e56f9bd-5f2e-4185-8099-5be2ef080b72-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424465
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 781ec00c-4864-46e6-9b87-aa821ee46d23
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 781ec00c-4864-46e6-9b87-aa821ee46d23
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
11 ms
|
|
[212232]
|
|
|
424466
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 748d4f95-4056-4052-acf8-789ce0e65ece
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 748d4f95-4056-4052-acf8-789ce0e65ece
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212233.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212233.0 (TID 212233) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-45080cc5-d46c-4d3c-a4a1-eba0d3863664-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212233.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212233.0 (TID 212233) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-45080cc5-d46c-4d3c-a4a1-eba0d3863664-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424467
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 748d4f95-4056-4052-acf8-789ce0e65ece
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 748d4f95-4056-4052-acf8-789ce0e65ece
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
11 ms
|
|
[212233]
|
|
|
424468
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e321f635-4e4e-4200-9657-0cf3ac5e861a
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e321f635-4e4e-4200-9657-0cf3ac5e861a
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
23 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212234.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212234.0 (TID 212234) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-92d6da24-655d-421c-86a2-d0e30782cca9-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212234.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212234.0 (TID 212234) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-92d6da24-655d-421c-86a2-d0e30782cca9-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424469
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e321f635-4e4e-4200-9657-0cf3ac5e861a
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e321f635-4e4e-4200-9657-0cf3ac5e861a
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
21 ms
|
|
[212234]
|
|
|
424470
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9ad93647-57d4-41d9-86bb-451be9628ace
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9ad93647-57d4-41d9-86bb-451be9628ace
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
18 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212235.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212235.0 (TID 212235) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f5cdcf0f-3ad1-4942-8051-c0c73329756d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212235.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212235.0 (TID 212235) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f5cdcf0f-3ad1-4942-8051-c0c73329756d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424471
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9ad93647-57d4-41d9-86bb-451be9628ace
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9ad93647-57d4-41d9-86bb-451be9628ace
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
14 ms
|
|
[212235]
|
|
|
424472
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 77d1c406-fb45-4f9d-8b1f-c5c2e9016023
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 77d1c406-fb45-4f9d-8b1f-c5c2e9016023
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212236.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212236.0 (TID 212236) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9847863f-ec7d-42cf-bd22-22061facbd50-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212236.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212236.0 (TID 212236) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9847863f-ec7d-42cf-bd22-22061facbd50-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424473
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 77d1c406-fb45-4f9d-8b1f-c5c2e9016023
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 77d1c406-fb45-4f9d-8b1f-c5c2e9016023
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
11 ms
|
|
[212236]
|
|
|
424474
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9e1612a5-b7f0-49de-8f53-fe70940a68fe
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9e1612a5-b7f0-49de-8f53-fe70940a68fe
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212237.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212237.0 (TID 212237) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-10cefb10-5f53-4d90-8c55-e3637d0f04b7-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212237.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212237.0 (TID 212237) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-10cefb10-5f53-4d90-8c55-e3637d0f04b7-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424475
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9e1612a5-b7f0-49de-8f53-fe70940a68fe
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9e1612a5-b7f0-49de-8f53-fe70940a68fe
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
11 ms
|
|
[212237]
|
|
|
424476
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = fd16799e-bec3-42ee-9761-7da4c9737536
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = fd16799e-bec3-42ee-9761-7da4c9737536
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212238.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212238.0 (TID 212238) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9988badf-de1c-453a-857b-f34918023c22-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212238.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212238.0 (TID 212238) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9988badf-de1c-453a-857b-f34918023c22-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424477
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = fd16799e-bec3-42ee-9761-7da4c9737536
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = fd16799e-bec3-42ee-9761-7da4c9737536
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
11 ms
|
|
[212238]
|
|
|
424478
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b67091fb-3a14-4c67-8bdf-08ed07d940ba
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b67091fb-3a14-4c67-8bdf-08ed07d940ba
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212239.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212239.0 (TID 212239) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-946579d6-3016-4dcc-af56-a88d8f9c725f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212239.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212239.0 (TID 212239) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-946579d6-3016-4dcc-af56-a88d8f9c725f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424479
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b67091fb-3a14-4c67-8bdf-08ed07d940ba
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b67091fb-3a14-4c67-8bdf-08ed07d940ba
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
11 ms
|
|
[212239]
|
|
|
424480
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 92b41fcd-f44a-4282-a825-09773ed00b8c
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 92b41fcd-f44a-4282-a825-09773ed00b8c
