Я пытаюсь запустить задание Spark Structured Streaming и сохранить контрольную точку в Google Storage. У меня есть пара заданий, одно без агрегации работает отлично, а второе с исключением агрегации.Я обнаружил, что у кого-то есть похожие проблемы с контрольными точками на S3, потому что S3 не поддерживает семантику чтения после записи https://blog.yuvalitzchakov.com/improving-spark-streaming-checkpoint-performance-with-aws-efs/,, но у GS есть, и все должно быть в порядке, я буду рад, если кто-нибудь поделится своим опытом с контрольными точками.
val writeToKafka = stream.writeStream
.format("kafka")
.trigger(ProcessingTime(5000))
.option("kafka.bootstrap.servers", "localhost:29092")
.option("topic", "test_topic")
.option("checkpointLocation", "gs://test/check_test/Job1")
.start()
Executor task launch worker for task 1] INFO org.apache.kafka.common.utils.AppInfoParser - Kafka version : 2.0.0
[Executor task launch worker for task 1] INFO org.apache.kafka.common.utils.AppInfoParser - Kafka commitId : 3402a8361b734732
[Executor task launch worker for task 1] INFO org.apache.spark.sql.execution.datasources.v2.DataWritingSparkTask - Committed partition 0 (task 1, attempt 0stage 1.0)
[Executor task launch worker for task 1] INFO org.apache.spark.sql.execution.streaming.CheckpointFileManager - Writing atomically to gs://test/check_test/Job1/state/0/0/1.delta using temp file gs://test/check_test/Job1/state/0/0/.1.delta.8a93d644-0d8e-4cb9-82b5-6418b9e63ffd.TID1.tmp
[Executor task launch worker for task 1] ERROR org.apache.spark.TaskContextImpl - Error in TaskCompletionListener
java.lang.NullPointerException
at com.google.cloud.hadoop.fs.gcs.GoogleHadoopOutputStream.write(GoogleHadoopOutputStream.java:114)
at org.apache.hadoop.fs.FSDataOutputStream$PositionCache.write(FSDataOutputStream.java:58)
at java.io.DataOutputStream.write(DataOutputStream.java:107)
at org.apache.hadoop.fs.FSDataOutputStream$PositionCache.write(FSDataOutputStream.java:58)
at java.io.DataOutputStream.write(DataOutputStream.java:107)
at net.jpountz.lz4.LZ4BlockOutputStream.finish(LZ4BlockOutputStream.java:261)
at net.jpountz.lz4.LZ4BlockOutputStream.close(LZ4BlockOutputStream.java:193)
at java.io.FilterOutputStream.close(FilterOutputStream.java:159)
at org.apache.commons.io.IOUtils.closeQuietly(IOUtils.java:303)
at org.apache.commons.io.IOUtils.closeQuietly(IOUtils.java:274)
at org.apache.spark.sql.execution.streaming.state.HDFSBackedStateStoreProvider.org$apache$spark$sql$execution$streaming$state$HDFSBackedStateStoreProvider$$cancelDeltaFile(HDFSBackedStateStoreProvider.scala:508)
at org.apache.spark.sql.execution.streaming.state.HDFSBackedStateStoreProvider$HDFSBackedStateStore.abort(HDFSBackedStateStoreProvider.scala:150)
at org.apache.spark.sql.execution.streaming.state.package$StateStoreOps$$anonfun$1$$anonfun$apply$1.apply(package.scala:65)
at org.apache.spark.sql.execution.streaming.state.package$StateStoreOps$$anonfun$1$$anonfun$apply$1.apply(package.scala:64)
at org.apache.spark.TaskContext$$anon$1.onTaskCompletion(TaskContext.scala:131)
at org.apache.spark.TaskContextImpl$$anonfun$markTaskCompleted$1.apply(TaskContextImpl.scala:117)
at org.apache.spark.TaskContextImpl$$anonfun$markTaskCompleted$1.apply(TaskContextImpl.scala:117)
at org.apache.spark.TaskContextImpl$$anonfun$invokeListeners$1.apply(TaskContextImpl.scala:130)
at org.apache.spark.TaskContextImpl$$anonfun$invokeListeners$1.apply(TaskContextImpl.scala:128)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.TaskContextImpl.invokeListeners(TaskContextImpl.scala:128)
at org.apache.spark.TaskContextImpl.markTaskCompleted(TaskContextImpl.scala:116)
at org.apache.spark.scheduler.Task.run(Task.scala:137)
