Uploaded image for project: 'Flink'
  1. Flink
  2. FLINK-20328

UnalignedCheckpointITCase.execute failed with "Insufficient number of network buffers: required 1, but only 0 available"

    XMLWordPrintableJSON

Details

    Description

      https://dev.azure.com/apache-flink/apache-flink/_build/results?buildId=10008&view=logs&j=5c8e7682-d68f-54d1-16a2-a09310218a49&t=f508e270-48d6-5f1e-3138-42a17e0714f0

      2020-11-24T08:18:15.0273526Z [ERROR] execute[non-parallel pipeline with local channels](org.apache.flink.test.checkpointing.UnalignedCheckpointITCase)  Time elapsed: 4.338 s  <<< ERROR!
      2020-11-24T08:18:15.0287436Z org.apache.flink.runtime.client.JobExecutionException: Job execution failed.
      2020-11-24T08:18:15.0288449Z 	at org.apache.flink.runtime.jobmaster.JobResult.toJobExecutionResult(JobResult.java:147)
      2020-11-24T08:18:15.0292752Z 	at org.apache.flink.runtime.minicluster.MiniClusterJobClient.lambda$getJobExecutionResult$2(MiniClusterJobClient.java:119)
      2020-11-24T08:18:15.0293717Z 	at java.util.concurrent.CompletableFuture.uniApply(CompletableFuture.java:616)
      2020-11-24T08:18:15.0294586Z 	at java.util.concurrent.CompletableFuture$UniApply.tryFire(CompletableFuture.java:591)
      2020-11-24T08:18:15.0295320Z 	at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488)
      2020-11-24T08:18:15.0296301Z 	at java.util.concurrent.CompletableFuture.complete(CompletableFuture.java:1975)
      2020-11-24T08:18:15.0297083Z 	at org.apache.flink.runtime.rpc.akka.AkkaInvocationHandler.lambda$invokeRpc$0(AkkaInvocationHandler.java:229)
      2020-11-24T08:18:15.0299675Z 	at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:774)
      2020-11-24T08:18:15.0300561Z 	at java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:750)
      2020-11-24T08:18:15.0301312Z 	at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488)
      2020-11-24T08:18:15.0302041Z 	at java.util.concurrent.CompletableFuture.complete(CompletableFuture.java:1975)
      2020-11-24T08:18:15.0302911Z 	at org.apache.flink.runtime.concurrent.FutureUtils$1.onComplete(FutureUtils.java:996)
      2020-11-24T08:18:15.0303568Z 	at akka.dispatch.OnComplete.internal(Future.scala:264)
      2020-11-24T08:18:15.0304112Z 	at akka.dispatch.OnComplete.internal(Future.scala:261)
      2020-11-24T08:18:15.0304823Z 	at akka.dispatch.japi$CallbackBridge.apply(Future.scala:191)
      2020-11-24T08:18:15.0305426Z 	at akka.dispatch.japi$CallbackBridge.apply(Future.scala:188)
      2020-11-24T08:18:15.0349665Z 	at scala.concurrent.impl.CallbackRunnable.run(Promise.scala:36)
      2020-11-24T08:18:15.0350525Z 	at org.apache.flink.runtime.concurrent.Executors$DirectExecutionContext.execute(Executors.java:74)
      2020-11-24T08:18:15.0351135Z 	at scala.concurrent.impl.CallbackRunnable.executeWithValue(Promise.scala:44)
      2020-11-24T08:18:15.0351615Z 	at scala.concurrent.impl.Promise$DefaultPromise.tryComplete(Promise.scala:252)
      2020-11-24T08:18:15.0352100Z 	at akka.pattern.PromiseActorRef.$bang(AskSupport.scala:572)
      2020-11-24T08:18:15.0352715Z 	at akka.pattern.PipeToSupport$PipeableFuture$$anonfun$pipeTo$1.applyOrElse(PipeToSupport.scala:22)
      2020-11-24T08:18:15.0353389Z 	at akka.pattern.PipeToSupport$PipeableFuture$$anonfun$pipeTo$1.applyOrElse(PipeToSupport.scala:21)
      2020-11-24T08:18:15.0353992Z 	at scala.concurrent.Future$$anonfun$andThen$1.apply(Future.scala:436)
      2020-11-24T08:18:15.0354631Z 	at scala.concurrent.Future$$anonfun$andThen$1.apply(Future.scala:435)
      2020-11-24T08:18:15.0355099Z 	at scala.concurrent.impl.CallbackRunnable.run(Promise.scala:36)
      2020-11-24T08:18:15.0355553Z 	at akka.dispatch.BatchingExecutor$AbstractBatch.processBatch(BatchingExecutor.scala:55)
      2020-11-24T08:18:15.0356110Z 	at akka.dispatch.BatchingExecutor$BlockableBatch$$anonfun$run$1.apply$mcV$sp(BatchingExecutor.scala:91)