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212240.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212240.0 (TID 212240) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4b891a18-d002-44f6-8d86-20d014f92c5a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212240.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212240.0 (TID 212240) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4b891a18-d002-44f6-8d86-20d014f92c5a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424481
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 92b41fcd-f44a-4282-a825-09773ed00b8c
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 92b41fcd-f44a-4282-a825-09773ed00b8c
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
11 ms
|
|
[212240]
|
|
|
424482
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ef0e1140-bc04-41da-9939-316e12f78997
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ef0e1140-bc04-41da-9939-316e12f78997
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212241.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212241.0 (TID 212241) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-948f0598-e108-41d6-bf75-8fac63090296-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212241.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212241.0 (TID 212241) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-948f0598-e108-41d6-bf75-8fac63090296-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424483
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ef0e1140-bc04-41da-9939-316e12f78997
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ef0e1140-bc04-41da-9939-316e12f78997
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
11 ms
|
|
[212241]
|
|
|
424484
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a01053a3-b632-4b22-812a-8cf166a0bd44
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a01053a3-b632-4b22-812a-8cf166a0bd44
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212242.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212242.0 (TID 212242) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-63e0b25a-1d34-4b15-a339-3466d2843862-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212242.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212242.0 (TID 212242) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-63e0b25a-1d34-4b15-a339-3466d2843862-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424485
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a01053a3-b632-4b22-812a-8cf166a0bd44
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a01053a3-b632-4b22-812a-8cf166a0bd44
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
11 ms
|
|
[212242]
|
|
|
424486
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ae2ea4da-1411-41b7-a60f-7fdb96dfb507
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ae2ea4da-1411-41b7-a60f-7fdb96dfb507
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
19 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212243.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212243.0 (TID 212243) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-759c0a34-aa55-4145-b77f-665f635fe71e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212243.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212243.0 (TID 212243) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-759c0a34-aa55-4145-b77f-665f635fe71e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424487
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ae2ea4da-1411-41b7-a60f-7fdb96dfb507
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ae2ea4da-1411-41b7-a60f-7fdb96dfb507
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
17 ms
|
|
[212243]
|
|
|
424488
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d472038b-a230-481f-86d4-ff863d42ad97
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d472038b-a230-481f-86d4-ff863d42ad97
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
31 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212244.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212244.0 (TID 212244) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1fca19f1-8cd9-43f8-9701-f0b744b584f4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212244.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212244.0 (TID 212244) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1fca19f1-8cd9-43f8-9701-f0b744b584f4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424489
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d472038b-a230-481f-86d4-ff863d42ad97
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d472038b-a230-481f-86d4-ff863d42ad97
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
27 ms
|
|
[212244]
|
|
|
424490
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = dae8825f-1116-4c8d-b85a-ba240d48fbad
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = dae8825f-1116-4c8d-b85a-ba240d48fbad
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212245.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212245.0 (TID 212245) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-736f1077-7f19-4505-ab45-ba02bd6c9854-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212245.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212245.0 (TID 212245) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-736f1077-7f19-4505-ab45-ba02bd6c9854-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424491
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = dae8825f-1116-4c8d-b85a-ba240d48fbad
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = dae8825f-1116-4c8d-b85a-ba240d48fbad
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
12 ms
|
|
[212245]
|
|
|
424492
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = adc9fc92-1946-4f2f-8120-91610b5ea41e
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = adc9fc92-1946-4f2f-8120-91610b5ea41e
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
17 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212246.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212246.0 (TID 212246) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e59105bc-c2fa-4d73-a763-7944462fc639-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212246.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212246.0 (TID 212246) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e59105bc-c2fa-4d73-a763-7944462fc639-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424493
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = adc9fc92-1946-4f2f-8120-91610b5ea41e
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = adc9fc92-1946-4f2f-8120-91610b5ea41e
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
13 ms
|
|
[212246]
|
|
|
424494
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 039b92c0-2384-4e49-b3cb-ef6fa7e33c76
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 039b92c0-2384-4e49-b3cb-ef6fa7e33c76
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212247.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212247.0 (TID 212247) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5e4253bc-9617-4876-9071-2489e47e8b1b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212247.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212247.0 (TID 212247) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5e4253bc-9617-4876-9071-2489e47e8b1b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424495
