|
298890
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9d6b09f5-b883-431c-815d-75869ac41508
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9d6b09f5-b883-431c-815d-75869ac41508
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 11:20:09
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149445.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149445.0 (TID 149445) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-968fc7cd-34cc-44c1-8eed-cf2eba0b9b2e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149445.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149445.0 (TID 149445) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-968fc7cd-34cc-44c1-8eed-cf2eba0b9b2e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298891
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9d6b09f5-b883-431c-815d-75869ac41508
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9d6b09f5-b883-431c-815d-75869ac41508
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:09
|
11 ms
|
|
[149445]
|
|
|
298888
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ab5a861b-8544-4d51-8c61-3f93428d43fc
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ab5a861b-8544-4d51-8c61-3f93428d43fc
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:08
|
30 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149444.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149444.0 (TID 149444) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5a49381d-5560-4153-9812-0db18c70f822-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149444.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149444.0 (TID 149444) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5a49381d-5560-4153-9812-0db18c70f822-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298889
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ab5a861b-8544-4d51-8c61-3f93428d43fc
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ab5a861b-8544-4d51-8c61-3f93428d43fc
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:08
|
28 ms
|
|
[149444]
|
|
|
298886
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4edc35d7-32bd-4a15-8851-7de3d6ef3f10
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4edc35d7-32bd-4a15-8851-7de3d6ef3f10
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 11:20:08
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149443.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149443.0 (TID 149443) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-010fbf1d-c061-4e93-83fe-6f920414e5ec-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149443.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149443.0 (TID 149443) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-010fbf1d-c061-4e93-83fe-6f920414e5ec-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298887
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4edc35d7-32bd-4a15-8851-7de3d6ef3f10
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4edc35d7-32bd-4a15-8851-7de3d6ef3f10
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:08
|
10 ms
|
|
[149443]
|
|
|
298884
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 529b681e-78d7-40e2-b2e1-71ae449cf335
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 529b681e-78d7-40e2-b2e1-71ae449cf335
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:08
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149442.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149442.0 (TID 149442) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ea5e366a-9917-4e65-8dd0-8dff9292c63a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149442.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149442.0 (TID 149442) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ea5e366a-9917-4e65-8dd0-8dff9292c63a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298885
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 529b681e-78d7-40e2-b2e1-71ae449cf335
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 529b681e-78d7-40e2-b2e1-71ae449cf335
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:08
|
12 ms
|
|
[149442]
|
|
|
298882
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d8ba7a83-b61d-4241-a550-5d16d33f1e8a
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d8ba7a83-b61d-4241-a550-5d16d33f1e8a
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 11:20:08
|
19 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149441.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149441.0 (TID 149441) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0e3bc3be-3484-4fbf-af01-629634214ba2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149441.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149441.0 (TID 149441) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0e3bc3be-3484-4fbf-af01-629634214ba2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298883
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d8ba7a83-b61d-4241-a550-5d16d33f1e8a
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d8ba7a83-b61d-4241-a550-5d16d33f1e8a
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:08
|
17 ms
|
|
[149441]
|
|
|
298880
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 41991abd-1eed-4f95-b99d-08797ad756cc
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 41991abd-1eed-4f95-b99d-08797ad756cc
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:08
|
20 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149440.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149440.0 (TID 149440) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ae82f95e-6807-4e7d-81fb-98943925b50c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149440.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149440.0 (TID 149440) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ae82f95e-6807-4e7d-81fb-98943925b50c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298881
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 41991abd-1eed-4f95-b99d-08797ad756cc
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 41991abd-1eed-4f95-b99d-08797ad756cc
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:08
|
17 ms
|
|
[149440]
|
|
|
298878
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 430a5ee7-3add-4e45-a917-c79bb039d139
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 430a5ee7-3add-4e45-a917-c79bb039d139
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 11:20:08
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149439.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149439.0 (TID 149439) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f5f9a9ac-6b38-45a9-81a2-ce7912dbc1ba-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149439.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149439.0 (TID 149439) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f5f9a9ac-6b38-45a9-81a2-ce7912dbc1ba-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298879
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 430a5ee7-3add-4e45-a917-c79bb039d139
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 430a5ee7-3add-4e45-a917-c79bb039d139
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:08
|
11 ms
|
|
[149439]
|
|
|
298876
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = be275db2-9c53-492d-8297-95059dc81136
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = be275db2-9c53-492d-8297-95059dc81136
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:08
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149438.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149438.0 (TID 149438) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-69e00e32-b045-47bf-9f54-f210287fd6a0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149438.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149438.0 (TID 149438) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-69e00e32-b045-47bf-9f54-f210287fd6a0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298877
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = be275db2-9c53-492d-8297-95059dc81136
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = be275db2-9c53-492d-8297-95059dc81136
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:08
|
11 ms
|
|
[149438]
|
|
|
298874
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 70637390-3072-4393-896d-545f8e291bb2
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 70637390-3072-4393-896d-545f8e291bb2
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 11:20:08
|
25 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149437.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149437.0 (TID 149437) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-cf03bee7-2fcf-4ae6-8ca7-3e57c312376f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149437.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149437.0 (TID 149437) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-cf03bee7-2fcf-4ae6-8ca7-3e57c312376f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298875
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 70637390-3072-4393-896d-545f8e291bb2
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 70637390-3072-4393-896d-545f8e291bb2
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:08
|
22 ms
|
|
[149437]
|
|
|
298872
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e5cca7ad-04ec-44ad-9b4e-42de4994bf7f
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e5cca7ad-04ec-44ad-9b4e-42de4994bf7f
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:08
|
20 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149436.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149436.0 (TID 149436) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ae2ad175-02fa-45d8-85c8-b292e5006da3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149436.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149436.0 (TID 149436) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ae2ad175-02fa-45d8-85c8-b292e5006da3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298873
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e5cca7ad-04ec-44ad-9b4e-42de4994bf7f
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e5cca7ad-04ec-44ad-9b4e-42de4994bf7f
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:08
|
18 ms
|
|
[149436]
|
|
|
298870
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 18eb210f-1683-4e05-af41-3147f8cd4951
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 18eb210f-1683-4e05-af41-3147f8cd4951
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 11:20:08
|
17 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149435.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149435.0 (TID 149435) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9e292c6d-dbb9-4842-92bc-2e4ff7d58d11-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149435.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149435.0 (TID 149435) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9e292c6d-dbb9-4842-92bc-2e4ff7d58d11-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298871
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 18eb210f-1683-4e05-af41-3147f8cd4951
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 18eb210f-1683-4e05-af41-3147f8cd4951
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:08
|
13 ms
|
|
[149435]
|
|
|
298868
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 51692194-fd68-492a-8ae0-10fbf39fa5bc
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 51692194-fd68-492a-8ae0-10fbf39fa5bc
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:08
|
34 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149434.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149434.0 (TID 149434) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-25874c6d-27cd-4ff7-b7a5-eb967159c319-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149434.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149434.0 (TID 149434) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-25874c6d-27cd-4ff7-b7a5-eb967159c319-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298869
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 51692194-fd68-492a-8ae0-10fbf39fa5bc
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 51692194-fd68-492a-8ae0-10fbf39fa5bc
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:08
|
31 ms
|
|
[149434]
|
|
|
298866
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 723cde20-3522-4262-9ae5-c953b4f20b0d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 723cde20-3522-4262-9ae5-c953b4f20b0d
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 11:20:08
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149433.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149433.0 (TID 149433) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9b390767-bc52-4771-acae-0d4be3b93c63-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149433.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149433.0 (TID 149433) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9b390767-bc52-4771-acae-0d4be3b93c63-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298867
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 723cde20-3522-4262-9ae5-c953b4f20b0d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 723cde20-3522-4262-9ae5-c953b4f20b0d
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:08
|
11 ms
|
|
[149433]
|
|
|
298864
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 64c61e44-918e-41aa-bcdd-d81c0fcf84ec
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 64c61e44-918e-41aa-bcdd-d81c0fcf84ec
