org.apache.spark.sql.streaming.StreamingQueryException: Query query-6 terminated with exception: Job aborted due to stage failure: Task 2 in stage 18.0 failed 1 times, most recent failure: Lost task 2.0 in stage 18.0 (TID 88, localhost): java.lang.AssertionError: assertion failed: Failed to get records for spark-kafka-source-ccf20642-b267-48da-bd6e-9c26cf96919d--1721094166-executor topic-4-3 0 after polling for 512 at scala.Predef$.assert(Predef.scala:170) at org.apache.spark.sql.kafka010.CachedKafkaConsumer.get(CachedKafkaConsumer.scala:65) at org.apache.spark.sql.kafka010.KafkaSourceRDD$$anon$1.next(KafkaSourceRDD.scala:146) at org.apache.spark.sql.kafka010.KafkaSourceRDD$$anon$1.next(KafkaSourceRDD.scala:142) at scala.collection.Iterator$$anon$11.next(Iterator.scala:409) at scala.collection.Iterator$$anon$11.next(Iterator.scala:409) at scala.collection.Iterator$$anon$11.next(Iterator.scala:409) at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source) at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43) at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:370) at org.apache.spark.sql.execution.SparkPlan$$anonfun$4.apply(SparkPlan.scala:246) at org.apache.spark.sql.execution.SparkPlan$$anonfun$4.apply(SparkPlan.scala:240) at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:803) at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:803) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:319) at org.apache.spark.rdd.RDD.iterator(RDD.scala:283) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70) at org.apache.spark.scheduler.Task.run(Task.scala:86) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:314) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) at java.lang.Thread.run(Thread.java:745) Driver stacktrace:
sbt.ForkMain$ForkError: org.apache.spark.sql.streaming.StreamingQueryException: Query query-6 terminated with exception: Job aborted due to stage failure: Task 2 in stage 18.0 failed 1 times, most recent failure: Lost task 2.0 in stage 18.0 (TID 88, localhost): java.lang.AssertionError: assertion failed: Failed to get records for spark-kafka-source-ccf20642-b267-48da-bd6e-9c26cf96919d--1721094166-executor topic-4-3 0 after polling for 512
at scala.Predef$.assert(Predef.scala:170)
at org.apache.spark.sql.kafka010.CachedKafkaConsumer.get(CachedKafkaConsumer.scala:65)
at org.apache.spark.sql.kafka010.KafkaSourceRDD$$anon$1.next(KafkaSourceRDD.scala:146)
at org.apache.spark.sql.kafka010.KafkaSourceRDD$$anon$1.next(KafkaSourceRDD.scala:142)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:370)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$4.apply(SparkPlan.scala:246)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$4.apply(SparkPlan.scala:240)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:803)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:803)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:319)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:283)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70)
at org.apache.spark.scheduler.Task.run(Task.scala:86)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:314)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runBatches(StreamExecution.scala:248)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:142)
Caused by: sbt.ForkMain$ForkError: org.apache.spark.SparkException: Job aborted due to stage failure: Task 2 in stage 18.0 failed 1 times, most recent failure: Lost task 2.0 in stage 18.0 (TID 88, localhost): java.lang.AssertionError: assertion failed: Failed to get records for spark-kafka-source-ccf20642-b267-48da-bd6e-9c26cf96919d--1721094166-executor topic-4-3 0 after polling for 512
at scala.Predef$.assert(Predef.scala:170)
at org.apache.spark.sql.kafka010.CachedKafkaConsumer.get(CachedKafkaConsumer.scala:65)
at org.apache.spark.sql.kafka010.KafkaSourceRDD$$anon$1.next(KafkaSourceRDD.scala:146)
at org.apache.spark.sql.kafka010.KafkaSourceRDD$$anon$1.next(KafkaSourceRDD.scala:142)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:370)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$4.apply(SparkPlan.scala:246)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$4.apply(SparkPlan.scala:240)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:803)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:803)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:319)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:283)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70)
at org.apache.spark.scheduler.Task.run(Task.scala:86)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:314)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1454)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1442)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1441)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1441)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:811)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:811)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:811)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1667)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1622)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1611)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:632)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1890)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1903)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1916)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1930)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:912)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:358)
at org.apache.spark.rdd.RDD.collect(RDD.scala:911)
at org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:290)
at org.apache.spark.sql.Dataset$$anonfun$org$apache$spark$sql$Dataset$$execute$1$1.apply(Dataset.scala:2193)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57)
at org.apache.spark.sql.Dataset.withNewExecutionId(Dataset.scala:2546)
at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$execute$1(Dataset.scala:2192)
at org.apache.spark.sql.Dataset$$anonfun$org$apache$spark$sql$Dataset$$collect$1.apply(Dataset.scala:2197)
at org.apache.spark.sql.Dataset$$anonfun$org$apache$spark$sql$Dataset$$collect$1.apply(Dataset.scala:2197)
at org.apache.spark.sql.Dataset.withCallback(Dataset.scala:2559)
at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collect(Dataset.scala:2197)
at org.apache.spark.sql.Dataset.collect(Dataset.scala:2173)
at org.apache.spark.sql.execution.streaming.MemorySink.addBatch(memory.scala:192)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runBatch(StreamExecution.scala:437)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anonfun$org$apache$spark$sql$execution$streaming$StreamExecution$$runBatches$1$$anonfun$1.apply$mcZ$sp(StreamExecution.scala:225)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anonfun$org$apache$spark$sql$execution$streaming$StreamExecution$$runBatches$1$$anonfun$1.apply(StreamExecution.scala:213)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anonfun$org$apache$spark$sql$execution$streaming$StreamExecution$$runBatches$1$$anonfun$1.apply(StreamExecution.scala:213)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$reportTimeTaken(StreamExecution.scala:656)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anonfun$org$apache$spark$sql$execution$streaming$StreamExecution$$runBatches$1.apply$mcZ$sp(StreamExecution.scala:212)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:43)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runBatches(StreamExecution.scala:208)
... 1 more
Caused by: sbt.ForkMain$ForkError: java.lang.AssertionError: assertion failed: Failed to get records for spark-kafka-source-ccf20642-b267-48da-bd6e-9c26cf96919d--1721094166-executor topic-4-3 0 after polling for 512
at scala.Predef$.assert(Predef.scala:170)
at org.apache.spark.sql.kafka010.CachedKafkaConsumer.get(CachedKafkaConsumer.scala:65)
at org.apache.spark.sql.kafka010.KafkaSourceRDD$$anon$1.next(KafkaSourceRDD.scala:146)
at org.apache.spark.sql.kafka010.KafkaSourceRDD$$anon$1.next(KafkaSourceRDD.scala:142)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:370)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$4.apply(SparkPlan.scala:246)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$4.apply(SparkPlan.scala:240)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:803)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:803)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:319)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:283)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70)
at org.apache.spark.scheduler.Task.run(Task.scala:86)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:314)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)