[ https://issues.apache.org/jira/browse/FLINK-22180?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Chesnay Schepler closed FLINK-22180. ------------------------------------ Resolution: Fixed master: 9fd6ecf18ddb744a971f575ab11eb19b44383899 > RM reclaims slots while batch job is in progress > ------------------------------------------------ > > Key: FLINK-22180 > URL: https://issues.apache.org/jira/browse/FLINK-22180 > Project: Flink > Issue Type: Bug > Components: Runtime / Coordination > Affects Versions: 1.13.0 > Reporter: Dawid Wysakowicz > Assignee: Chesnay Schepler > Priority: Blocker > Labels: pull-request-available, test-stability > Fix For: 1.13.0 > > > https://dev.azure.com/apache-flink/apache-flink/_build/results?buildId=16271&view=logs&j=5c8e7682-d68f-54d1-16a2-a09310218a49&t=f508e270-48d6-5f1e-3138-42a17e0714f0&l=4036 > {code} > 2021-04-09T09:51:37.9803869Z [INFO] Running > org.apache.flink.test.iterative.ConnectedComponentsWithSolutionSetFirstITCase > 2021-04-09T09:51:42.3003700Z Job execution failed. > 2021-04-09T09:51:42.3125900Z > org.apache.flink.runtime.client.JobExecutionException: Job execution failed. > 2021-04-09T09:51:42.3128088Z at > org.apache.flink.runtime.jobmaster.JobResult.toJobExecutionResult(JobResult.java:144) > 2021-04-09T09:51:42.3129160Z at > org.apache.flink.runtime.minicluster.MiniClusterJobClient.lambda$getJobExecutionResult$3(MiniClusterJobClient.java:137) > 2021-04-09T09:51:42.3130010Z at > java.util.concurrent.CompletableFuture.uniApply(CompletableFuture.java:616) > 2021-04-09T09:51:42.3130773Z at > java.util.concurrent.CompletableFuture$UniApply.tryFire(CompletableFuture.java:591) > 2021-04-09T09:51:42.3131511Z at > java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488) > 2021-04-09T09:51:42.3137024Z at > java.util.concurrent.CompletableFuture.complete(CompletableFuture.java:1975) > 2021-04-09T09:51:42.3138081Z at > org.apache.flink.runtime.rpc.akka.AkkaInvocationHandler.lambda$invokeRpc$0(AkkaInvocationHandler.java:237) > 2021-04-09T09:51:42.3138945Z at > java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:774) > 2021-04-09T09:51:42.3139739Z at > java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:750) > 2021-04-09T09:51:42.3140492Z at > java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488) > 2021-04-09T09:51:42.3141212Z at > java.util.concurrent.CompletableFuture.complete(CompletableFuture.java:1975) > 2021-04-09T09:51:42.3141999Z at > org.apache.flink.runtime.concurrent.FutureUtils$1.onComplete(FutureUtils.java:1066) > 2021-04-09T09:51:42.3142892Z at > akka.dispatch.OnComplete.internal(Future.scala:264) > 2021-04-09T09:51:42.3143460Z at > akka.dispatch.OnComplete.internal(Future.scala:261) > 2021-04-09T09:51:42.3144072Z at > akka.dispatch.japi$CallbackBridge.apply(Future.scala:191) > 2021-04-09T09:51:42.3144857Z at > akka.dispatch.japi$CallbackBridge.apply(Future.scala:188) > 2021-04-09T09:51:42.3145476Z at > scala.concurrent.impl.CallbackRunnable.run(Promise.scala:36) > 2021-04-09T09:51:42.3146230Z at > org.apache.flink.runtime.concurrent.Executors$DirectExecutionContext.execute(Executors.java:73) > 2021-04-09T09:51:42.3147022Z at > scala.concurrent.impl.CallbackRunnable.executeWithValue(Promise.scala:44) > 2021-04-09T09:51:42.3147857Z at > scala.concurrent.impl.Promise$DefaultPromise.tryComplete(Promise.scala:252) > 2021-04-09T09:51:42.3148552Z at > akka.pattern.PromiseActorRef.