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:08
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149432.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149432.0 (TID 149432) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-822be724-5cec-4d25-a550-da498bbf69d8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149432.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149432.0 (TID 149432) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-822be724-5cec-4d25-a550-da498bbf69d8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298865
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 64c61e44-918e-41aa-bcdd-d81c0fcf84ec
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 64c61e44-918e-41aa-bcdd-d81c0fcf84ec
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:08
|
11 ms
|
|
[149432]
|
|
|
298862
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6cac7256-9aac-404d-b6fa-700335b55533
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6cac7256-9aac-404d-b6fa-700335b55533
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 11:20:08
|
19 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149431.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149431.0 (TID 149431) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-cf88aa8c-09f8-4c63-836b-93af264cb12b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149431.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149431.0 (TID 149431) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-cf88aa8c-09f8-4c63-836b-93af264cb12b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298863
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6cac7256-9aac-404d-b6fa-700335b55533
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6cac7256-9aac-404d-b6fa-700335b55533
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:08
|
17 ms
|
|
[149431]
|
|
|
298860
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 31629c4d-4efd-4421-9d0e-83e79109040d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 31629c4d-4efd-4421-9d0e-83e79109040d
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:08
|
21 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149430.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149430.0 (TID 149430) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fb075525-ef0c-4a52-9aa0-58dd602ec9b0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149430.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149430.0 (TID 149430) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fb075525-ef0c-4a52-9aa0-58dd602ec9b0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298861
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 31629c4d-4efd-4421-9d0e-83e79109040d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 31629c4d-4efd-4421-9d0e-83e79109040d
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:08
|
18 ms
|
|
[149430]
|
|
|
298858
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9d6403f5-9610-4176-9006-72ba9c2c0626
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9d6403f5-9610-4176-9006-72ba9c2c0626
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 11:20:08
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149429.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149429.0 (TID 149429) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1f756911-d058-42cd-8735-e6da32218d55-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149429.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149429.0 (TID 149429) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1f756911-d058-42cd-8735-e6da32218d55-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298859
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9d6403f5-9610-4176-9006-72ba9c2c0626
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9d6403f5-9610-4176-9006-72ba9c2c0626
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:08
|
11 ms
|
|
[149429]
|
|
|
298856
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4e201f75-50bc-4816-ac17-1040760b8804
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4e201f75-50bc-4816-ac17-1040760b8804
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:08
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149428.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149428.0 (TID 149428) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2c828ace-676f-4e7e-83b3-d597af473faf-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149428.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149428.0 (TID 149428) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2c828ace-676f-4e7e-83b3-d597af473faf-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298857
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4e201f75-50bc-4816-ac17-1040760b8804
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4e201f75-50bc-4816-ac17-1040760b8804
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:08
|
11 ms
|
|
[149428]
|
|
|
298854
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4d21db72-e3f0-468f-b13c-f0cf8e7f8344
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4d21db72-e3f0-468f-b13c-f0cf8e7f8344
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 11:20:08
|
19 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149427.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149427.0 (TID 149427) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ff07d0f9-122f-48da-bca4-6f3350347252-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149427.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149427.0 (TID 149427) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ff07d0f9-122f-48da-bca4-6f3350347252-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298855
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4d21db72-e3f0-468f-b13c-f0cf8e7f8344
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4d21db72-e3f0-468f-b13c-f0cf8e7f8344
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:08
|
17 ms
|
|
[149427]
|
|
|
298852
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b41ba7ca-7190-4366-8b4f-51a88f20730d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b41ba7ca-7190-4366-8b4f-51a88f20730d
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:08
|
20 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149426.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149426.0 (TID 149426) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-72663360-8827-45c9-ae70-4455fbba2a9f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149426.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149426.0 (TID 149426) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-72663360-8827-45c9-ae70-4455fbba2a9f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298853
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b41ba7ca-7190-4366-8b4f-51a88f20730d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b41ba7ca-7190-4366-8b4f-51a88f20730d
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:08
|
17 ms
|
|
[149426]
|
|
|
298850
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4fc21dcf-1f3c-4360-aca6-882653b01ce5
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4fc21dcf-1f3c-4360-aca6-882653b01ce5
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 11:20:08
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149425.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149425.0 (TID 149425) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2c4c343e-9ad5-47ad-9c07-6296a06595df-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149425.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149425.0 (TID 149425) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2c4c343e-9ad5-47ad-9c07-6296a06595df-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298851
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4fc21dcf-1f3c-4360-aca6-882653b01ce5
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 4fc21dcf-1f3c-4360-aca6-882653b01ce5
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:08
|
12 ms
|
|
[149425]
|
|
|
298848
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 015f3910-931b-4c57-8dbe-cb792f5a35fe
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 015f3910-931b-4c57-8dbe-cb792f5a35fe
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:08
|
30 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149424.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149424.0 (TID 149424) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-cb8b4356-43ea-4c23-8265-c219b8d6b224-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149424.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149424.0 (TID 149424) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-cb8b4356-43ea-4c23-8265-c219b8d6b224-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298849
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 015f3910-931b-4c57-8dbe-cb792f5a35fe
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 015f3910-931b-4c57-8dbe-cb792f5a35fe
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:08
|
27 ms
|
|
[149424]
|
|
|
298846
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c23216e5-1b40-40d8-833a-bb6653eb9b55
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c23216e5-1b40-40d8-833a-bb6653eb9b55
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 11:20:08
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149423.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149423.0 (TID 149423) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8391a23f-6a45-4cf9-ac3a-0283284bb85f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149423.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149423.0 (TID 149423) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8391a23f-6a45-4cf9-ac3a-0283284bb85f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298847
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c23216e5-1b40-40d8-833a-bb6653eb9b55
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c23216e5-1b40-40d8-833a-bb6653eb9b55
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:08
|
11 ms
|
|
[149423]
|
|
|
298844
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 87f84d36-0190-4c9d-9e96-bf31f12acb7a
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 87f84d36-0190-4c9d-9e96-bf31f12acb7a
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:08
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149422.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149422.0 (TID 149422) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3a8b001a-b65c-4e2f-bb44-b1546a096c5f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149422.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149422.0 (TID 149422) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3a8b001a-b65c-4e2f-bb44-b1546a096c5f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298845
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 87f84d36-0190-4c9d-9e96-bf31f12acb7a
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 87f84d36-0190-4c9d-9e96-bf31f12acb7a
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:08
|
11 ms
|
|
[149422]
|
|
|
298842
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = fdf5df9f-828c-464f-9753-b6404f242b3e
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = fdf5df9f-828c-464f-9753-b6404f242b3e
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 11:20:08
|
19 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149421.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149421.0 (TID 149421) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-239b54fd-ce56-4c07-955a-f3d5998d3535-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149421.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149421.0 (TID 149421) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-239b54fd-ce56-4c07-955a-f3d5998d3535-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298843
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = fdf5df9f-828c-464f-9753-b6404f242b3e
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = fdf5df9f-828c-464f-9753-b6404f242b3e
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:08
|
17 ms
|
|
[149421]
|
|
|
298840
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 80b52d3b-891c-4897-a39b-167aea1424bd
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 80b52d3b-891c-4897-a39b-167aea1424bd
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:07
|
20 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149420.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149420.0 (TID 149420) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4cea2c42-ab33-48bb-a6b3-ad34a1546a4d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149420.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149420.0 (TID 149420) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-4cea2c42-ab33-48bb-a6b3-ad34a1546a4d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298841
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 80b52d3b-891c-4897-a39b-167aea1424bd
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 80b52d3b-891c-4897-a39b-167aea1424bd
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:07
|
17 ms
|
|
[149420]
|
|
|
298838
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 94c08ee2-7ea0-4a0e-9e12-4a1c78f205c1
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 94c08ee2-7ea0-4a0e-9e12-4a1c78f205c1
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 11:20:07
|