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 039b92c0-2384-4e49-b3cb-ef6fa7e33c76
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 039b92c0-2384-4e49-b3cb-ef6fa7e33c76
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:47
|
13 ms
|
|
[212247]
|
|
|
424496
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a88fbc3a-6add-4886-a46c-4dbd58e96742
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a88fbc3a-6add-4886-a46c-4dbd58e96742
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
17 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212248.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212248.0 (TID 212248) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2db05d99-c847-4d91-b6ed-0076849552f2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212248.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212248.0 (TID 212248) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2db05d99-c847-4d91-b6ed-0076849552f2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424497
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a88fbc3a-6add-4886-a46c-4dbd58e96742
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a88fbc3a-6add-4886-a46c-4dbd58e96742
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
14 ms
|
|
[212248]
|
|
|
424498
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ee571566-22f5-4147-bd22-d4b4d6e73631
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ee571566-22f5-4147-bd22-d4b4d6e73631
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212249.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212249.0 (TID 212249) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8b2e1c7f-daea-4a91-bc50-41bf512a4f74-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212249.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212249.0 (TID 212249) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8b2e1c7f-daea-4a91-bc50-41bf512a4f74-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424499
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ee571566-22f5-4147-bd22-d4b4d6e73631
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ee571566-22f5-4147-bd22-d4b4d6e73631
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
14 ms
|
|
[212249]
|
|
|
424500
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 7c3d7013-6c09-4eed-9aab-38a2828d8498
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 7c3d7013-6c09-4eed-9aab-38a2828d8498
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212250.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212250.0 (TID 212250) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fe009366-c6dd-480d-b4a2-c466db0fbbb4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212250.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212250.0 (TID 212250) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fe009366-c6dd-480d-b4a2-c466db0fbbb4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424501
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 7c3d7013-6c09-4eed-9aab-38a2828d8498
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 7c3d7013-6c09-4eed-9aab-38a2828d8498
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
12 ms
|
|
[212250]
|
|
|
424502
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6c2de500-cf9c-4a8d-ba98-fcccc7bb396e
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6c2de500-cf9c-4a8d-ba98-fcccc7bb396e
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
20 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212251.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212251.0 (TID 212251) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-18007579-476a-46bd-b80b-03f7d79a9ae1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212251.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212251.0 (TID 212251) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-18007579-476a-46bd-b80b-03f7d79a9ae1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424503
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6c2de500-cf9c-4a8d-ba98-fcccc7bb396e
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6c2de500-cf9c-4a8d-ba98-fcccc7bb396e
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
16 ms
|
|
[212251]
|
|
|
424504
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 2f08fa62-92d4-4b09-9fca-fd0d2ffe1988
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 2f08fa62-92d4-4b09-9fca-fd0d2ffe1988
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212252.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212252.0 (TID 212252) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7cebc495-950e-4a00-96ca-d898b18abc04-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212252.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212252.0 (TID 212252) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7cebc495-950e-4a00-96ca-d898b18abc04-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424505
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 2f08fa62-92d4-4b09-9fca-fd0d2ffe1988
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 2f08fa62-92d4-4b09-9fca-fd0d2ffe1988
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
13 ms
|
|
[212252]
|
|
|
424506
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d4dcf2ab-26cf-4cff-b566-3533bc3c6149
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d4dcf2ab-26cf-4cff-b566-3533bc3c6149
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212253.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212253.0 (TID 212253) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-cc816191-d713-42aa-b7dd-e771713b19d1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212253.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212253.0 (TID 212253) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-cc816191-d713-42aa-b7dd-e771713b19d1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424507
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d4dcf2ab-26cf-4cff-b566-3533bc3c6149
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d4dcf2ab-26cf-4cff-b566-3533bc3c6149
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
12 ms
|
|
[212253]
|
|
|
424508
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 64d6f4a6-16ec-4087-9e54-83561d874124
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 64d6f4a6-16ec-4087-9e54-83561d874124
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
29 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212254.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212254.0 (TID 212254) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6e14c861-a284-4d4b-b1ff-09ee6923d8d6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212254.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212254.0 (TID 212254) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-6e14c861-a284-4d4b-b1ff-09ee6923d8d6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424509
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 64d6f4a6-16ec-4087-9e54-83561d874124
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 64d6f4a6-16ec-4087-9e54-83561d874124
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
26 ms
|
|
[212254]
|
|
|
424510
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 576b7416-4796-4531-8a68-f91938698dd9
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 576b7416-4796-4531-8a68-f91938698dd9
