[ https://issues.apache.org/jira/browse/FLINK-21535?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17301851#comment-17301851 ]
Arvid Heise commented on FLINK-21535: ------------------------------------- Merged as c177d15323d5025f0cf737b98bb051efbc08a149 into master. > UnalignedCheckpointITCase.execute failed with "OutOfMemoryError: Java heap > space" > --------------------------------------------------------------------------------- > > Key: FLINK-21535 > URL: https://issues.apache.org/jira/browse/FLINK-21535 > Project: Flink > Issue Type: Bug > Components: Runtime / Checkpointing > Affects Versions: 1.13.0 > Reporter: Dawid Wysakowicz > Assignee: Arvid Heise > Priority: Major > Labels: pull-request-available, test-stability > > https://dev.azure.com/apache-flink/apache-flink/_build/results?buildId=13866&view=logs&j=39d5b1d5-3b41-54dc-6458-1e2ddd1cdcf3&t=a99e99c7-21cd-5a1f-7274-585e62b72f56 > {code} > 2021-02-27T02:11:41.5659201Z > org.apache.flink.runtime.client.JobExecutionException: Job execution failed. > 2021-02-27T02:11:41.5659947Z at > org.apache.flink.runtime.jobmaster.JobResult.toJobExecutionResult(JobResult.java:144) > 2021-02-27T02:11:41.5660794Z at > org.apache.flink.runtime.minicluster.MiniClusterJobClient.lambda$getJobExecutionResult$3(MiniClusterJobClient.java:137) > 2021-02-27T02:11:41.5661618Z at > java.util.concurrent.CompletableFuture.uniApply(CompletableFuture.java:616) > 2021-02-27T02:11:41.5662356Z at > java.util.concurrent.CompletableFuture$UniApply.tryFire(CompletableFuture.java:591) > 2021-02-27T02:11:41.5663104Z at > java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488) > 2021-02-27T02:11:41.5664016Z at > java.util.concurrent.CompletableFuture.complete(CompletableFuture.java:1975) > 2021-02-27T02:11:41.5664817Z at > org.apache.flink.runtime.rpc.akka.AkkaInvocationHandler.lambda$invokeRpc$0(AkkaInvocationHandler.java:237) > 2021-02-27T02:11:41.5665638Z at > java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:774) > 2021-02-27T02:11:41.5666405Z at > java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:750) > 2021-02-27T02:11:41.5667609Z at > java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488) > 2021-02-27T02:11:41.5668358Z at > java.util.concurrent.CompletableFuture.complete(CompletableFuture.java:1975) > 2021-02-27T02:11:41.5669218Z at > org.apache.flink.runtime.concurrent.FutureUtils$1.onComplete(FutureUtils.java:1066) > 2021-02-27T02:11:41.5669928Z at > akka.dispatch.OnComplete.internal(Future.scala:264) > 2021-02-27T02:11:41.5670540Z at > akka.dispatch.OnComplete.internal(Future.scala:261) > 2021-02-27T02:11:41.5671268Z at > akka.dispatch.japi$CallbackBridge.apply(Future.scala:191) > 2021-02-27T02:11:41.5671881Z at > akka.dispatch.japi$CallbackBridge.apply(Future.scala:188) > 2021-02-27T02:11:41.5672512Z at > scala.concurrent.impl.CallbackRunnable.run(Promise.scala:36) > 2021-02-27T02:11:41.5673219Z at > org.apache.flink.runtime.concurrent.Executors$DirectExecutionContext.execute(Executors.java:73) > 2021-02-27T02:11:41.5674085Z at > scala.concurrent.impl.CallbackRunnable.executeWithValue(Promise.scala:44) > 2021-02-27T02:11:41.5674794Z at > scala.concurrent.impl.Promise$DefaultPromise.tryComplete(Promise.scala:252) > 2021-02-27T02:11:41.5675466Z at > akka.pattern.PromiseActorRef.