16 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149419.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149419.0 (TID 149419) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fe2384ff-1ec0-44c6-8608-3e70426b207b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149419.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149419.0 (TID 149419) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fe2384ff-1ec0-44c6-8608-3e70426b207b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298839
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 94c08ee2-7ea0-4a0e-9e12-4a1c78f205c1
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 94c08ee2-7ea0-4a0e-9e12-4a1c78f205c1
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:07
|
13 ms
|
|
[149419]
|
|
|
298836
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5ebd41eb-60b1-4d21-b12a-b4a96f217f5b
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5ebd41eb-60b1-4d21-b12a-b4a96f217f5b
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:07
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149418.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149418.0 (TID 149418) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2d3f95e8-b3c6-462d-b42a-acb4ed57f890-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149418.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149418.0 (TID 149418) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2d3f95e8-b3c6-462d-b42a-acb4ed57f890-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298837
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5ebd41eb-60b1-4d21-b12a-b4a96f217f5b
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 5ebd41eb-60b1-4d21-b12a-b4a96f217f5b
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:07
|
11 ms
|
|
[149418]
|
|
|
298834
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 60d224ed-4ae9-4b57-be52-706bd0eee016
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 60d224ed-4ae9-4b57-be52-706bd0eee016
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 11:20:07
|
20 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149417.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149417.0 (TID 149417) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7f3a6ec6-fe00-401f-8698-43629edd4172-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149417.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149417.0 (TID 149417) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7f3a6ec6-fe00-401f-8698-43629edd4172-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298835
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 60d224ed-4ae9-4b57-be52-706bd0eee016
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 60d224ed-4ae9-4b57-be52-706bd0eee016
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:07
|
18 ms
|
|
[149417]
|
|
|
298832
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 89499fa2-818f-4004-bd86-8ffc1053459e
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 89499fa2-818f-4004-bd86-8ffc1053459e
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:07
|
21 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149416.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149416.0 (TID 149416) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e2a57741-4354-4d55-b937-8b2958281b46-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149416.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149416.0 (TID 149416) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-e2a57741-4354-4d55-b937-8b2958281b46-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298833
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 89499fa2-818f-4004-bd86-8ffc1053459e
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 89499fa2-818f-4004-bd86-8ffc1053459e
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:07
|
19 ms
|
|
[149416]
|
|
|
298830
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 61adacc2-2775-4bbd-94d0-08777aa74606
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 61adacc2-2775-4bbd-94d0-08777aa74606
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 11:20:07
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149415.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149415.0 (TID 149415) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-cb843685-1edd-406c-88eb-5ba40c5dc9c0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149415.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149415.0 (TID 149415) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-cb843685-1edd-406c-88eb-5ba40c5dc9c0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298831
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 61adacc2-2775-4bbd-94d0-08777aa74606
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 61adacc2-2775-4bbd-94d0-08777aa74606
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:07
|
13 ms
|
|
[149415]
|
|
|
298828
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 218977ba-50aa-4876-aeac-47621cac4857
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 218977ba-50aa-4876-aeac-47621cac4857
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:07
|
31 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149414.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149414.0 (TID 149414) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-705d7c70-a1d4-4cc2-8fc9-d424be168116-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149414.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149414.0 (TID 149414) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-705d7c70-a1d4-4cc2-8fc9-d424be168116-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298829
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 218977ba-50aa-4876-aeac-47621cac4857
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 218977ba-50aa-4876-aeac-47621cac4857
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:07
|
29 ms
|
|
[149414]
|
|
|
298826
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = f963b87d-eebb-4ac9-b922-d324406a56fe
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = f963b87d-eebb-4ac9-b922-d324406a56fe
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 11:20:07
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149413.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149413.0 (TID 149413) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-805add19-eda2-486d-9ebc-71cb687a4a16-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149413.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149413.0 (TID 149413) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-805add19-eda2-486d-9ebc-71cb687a4a16-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298827
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = f963b87d-eebb-4ac9-b922-d324406a56fe
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = f963b87d-eebb-4ac9-b922-d324406a56fe
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:07
|
12 ms
|
|
[149413]
|
|
|
298824
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a5863777-9efc-47d1-8928-2ec818e2d283
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a5863777-9efc-47d1-8928-2ec818e2d283
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:07
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149412.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149412.0 (TID 149412) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-48453fe1-18c3-4f80-bc34-543db05e6230-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149412.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149412.0 (TID 149412) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-48453fe1-18c3-4f80-bc34-543db05e6230-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298825
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a5863777-9efc-47d1-8928-2ec818e2d283
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a5863777-9efc-47d1-8928-2ec818e2d283
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:07
|
11 ms
|
|
[149412]
|
|
|
298822
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6f10b692-7d65-4b18-998f-c9ed6a1aa6e0
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6f10b692-7d65-4b18-998f-c9ed6a1aa6e0
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 11:20:07
|
21 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149411.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149411.0 (TID 149411) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ed73354b-f67d-4b06-a58a-5eb628829344-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149411.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149411.0 (TID 149411) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ed73354b-f67d-4b06-a58a-5eb628829344-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298823
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6f10b692-7d65-4b18-998f-c9ed6a1aa6e0
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6f10b692-7d65-4b18-998f-c9ed6a1aa6e0
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:07
|
18 ms
|
|
[149411]
|
|
|
298820
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c0274398-8ca4-4742-8401-5e8565add52c
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c0274398-8ca4-4742-8401-5e8565add52c
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:07
|
21 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149410.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149410.0 (TID 149410) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a510d2c9-a983-45f8-86dd-17abce8168d5-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149410.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149410.0 (TID 149410) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a510d2c9-a983-45f8-86dd-17abce8168d5-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298821
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c0274398-8ca4-4742-8401-5e8565add52c
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c0274398-8ca4-4742-8401-5e8565add52c
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:07
|
18 ms
|
|
[149410]
|
|
|
298818
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = da3a1eb8-44d1-453e-9024-65034cf12536
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = da3a1eb8-44d1-453e-9024-65034cf12536
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 11:20:07
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149409.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149409.0 (TID 149409) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7c6a2e1d-58c1-4e76-9943-a02d409bf5b2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149409.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149409.0 (TID 149409) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7c6a2e1d-58c1-4e76-9943-a02d409bf5b2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298819
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = da3a1eb8-44d1-453e-9024-65034cf12536
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = da3a1eb8-44d1-453e-9024-65034cf12536
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:07
|
11 ms
|
|
[149409]
|
|
|
298816
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 626e1602-6c76-4129-b4f6-fd9d9f5b9339
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 626e1602-6c76-4129-b4f6-fd9d9f5b9339
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:07
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149408.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149408.0 (TID 149408) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a14b6651-4e29-4db6-b52b-d282373ef2d7-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149408.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149408.0 (TID 149408) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a14b6651-4e29-4db6-b52b-d282373ef2d7-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298817
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 626e1602-6c76-4129-b4f6-fd9d9f5b9339
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 626e1602-6c76-4129-b4f6-fd9d9f5b9339
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:07
|
12 ms
|
|
[149408]
|
|
|
298814
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 43d78c16-0f18-4ac0-9d66-8cdcbcb4105e
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 43d78c16-0f18-4ac0-9d66-8cdcbcb4105e
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 11:20:07
|
19 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149407.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149407.0 (TID 149407) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-53f1b753-e01c-47dd-af73-0da2b81fe300-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149407.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149407.0 (TID 149407) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-53f1b753-e01c-47dd-af73-0da2b81fe300-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298815
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 43d78c16-0f18-4ac0-9d66-8cdcbcb4105e
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 43d78c16-0f18-4ac0-9d66-8cdcbcb4105e
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:07
|
17 ms
|
|
[149407]
|
|
|
298812
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = cf659d7e-788a-4b1a-827c-ecbcf2fcfab0
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = cf659d7e-788a-4b1a-827c-ecbcf2fcfab0
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:07
|
20 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149406.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149406.0 (TID 149406) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8cf163aa-03d3-4cfa-a391-fcdebe262323-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149406.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149406.0 (TID 149406) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8cf163aa-03d3-4cfa-a391-fcdebe262323-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298813