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212255.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212255.0 (TID 212255) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-58c41b2a-569a-40b1-be6c-43216eec0f8e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212255.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212255.0 (TID 212255) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-58c41b2a-569a-40b1-be6c-43216eec0f8e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424511
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 576b7416-4796-4531-8a68-f91938698dd9
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 576b7416-4796-4531-8a68-f91938698dd9
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
13 ms
|
|
[212255]
|
|
|
424512
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 47626677-072d-4e0d-835b-a3486d701fcc
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 47626677-072d-4e0d-835b-a3486d701fcc
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
17 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212256.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212256.0 (TID 212256) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e8ff3785-773e-47d6-b697-ba26e5beef77-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212256.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212256.0 (TID 212256) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e8ff3785-773e-47d6-b697-ba26e5beef77-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424513
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 47626677-072d-4e0d-835b-a3486d701fcc
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 47626677-072d-4e0d-835b-a3486d701fcc
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
14 ms
|
|
[212256]
|
|
|
424514
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 37bdb494-39c9-4df0-80f2-71e4095d7cf0
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 37bdb494-39c9-4df0-80f2-71e4095d7cf0
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212257.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212257.0 (TID 212257) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c7a8854a-5434-4ff6-8e64-9fb58bc54ec7-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212257.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212257.0 (TID 212257) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c7a8854a-5434-4ff6-8e64-9fb58bc54ec7-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424515
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 37bdb494-39c9-4df0-80f2-71e4095d7cf0
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 37bdb494-39c9-4df0-80f2-71e4095d7cf0
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
13 ms
|
|
[212257]
|
|
|
424516
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b42ddf55-8d45-48eb-90af-7f0790d54811
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b42ddf55-8d45-48eb-90af-7f0790d54811
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212258.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212258.0 (TID 212258) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8b3c152d-8592-4312-86e3-931719b72984-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212258.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212258.0 (TID 212258) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8b3c152d-8592-4312-86e3-931719b72984-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424517
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b42ddf55-8d45-48eb-90af-7f0790d54811
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b42ddf55-8d45-48eb-90af-7f0790d54811
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
13 ms
|
|
[212258]
|
|
|
424518
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 39931d29-a058-4008-a42c-d5200ef201e4
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 39931d29-a058-4008-a42c-d5200ef201e4
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212259.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212259.0 (TID 212259) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f20d7ddb-1259-46fa-86ae-f163094b810a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212259.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212259.0 (TID 212259) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f20d7ddb-1259-46fa-86ae-f163094b810a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424519
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 39931d29-a058-4008-a42c-d5200ef201e4
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 39931d29-a058-4008-a42c-d5200ef201e4
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
13 ms
|
|
[212259]
|
|
|
424520
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c738ac28-7112-47ce-97ff-fbbb96de6a24
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c738ac28-7112-47ce-97ff-fbbb96de6a24
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
24 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212260.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212260.0 (TID 212260) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c84891c5-cb43-47e1-b58a-4241512c28d2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212260.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212260.0 (TID 212260) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c84891c5-cb43-47e1-b58a-4241512c28d2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424521
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c738ac28-7112-47ce-97ff-fbbb96de6a24
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c738ac28-7112-47ce-97ff-fbbb96de6a24
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
21 ms
|
|
[212260]
|
|
|
424522
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = f2258848-8adc-4df8-9da1-939cbe9a49e4
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = f2258848-8adc-4df8-9da1-939cbe9a49e4
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212261.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212261.0 (TID 212261) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9b97edd6-be27-43ba-8bc5-7fa8ace5cc33-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212261.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212261.0 (TID 212261) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9b97edd6-be27-43ba-8bc5-7fa8ace5cc33-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424523
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = f2258848-8adc-4df8-9da1-939cbe9a49e4
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = f2258848-8adc-4df8-9da1-939cbe9a49e4
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
13 ms
|
|
[212261]
|
|
|
424524
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 7dc90fbe-5e7b-414d-a3f8-210e6ee23c13
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 7dc90fbe-5e7b-414d-a3f8-210e6ee23c13
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
18 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212262.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212262.0 (TID 212262) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7466715e-5eea-4cf2-876c-9528244253cb-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212262.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212262.0 (TID 212262) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7466715e-5eea-4cf2-876c-9528244253cb-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424525
