[
https://issues.apache.org/jira/browse/FLINK-24071?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
zhuzhengjun updated FLINK-24071:
--------------------------------
Description:
{code:java}
org.apache.flink.runtime.JobException: Recovery is suppressed by
NoRestartBackoffTimeStrategy at
org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:118)
at
org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:80)
at
org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:233)
at
org.apache.flink.runtime.scheduler.DefaultScheduler.maybeHandleTaskFailure(DefaultScheduler.java:224)
at
org.apache.flink.runtime.scheduler.DefaultScheduler.updateTaskExecutionStateInternal(DefaultScheduler.java:215)
at
org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:669)
at
org.apache.flink.runtime.scheduler.SchedulerNG.updateTaskExecutionState(SchedulerNG.java:89)
at
org.apache.flink.runtime.jobmaster.JobMaster.updateTaskExecutionState(JobMaster.java:449)
at sun.reflect.GeneratedMethodAccessor144.invoke(Unknown Source) at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498) at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcInvocation(AkkaRpcActor.java:305)
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:212)
at
org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:77)
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:158)
at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26) at
akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21) at
scala.PartialFunction$class.applyOrElse(PartialFunction.scala:123) at
akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21) at
scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:170) at
scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171) at
scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171) at
akka.actor.Actor$class.aroundReceive(Actor.scala:517) at
akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:225) at
akka.actor.ActorCell.receiveMessage(ActorCell.scala:592) at
akka.actor.ActorCell.invoke(ActorCell.scala:561) at
akka.dispatch.Mailbox.processMailbox(Mailbox.scala:258) at
akka.dispatch.Mailbox.run(Mailbox.scala:225) at
akka.dispatch.Mailbox.exec(Mailbox.scala:235) at
akka.dispatch.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260) at
akka.dispatch.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
at akka.dispatch.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979) at
akka.dispatch.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
Caused by: java.lang.OutOfMemoryError: Java heap space at
java.util.HashMap.entrySet(HashMap.java:1007) at
com.esotericsoftware.kryo.serializers.MapSerializer.write(MapSerializer.java:80)
at
com.esotericsoftware.kryo.serializers.MapSerializer.write(MapSerializer.java:21)
at com.esotericsoftware.kryo.Kryo.writeObject(Kryo.java:523) at
com.esotericsoftware.kryo.serializers.ObjectField.write(ObjectField.java:61) at
com.esotericsoftware.kryo.serializers.FieldSerializer.write(FieldSerializer.java:495)
at com.esotericsoftware.kryo.Kryo.writeClassAndObject(Kryo.java:599) at
org.apache.flink.api.java.typeutils.runtime.kryo.KryoSerializer.serialize(KryoSerializer.java:316)
at
org.apache.flink.streaming.runtime.streamrecord.StreamElementSerializer.serialize(StreamElementSerializer.java:168)
at
org.apache.flink.streaming.runtime.streamrecord.StreamElementSerializer.serialize(StreamElementSerializer.java:46)
at
org.apache.flink.runtime.plugable.SerializationDelegate.write(SerializationDelegate.java:54)
at
org.apache.flink.runtime.io.network.api.writer.RecordWriter.serializeRecord(RecordWriter.java:130)
at
org.apache.flink.runtime.io.network.api.writer.RecordWriter.emit(RecordWriter.java:104)
at
org.apache.flink.runtime.io.network.api.writer.ChannelSelectorRecordWriter.emit(ChannelSelectorRecordWriter.java:54)
at
org.apache.flink.streaming.runtime.io.RecordWriterOutput.pushToRecordWriter(RecordWriterOutput.java:101)
at
org.apache.flink.streaming.runtime.io.RecordWriterOutput.collect(RecordWriterOutput.java:87)
at
org.apache.flink.streaming.runtime.io.RecordWriterOutput.collect(RecordWriterOutput.java:43)
at
org.apache.flink.streaming.api.operators.CountingOutput.collect(CountingOutput.java:50)
at
org.apache.flink.streaming.api.operators.CountingOutput.collect(CountingOutput.java:28)
at