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = cf659d7e-788a-4b1a-827c-ecbcf2fcfab0
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = cf659d7e-788a-4b1a-827c-ecbcf2fcfab0
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:07
|
18 ms
|
|
[149406]
|
|
|
298810
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c39e9b78-3f84-4c53-b005-7e89ac273962
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c39e9b78-3f84-4c53-b005-7e89ac273962
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 11:20:07
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149405.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149405.0 (TID 149405) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-812bf4fa-f36a-4128-b646-4edf8e9eaa04-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149405.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149405.0 (TID 149405) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-812bf4fa-f36a-4128-b646-4edf8e9eaa04-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298811
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c39e9b78-3f84-4c53-b005-7e89ac273962
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c39e9b78-3f84-4c53-b005-7e89ac273962
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:07
|
12 ms
|
|
[149405]
|
|
|
298808
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 562d9d63-0351-4d5a-86ee-89a8d2759c45
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 562d9d63-0351-4d5a-86ee-89a8d2759c45
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:07
|
24 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149404.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149404.0 (TID 149404) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-59c6468f-5a99-4bd2-b2db-d25c663eac49-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149404.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149404.0 (TID 149404) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-59c6468f-5a99-4bd2-b2db-d25c663eac49-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298809
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 562d9d63-0351-4d5a-86ee-89a8d2759c45
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 562d9d63-0351-4d5a-86ee-89a8d2759c45
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:07
|
22 ms
|
|
[149404]
|
|
|
298806
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b483ec0b-40c3-4cca-a550-e7e34029df31
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b483ec0b-40c3-4cca-a550-e7e34029df31
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 11:20:07
|
20 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149403.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149403.0 (TID 149403) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2265652e-27ad-4db4-8932-07616ba7041b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149403.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149403.0 (TID 149403) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2265652e-27ad-4db4-8932-07616ba7041b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298807
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b483ec0b-40c3-4cca-a550-e7e34029df31
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b483ec0b-40c3-4cca-a550-e7e34029df31
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:07
|
17 ms
|
|
[149403]
|
|
|
298804
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6020f803-6917-4873-b239-1aff1ee1dd61
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6020f803-6917-4873-b239-1aff1ee1dd61
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:07
|
21 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149402.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149402.0 (TID 149402) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0f346ad8-9ac7-47fb-bb2d-85a1ed51f126-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149402.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149402.0 (TID 149402) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0f346ad8-9ac7-47fb-bb2d-85a1ed51f126-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298805
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6020f803-6917-4873-b239-1aff1ee1dd61
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6020f803-6917-4873-b239-1aff1ee1dd61
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:07
|
18 ms
|
|
[149402]
|
|
|
298802
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ff68030b-8820-4527-b2fb-644fd6d648c5
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ff68030b-8820-4527-b2fb-644fd6d648c5
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 11:20:07
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149401.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149401.0 (TID 149401) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-effec50f-7af8-48d8-b2c7-cd160aa58081-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149401.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149401.0 (TID 149401) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-effec50f-7af8-48d8-b2c7-cd160aa58081-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298803
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ff68030b-8820-4527-b2fb-644fd6d648c5
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ff68030b-8820-4527-b2fb-644fd6d648c5
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:07
|
11 ms
|
|
[149401]
|
|
|
298800
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 34b412f2-15f7-4141-8097-8029ebb158c4
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 34b412f2-15f7-4141-8097-8029ebb158c4
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:07
|
19 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149400.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149400.0 (TID 149400) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-238d4e41-7bc2-42de-89af-77a80966e5df-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149400.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149400.0 (TID 149400) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-238d4e41-7bc2-42de-89af-77a80966e5df-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298801
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 34b412f2-15f7-4141-8097-8029ebb158c4
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 34b412f2-15f7-4141-8097-8029ebb158c4
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:07
|
17 ms
|
|
[149400]
|
|
|
298798
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ee04e29d-d94e-499f-9f32-bae6e4fcffe5
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ee04e29d-d94e-499f-9f32-bae6e4fcffe5
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 11:20:07
|
20 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149399.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149399.0 (TID 149399) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ff0b71a1-a510-45f0-ae46-045fc5b4fdd3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149399.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149399.0 (TID 149399) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ff0b71a1-a510-45f0-ae46-045fc5b4fdd3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298799
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ee04e29d-d94e-499f-9f32-bae6e4fcffe5
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ee04e29d-d94e-499f-9f32-bae6e4fcffe5
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:07
|
17 ms
|
|
[149399]
|
|
|
298796
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 453d9cb2-9dfd-4b6b-ad52-46886a9f542d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 453d9cb2-9dfd-4b6b-ad52-46886a9f542d
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:07
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149398.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149398.0 (TID 149398) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-93ef2cd7-a4af-485d-9c03-0b7f091b4a67-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149398.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149398.0 (TID 149398) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-93ef2cd7-a4af-485d-9c03-0b7f091b4a67-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298797
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 453d9cb2-9dfd-4b6b-ad52-46886a9f542d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 453d9cb2-9dfd-4b6b-ad52-46886a9f542d
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:07
|
11 ms
|
|
[149398]
|
|
|
298794
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1fecb7c2-0753-428b-a23d-652f824cf191
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1fecb7c2-0753-428b-a23d-652f824cf191
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 11:20:06
|
21 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149397.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149397.0 (TID 149397) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1b21ed5d-0ddf-443c-915b-b570820d68f7-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149397.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149397.0 (TID 149397) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1b21ed5d-0ddf-443c-915b-b570820d68f7-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298795
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1fecb7c2-0753-428b-a23d-652f824cf191
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1fecb7c2-0753-428b-a23d-652f824cf191
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:06
|
18 ms
|
|
[149397]
|
|
|
298792
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = bb9e3436-b017-4ed1-b7bf-8c8f11075ce6
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = bb9e3436-b017-4ed1-b7bf-8c8f11075ce6
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:06
|
21 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149396.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149396.0 (TID 149396) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3ffd97bc-3f12-428d-8756-4d38a2eea0da-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149396.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149396.0 (TID 149396) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3ffd97bc-3f12-428d-8756-4d38a2eea0da-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298793
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = bb9e3436-b017-4ed1-b7bf-8c8f11075ce6
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = bb9e3436-b017-4ed1-b7bf-8c8f11075ce6
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:06
|
18 ms
|
|
[149396]
|
|
|
298790
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 34f862f7-22dd-479f-ae66-076316351162
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 34f862f7-22dd-479f-ae66-076316351162
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 11:20:06
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149395.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149395.0 (TID 149395) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-50584a4c-ee85-4925-a54d-22d79ccc8ed8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149395.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149395.0 (TID 149395) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-50584a4c-ee85-4925-a54d-22d79ccc8ed8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298791
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 34f862f7-22dd-479f-ae66-076316351162
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 34f862f7-22dd-479f-ae66-076316351162
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:06
|
12 ms
|
|
[149395]
|
|
|
298788
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9c90d754-921f-4e65-8731-b5369a24fb04
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9c90d754-921f-4e65-8731-b5369a24fb04
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:06
|
23 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149394.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149394.0 (TID 149394) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-34caaeaa-b89f-4e90-bdec-1f2f50da317f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149394.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149394.0 (TID 149394) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-34caaeaa-b89f-4e90-bdec-1f2f50da317f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298789
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9c90d754-921f-4e65-8731-b5369a24fb04
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9c90d754-921f-4e65-8731-b5369a24fb04
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:06
|
20 ms
|
|
[149394]
|
|
|
298786
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c3b9c54c-ab1b-454b-a6ef-64e888937855
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c3b9c54c-ab1b-454b-a6ef-64e888937855
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 11:20:06
|
21 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149393.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149393.0 (TID 149393) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-90c906a2-9bdf-4026-9b5a-1d4c21ff7b22-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149393.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149393.0 (TID 149393) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-90c906a2-9bdf-4026-9b5a-1d4c21ff7b22-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298787
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c3b9c54c-ab1b-454b-a6ef-64e888937855