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 7dc90fbe-5e7b-414d-a3f8-210e6ee23c13
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 7dc90fbe-5e7b-414d-a3f8-210e6ee23c13
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
14 ms
|
|
[212262]
|
|
|
424526
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ea8fbcb2-3e0f-43e5-bfb8-51f779d8108d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ea8fbcb2-3e0f-43e5-bfb8-51f779d8108d
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212263.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212263.0 (TID 212263) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1236b022-d8c0-46d7-83f9-c82de381c5e0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212263.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212263.0 (TID 212263) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1236b022-d8c0-46d7-83f9-c82de381c5e0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424527
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ea8fbcb2-3e0f-43e5-bfb8-51f779d8108d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ea8fbcb2-3e0f-43e5-bfb8-51f779d8108d
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
11 ms
|
|
[212263]
|
|
|
424528
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 7ee17385-a200-4a33-bda6-cea948cad975
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 7ee17385-a200-4a33-bda6-cea948cad975
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
23 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212264.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212264.0 (TID 212264) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e9eefcad-0932-4142-aa95-b5e57c31f463-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212264.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212264.0 (TID 212264) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e9eefcad-0932-4142-aa95-b5e57c31f463-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424529
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 7ee17385-a200-4a33-bda6-cea948cad975
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 7ee17385-a200-4a33-bda6-cea948cad975
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
20 ms
|
|
[212264]
|
|
|
424530
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 0e8b5303-1801-45a1-b854-b1c346792441
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 0e8b5303-1801-45a1-b854-b1c346792441
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212265.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212265.0 (TID 212265) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e646570e-c378-4562-b1e4-25a51903cbd5-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212265.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212265.0 (TID 212265) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e646570e-c378-4562-b1e4-25a51903cbd5-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424531
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 0e8b5303-1801-45a1-b854-b1c346792441
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 0e8b5303-1801-45a1-b854-b1c346792441
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
11 ms
|
|
[212265]
|
|
|
424532
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 15bc81db-d2fa-4f30-b250-f80ec30cea4d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 15bc81db-d2fa-4f30-b250-f80ec30cea4d
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212266.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212266.0 (TID 212266) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-94100587-db16-4198-9e2a-e2da8b3a1c75-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212266.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212266.0 (TID 212266) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-94100587-db16-4198-9e2a-e2da8b3a1c75-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424533
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 15bc81db-d2fa-4f30-b250-f80ec30cea4d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 15bc81db-d2fa-4f30-b250-f80ec30cea4d
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
11 ms
|
|
[212266]
|
|
|
424534
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 78503f0b-d766-48bf-b805-2c17fe8c9b86
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 78503f0b-d766-48bf-b805-2c17fe8c9b86
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212267.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212267.0 (TID 212267) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4a157d01-f6a5-4468-98b2-0e717539def9-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212267.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212267.0 (TID 212267) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4a157d01-f6a5-4468-98b2-0e717539def9-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424535
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 78503f0b-d766-48bf-b805-2c17fe8c9b86
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 78503f0b-d766-48bf-b805-2c17fe8c9b86
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
11 ms
|
|
[212267]
|
|
|
424536
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d021f24d-61cf-4e47-9753-8a8e0a8936d8
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d021f24d-61cf-4e47-9753-8a8e0a8936d8
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212268.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212268.0 (TID 212268) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-17f619a7-6ed9-4d4c-955d-69cd82e9fc82-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212268.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212268.0 (TID 212268) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-17f619a7-6ed9-4d4c-955d-69cd82e9fc82-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424537
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d021f24d-61cf-4e47-9753-8a8e0a8936d8
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d021f24d-61cf-4e47-9753-8a8e0a8936d8
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
10 ms
|
|
[212268]
|
|
|
424538
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 800ed3ea-6cbc-4adc-bc3f-e459bca06ca9
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 800ed3ea-6cbc-4adc-bc3f-e459bca06ca9
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212269.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212269.0 (TID 212269) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2b7047a2-db3a-4b35-abff-8aa6cf2a3400-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212269.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212269.0 (TID 212269) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2b7047a2-db3a-4b35-abff-8aa6cf2a3400-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424539
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 800ed3ea-6cbc-4adc-bc3f-e459bca06ca9
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 800ed3ea-6cbc-4adc-bc3f-e459bca06ca9
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
11 ms
|
|
[212269]
|
|
|
424540
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d89169a0-917f-4d70-99d6-a25d6fa6a042
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d89169a0-917f-4d70-99d6-a25d6fa6a042