$bang(AskSupport.scala:572) > 2021-04-09T09:51:42.3149277Z at > akka.pattern.PipeToSupport$PipeableFuture$$anonfun$pipeTo$1.applyOrElse(PipeToSupport.scala:22) > 2021-04-09T09:51:42.3150172Z at > akka.pattern.PipeToSupport$PipeableFuture$$anonfun$pipeTo$1.applyOrElse(PipeToSupport.scala:21) > 2021-04-09T09:51:42.3233576Z at > scala.concurrent.Future$$anonfun$andThen$1.apply(Future.scala:436) > 2021-04-09T09:51:42.3234583Z at > scala.concurrent.Future$$anonfun$andThen$1.apply(Future.scala:435) > 2021-04-09T09:51:42.3235304Z at > scala.concurrent.impl.CallbackRunnable.run(Promise.scala:36) > 2021-04-09T09:51:42.3236015Z at > akka.dispatch.BatchingExecutor$AbstractBatch.processBatch(BatchingExecutor.scala:55) > 2021-04-09T09:51:42.3237181Z at > akka.dispatch.BatchingExecutor$BlockableBatch$$anonfun$run$1.apply$mcV$sp(BatchingExecutor.scala:91) > 2021-04-09T09:51:42.3238165Z at > akka.dispatch.BatchingExecutor$BlockableBatch$$anonfun$run$1.apply(BatchingExecutor.scala:91) > 2021-04-09T09:51:42.3239041Z at > akka.dispatch.BatchingExecutor$BlockableBatch$$anonfun$run$1.apply(BatchingExecutor.scala:91) > 2021-04-09T09:51:42.3239798Z at > scala.concurrent.BlockContext$.withBlockContext(BlockContext.scala:72) > 2021-04-09T09:51:42.3240522Z at > akka.dispatch.BatchingExecutor$BlockableBatch.run(BatchingExecutor.scala:90) > 2021-04-09T09:51:42.3241216Z at > akka.dispatch.TaskInvocation.run(AbstractDispatcher.scala:40) > 2021-04-09T09:51:42.3241986Z at > akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(ForkJoinExecutorConfigurator.scala:44) > 2021-04-09T09:51:42.3243232Z at > akka.dispatch.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260) > 2021-04-09T09:51:42.3243930Z at > akka.dispatch.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339) > 2021-04-09T09:51:42.3244748Z at > akka.dispatch.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979) > 2021-04-09T09:51:42.3245429Z at > akka.dispatch.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107) > 2021-04-09T09:51:42.3246212Z Caused by: > org.apache.flink.runtime.JobException: Recovery is suppressed by > NoRestartBackoffTimeStrategy > 2021-04-09T09:51:42.3247118Z at > org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:138) > 2021-04-09T09:51:42.3248306Z at > org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:82) > 2021-04-09T09:51:42.3249304Z at > org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:206) > 2021-04-09T09:51:42.3250180Z at > org.apache.flink.runtime.scheduler.DefaultScheduler.maybeHandleTaskFailure(DefaultScheduler.java:196) > 2021-04-09T09:51:42.3251112Z at > org.apache.flink.runtime.scheduler.DefaultScheduler.updateTaskExecutionStateInternal(DefaultScheduler.java:187) > 2021-04-09T09:51:42.3252068Z at > org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:680) > 2021-04-09T09:51:42.3253223Z at > org.apache.flink.runtime.scheduler.UpdateSchedulerNgOnInternalFailuresListener.notifyTaskFailure(UpdateSchedulerNgOnInternalFailuresListener.java:51) > 2021-04-09T09:51:42.3254507Z at > org.apache.flink.runtime.executiongraph.DefaultExecutionGraph.notifySchedulerNgAboutInternalTaskFailure(DefaultExecutionGraph.java:1462) > 2021-04-09T09:51:42.3255444Z at > org.apache.flink.runtime.executiongraph.Execution.processFail(Execution.java:1112) > 2021-04-09T09:51:42.3256235Z at > org.apache.flink.runtime.executiongraph.Execution.processFail(Execution.java:1052) > 2021-04-09T09:51:42.3257025Z at > org.apache.flink.runtime.executiongraph.Execution.markFailed(Execution.java:883) > 2021-04-09T09:51:42.3289873Z at > org.apache.flink.runtime.executiongraph.Execution.lambda$deploy$5(Execution.java:598) > 2021-04-09T09:51:42.3290986Z at > java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:774) > 2021-04-09T09:51:42.3291964Z at > java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:750) > 2021-04-09T09:51:42.3293107Z at > java.util.concurrent.CompletableFuture$Completion.run(CompletableFuture.java:456) > 2021-04-09T09:51:42.3294152Z at > org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRunAsync(AkkaRpcActor.java:440) > 2021-04-09T09:51:42.3295130Z at > org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:208) > 2021-04-09T09:51:42.3295943Z at > org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:77) > 2021-04-09T09:51:42.3296927Z at > org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:158) > 