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = c3b9c54c-ab1b-454b-a6ef-64e888937855
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:06
|
17 ms
|
|
[149393]
|
|
|
298784
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 2a92ceac-a145-44af-bfbe-cb76501a00eb
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 2a92ceac-a145-44af-bfbe-cb76501a00eb
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:06
|
19 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149392.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149392.0 (TID 149392) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-afc5a20e-d3c6-45ea-8f3c-a0878d862a77-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149392.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149392.0 (TID 149392) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-afc5a20e-d3c6-45ea-8f3c-a0878d862a77-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298785
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 2a92ceac-a145-44af-bfbe-cb76501a00eb
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 2a92ceac-a145-44af-bfbe-cb76501a00eb
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:06
|
17 ms
|
|
[149392]
|
|
|
298782
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6ae48792-a061-43c7-82cd-b0533871b5fd
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6ae48792-a061-43c7-82cd-b0533871b5fd
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 11:20:06
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149391.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149391.0 (TID 149391) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0b4a3060-fd82-4ab3-b13c-042bfdbae5cd-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149391.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149391.0 (TID 149391) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0b4a3060-fd82-4ab3-b13c-042bfdbae5cd-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298783
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6ae48792-a061-43c7-82cd-b0533871b5fd
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6ae48792-a061-43c7-82cd-b0533871b5fd
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:06
|
10 ms
|
|
[149391]
|
|
|
298780
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6b5022eb-0b11-4d82-9adb-ea52d5517634
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6b5022eb-0b11-4d82-9adb-ea52d5517634
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:06
|
18 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149390.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149390.0 (TID 149390) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-295f0eea-2cc9-498b-8e0d-a15b6c778e3c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149390.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149390.0 (TID 149390) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-295f0eea-2cc9-498b-8e0d-a15b6c778e3c-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298781
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6b5022eb-0b11-4d82-9adb-ea52d5517634
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6b5022eb-0b11-4d82-9adb-ea52d5517634
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:06
|
16 ms
|
|
[149390]
|
|
|
298778
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 0c7c0459-d72a-4ac7-a7d0-7aff38909a34
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 0c7c0459-d72a-4ac7-a7d0-7aff38909a34
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 11:20:06
|
20 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149389.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149389.0 (TID 149389) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d87783c9-b8f2-49b9-95ad-664456cbab45-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149389.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149389.0 (TID 149389) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d87783c9-b8f2-49b9-95ad-664456cbab45-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298779
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 0c7c0459-d72a-4ac7-a7d0-7aff38909a34
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 0c7c0459-d72a-4ac7-a7d0-7aff38909a34
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:06
|
17 ms
|
|
[149389]
|
|
|
298776
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e5679813-0804-431f-97e1-7fa7183f9881
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e5679813-0804-431f-97e1-7fa7183f9881
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:06
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149388.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149388.0 (TID 149388) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5f8e698a-a363-4055-9f5f-b36ce1e3327d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149388.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149388.0 (TID 149388) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5f8e698a-a363-4055-9f5f-b36ce1e3327d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298777
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e5679813-0804-431f-97e1-7fa7183f9881
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e5679813-0804-431f-97e1-7fa7183f9881
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:06
|
11 ms
|
|
[149388]
|
|
|
298774
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a5b7dac9-a0db-4fbe-a062-390812cd7628
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a5b7dac9-a0db-4fbe-a062-390812cd7628
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 11:20:06
|
20 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149387.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149387.0 (TID 149387) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ddf39e24-780c-41f9-a9ae-0ba7a27d0fe2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149387.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149387.0 (TID 149387) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ddf39e24-780c-41f9-a9ae-0ba7a27d0fe2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298775
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a5b7dac9-a0db-4fbe-a062-390812cd7628
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = a5b7dac9-a0db-4fbe-a062-390812cd7628
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:06
|
18 ms
|
|
[149387]
|
|
|
298772
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d79ea1ef-2f0c-4bf2-9e45-90cd950f0f0f
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d79ea1ef-2f0c-4bf2-9e45-90cd950f0f0f
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:06
|
32 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149386.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149386.0 (TID 149386) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c11dcc6c-343d-4f90-bd65-616afdfcea54-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149386.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149386.0 (TID 149386) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c11dcc6c-343d-4f90-bd65-616afdfcea54-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298773
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d79ea1ef-2f0c-4bf2-9e45-90cd950f0f0f
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d79ea1ef-2f0c-4bf2-9e45-90cd950f0f0f
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:06
|
28 ms
|
|
[149386]
|
|
|
298770
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 30e4b55b-332b-44a9-ae2e-86466cffbfde
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 30e4b55b-332b-44a9-ae2e-86466cffbfde
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 11:20:06
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149385.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149385.0 (TID 149385) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c748fed9-5161-4659-8157-425b6b7f4b1a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149385.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149385.0 (TID 149385) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c748fed9-5161-4659-8157-425b6b7f4b1a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298771
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 30e4b55b-332b-44a9-ae2e-86466cffbfde
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 30e4b55b-332b-44a9-ae2e-86466cffbfde
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:06
|
12 ms
|
|
[149385]
|
|
|
298768
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 70575a16-ec8f-42e3-80ec-064f2cc6c7e2
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 70575a16-ec8f-42e3-80ec-064f2cc6c7e2
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:06
|
29 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149384.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149384.0 (TID 149384) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2782b781-a4b9-40d6-805b-138c5d39ef22-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149384.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149384.0 (TID 149384) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2782b781-a4b9-40d6-805b-138c5d39ef22-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298769
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 70575a16-ec8f-42e3-80ec-064f2cc6c7e2
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 70575a16-ec8f-42e3-80ec-064f2cc6c7e2
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:06
|
26 ms
|
|
[149384]
|
|
|
298766
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d491caee-2648-455a-96eb-2c0e75344905
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d491caee-2648-455a-96eb-2c0e75344905
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 11:20:06
|
20 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149383.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149383.0 (TID 149383) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-375481ca-b90e-4be9-9505-7a88a742384a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149383.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149383.0 (TID 149383) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-375481ca-b90e-4be9-9505-7a88a742384a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298767
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d491caee-2648-455a-96eb-2c0e75344905
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d491caee-2648-455a-96eb-2c0e75344905
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:06
|
18 ms
|
|
[149383]
|
|
|
298764
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e9cb0604-36c1-46bd-934c-1037ca019417
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e9cb0604-36c1-46bd-934c-1037ca019417
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:06
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149382.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149382.0 (TID 149382) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-66eb20fd-fcc2-4461-bd2e-fb3a64d65541-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149382.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149382.0 (TID 149382) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-66eb20fd-fcc2-4461-bd2e-fb3a64d65541-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298765
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e9cb0604-36c1-46bd-934c-1037ca019417
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = e9cb0604-36c1-46bd-934c-1037ca019417
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:06
|
10 ms
|
|
[149382]
|
|
|
298762
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 50cebcbd-4a7b-4131-ad93-cd4f2dbf1d0e
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 50cebcbd-4a7b-4131-ad93-cd4f2dbf1d0e
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 11:20:06
|
20 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149381.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149381.0 (TID 149381) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-52fb710b-c51b-465c-9bdf-e929e0740aaf-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149381.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149381.0 (TID 149381) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-52fb710b-c51b-465c-9bdf-e929e0740aaf-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298763
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 50cebcbd-4a7b-4131-ad93-cd4f2dbf1d0e
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 50cebcbd-4a7b-4131-ad93-cd4f2dbf1d0e
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:06
|
18 ms
|
|
[149381]
|
|
|
298760
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6ca41171-b4ae-4b74-969d-22119ecd0911
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6ca41171-b4ae-4b74-969d-22119ecd0911
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:06
|
21 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149380.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149380.0 (TID 149380) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f56e6d69-b064-41e2-b3d6-8266a8e049d9-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149380.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149380.0 (TID 149380) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f56e6d69-b064-41e2-b3d6-8266a8e049d9-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298761
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6ca41171-b4ae-4b74-969d-22119ecd0911
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6ca41171-b4ae-4b74-969d-22119ecd0911
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:06
|
19 ms
|
|
[149380]
|
|
|