$bang(AskSupport.scala:572) > 2021-02-27T02:11:41.5676181Z at > akka.pattern.PipeToSupport$PipeableFuture$$anonfun$pipeTo$1.applyOrElse(PipeToSupport.scala:22) > 2021-02-27T02:11:41.5676977Z at > akka.pattern.PipeToSupport$PipeableFuture$$anonfun$pipeTo$1.applyOrElse(PipeToSupport.scala:21) > 2021-02-27T02:11:41.5677717Z at > scala.concurrent.Future$$anonfun$andThen$1.apply(Future.scala:436) > 2021-02-27T02:11:41.5678409Z at > scala.concurrent.Future$$anonfun$andThen$1.apply(Future.scala:435) > 2021-02-27T02:11:41.5679071Z at > scala.concurrent.impl.CallbackRunnable.run(Promise.scala:36) > 2021-02-27T02:11:41.5679776Z at > akka.dispatch.BatchingExecutor$AbstractBatch.processBatch(BatchingExecutor.scala:55) > 2021-02-27T02:11:41.5680576Z at > akka.dispatch.BatchingExecutor$BlockableBatch$$anonfun$run$1.apply$mcV$sp(BatchingExecutor.scala:91) > 2021-02-27T02:11:41.5681383Z at > akka.dispatch.BatchingExecutor$BlockableBatch$$anonfun$run$1.apply(BatchingExecutor.scala:91) > 2021-02-27T02:11:41.5682167Z at > akka.dispatch.BatchingExecutor$BlockableBatch$$anonfun$run$1.apply(BatchingExecutor.scala:91) > 2021-02-27T02:11:41.5683040Z at > scala.concurrent.BlockContext$.withBlockContext(BlockContext.scala:72) > 2021-02-27T02:11:41.5683759Z at > akka.dispatch.BatchingExecutor$BlockableBatch.run(BatchingExecutor.scala:90) > 2021-02-27T02:11:41.5684493Z at > akka.dispatch.TaskInvocation.run(AbstractDispatcher.scala:40) > 2021-02-27T02:11:41.5685238Z at > akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(ForkJoinExecutorConfigurator.scala:44) > 2021-02-27T02:11:41.5686193Z at > akka.dispatch.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260) > 2021-02-27T02:11:41.5686901Z at > akka.dispatch.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339) > 2021-02-27T02:11:41.5687621Z at > akka.dispatch.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979) > 2021-02-27T02:11:41.5688337Z at > akka.dispatch.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107) > 2021-02-27T02:11:41.5689199Z Caused by: > org.apache.flink.runtime.JobException: Recovery is suppressed by > FixedDelayRestartBackoffTimeStrategy(maxNumberRestartAttempts=5, > backoffTimeMS=100) > 2021-02-27T02:11:41.5690155Z at > org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:130) > 2021-02-27T02:11:41.5691115Z at > org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:81) > 2021-02-27T02:11:41.5692140Z at > org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:221) > 2021-02-27T02:11:41.5693174Z at > org.apache.flink.runtime.scheduler.DefaultScheduler.maybeHandleTaskFailure(DefaultScheduler.java:212) > 2021-02-27T02:11:41.5694037Z at > org.apache.flink.runtime.scheduler.DefaultScheduler.updateTaskExecutionStateInternal(DefaultScheduler.java:203) > 2021-02-27T02:11:41.5694882Z at > org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:696) > 2021-02-27T02:11:41.5695679Z at > org.apache.flink.runtime.scheduler.SchedulerNG.updateTaskExecutionState(SchedulerNG.java:80) > 2021-02-27T02:11:41.5696679Z at > org.apache.flink.runtime.jobmaster.JobMaster.updateTaskExecutionState(JobMaster.java:433) > 2021-02-27T02:11:41.5697369Z at > sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) > 