at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:402)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:408)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
[Executor task launch worker for task 1] ERROR org.apache.spark.executor.Executor - Exception in task 0.0 in stage 1.0 (TID 1)
org.apache.spark.util.TaskCompletionListenerException: null
at org.apache.spark.TaskContextImpl.invokeListeners(TaskContextImpl.scala:138)
at org.apache.spark.TaskContextImpl.markTaskCompleted(TaskContextImpl.scala:116)
at org.apache.spark.scheduler.Task.run(Task.scala:137)
at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:402)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:408)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
[task-result-getter-1] WARN org.apache.spark.scheduler.TaskSetManager - Lost task 0.0 in stage 1.0 (TID 1, localhost, executor driver): org.apache.spark.util.TaskCompletionListenerException: null
at org.apache.spark.TaskContextImpl.invokeListeners(TaskContextImpl.scala:138)
at org.apache.spark.TaskContextImpl.markTaskCompleted(TaskContextImpl.scala:116)
at org.apache.spark.scheduler.Task.run(Task.scala:137)
at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:402)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:408)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
[task-result-getter-1] ERROR org.apache.spark.scheduler.TaskSetManager - Task 0 in stage 1.0 failed 1 times; aborting job
[task-result-getter-1] INFO org.apache.spark.scheduler.TaskSchedulerImpl - Removed TaskSet 1.0, whose tasks have all completed, from pool
[dag-scheduler-event-loop] INFO org.apache.spark.scheduler.TaskSchedulerImpl - Cancelling stage 1
[dag-scheduler-event-loop] INFO org.apache.spark.scheduler.TaskSchedulerImpl - Killing all running tasks in stage 1: Stage cancelled
[dag-scheduler-event-loop] INFO org.apache.spark.scheduler.DAGScheduler - ResultStage 1 (start at Job1.scala:53) failed in 9.863 s due to Job aborted due to stage failure: Task 0 in stage 1.0 failed 1 times, most recent failure: Lost task 0.0 in stage 1.0 (TID 1, localhost, executor driver): org.apache.spark.util.TaskCompletionListenerException: null
at org.apache.spark.TaskContextImpl.invokeListeners(TaskContextImpl.scala:138)
at org.apache.spark.TaskContextImpl.markTaskCompleted(TaskContextImpl.scala:116)
at org.apache.spark.scheduler.Task.run(Task.scala:137)
at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:402)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:408)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Driver stacktrace:
[stream execution thread for [id = f130d772-fc9e-4b0f-a81e-942af0741ae9, runId = 7dc1cb33-c5f2-4ebe-8707-251de2503ee1]] INFO org.apache.spark.scheduler.DAGScheduler - Job 0 failed: start at Job1.scala:53, took 20.926657 s
[stream execution thread for [id = f130d772-fc9e-4b0f-a81e-942af0741ae9, runId = 7dc1cb33-c5f2-4ebe-8707-251de2503ee1]] ERROR org.apache.spark.sql.execution.datasources.v2.WriteToDataSourceV2Exec - Data source writer org.apache.spark.sql.execution.streaming.sources.MicroBatchWriter@228cec9e is aborting.
[stream execution thread for [id = f130d772-fc9e-4b0f-a81e-942af0741ae9, runId = 7dc1cb33-c5f2-4ebe-8707-251de2503ee1]] ERROR org.apache.spark.sql.execution.datasources.v2.WriteToDataSourceV2Exec - Data source writer org.apache.spark.sql.execution.streaming.sources.MicroBatchWriter@228cec9e aborted.
[stream execution thread for [id = f130d772-fc9e-4b0f-a81e-942af0741ae9, runId = 7dc1cb33-c5f2-4ebe-8707-251de2503ee1]] ERROR org.apache.spark.sql.execution.streaming.MicroBatchExecution - Query [id = f130d772-fc9e-4b0f-a81e-942af0741ae9, runId = 7dc1cb33-c5f2-4ebe-8707-251de2503ee1] terminated with error
org.apache.spark.SparkException: Writing job aborted.