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212270.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212270.0 (TID 212270) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c00a5b6b-e323-4b1b-93d1-e77fa80c8979-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212270.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212270.0 (TID 212270) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c00a5b6b-e323-4b1b-93d1-e77fa80c8979-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424541
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d89169a0-917f-4d70-99d6-a25d6fa6a042
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d89169a0-917f-4d70-99d6-a25d6fa6a042
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:48
|
11 ms
|
|
[212270]
|
|
|
424542
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b56f5d40-c621-4758-856d-5c21b0ebb65e
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b56f5d40-c621-4758-856d-5c21b0ebb65e
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212271.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212271.0 (TID 212271) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-80beb51a-d156-436f-9ba6-3105b4e030ef-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212271.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212271.0 (TID 212271) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-80beb51a-d156-436f-9ba6-3105b4e030ef-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424543
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b56f5d40-c621-4758-856d-5c21b0ebb65e
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b56f5d40-c621-4758-856d-5c21b0ebb65e
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
11 ms
|
|
[212271]
|
|
|
424544
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1bee717e-8e74-44fb-a307-42a8407e61a4
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1bee717e-8e74-44fb-a307-42a8407e61a4
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212272.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212272.0 (TID 212272) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a289c2d3-7ee7-4af8-908d-91276fc6c948-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212272.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212272.0 (TID 212272) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a289c2d3-7ee7-4af8-908d-91276fc6c948-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424545
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1bee717e-8e74-44fb-a307-42a8407e61a4
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1bee717e-8e74-44fb-a307-42a8407e61a4
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
11 ms
|
|
[212272]
|
|
|
424546
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b312a8db-78b6-4d81-a42f-a63e454c2eab
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b312a8db-78b6-4d81-a42f-a63e454c2eab
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212273.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212273.0 (TID 212273) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4f7fc7b4-a1ad-4ec1-9ff6-6bbda2a09199-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212273.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212273.0 (TID 212273) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4f7fc7b4-a1ad-4ec1-9ff6-6bbda2a09199-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424547
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b312a8db-78b6-4d81-a42f-a63e454c2eab
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b312a8db-78b6-4d81-a42f-a63e454c2eab
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
11 ms
|
|
[212273]
|
|
|
424548
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 85519fa4-dc3d-47a3-8e3a-3e2295495912
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 85519fa4-dc3d-47a3-8e3a-3e2295495912
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
29 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212274.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212274.0 (TID 212274) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-671eed73-8d88-4541-a485-7e8b50e5b9f6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212274.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212274.0 (TID 212274) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-671eed73-8d88-4541-a485-7e8b50e5b9f6-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424549
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 85519fa4-dc3d-47a3-8e3a-3e2295495912
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 85519fa4-dc3d-47a3-8e3a-3e2295495912
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
26 ms
|
|
[212274]
|
|
|
424550
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a1695f21-53e8-4194-b497-a26032a86cfc
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a1695f21-53e8-4194-b497-a26032a86cfc
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
17 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212275.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212275.0 (TID 212275) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-cef884ec-3b1e-4664-b787-a9e72f5dc23f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212275.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212275.0 (TID 212275) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-cef884ec-3b1e-4664-b787-a9e72f5dc23f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424551
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a1695f21-53e8-4194-b497-a26032a86cfc
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a1695f21-53e8-4194-b497-a26032a86cfc
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
15 ms
|
|
[212275]
|
|
|
424552
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 94f5e144-d55b-4032-b4a0-f93bbac06871
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 94f5e144-d55b-4032-b4a0-f93bbac06871
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212276.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212276.0 (TID 212276) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b69e5988-0bd1-4005-ac9f-893df5b1576e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212276.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212276.0 (TID 212276) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b69e5988-0bd1-4005-ac9f-893df5b1576e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424553
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 94f5e144-d55b-4032-b4a0-f93bbac06871
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 94f5e144-d55b-4032-b4a0-f93bbac06871
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
12 ms
|
|
[212276]
|
|
|
424554
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b017ff61-8fa5-4982-85a5-a9050820e695
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b017ff61-8fa5-4982-85a5-a9050820e695
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212277.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212277.0 (TID 212277) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3385322b-5802-499d-8eeb-b2b4f3aaba60-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212277.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212277.0 (TID 212277) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3385322b-5802-499d-8eeb-b2b4f3aaba60-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424555
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b017ff61-8fa5-4982-85a5-a9050820e695
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b017ff61-8fa5-4982-85a5-a9050820e695