org.apache.flink.streaming.runtime.operators.TimestampsAndWatermarksOperator.processElement(TimestampsAndWatermarksOperator.java:104)
at
org.apache.flink.streaming.runtime.tasks.OneInputStreamTask$StreamTaskNetworkOutput.emitRecord(OneInputStreamTask.java:191)
at
org.apache.flink.streaming.runtime.io.StreamTaskNetworkInput.processElement(StreamTaskNetworkInput.java:204)
at
org.apache.flink.streaming.runtime.io.StreamTaskNetworkInput.emitNext(StreamTaskNetworkInput.java:174)
at
org.apache.flink.streaming.runtime.io.StreamOneInputProcessor.processInput(StreamOneInputProcessor.java:65)
at
org.apache.flink.streaming.runtime.tasks.StreamTask.processInput(StreamTask.java:396)
at
org.apache.flink.streaming.runtime.tasks.StreamTask$$Lambda$219/1969922351.runDefaultAction(Unknown
Source) at
org.apache.flink.streaming.runtime.tasks.mailbox.MailboxProcessor.runMailboxLoop(MailboxProcessor.java:191)
at
org.apache.flink.streaming.runtime.tasks.StreamTask.runMailboxLoop(StreamTask.java:617)
at
org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:581)
at org.apache.flink.runtime.taskmanager.Task.doRun(Task.java:755) at
org.apache.flink.runtime.taskmanager.Task.run(Task.java:570) at
java.lang.Thread.run(Thread.java:748)
{code}
we find this problem when we tested file compaction,and this problem may not
produced by us so that we report this problem to find help.
was:
{code}
org.apache.flink.runtime.JobException: Recovery is suppressed by
NoRestartBackoffTimeStrategy at
org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:118)
at
org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:80)
at
org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:233)
at
org.apache.flink.runtime.scheduler.DefaultScheduler.maybeHandleTaskFailure(DefaultScheduler.java:224)
at
org.apache.flink.runtime.scheduler.DefaultScheduler.updateTaskExecutionStateInternal(DefaultScheduler.java:215)
at
org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:669)
at
org.apache.flink.runtime.scheduler.SchedulerNG.updateTaskExecutionState(SchedulerNG.java:89)
at
org.apache.flink.runtime.jobmaster.JobMaster.updateTaskExecutionState(JobMaster.java:449)
at sun.reflect.GeneratedMethodAccessor144.invoke(Unknown Source) at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498) at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcInvocation(AkkaRpcActor.java:305)
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:212)
at
org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:77)
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:158)
at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26) at
akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21) at
scala.PartialFunction$class.applyOrElse(PartialFunction.scala:123) at
akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21) at
scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:170) at
scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171) at
scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171) at
akka.actor.Actor$class.aroundReceive(Actor.scala:517) at
akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:225) at
akka.actor.ActorCell.receiveMessage(ActorCell.scala:592) at
akka.actor.ActorCell.invoke(ActorCell.scala:561) at
akka.dispatch.Mailbox.processMailbox(Mailbox.scala:258) at
akka.dispatch.Mailbox.run(Mailbox.scala:225) at
akka.dispatch.Mailbox.exec(Mailbox.scala:235) at
akka.dispatch.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260) at
akka.dispatch.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
at akka.dispatch.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979) at
akka.dispatch.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
Caused by: java.lang.OutOfMemoryError: Java heap space at
java.util.HashMap.entrySet(HashMap.java:1007) at
com.esotericsoftware.kryo.serializers.MapSerializer.write(MapSerializer.java:80)
at
com.esotericsoftware.kryo.serializers.MapSerializer.write(MapSerializer.java:21)
at com.esotericsoftware.kryo.Kryo.writeObject(Kryo.java:523) at
com.esotericsoftware.kryo.serializers.ObjectField.write(ObjectField.java:61) at
com.esotericsoftware.kryo.serializers.FieldSerializer.write(FieldSerializer.java:495)
at com.esotericsoftware.kryo.Kryo.writeClassAndObject(Kryo.java:599) at
org.apache.flink.api.java.typeutils.runtime.kryo.KryoSerializer.serialize(KryoSerializer.java:316)