2021-04-09T09:51:42.3297919Z at > akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26) > 2021-04-09T09:51:42.3298763Z at > akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21) > 2021-04-09T09:51:42.3299880Z at > scala.PartialFunction$class.applyOrElse(PartialFunction.scala:123) > 2021-04-09T09:51:42.3300709Z at > akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21) > 2021-04-09T09:51:42.3301554Z at > scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:170) > 2021-04-09T09:51:42.3302472Z at > scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171) > 2021-04-09T09:51:42.3303309Z at > scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171) > 2021-04-09T09:51:42.3304144Z at > akka.actor.Actor$class.aroundReceive(Actor.scala:517) > 2021-04-09T09:51:42.3304918Z at > akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:225) > 2021-04-09T09:51:42.3305541Z at > akka.actor.ActorCell.receiveMessage(ActorCell.scala:592) > 2021-04-09T09:51:42.3306224Z at > akka.actor.ActorCell.invoke(ActorCell.scala:561) > 2021-04-09T09:51:42.3306711Z at > akka.dispatch.Mailbox.processMailbox(Mailbox.scala:258) > 2021-04-09T09:51:42.3307516Z at akka.dispatch.Mailbox.run(Mailbox.scala:225) > 2021-04-09T09:51:42.3308219Z at akka.dispatch.Mailbox.exec(Mailbox.scala:235) > 2021-04-09T09:51:42.3308813Z ... 4 more > 2021-04-09T09:51:42.3309940Z Caused by: > java.util.concurrent.CompletionException: > org.apache.flink.runtime.taskexecutor.exceptions.TaskSubmissionException: No > task slot allocated for job ID eb55ab4ea4591c142078631839e1216f and > allocation ID 802cf7ad875c5d2c3220b55a32b00401. > 2021-04-09T09:51:42.3311414Z at > java.util.concurrent.CompletableFuture.encodeRelay(CompletableFuture.java:326) > 2021-04-09T09:51:42.3311964Z at > java.util.concurrent.CompletableFuture.completeRelay(CompletableFuture.java:338) > 2021-04-09T09:51:42.3312509Z at > java.util.concurrent.CompletableFuture.uniRelay(CompletableFuture.java:925) > 2021-04-09T09:51:42.3313227Z at > java.util.concurrent.CompletableFuture$UniRelay.tryFire(CompletableFuture.java:913) > 2021-04-09T09:51:42.3313894Z at > java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488) > 2021-04-09T09:51:42.3314805Z at > java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:1990) > 2021-04-09T09:51:42.3315888Z at > org.apache.flink.runtime.rpc.akka.AkkaInvocationHandler.lambda$invokeRpc$0(AkkaInvocationHandler.java:234) > 2021-04-09T09:51:42.3317047Z at > java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:774) > 2021-04-09T09:51:42.3318060Z at > java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:750) > 2021-04-09T09:51:42.3319103Z at > java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488) > 2021-04-09T09:51:42.3320125Z at > java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:1990) > 2021-04-09T09:51:42.3321082Z at > org.apache.flink.runtime.concurrent.FutureUtils$1.onComplete(FutureUtils.java:1064) > 2021-04-09T09:51:42.3321711Z at > akka.dispatch.OnComplete.internal(Future.scala:263) > 2021-04-09T09:51:42.3322067Z at > akka.dispatch.OnComplete.internal(Future.scala:261) > 2021-04-09T09:51:42.3322537Z at > akka.dispatch.japi$CallbackBridge.apply(Future.scala:191) > 2021-04-09T09:51:42.3322940Z at > akka.dispatch.japi$CallbackBridge.apply(Future.scala:188) > 2021-04-09T09:51:42.3323322Z at > scala.concurrent.impl.CallbackRunnable.run(Promise.scala:36) > 2021-04-09T09:51:42.3323789Z at > org.apache.flink.runtime.concurrent.Executors$DirectExecutionContext.execute(Executors.java:73) > 2021-04-09T09:51:42.3324269Z at > scala.concurrent.impl.CallbackRunnable.executeWithValue(Promise.scala:44) > 2021-04-09T09:51:42.3324728Z at > scala.concurrent.impl.Promise$DefaultPromise.tryComplete(Promise.scala:252) > 2021-04-09T09:51:42.3325177Z at > akka.pattern.PromiseActorRef.