298758
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1b03ec74-2197-439a-b72c-a1018165f747
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1b03ec74-2197-439a-b72c-a1018165f747
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 11:20:06
|
22 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149379.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149379.0 (TID 149379) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-74fe55c4-f6a4-401e-9b56-ef50d2d6d41d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149379.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149379.0 (TID 149379) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-74fe55c4-f6a4-401e-9b56-ef50d2d6d41d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298759
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1b03ec74-2197-439a-b72c-a1018165f747
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1b03ec74-2197-439a-b72c-a1018165f747
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:06
|
20 ms
|
|
[149379]
|
|
|
298756
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 55b51303-9ce0-405d-9970-814ffbac07a1
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 55b51303-9ce0-405d-9970-814ffbac07a1
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:06
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149378.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149378.0 (TID 149378) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8c066f84-0cd7-46d4-beed-b3b4aded37c3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149378.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149378.0 (TID 149378) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8c066f84-0cd7-46d4-beed-b3b4aded37c3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298757
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 55b51303-9ce0-405d-9970-814ffbac07a1
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 55b51303-9ce0-405d-9970-814ffbac07a1
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:06
|
11 ms
|
|
[149378]
|
|
|
298754
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 933effb9-2e4d-45a4-9780-4780d51aa0f7
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 933effb9-2e4d-45a4-9780-4780d51aa0f7
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 11:20:06
|
21 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149377.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149377.0 (TID 149377) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0dbcc6d0-0ef7-43c5-a1ff-d0e463374445-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149377.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149377.0 (TID 149377) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0dbcc6d0-0ef7-43c5-a1ff-d0e463374445-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298755
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 933effb9-2e4d-45a4-9780-4780d51aa0f7
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 933effb9-2e4d-45a4-9780-4780d51aa0f7
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:06
|
19 ms
|
|
[149377]
|
|
|
298752
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 603aea5f-a698-47f0-9314-ff7d0070c6a3
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 603aea5f-a698-47f0-9314-ff7d0070c6a3
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:06
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149376.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149376.0 (TID 149376) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b7cd30bf-0e43-48af-ab0d-1131a7a21b3d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149376.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149376.0 (TID 149376) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b7cd30bf-0e43-48af-ab0d-1131a7a21b3d-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298753
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 603aea5f-a698-47f0-9314-ff7d0070c6a3
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 603aea5f-a698-47f0-9314-ff7d0070c6a3
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:06
|
11 ms
|
|
[149376]
|
|
|
298750
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = acf209e3-02f2-4e30-a280-1c45e692c15c
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = acf209e3-02f2-4e30-a280-1c45e692c15c
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 11:20:06
|
21 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149375.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149375.0 (TID 149375) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8a4424af-0692-4c9d-863f-6850dd2eb4dd-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149375.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149375.0 (TID 149375) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8a4424af-0692-4c9d-863f-6850dd2eb4dd-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298751
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = acf209e3-02f2-4e30-a280-1c45e692c15c
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = acf209e3-02f2-4e30-a280-1c45e692c15c
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:06
|
19 ms
|
|
[149375]
|
|
|
298748
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = be67606d-161c-4f56-b2dc-0f55e568f45a
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = be67606d-161c-4f56-b2dc-0f55e568f45a
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:05
|
22 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149374.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149374.0 (TID 149374) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-629a8c78-6d19-4e88-ab26-fdd99ae4c636-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149374.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149374.0 (TID 149374) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-629a8c78-6d19-4e88-ab26-fdd99ae4c636-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298749
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = be67606d-161c-4f56-b2dc-0f55e568f45a
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = be67606d-161c-4f56-b2dc-0f55e568f45a
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:05
|
20 ms
|
|
[149374]
|
|
|
298746
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d73e731a-afce-4f99-a1af-def91ca3a8c7
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d73e731a-afce-4f99-a1af-def91ca3a8c7
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 11:20:05
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149373.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149373.0 (TID 149373) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2e5a1ef9-ea55-440a-8442-5722b79c22f5-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149373.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149373.0 (TID 149373) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2e5a1ef9-ea55-440a-8442-5722b79c22f5-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298747
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d73e731a-afce-4f99-a1af-def91ca3a8c7
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = d73e731a-afce-4f99-a1af-def91ca3a8c7
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:05
|
13 ms
|
|
[149373]
|
|
|
298744
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 27226e4e-ac45-4642-871b-f2583dcbcce8
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 27226e4e-ac45-4642-871b-f2583dcbcce8
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:05
|
26 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149372.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149372.0 (TID 149372) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-65cccee9-b25f-412f-87f8-b9a68de8f907-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149372.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149372.0 (TID 149372) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-65cccee9-b25f-412f-87f8-b9a68de8f907-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298745
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 27226e4e-ac45-4642-871b-f2583dcbcce8
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 27226e4e-ac45-4642-871b-f2583dcbcce8
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:05
|
24 ms
|
|
[149372]
|
|
|
298742
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 83528d9f-b8d0-43f9-86af-80203ee0bfa9
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 83528d9f-b8d0-43f9-86af-80203ee0bfa9
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 11:20:05
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149371.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149371.0 (TID 149371) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9d48c7a4-41f9-4a52-88de-35ccca13dfe2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149371.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149371.0 (TID 149371) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-9d48c7a4-41f9-4a52-88de-35ccca13dfe2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298743
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 83528d9f-b8d0-43f9-86af-80203ee0bfa9
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 83528d9f-b8d0-43f9-86af-80203ee0bfa9
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:05
|
11 ms
|
|
[149371]
|
|
|
298740
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 84f3ca46-aed3-4371-ae41-a9d0e885e056
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 84f3ca46-aed3-4371-ae41-a9d0e885e056
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:05
|
17 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149370.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149370.0 (TID 149370) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2bd4ddc6-2635-49d5-affe-7b10531b3c3e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149370.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149370.0 (TID 149370) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-2bd4ddc6-2635-49d5-affe-7b10531b3c3e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298741
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 84f3ca46-aed3-4371-ae41-a9d0e885e056
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 84f3ca46-aed3-4371-ae41-a9d0e885e056
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:05
|
14 ms
|
|
[149370]
|
|
|
298738
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6aafe23b-352e-4078-b381-f9d23bff13c3
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6aafe23b-352e-4078-b381-f9d23bff13c3
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 11:20:05
|
15 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149369.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149369.0 (TID 149369) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d28b34c9-f3e3-42db-a52b-1cf5e0d572f1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149369.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149369.0 (TID 149369) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-d28b34c9-f3e3-42db-a52b-1cf5e0d572f1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298739
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6aafe23b-352e-4078-b381-f9d23bff13c3
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 6aafe23b-352e-4078-b381-f9d23bff13c3
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:05
|
13 ms
|
|
[149369]
|
|
|
298736
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 078098b1-e060-4f98-b8fb-ff698b99365c
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 078098b1-e060-4f98-b8fb-ff698b99365c
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:05
|
26 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149368.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149368.0 (TID 149368) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1c29fe19-cdab-47be-9f7e-b80a7e198acb-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149368.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149368.0 (TID 149368) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-1c29fe19-cdab-47be-9f7e-b80a7e198acb-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298737
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 078098b1-e060-4f98-b8fb-ff698b99365c
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 078098b1-e060-4f98-b8fb-ff698b99365c
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:05
|
24 ms
|
|
[149368]
|
|
|
298734
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 087cd34a-451b-4f79-9df7-e2a464bdfbc7
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 087cd34a-451b-4f79-9df7-e2a464bdfbc7
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 11:20:05
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149367.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149367.0 (TID 149367) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7ee92dfe-9647-43ee-899f-7c2389491d08-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149367.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149367.0 (TID 149367) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-7ee92dfe-9647-43ee-899f-7c2389491d08-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298735
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 087cd34a-451b-4f79-9df7-e2a464bdfbc7
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 087cd34a-451b-4f79-9df7-e2a464bdfbc7
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:05
|
12 ms
|
|
[149367]
|
|
|
298732
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b2342884-ba39-4273-8ff1-652d8530746f
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b2342884-ba39-4273-8ff1-652d8530746f