at
org.apache.flink.streaming.runtime.streamrecord.StreamElementSerializer.serialize(StreamElementSerializer.java:168)
at
org.apache.flink.streaming.runtime.streamrecord.StreamElementSerializer.serialize(StreamElementSerializer.java:46)
at
org.apache.flink.runtime.plugable.SerializationDelegate.write(SerializationDelegate.java:54)
at
org.apache.flink.runtime.io.network.api.writer.RecordWriter.serializeRecord(RecordWriter.java:130)
at
org.apache.flink.runtime.io.network.api.writer.RecordWriter.emit(RecordWriter.java:104)
at
org.apache.flink.runtime.io.network.api.writer.ChannelSelectorRecordWriter.emit(ChannelSelectorRecordWriter.java:54)
at
org.apache.flink.streaming.runtime.io.RecordWriterOutput.pushToRecordWriter(RecordWriterOutput.java:101)
at
org.apache.flink.streaming.runtime.io.RecordWriterOutput.collect(RecordWriterOutput.java:87)
at
org.apache.flink.streaming.runtime.io.RecordWriterOutput.collect(RecordWriterOutput.java:43)
at
org.apache.flink.streaming.api.operators.CountingOutput.collect(CountingOutput.java:50)
at
org.apache.flink.streaming.api.operators.CountingOutput.collect(CountingOutput.java:28)
at
org.apache.flink.streaming.runtime.operators.TimestampsAndWatermarksOperator.processElement(TimestampsAndWatermarksOperator.java:104)
at
org.apache.flink.streaming.runtime.tasks.OneInputStreamTask$StreamTaskNetworkOutput.emitRecord(OneInputStreamTask.java:191)
at
org.apache.flink.streaming.runtime.io.StreamTaskNetworkInput.processElement(StreamTaskNetworkInput.java:204)
at
org.apache.flink.streaming.runtime.io.StreamTaskNetworkInput.emitNext(StreamTaskNetworkInput.java:174)
at
org.apache.flink.streaming.runtime.io.StreamOneInputProcessor.processInput(StreamOneInputProcessor.java:65)
at
org.apache.flink.streaming.runtime.tasks.StreamTask.processInput(StreamTask.java:396)
at
org.apache.flink.streaming.runtime.tasks.StreamTask$$Lambda$219/1969922351.runDefaultAction(Unknown
Source) at
org.apache.flink.streaming.runtime.tasks.mailbox.MailboxProcessor.runMailboxLoop(MailboxProcessor.java:191)
at
org.apache.flink.streaming.runtime.tasks.StreamTask.runMailboxLoop(StreamTask.java:617)
at
org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:581)
at org.apache.flink.runtime.taskmanager.Task.doRun(Task.java:755) at
org.apache.flink.runtime.taskmanager.Task.run(Task.java:570) at
java.lang.Thread.run(Thread.java:748)
{code}
we find this problem when we tested small file merge,and this problem may not
produced by us so that we report this problem to find help.
> Flink 1.12 HDFS sink have a problem,reported as OOM
> ------------------------------------------------------
>
> Key: FLINK-24071
> URL: https://issues.apache.org/jira/browse/FLINK-24071
> Project: Flink
> Issue Type: Bug
> Components: Connectors / FileSystem
> Affects Versions: 1.12.0
> Reporter: zhuzhengjun
> Priority: Major
>
> {code:java}
> org.apache.flink.runtime.JobException: Recovery is suppressed by
> NoRestartBackoffTimeStrategy at
> org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:118)
> at
> org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:80)
> at
> org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:233)
> at
> org.apache.flink.runtime.scheduler.DefaultScheduler.maybeHandleTaskFailure(DefaultScheduler.java:224)
> at
> org.apache.flink.runtime.scheduler.DefaultScheduler.updateTaskExecutionStateInternal(DefaultScheduler.java:215)
> at
> org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:669)
> at
> org.apache.flink.runtime.scheduler.SchedulerNG.updateTaskExecutionState(SchedulerNG.java:89)
> at
> org.apache.flink.runtime.jobmaster.JobMaster.updateTaskExecutionState(JobMaster.java:449)
> at sun.reflect.GeneratedMethodAccessor144.invoke(Unknown Source) at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:498) at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcInvocation(AkkaRpcActor.java:305)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:212)
> at
> org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:77)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:158)
> at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26) at
> akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21) at
> scala.PartialFunction$class.applyOrElse(PartialFunction.scala:123) at
> akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21) at
> scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:170) at
> scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171) at
> scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171) at
> akka.actor.Actor$class.aroundReceive(Actor.scala:517) at
> akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:225) at
> akka.actor.ActorCell.receiveMessage(ActorCell.scala:592) at
> akka.actor.ActorCell.invoke(ActorCell.scala:561) at
> akka.dispatch.Mailbox.processMailbox(Mailbox.scala:258) at
> akka.dispatch.Mailbox.run(Mailbox.scala:225) at
> akka.dispatch.Mailbox.exec(Mailbox.scala:235) at
> akka.dispatch.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260) at
> akka.dispatch.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
> at akka.dispatch.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979) at
> akka.dispatch.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
> Caused by: java.lang.OutOfMemoryError: Java heap space at
> java.util.HashMap.entrySet(HashMap.java:1007) at
> com.esotericsoftware.kryo.serializers.MapSerializer.write(MapSerializer.java:80)
> at
> com.esotericsoftware.kryo.serializers.MapSerializer.write(MapSerializer.java:21)
> at com.esotericsoftware.kryo.Kryo.writeObject(Kryo.java:523) at
> com.esotericsoftware.kryo.serializers.ObjectField.write(ObjectField.java:61)
> at
> com.esotericsoftware.kryo.serializers.FieldSerializer.write(FieldSerializer.java:495)
> at com.esotericsoftware.kryo.Kryo.writeClassAndObject(Kryo.java:599) at
> org.apache.flink.api.java.typeutils.runtime.kryo.KryoSerializer.serialize(KryoSerializer.java:316)
> at
> org.apache.flink.streaming.runtime.streamrecord.StreamElementSerializer.serialize(StreamElementSerializer.java:168)
> at
> org.apache.flink.streaming.runtime.streamrecord.StreamElementSerializer.serialize(StreamElementSerializer.java:46)
> at
> org.apache.flink.runtime.plugable.SerializationDelegate.write(SerializationDelegate.java:54)
> at
> org.apache.flink.runtime.io.network.api.writer.RecordWriter.serializeRecord(RecordWriter.java:130)
> at
> org.apache.flink.runtime.io.network.api.writer.RecordWriter.emit(RecordWriter.java:104)
> at
> org.apache.flink.runtime.io.network.api.writer.ChannelSelectorRecordWriter.emit(ChannelSelectorRecordWriter.java:54)
> at
> org.apache.flink.streaming.runtime.io.RecordWriterOutput.pushToRecordWriter(RecordWriterOutput.java:101)
> at
> org.apache.flink.streaming.runtime.io.RecordWriterOutput.collect(RecordWriterOutput.java:87)
> at
> org.apache.flink.streaming.runtime.io.RecordWriterOutput.collect(RecordWriterOutput.java:43)
> at
> org.apache.flink.streaming.api.operators.CountingOutput.collect(CountingOutput.java:50)
> at
> org.apache.flink.streaming.api.operators.CountingOutput.collect(CountingOutput.java:28)
> at
> org.apache.flink.streaming.runtime.operators.TimestampsAndWatermarksOperator.processElement(TimestampsAndWatermarksOperator.java:104)
> at
> org.apache.flink.streaming.runtime.tasks.OneInputStreamTask$StreamTaskNetworkOutput.emitRecord(OneInputStreamTask.java:191)
> at
> org.apache.flink.streaming.runtime.io.StreamTaskNetworkInput.processElement(StreamTaskNetworkInput.java:204)
> at
> org.apache.flink.streaming.runtime.io.StreamTaskNetworkInput.emitNext(StreamTaskNetworkInput.java:174)
> at
> org.apache.flink.streaming.runtime.io.StreamOneInputProcessor.processInput(StreamOneInputProcessor.java:65)
> at
> org.apache.flink.streaming.runtime.tasks.StreamTask.processInput(StreamTask.java:396)
> at
> org.apache.flink.streaming.runtime.tasks.StreamTask$$Lambda$219/1969922351.runDefaultAction(Unknown
> Source) at
> org.apache.flink.streaming.runtime.tasks.mailbox.MailboxProcessor.runMailboxLoop(MailboxProcessor.java:191)
> at
> org.apache.flink.streaming.runtime.tasks.StreamTask.runMailboxLoop(StreamTask.java:617)
> at
> org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:581)
> at org.apache.flink.runtime.taskmanager.Task.doRun(Task.java:755) at
> org.apache.flink.runtime.taskmanager.Task.run(Task.java:570) at
> java.lang.Thread.run(Thread.java:748)
> {code}
>
> we find this problem when we tested file compaction,and this problem may not
> produced by us so that we report this problem to find help.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)