$bang(AskSupport.scala:572) > 2021-04-09T09:51:42.3325638Z at > akka.pattern.PipeToSupport$PipeableFuture$$anonfun$pipeTo$1.applyOrElse(PipeToSupport.scala:23) > 2021-04-09T09:51:42.3326176Z at > akka.pattern.PipeToSupport$PipeableFuture$$anonfun$pipeTo$1.applyOrElse(PipeToSupport.scala:21) > 2021-04-09T09:51:42.3326634Z at > scala.concurrent.Future$$anonfun$andThen$1.apply(Future.scala:436) > 2021-04-09T09:51:42.3327697Z at > scala.concurrent.Future$$anonfun$andThen$1.apply(Future.scala:435) > 2021-04-09T09:51:42.3328547Z at > scala.concurrent.impl.CallbackRunnable.run(Promise.scala:36) > 2021-04-09T09:51:42.3329434Z at > akka.dispatch.BatchingExecutor$AbstractBatch.processBatch(BatchingExecutor.scala:55) > 2021-04-09T09:51:42.3330625Z at > akka.dispatch.BatchingExecutor$BlockableBatch$$anonfun$run$1.apply$mcV$sp(BatchingExecutor.scala:91) > 2021-04-09T09:51:42.3331784Z at > akka.dispatch.BatchingExecutor$BlockableBatch$$anonfun$run$1.apply(BatchingExecutor.scala:91) > 2021-04-09T09:51:42.3333847Z at > akka.dispatch.BatchingExecutor$BlockableBatch$$anonfun$run$1.apply(BatchingExecutor.scala:91) > 2021-04-09T09:51:42.3334886Z at > scala.concurrent.BlockContext$.withBlockContext(BlockContext.scala:72) > 2021-04-09T09:51:42.3335978Z at > akka.dispatch.BatchingExecutor$BlockableBatch.run(BatchingExecutor.scala:90) > 2021-04-09T09:51:42.3336866Z at > akka.dispatch.TaskInvocation.run(AbstractDispatcher.scala:40) > 2021-04-09T09:51:42.3337874Z at > akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(ForkJoinExecutorConfigurator.scala:44) > 2021-04-09T09:51:42.3338622Z ... 4 more > 2021-04-09T09:51:42.3339740Z Caused by: > org.apache.flink.runtime.taskexecutor.exceptions.TaskSubmissionException: No > task slot allocated for job ID eb55ab4ea4591c142078631839e1216f and > allocation ID 802cf7ad875c5d2c3220b55a32b00401. > 2021-04-09T09:51:42.3340997Z at > org.apache.flink.runtime.taskexecutor.TaskExecutor.submitTask(TaskExecutor.java:593) > 2021-04-09T09:51:42.3341839Z at > sun.reflect.GeneratedMethodAccessor11.invoke(Unknown Source) > 2021-04-09T09:51:42.3342854Z at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > 2021-04-09T09:51:42.3343581Z at > java.lang.reflect.Method.invoke(Method.java:498) > 2021-04-09T09:51:42.3344553Z at > org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcInvocation(AkkaRpcActor.java:305) > 2021-04-09T09:51:42.3374800Z at > org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:212) > 2021-04-09T09:51:42.3375800Z at > org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:158) > 2021-04-09T09:51:42.3376525Z at > akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26) > 2021-04-09T09:51:42.3377185Z at > akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21) > 2021-04-09T09:51:42.3377950Z at > scala.PartialFunction$class.applyOrElse(PartialFunction.scala:123) > 2021-04-09T09:51:42.3378595Z at > akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21) > 2021-04-09T09:51:42.3379277Z at > scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:170) > 2021-04-09T09:51:42.3379924Z at > scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171) > 2021-04-09T09:51:42.3380572Z at > scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171) > 2021-04-09T09:51:42.3381245Z at > akka.actor.Actor$class.aroundReceive(Actor.scala:517) > 2021-04-09T09:51:42.3381877Z at > akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:225) > 2021-04-09T09:51:42.3382769Z at > akka.actor.ActorCell.receiveMessage(ActorCell.scala:592) > 2021-04-09T09:51:42.3383336Z at > akka.actor.ActorCell.invoke(ActorCell.scala:561) > 2021-04-09T09:51:42.3383880Z at > akka.dispatch.Mailbox.processMailbox(Mailbox.scala:258) > 2021-04-09T09:51:42.3384422Z at akka.dispatch.Mailbox.run(Mailbox.scala:225) > 2021-04-09T09:51:42.3384921Z at akka.dispatch.Mailbox.exec(Mailbox.scala:235) > 2021-04-09T09:51:42.3385319Z ... 4 more > {code} -- This message was sent by Atlassian Jira (v8.3.4#803005)