at org.apache.spark.sql.execution.datasources.v2.WriteToDataSourceV2Exec.doExecute(WriteToDataSourceV2Exec.scala:92)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at org.apache.spark.sql.execution.SparkPlan.getByteArrayRdd(SparkPlan.scala:247)
at org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:296)
at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collectFromPlan(Dataset.scala:3384)
at org.apache.spark.sql.Dataset$$anonfun$collect$1.apply(Dataset.scala:2783)
at org.apache.spark.sql.Dataset$$anonfun$collect$1.apply(Dataset.scala:2783)
at org.apache.spark.sql.Dataset$$anonfun$53.apply(Dataset.scala:3365)
at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:78)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3364)
at org.apache.spark.sql.Dataset.collect(Dataset.scala:2783)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$runBatch$5$$anonfun$apply$17.apply(MicroBatchExecution.scala:537)
at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:78)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$runBatch$5.apply(MicroBatchExecution.scala:532)
at org.apache.spark.sql.execution.streaming.ProgressReporter$class.reportTimeTaken(ProgressReporter.scala:351)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:58)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.org$apache$spark$sql$execution$streaming$MicroBatchExecution$$runBatch(MicroBatchExecution.scala:531)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply$mcV$sp(MicroBatchExecution.scala:198)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply(MicroBatchExecution.scala:166)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply(MicroBatchExecution.scala:166)
at org.apache.spark.sql.execution.streaming.ProgressReporter$class.reportTimeTaken(ProgressReporter.scala:351)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:58)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1.apply$mcZ$sp(MicroBatchExecution.scala:166)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:56)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:160)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:279)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:189)
Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 1.0 failed 1 times, most recent failure: Lost task 0.0 in stage 1.0 (TID 1, localhost, executor driver): org.apache.spark.util.TaskCompletionListenerException: null
at org.apache.spark.TaskContextImpl.invokeListeners(TaskContextImpl.scala:138)
at org.apache.spark.TaskContextImpl.markTaskCompleted(TaskContextImpl.scala:116)
at org.apache.spark.scheduler.Task.run(Task.scala:137)
at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:402)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:408)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1887)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1875)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1874)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1874)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:926)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:926)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:926)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2108)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2057)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2046)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:737)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2061)
at org.apache.spark.sql.execution.datasources.v2.WriteToDataSourceV2Exec.doExecute(WriteToDataSourceV2Exec.scala:64)
... 35 more
Caused by: org.apache.spark.util.TaskCompletionListenerException: null
at org.apache.spark.TaskContextImpl.invokeListeners(TaskContextImpl.scala:138)
at org.apache.spark.TaskContextImpl.markTaskCompleted(TaskContextImpl.scala:116)
at org.apache.spark.scheduler.Task.run(Task.scala:137)
at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:402)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:408)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Exception in thread "main" org.apache.spark.sql.streaming.StreamingQueryException: Writing job aborted.
=== Streaming Query ===
Identifier: [id = f130d772-fc9e-4b0f-a81e-942af0741ae9, runId = 7dc1cb33-c5f2-4ebe-8707-251de2503ee1]
Current Committed Offsets: {}
Current Available Offsets: {KafkaV2[Subscribe[NormalizedEvents]]: {"NormalizedEvents":{"0":46564}}}
Current State: ACTIVE
Thread State: RUNNABLE
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:295)
at org.apache.spark.sql.execution.streaming.StreamExecution$$anon$1.run(StreamExecution.scala:189)
Caused by: org.apache.spark.SparkException: Writing job aborted.