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
11 ms
|
|
[212277]
|
|
|
424556
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 70a4b97d-7d29-42ea-a499-180c0c1a0ad4
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 70a4b97d-7d29-42ea-a499-180c0c1a0ad4
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
24 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212278.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212278.0 (TID 212278) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ecb4783d-b185-412a-8c95-00093b491fd1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212278.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212278.0 (TID 212278) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ecb4783d-b185-412a-8c95-00093b491fd1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424557
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 70a4b97d-7d29-42ea-a499-180c0c1a0ad4
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 70a4b97d-7d29-42ea-a499-180c0c1a0ad4
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
22 ms
|
|
[212278]
|
|
|
424558
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 8258b84c-f189-4e70-8adf-bea3c7ffadac
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 8258b84c-f189-4e70-8adf-bea3c7ffadac
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212279.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212279.0 (TID 212279) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-bd09a01f-291e-42bb-bbef-00f8ec820bc2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212279.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212279.0 (TID 212279) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-bd09a01f-291e-42bb-bbef-00f8ec820bc2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424559
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 8258b84c-f189-4e70-8adf-bea3c7ffadac
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 8258b84c-f189-4e70-8adf-bea3c7ffadac
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
12 ms
|
|
[212279]
|
|
|
424560
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = efaff165-90fd-4cdf-886c-6bc325935ca4
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = efaff165-90fd-4cdf-886c-6bc325935ca4
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
25 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212280.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212280.0 (TID 212280) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b2eaf03d-2307-42c9-ac17-721ea90a627b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212280.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212280.0 (TID 212280) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b2eaf03d-2307-42c9-ac17-721ea90a627b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424561
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = efaff165-90fd-4cdf-886c-6bc325935ca4
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = efaff165-90fd-4cdf-886c-6bc325935ca4
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
21 ms
|
|
[212280]
|
|
|
424562
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 40ba4a46-7d85-4120-965d-1d6dc51cf416
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 40ba4a46-7d85-4120-965d-1d6dc51cf416
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212281.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212281.0 (TID 212281) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1f41df1e-afea-4a63-9f82-62a0d43cf71e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212281.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212281.0 (TID 212281) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1f41df1e-afea-4a63-9f82-62a0d43cf71e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424563
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 40ba4a46-7d85-4120-965d-1d6dc51cf416
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 40ba4a46-7d85-4120-965d-1d6dc51cf416
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
11 ms
|
|
[212281]
|
|
|
424564
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4791e249-8911-4d2b-9d0f-bd4b88a1e2dc
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4791e249-8911-4d2b-9d0f-bd4b88a1e2dc
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212282.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212282.0 (TID 212282) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-15dc0411-e1ca-4421-b360-757b5a47357d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212282.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212282.0 (TID 212282) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-15dc0411-e1ca-4421-b360-757b5a47357d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424565
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4791e249-8911-4d2b-9d0f-bd4b88a1e2dc
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4791e249-8911-4d2b-9d0f-bd4b88a1e2dc
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
11 ms
|
|
[212282]
|
|
|
424566
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = caee02f1-9de9-49e9-8a9c-4430d9191f7b
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = caee02f1-9de9-49e9-8a9c-4430d9191f7b
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212283.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212283.0 (TID 212283) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d770c263-dc3b-445a-a193-a3d0ad55c01e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212283.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212283.0 (TID 212283) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d770c263-dc3b-445a-a193-a3d0ad55c01e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.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:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424567
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = caee02f1-9de9-49e9-8a9c-4430d9191f7b
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = caee02f1-9de9-49e9-8a9c-4430d9191f7b
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
11 ms
|
|
[212283]
|
|
|
424568
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5ec8944e-e068-4fb5-8648-e884108dd95c
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5ec8944e-e068-4fb5-8648-e884108dd95c
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
27 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 212284.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212284.0 (TID 212284) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-cc10633a-e625-45b4-8f09-045dbf5b2e9c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 212284.0 failed 1 times, most recent failure: Lost task 0.0 in stage 212284.0 (TID 212284) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-cc10633a-e625-45b4-8f09-045dbf5b2e9c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
424569
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5ec8944e-e068-4fb5-8648-e884108dd95c
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5ec8944e-e068-4fb5-8648-e884108dd95c
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1034)
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:199)
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:222)
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:91)
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 12:04:49
|
24 ms
|
|
[212284]
|
|