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:05
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149366.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149366.0 (TID 149366) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-69fd4408-7e9e-4387-8620-657d4853c251-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149366.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149366.0 (TID 149366) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-69fd4408-7e9e-4387-8620-657d4853c251-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298733
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b2342884-ba39-4273-8ff1-652d8530746f
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = b2342884-ba39-4273-8ff1-652d8530746f
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:05
|
12 ms
|
|
[149366]
|
|
|
298730
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 607e3136-c501-4c45-9bd0-ee1ba4d31e1d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 607e3136-c501-4c45-9bd0-ee1ba4d31e1d
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 11:20:05
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149365.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149365.0 (TID 149365) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8d8aa59f-d27b-45d6-a754-445e4988cd3b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149365.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149365.0 (TID 149365) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8d8aa59f-d27b-45d6-a754-445e4988cd3b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298731
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 607e3136-c501-4c45-9bd0-ee1ba4d31e1d
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 607e3136-c501-4c45-9bd0-ee1ba4d31e1d
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:05
|
12 ms
|
|
[149365]
|
|
|
298728
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 0fad0bb6-74d5-4f6a-be66-2255b8b9e1b4
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 0fad0bb6-74d5-4f6a-be66-2255b8b9e1b4
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:05
|
23 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149364.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149364.0 (TID 149364) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f959c575-d621-40fa-aef1-c4d5bc869d5e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149364.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149364.0 (TID 149364) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f959c575-d621-40fa-aef1-c4d5bc869d5e-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298729
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 0fad0bb6-74d5-4f6a-be66-2255b8b9e1b4
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 0fad0bb6-74d5-4f6a-be66-2255b8b9e1b4
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:05
|
21 ms
|
|
[149364]
|
|
|
298726
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 27040332-f527-431a-bf78-817a7b90e747
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 27040332-f527-431a-bf78-817a7b90e747
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 11:20:05
|
21 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149363.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149363.0 (TID 149363) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5003ba07-5e72-4d83-8f6b-73e09e98e2b0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149363.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149363.0 (TID 149363) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5003ba07-5e72-4d83-8f6b-73e09e98e2b0-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298727
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 27040332-f527-431a-bf78-817a7b90e747
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 27040332-f527-431a-bf78-817a7b90e747
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:05
|
18 ms
|
|
[149363]
|
|
|
298724
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = aa1a0114-6b92-40cd-91e6-7a3552b272b6
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = aa1a0114-6b92-40cd-91e6-7a3552b272b6
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:05
|
24 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149362.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149362.0 (TID 149362) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-df5109f1-742d-4f7e-9dd5-a2ba9764e4bf-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149362.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149362.0 (TID 149362) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-df5109f1-742d-4f7e-9dd5-a2ba9764e4bf-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298725
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = aa1a0114-6b92-40cd-91e6-7a3552b272b6
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = aa1a0114-6b92-40cd-91e6-7a3552b272b6
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:05
|
22 ms
|
|
[149362]
|
|
|
298722
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 313387aa-41fd-4f30-9a28-f2c42dcd0624
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 313387aa-41fd-4f30-9a28-f2c42dcd0624
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 11:20:05
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149361.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149361.0 (TID 149361) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-393b57cc-9ce3-4dac-b109-d4ea3441a1e3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149361.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149361.0 (TID 149361) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-393b57cc-9ce3-4dac-b109-d4ea3441a1e3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298723
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 313387aa-41fd-4f30-9a28-f2c42dcd0624
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 313387aa-41fd-4f30-9a28-f2c42dcd0624
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:05
|
12 ms
|
|
[149361]
|
|
|
298720
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 34180b3e-8603-4cbc-aacc-9153594c4c99
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 34180b3e-8603-4cbc-aacc-9153594c4c99
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:05
|
20 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149360.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149360.0 (TID 149360) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-cc6c1f77-3eb8-4d0e-9f2e-7a4318633937-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149360.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149360.0 (TID 149360) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-cc6c1f77-3eb8-4d0e-9f2e-7a4318633937-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298721
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 34180b3e-8603-4cbc-aacc-9153594c4c99
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 34180b3e-8603-4cbc-aacc-9153594c4c99
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:05
|
18 ms
|
|
[149360]
|
|
|
298718
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 0c901e89-04a2-48ca-abc8-3ed1656c4408
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 0c901e89-04a2-48ca-abc8-3ed1656c4408
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 11:20:05
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149359.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149359.0 (TID 149359) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5620a295-17b1-4222-b990-4151f3f398a1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149359.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149359.0 (TID 149359) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-5620a295-17b1-4222-b990-4151f3f398a1-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298719
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 0c901e89-04a2-48ca-abc8-3ed1656c4408
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 0c901e89-04a2-48ca-abc8-3ed1656c4408
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:05
|
11 ms
|
|
[149359]
|
|
|
298716
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9ab8d656-4ea4-401c-bc0c-756d5a466e0b
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9ab8d656-4ea4-401c-bc0c-756d5a466e0b
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:05
|
20 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149358.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149358.0 (TID 149358) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fcf0a210-be70-4c53-9a2a-6a53abba5c32-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149358.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149358.0 (TID 149358) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-fcf0a210-be70-4c53-9a2a-6a53abba5c32-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298717
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9ab8d656-4ea4-401c-bc0c-756d5a466e0b
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9ab8d656-4ea4-401c-bc0c-756d5a466e0b
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:05
|
18 ms
|
|
[149358]
|
|
|
298714
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 18aa81cd-9e23-4f52-b633-18b666b27852
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 18aa81cd-9e23-4f52-b633-18b666b27852
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 11:20:05
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149357.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149357.0 (TID 149357) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-57f3eeb5-9f78-428b-a572-4ed2529be50f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149357.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149357.0 (TID 149357) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-57f3eeb5-9f78-428b-a572-4ed2529be50f-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298715
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 18aa81cd-9e23-4f52-b633-18b666b27852
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 18aa81cd-9e23-4f52-b633-18b666b27852
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:05
|
11 ms
|
|
[149357]
|
|
|
298712
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 666ca7fc-d8ee-4b21-bf3a-b8a633ddaebe
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 666ca7fc-d8ee-4b21-bf3a-b8a633ddaebe
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:05
|
20 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149356.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149356.0 (TID 149356) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ec9b414f-fb2b-4890-ac17-f6be6d7c4434-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149356.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149356.0 (TID 149356) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-ec9b414f-fb2b-4890-ac17-f6be6d7c4434-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298713
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 666ca7fc-d8ee-4b21-bf3a-b8a633ddaebe
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 666ca7fc-d8ee-4b21-bf3a-b8a633ddaebe
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:05
|
17 ms
|
|
[149356]
|
|
|
298710
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ab2c77da-96ee-4cce-a852-cceb48d9db95
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ab2c77da-96ee-4cce-a852-cceb48d9db95
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 11:20:05
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149355.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149355.0 (TID 149355) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-57646344-eb98-4aed-95f5-ee5532eec1a4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149355.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149355.0 (TID 149355) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-57646344-eb98-4aed-95f5-ee5532eec1a4-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298711
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ab2c77da-96ee-4cce-a852-cceb48d9db95
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ab2c77da-96ee-4cce-a852-cceb48d9db95
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:05
|
11 ms
|
|
[149355]
|
|
|
298708
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1fb14d86-b3d5-4582-8098-9c45b50c7f34
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1fb14d86-b3d5-4582-8098-9c45b50c7f34
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:05
|
23 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149354.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149354.0 (TID 149354) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f7380892-4435-4cd8-8088-0141dd025fe3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149354.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149354.0 (TID 149354) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-f7380892-4435-4cd8-8088-0141dd025fe3-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298709
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1fb14d86-b3d5-4582-8098-9c45b50c7f34
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1fb14d86-b3d5-4582-8098-9c45b50c7f34
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:05
|
20 ms
|
|
[149354]
|
|
|
298706
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9c85478b-6950-4a63-88fb-a3551bd5573e
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9c85478b-6950-4a63-88fb-a3551bd5573e
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 11:20:05
|