2021-02-27T02:11:41.5698136Z at > sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) > 2021-02-27T02:11:41.5699013Z at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > 2021-02-27T02:11:41.5699822Z at > java.lang.reflect.Method.invoke(Method.java:498) > 2021-02-27T02:11:41.5700518Z at > org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcInvocation(AkkaRpcActor.java:305) > 2021-02-27T02:11:41.5701297Z at > org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:212) > 2021-02-27T02:11:41.5702092Z at > org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:77) > 2021-02-27T02:11:41.5702872Z at > org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:158) > 2021-02-27T02:11:41.5703579Z at > akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26) > 2021-02-27T02:11:41.5704234Z at > akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21) > 2021-02-27T02:11:41.5704897Z at > scala.PartialFunction$class.applyOrElse(PartialFunction.scala:123) > 2021-02-27T02:11:41.5705584Z at > akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21) > 2021-02-27T02:11:41.5706268Z at > scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:170) > 2021-02-27T02:11:41.5706950Z at > scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171) > 2021-02-27T02:11:41.5707627Z at > scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171) > 2021-02-27T02:11:41.5708276Z at > akka.actor.Actor$class.aroundReceive(Actor.scala:517) > 2021-02-27T02:11:41.5708920Z at > akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:225) > 2021-02-27T02:11:41.5709572Z at > akka.actor.ActorCell.receiveMessage(ActorCell.scala:592) > 2021-02-27T02:11:41.5710192Z at > akka.actor.ActorCell.invoke(ActorCell.scala:561) > 2021-02-27T02:11:41.5710808Z at > akka.dispatch.Mailbox.processMailbox(Mailbox.scala:258) > 2021-02-27T02:11:41.5711511Z at akka.dispatch.Mailbox.run(Mailbox.scala:225) > 2021-02-27T02:11:41.5712074Z at akka.dispatch.Mailbox.exec(Mailbox.scala:235) > 2021-02-27T02:11:41.5712561Z ... 4 more > 2021-02-27T02:11:41.5713267Z Caused by: java.lang.OutOfMemoryError: Java heap > space > 2021-02-27T02:11:41.5713740Z at java.util.Arrays.copyOf(Arrays.java:3236) > 2021-02-27T02:11:41.5714369Z at > java.io.ByteArrayOutputStream.grow(ByteArrayOutputStream.java:118) > 2021-02-27T02:11:41.5714949Z at > java.io.ByteArrayOutputStream.ensureCapacity(ByteArrayOutputStream.java:93) > 2021-02-27T02:11:41.5715639Z at > java.io.ByteArrayOutputStream.write(ByteArrayOutputStream.java:153) > 2021-02-27T02:11:41.5716279Z at > com.esotericsoftware.kryo.io.Output.flush(Output.java:163) > 2021-02-27T02:11:41.5716902Z at > com.esotericsoftware.kryo.io.Output.require(Output.java:142) > 2021-02-27T02:11:41.5717398Z at > com.esotericsoftware.kryo.io.Output.writeLong(Output.java:501) > 2021-02-27T02:11:41.5717941Z at > com.twitter.chill.java.BitSetSerializer.write(BitSetSerializer.java:79) > 2021-02-27T02:11:41.5718501Z at > com.twitter.chill.java.BitSetSerializer.write(BitSetSerializer.java:35) > 2021-02-27T02:11:41.5719419Z at > com.esotericsoftware.kryo.Kryo.writeObject(Kryo.java:505) > 2021-02-27T02:11:41.5720114Z at > org.apache.flink.api.java.typeutils.runtime.kryo.KryoSerializer.copy(KryoSerializer.java:266) > 2021-02-27T02:11:41.5720879Z at > org.apache.flink.runtime.state.ArrayListSerializer.copy(ArrayListSerializer.java:75) > 2021-02-27T02:11:41.5721624Z at > org.apache.flink.runtime.state.PartitionableListState.