at org.apache.spark.sql.execution.datasources.v2.WriteToDataSourceV2Exec.doExecute(WriteToDataSourceV2Exec.scala:92)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127)
at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127)
at org.apache.spark.sql.execution.SparkPlan.getByteArrayRdd(SparkPlan.scala:247)
at org.apache.spark.sql.execution.SparkPlan.executeCollect(SparkPlan.scala:296)
at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collectFromPlan(Dataset.scala:3384)
at org.apache.spark.sql.Dataset$$anonfun$collect$1.apply(Dataset.scala:2783)
at org.apache.spark.sql.Dataset$$anonfun$collect$1.apply(Dataset.scala:2783)
at org.apache.spark.sql.Dataset$$anonfun$53.apply(Dataset.scala:3365)
at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:78)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3364)
at org.apache.spark.sql.Dataset.collect(Dataset.scala:2783)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$runBatch$5$$anonfun$apply$17.apply(MicroBatchExecution.scala:537)
at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:78)
at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125)
at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$org$apache$spark$sql$execution$streaming$MicroBatchExecution$$runBatch$5.apply(MicroBatchExecution.scala:532)
at org.apache.spark.sql.execution.streaming.ProgressReporter$class.reportTimeTaken(ProgressReporter.scala:351)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:58)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.org$apache$spark$sql$execution$streaming$MicroBatchExecution$$runBatch(MicroBatchExecution.scala:531)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply$mcV$sp(MicroBatchExecution.scala:198)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply(MicroBatchExecution.scala:166)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1$$anonfun$apply$mcZ$sp$1.apply(MicroBatchExecution.scala:166)
at org.apache.spark.sql.execution.streaming.ProgressReporter$class.reportTimeTaken(ProgressReporter.scala:351)
at org.apache.spark.sql.execution.streaming.StreamExecution.reportTimeTaken(StreamExecution.scala:58)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution$$anonfun$runActivatedStream$1.apply$mcZ$sp(MicroBatchExecution.scala:166)
at org.apache.spark.sql.execution.streaming.ProcessingTimeExecutor.execute(TriggerExecutor.scala:56)
at org.apache.spark.sql.execution.streaming.MicroBatchExecution.runActivatedStream(MicroBatchExecution.scala:160)
at org.apache.spark.sql.execution.streaming.StreamExecution.org$apache$spark$sql$execution$streaming$StreamExecution$$runStream(StreamExecution.scala:279)
... 1 more
Caused by: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 1.0 failed 1 times, most recent failure: Lost task 0.0 in stage 1.0 (TID 1, localhost, executor driver): org.apache.spark.util.TaskCompletionListenerException: null
at org.apache.spark.TaskContextImpl.invokeListeners(TaskContextImpl.scala:138)
at org.apache.spark.TaskContextImpl.markTaskCompleted(TaskContextImpl.scala:116)
at org.apache.spark.scheduler.Task.run(Task.scala:137)
at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:402)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:408)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1887)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1875)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1874)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1874)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:926)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:926)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:926)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2108)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2057)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2046)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:737)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2061)
at org.apache.spark.sql.execution.datasources.v2.WriteToDataSourceV2Exec.doExecute(WriteToDataSourceV2Exec.scala:64)
... 35 more
Caused by: org.apache.spark.util.TaskCompletionListenerException: null
at org.apache.spark.TaskContextImpl.invokeListeners(TaskContextImpl.scala:138)
at org.apache.spark.TaskContextImpl.markTaskCompleted(TaskContextImpl.scala:116)
at org.apache.spark.scheduler.Task.run(Task.scala:137)
at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:402)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:408)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
[Thread-1] INFO org.apache.spark.SparkContext - Invoking stop() from shutdown hook
[Thread-1] INFO org.spark_project.jetty.server.AbstractConnector - Stopped Spark@1ce93c18{HTTP/1.1,[http/1.1]}{0.0.0.0:4041}
[Thread-1] INFO org.apache.spark.ui.SparkUI - Stopped Spark web UI at http://10.25.12.222:4041
[dispatcher-event-loop-0] INFO org.apache.spark.MapOutputTrackerMasterEndpoint - MapOutputTrackerMasterEndpoint stopped!
[Thread-1] INFO org.apache.spark.storage.memory.MemoryStore - MemoryStore cleared
[Thread-1] INFO org.apache.spark.storage.BlockManager - BlockManager stopped
[Thread-1] INFO org.apache.spark.storage.BlockManagerMaster - BlockManagerMaster stopped
[dispatcher-event-loop-1] INFO org.apache.spark.scheduler.OutputCommitCoordinator$OutputCommitCoordinatorEndpoint - OutputCommitCoordinator stopped!
[Thread-1] INFO org.apache.spark.SparkContext - Successfully stopped SparkContext
[Thread-1] INFO org.apache.spark.util.ShutdownHookManager - Shutdown hook called
[Thread-1] INFO org.apache.spark.util.ShutdownHookManager - Deleting directory /private/var/folders/_t/7m21x7313gs74_yfv4txsr69b8yh87/T/temporaryReader-75fdf46f-7de0-4ca7-9c77-8bd034e4f5a3
[Thread-1] INFO org.apache.spark.util.ShutdownHookManager - Deleting directory /private/var/folders/_t/7m21x7313gs74_yfv4txsr69b8yh87/T/spark-bde783f1-fa66-420f-87e7-5c1895ab7ccc