20 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149353.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149353.0 (TID 149353) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-dba7c0ac-093e-4a2f-acce-3b5a529bf14b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149353.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149353.0 (TID 149353) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-dba7c0ac-093e-4a2f-acce-3b5a529bf14b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298707
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9c85478b-6950-4a63-88fb-a3551bd5573e
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 9c85478b-6950-4a63-88fb-a3551bd5573e
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:05
|
18 ms
|
|
[149353]
|
|
|
298704
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = bfe7e775-ed63-4115-a8dc-fe32d2588178
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = bfe7e775-ed63-4115-a8dc-fe32d2588178
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:05
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149352.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149352.0 (TID 149352) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-73c1febf-e0e3-4c59-9948-39e498073f12-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149352.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149352.0 (TID 149352) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-73c1febf-e0e3-4c59-9948-39e498073f12-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298705
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = bfe7e775-ed63-4115-a8dc-fe32d2588178
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = bfe7e775-ed63-4115-a8dc-fe32d2588178
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:05
|
11 ms
|
|
[149352]
|
|
|
298702
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1f78cfe7-f822-43f1-a462-993273dc770b
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1f78cfe7-f822-43f1-a462-993273dc770b
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 11:20:05
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149351.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149351.0 (TID 149351) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8765d1b0-19cc-4f96-846f-d600281565a8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149351.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149351.0 (TID 149351) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-8765d1b0-19cc-4f96-846f-d600281565a8-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298703
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1f78cfe7-f822-43f1-a462-993273dc770b
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1f78cfe7-f822-43f1-a462-993273dc770b
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:05
|
11 ms
|
|
[149351]
|
|
|
298700
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1b924254-89a4-4ad4-a7dc-07705dcd07b9
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1b924254-89a4-4ad4-a7dc-07705dcd07b9
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:04
|
14 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149350.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149350.0 (TID 149350) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b8b59cc1-d03d-4a2d-843a-9a6016449db2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149350.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149350.0 (TID 149350) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-b8b59cc1-d03d-4a2d-843a-9a6016449db2-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298701
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1b924254-89a4-4ad4-a7dc-07705dcd07b9
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1b924254-89a4-4ad4-a7dc-07705dcd07b9
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:05
|
11 ms
|
|
[149350]
|
|
|
298698
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1f06dafe-4cf8-405e-a18b-827bf4ddc5b7
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1f06dafe-4cf8-405e-a18b-827bf4ddc5b7
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 11:20:04
|
20 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149349.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149349.0 (TID 149349) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0e75ab85-93c6-4eea-a968-0f3bdb36522a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149349.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149349.0 (TID 149349) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-0e75ab85-93c6-4eea-a968-0f3bdb36522a-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298699
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1f06dafe-4cf8-405e-a18b-827bf4ddc5b7
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 1f06dafe-4cf8-405e-a18b-827bf4ddc5b7
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:04
|
18 ms
|
|
[149349]
|
|
|
298696
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 111ab078-6f3b-4de8-bb02-d0badeb065ca
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 111ab078-6f3b-4de8-bb02-d0badeb065ca
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:04
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149348.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149348.0 (TID 149348) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a3731da7-2059-4abc-9bef-bedce1cc420b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149348.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149348.0 (TID 149348) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-a3731da7-2059-4abc-9bef-bedce1cc420b-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298697
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 111ab078-6f3b-4de8-bb02-d0badeb065ca
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 111ab078-6f3b-4de8-bb02-d0badeb065ca
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:04
|
11 ms
|
|
[149348]
|
|
|
298694
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ff2f558a-80db-426e-9951-8a296632d349
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ff2f558a-80db-426e-9951-8a296632d349
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 11:20:04
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149347.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149347.0 (TID 149347) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3b53e818-50e6-464a-ac36-e9a742973e48-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149347.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149347.0 (TID 149347) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-3b53e818-50e6-464a-ac36-e9a742973e48-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.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 |
|
298695
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ff2f558a-80db-426e-9951-8a296632d349
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = ff2f558a-80db-426e-9951-8a296632d349
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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:04
|
11 ms
|
|
[149347]
|
|
|
298692
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 999bb16a-86ae-4459-b641-b50177d5c1d0
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 999bb16a-86ae-4459-b641-b50177d5c1d0
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$main$2(Main.scala:28)
Main$.$anonfun$main$2$adapted(Main.scala:28)
scala.collection.immutable.Set$Set1.foreach(Set.scala:141)
Main$.main(Main.scala:28)
Main.main(Main.scala)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
java.base/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
java.base/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
java.base/java.lang.reflect.Method.invoke(Unknown Source)
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$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$$anon$2.doSubmit(SparkSubmit.scala:1125)
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1134)
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
|
2026/09/03 11:20:04
|
13 ms
|
|
|
Job aborted due to stage failure: Task 0 in stage 149346.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149346.0 (TID 149346) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c1b60c96-3af9-4abc-afd0-9f1500c03b70-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
+details
Job aborted due to stage failure: Task 0 in stage 149346.0 failed 1 times, most recent failure: Lost task 0.0 in stage 149346.0 (TID 149346) (2d47ef339462 executor driver): java.lang.IllegalStateException: Cannot fetch offset 12 (GroupId: spark-kafka-source-c1b60c96-3af9-4abc-afd0-9f1500c03b70-1980890413-executor, TopicPartition: mothership.masteryconnect.classroom_teachers-0).
Some data may have been lost because they are not available in Kafka any more; either the
data was aged out by Kafka or the topic may have been deleted before all the data in the
topic was processed. If you don't want your streaming query to fail on such cases, set the
source option "failOnDataLoss" to "false".
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer$.org$apache$spark$sql$kafka010$consumer$KafkaDataConsumer$$reportDataLoss0(KafkaDataConsumer.scala:724)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.reportDataLoss(KafkaDataConsumer.scala:651)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:344)
at org.apache.spark.util.UninterruptibleThread.runUninterruptibly(UninterruptibleThread.scala:149)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.runUninterruptiblyIfPossible(KafkaDataConsumer.scala:656)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.get(KafkaDataConsumer.scala:299)
at org.apache.spark.sql.kafka010.KafkaBatchPartitionReader.next(KafkaBatchPartitionReader.scala:79)
at org.apache.spark.sql.execution.datasources.v2.PartitionIterator.hasNext(DataSourceRDD.scala:146)
at org.apache.spark.sql.execution.datasources.v2.MetricsIterator.hasNext(DataSourceRDD.scala:184)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.$anonfun$hasNext$1$adapted(DataSourceRDD.scala:71)
at scala.Option.exists(Option.scala:376)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.advanceToNextIter(DataSourceRDD.scala:102)
at org.apache.spark.sql.execution.datasources.v2.DataSourceRDD$$anon$1.hasNext(DataSourceRDD.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:460)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenEvaluatorFactory$WholeStageCodegenPartitionEvaluator$$anon$1.hasNext(WholeStageCodegenEvaluatorFactory.scala:43)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:388)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:893)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:893)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:367)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:331)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:93)
at org.apache.spark.TaskContext.runTaskWithListeners(TaskContext.scala:166)
at org.apache.spark.scheduler.Task.run(Task.scala:141)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$4(Executor.scala:621)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally(SparkErrorUtils.scala:64)
at org.apache.spark.util.SparkErrorUtils.tryWithSafeFinally$(SparkErrorUtils.scala:61)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:94)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:624)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.base/java.lang.Thread.run(Unknown Source)
Caused by: org.apache.kafka.clients.consumer.OffsetOutOfRangeException: Fetch position FetchPosition{offset=12, offsetEpoch=Optional.empty, currentLeader=LeaderAndEpoch{leader=Optional[kafka:9092 (id: 1001 rack: null)], epoch=0}} is out of range for partition mothership.masteryconnect.classroom_teachers-0
at org.apache.kafka.clients.consumer.internals.FetchCollector.handleInitializeErrors(FetchCollector.java:365)
at org.apache.kafka.clients.consumer.internals.FetchCollector.initialize(FetchCollector.java:231)
at org.apache.kafka.clients.consumer.internals.FetchCollector.collectFetch(FetchCollector.java:111)
at org.apache.kafka.clients.consumer.internals.Fetcher.collectFetch(Fetcher.java:146)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.pollForFetches(ClassicKafkaConsumer.java:699)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:623)
at org.apache.kafka.clients.consumer.internals.ClassicKafkaConsumer.poll(ClassicKafkaConsumer.java:596)
at org.apache.kafka.clients.consumer.KafkaConsumer.poll(KafkaConsumer.java:874)
at org.apache.spark.sql.kafka010.consumer.InternalKafkaConsumer.fetch(KafkaDataConsumer.scala:78)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$fetchData$1(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.timeNanos(KafkaDataConsumer.scala:666)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchData(KafkaDataConsumer.scala:579)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.fetchRecord(KafkaDataConsumer.scala:502)
at org.apache.spark.sql.kafka010.consumer.KafkaDataConsumer.$anonfun$get$1(KafkaDataConsumer.scala:323)
... 37 more
Driver stacktrace:
|
+details
|
|
|
| ID | Description | Submitted | Duration | Succeeded Job IDs | Failed Job IDs | Error Message |
|
298693
|
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 999bb16a-86ae-4459-b641-b50177d5c1d0
batch = 106
+details
id = 9848c4f2-c6f1-4b94-a125-6e64ef893aaa
runId = 999bb16a-86ae-4459-b641-b50177d5c1d0
batch = 106
org.apache.spark.sql.streaming.DataStreamWriter.start(DataStreamWriter.scala:251)
data.kafka.KafkaDataFrameDataSource.monitor(KafkaDataFrameDataSource.scala:46)
data.kafka.KafkaDataFrameDataSource.start(KafkaDataFrameDataSource.scala:23)
Main$.$anonfun$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 11:20:04
|
11 ms
|
|
[149346]
|
|