<init>(PartitionableListState.java:64) > 2021-02-27T02:11:41.5722507Z at > org.apache.flink.runtime.state.PartitionableListState.deepCopy(PartitionableListState.java:76) > 2021-02-27T02:11:41.5723353Z at > org.apache.flink.runtime.state.DefaultOperatorStateBackendSnapshotStrategy.syncPrepareResources(DefaultOperatorStateBackendSnapshotStrategy.java:77) > 2021-02-27T02:11:41.5724425Z at > org.apache.flink.runtime.state.DefaultOperatorStateBackendSnapshotStrategy.syncPrepareResources(DefaultOperatorStateBackendSnapshotStrategy.java:36) > 2021-02-27T02:11:41.5725434Z at > org.apache.flink.runtime.state.SnapshotStrategyRunner.snapshot(SnapshotStrategyRunner.java:82) > 2021-02-27T02:11:41.5726280Z at > org.apache.flink.runtime.state.DefaultOperatorStateBackend.snapshot(DefaultOperatorStateBackend.java:230) > 2021-02-27T02:11:41.5727152Z at > org.apache.flink.streaming.api.operators.StreamOperatorStateHandler.snapshotState(StreamOperatorStateHandler.java:220) > 2021-02-27T02:11:41.5728043Z at > org.apache.flink.streaming.api.operators.StreamOperatorStateHandler.snapshotState(StreamOperatorStateHandler.java:163) > 2021-02-27T02:11:41.5728921Z at > org.apache.flink.streaming.api.operators.AbstractStreamOperator.snapshotState(AbstractStreamOperator.java:371) > 2021-02-27T02:11:41.5729844Z at > org.apache.flink.streaming.runtime.tasks.SubtaskCheckpointCoordinatorImpl.checkpointStreamOperator(SubtaskCheckpointCoordinatorImpl.java:691) > 2021-02-27T02:11:41.5730849Z at > org.apache.flink.streaming.runtime.tasks.SubtaskCheckpointCoordinatorImpl.buildOperatorSnapshotFutures(SubtaskCheckpointCoordinatorImpl.java:612) > 2021-02-27T02:11:41.5731913Z at > org.apache.flink.streaming.runtime.tasks.SubtaskCheckpointCoordinatorImpl.takeSnapshotSync(SubtaskCheckpointCoordinatorImpl.java:575) > 2021-02-27T02:11:41.5733435Z at > org.apache.flink.streaming.runtime.tasks.SubtaskCheckpointCoordinatorImpl.checkpointState(SubtaskCheckpointCoordinatorImpl.java:298) > 2021-02-27T02:11:41.5734991Z at > org.apache.flink.streaming.runtime.tasks.StreamTask.lambda$performCheckpoint$9(StreamTask.java:1020) > 2021-02-27T02:11:41.5735786Z at > org.apache.flink.streaming.runtime.tasks.StreamTask$$Lambda$663/1514851121.run(Unknown > Source) > 2021-02-27T02:11:41.5736587Z at > org.apache.flink.streaming.runtime.tasks.StreamTaskActionExecutor$1.runThrowing(StreamTaskActionExecutor.java:50) > 2021-02-27T02:11:41.5737425Z at > org.apache.flink.streaming.runtime.tasks.StreamTask.performCheckpoint(StreamTask.java:1004) > 2021-02-27T02:11:41.5738230Z at > org.apache.flink.streaming.runtime.tasks.StreamTask.triggerCheckpointOnBarrier(StreamTask.java:960) > 2021-02-27T02:11:41.5739112Z at > org.apache.flink.streaming.runtime.io.checkpointing.CheckpointBarrierHandler.notifyCheckpoint(CheckpointBarrierHandler.java:115) > 2021-02-27T02:11:41.5740088Z at > org.apache.flink.streaming.runtime.io.checkpointing.SingleCheckpointBarrierHandler.handleBarrier(SingleCheckpointBarrierHandler.java:182) > {code} -- This message was sent by Atlassian Jira (v8.3.4#803005)