      2020-11-24T08:18:15.0356651Z 	at akka.dispatch.BatchingExecutor$BlockableBatch$$anonfun$run$1.apply(BatchingExecutor.scala:91)
      2020-11-24T08:18:15.0357188Z 	at akka.dispatch.BatchingExecutor$BlockableBatch$$anonfun$run$1.apply(BatchingExecutor.scala:91)
      2020-11-24T08:18:15.0357682Z 	at scala.concurrent.BlockContext$.withBlockContext(BlockContext.scala:72)
      2020-11-24T08:18:15.0358133Z 	at akka.dispatch.BatchingExecutor$BlockableBatch.run(BatchingExecutor.scala:90)
      2020-11-24T08:18:15.0358661Z 	at akka.dispatch.TaskInvocation.run(AbstractDispatcher.scala:40)
      2020-11-24T08:18:15.0359167Z 	at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(ForkJoinExecutorConfigurator.scala:44)
      2020-11-24T08:18:15.0359662Z 	at akka.dispatch.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
      2020-11-24T08:18:15.0360113Z 	at akka.dispatch.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
      2020-11-24T08:18:15.0360575Z 	at akka.dispatch.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
      2020-11-24T08:18:15.0361019Z 	at akka.dispatch.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
      2020-11-24T08:18:15.0361599Z Caused by: org.apache.flink.runtime.JobException: Recovery is suppressed by FixedDelayRestartBackoffTimeStrategy(maxNumberRestartAttempts=5, backoffTimeMS=100)
      2020-11-24T08:18:15.0362291Z 	at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:116)
      2020-11-24T08:18:15.0363012Z 	at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:78)
      2020-11-24T08:18:15.0450920Z 	at org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:224)
      2020-11-24T08:18:15.0451758Z 	at org.apache.flink.runtime.scheduler.DefaultScheduler.maybeHandleTaskFailure(DefaultScheduler.java:217)
      2020-11-24T08:18:15.0512154Z 	at org.apache.flink.runtime.scheduler.DefaultScheduler.updateTaskExecutionStateInternal(DefaultScheduler.java:208)
      2020-11-24T08:18:15.0512781Z 	at org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:534)
      2020-11-24T08:18:15.0513330Z 	at org.apache.flink.runtime.scheduler.SchedulerNG.updateTaskExecutionState(SchedulerNG.java:89)
      2020-11-24T08:18:15.0513856Z 	at org.apache.flink.runtime.jobmaster.JobMaster.updateTaskExecutionState(JobMaster.java:419)
      2020-11-24T08:18:15.0514482Z 	at sun.reflect.GeneratedMethodAccessor19.invoke(Unknown Source)
      2020-11-24T08:18:15.0514986Z 	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
      2020-11-24T08:18:15.0515459Z 	at java.lang.reflect.Method.invoke(Method.java:498)
      2020-11-24T08:18:15.0516031Z 	at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcInvocation(AkkaRpcActor.java:286)
      2020-11-24T08:18:15.0516566Z 	at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:201)
      2020-11-24T08:18:15.0517102Z 	at org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:74)
      2020-11-24T08:18:15.0517625Z 	at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:154)
      2020-11-24T08:18:15.0518095Z 	at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26)
      2020-11-24T08:18:15.0518622Z 	at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21)
      2020-11-24T08:18:15.0519204Z 	at scala.PartialFunction$class.applyOrElse(PartialFunction.scala:123)
      2020-11-24T08:18:15.0519830Z 	at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21)
      2020-11-24T08:18:15.0520684Z 	at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:170)
      2020-11-24T08:18:15.0521691Z 	at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
      2020-11-24T08:18:15.0522688Z 	at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
      2020-11-24T08:18:15.0523629Z 	at akka.actor.Actor$class.aroundReceive(Actor.scala:517)
      2020-11-24T08:18:15.0524469Z 	at akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:225)
      2020-11-24T08:18:15.0525164Z 	at akka.actor.ActorCell.receiveMessage(ActorCell.scala:592)
      2020-11-24T08:18:15.0525987Z 	at akka.actor.ActorCell.invoke(ActorCell.scala:561)
      2020-11-24T08:18:15.0526783Z 	at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:258)
      2020-11-24T08:18:15.0527490Z 	at akka.dispatch.Mailbox.run(Mailbox.scala:225)
      2020-11-24T08:18:15.0528118Z 	at akka.dispatch.Mailbox.exec(Mailbox.scala:235)
      2020-11-24T08:18:15.0528660Z 	... 4 more
      2020-11-24T08:18:15.0529196Z Caused by: org.apache.flink.streaming.runtime.tasks.AsynchronousException: Unable to read channel state
      2020-11-24T08:18:15.0530090Z 	at org.apache.flink.streaming.runtime.tasks.StreamTask$StreamTaskAsyncExceptionHandler.handleAsyncException(StreamTask.java:1108)
      2020-11-24T08:18:15.0530968Z 	at org.apache.flink.streaming.runtime.tasks.StreamTask.lambda$null$0(StreamTask.java:513)
      2020-11-24T08:18:15.0531720Z 	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
      2020-11-24T08:18:15.0532423Z 	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
      2020-11-24T08:18:15.0533016Z 	at java.lang.Thread.run(Thread.java:748)
      2020-11-24T08:18:15.0535340Z Caused by: java.io.IOException: Insufficient number of network buffers: required 1, but only 0 available. The total number of network buffers is currently set to 15 of 4096 bytes each. You can increase this number by setting the configuration keys 'taskmanager.memory.network.fraction', 'taskmanager.memory.network.min', and 'taskmanager.memory.network.max'.
      2020-11-24T08:18:15.0536721Z 	at org.apache.flink.runtime.io.network.buffer.NetworkBufferPool.tryRedistributeBuffers(NetworkBufferPool.java:428)
      2020-11-24T08:18:15.0565177Z 	at org.apache.flink.runtime.io.network.buffer.NetworkBufferPool.requestMemorySegments(NetworkBufferPool.java:166)
      2020-11-24T08:18:15.0566283Z 	at org.apache.flink.runtime.io.network.buffer.NetworkBufferPool.requestMemorySegments(NetworkBufferPool.java:60)
      2020-11-24T08:18:15.0567288Z 	at org.apache.flink.runtime.io.network.partition.consumer.BufferManager.requestExclusiveBuffers(BufferManager.java:131)
      2020-11-24T08:18:15.0568367Z 	at org.apache.flink.runtime.io.network.partition.consumer.RecoveredInputChannel.requestBufferBlocking(RecoveredInputChannel.java:226)
      2020-11-24T08:18:15.0569349Z 	at org.apache.flink.runtime.checkpoint.channel.InputChannelRecoveredStateHandler.getBuffer(RecoveredChannelStateHandler.java:60)
      2020-11-24T08:18:15.0570313Z 	at org.apache.flink.runtime.checkpoint.channel.InputChannelRecoveredStateHandler.getBuffer(RecoveredChannelStateHandler.java:50)
      2020-11-24T08:18:15.0571266Z 	at org.apache.flink.runtime.checkpoint.channel.ChannelStateChunkReader.readChunk(SequentialChannelStateReaderImpl.java:147)
      2020-11-24T08:18:15.0572257Z 	at org.apache.flink.runtime.checkpoint.channel.SequentialChannelStateReaderImpl.readSequentially(SequentialChannelStateReaderImpl.java:89)
      2020-11-24T08:18:15.0573281Z 	at org.apache.flink.runtime.checkpoint.channel.SequentialChannelStateReaderImpl.read(SequentialChannelStateReaderImpl.java:78)
      2020-11-24T08:18:15.0574468Z 	at org.apache.flink.runtime.checkpoint.channel.SequentialChannelStateReaderImpl.readInputData(SequentialChannelStateReaderImpl.java:63)
      2020-11-24T08:18:15.0575364Z 	at org.apache.flink.streaming.runtime.tasks.StreamTask.lambda$null$0(StreamTask.java:511)
      2020-11-24T08:18:15.0575882Z 	... 3 more
      

      Attachments

        Issue Links

          Activity

            People

              arvid Arvid Heise
              dian.fu Dian Fu
              Votes:
              0 Vote for this issue
              Watchers:
              3 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: