Huang Xingbo created FLINK-27791: ------------------------------------ Summary: SlotCountExceedingParallelismTest tests failed with NoResourceAvailableException Key: FLINK-27791 URL: https://issues.apache.org/jira/browse/FLINK-27791 Project: Flink Issue Type: Bug Components: Runtime / Coordination Affects Versions: 1.16.0 Reporter: Huang Xingbo
{code:java} 2022-05-25T12:16:09.2562348Z May 25 12:16:09 org.apache.flink.runtime.client.JobExecutionException: Job execution failed. 2022-05-25T12:16:09.2563741Z May 25 12:16:09 at org.apache.flink.runtime.jobmaster.JobResult.toJobExecutionResult(JobResult.java:144) 2022-05-25T12:16:09.2565457Z May 25 12:16:09 at org.apache.flink.runtime.minicluster.MiniCluster.executeJobBlocking(MiniCluster.java:982) 2022-05-25T12:16:09.2567245Z May 25 12:16:09 at org.apache.flink.runtime.jobmanager.SlotCountExceedingParallelismTest.submitJobGraphAndWait(SlotCountExceedingParallelismTest.java:101) 2022-05-25T12:16:09.2569329Z May 25 12:16:09 at org.apache.flink.runtime.jobmanager.SlotCountExceedingParallelismTest.testNoSlotSharingAndBlockingResultBoth(SlotCountExceedingParallelismTest.java:94) 2022-05-25T12:16:09.2571889Z May 25 12:16:09 at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) 2022-05-25T12:16:09.2573109Z May 25 12:16:09 at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) 2022-05-25T12:16:09.2574528Z May 25 12:16:09 at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) 2022-05-25T12:16:09.2575657Z May 25 12:16:09 at java.lang.reflect.Method.invoke(Method.java:498) 2022-05-25T12:16:09.2581380Z May 25 12:16:09 at org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:59) 2022-05-25T12:16:09.2582747Z May 25 12:16:09 at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12) 2022-05-25T12:16:09.2583600Z May 25 12:16:09 at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:56) 2022-05-25T12:16:09.2584455Z May 25 12:16:09 at org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17) 2022-05-25T12:16:09.2585172Z May 25 12:16:09 at org.apache.flink.util.TestNameProvider$1.evaluate(TestNameProvider.java:45) 2022-05-25T12:16:09.2585792Z May 25 12:16:09 at org.junit.rules.TestWatcher$1.evaluate(TestWatcher.java:61) 2022-05-25T12:16:09.2586376Z May 25 12:16:09 at org.junit.runners.ParentRunner$3.evaluate(ParentRunner.java:306) 2022-05-25T12:16:09.2587035Z May 25 12:16:09 at org.junit.runners.BlockJUnit4ClassRunner$1.evaluate(BlockJUnit4ClassRunner.java:100) 2022-05-25T12:16:09.2587682Z May 25 12:16:09 at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:366) 2022-05-25T12:16:09.2588589Z May 25 12:16:09 at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:103) 2022-05-25T12:16:09.2589623Z May 25 12:16:09 at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:63) 2022-05-25T12:16:09.2590262Z May 25 12:16:09 at org.junit.runners.ParentRunner$4.run(ParentRunner.java:331) 2022-05-25T12:16:09.2590856Z May 25 12:16:09 at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:79) 2022-05-25T12:16:09.2591453Z May 25 12:16:09 at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:329) 2022-05-25T12:16:09.2592063Z May 25 12:16:09 at org.junit.runners.ParentRunner.access$100(ParentRunner.java:66) 2022-05-25T12:16:09.2592673Z May 25 12:16:09 at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:293) 2022-05-25T12:16:09.2593288Z May 25 12:16:09 at org.junit.rules.ExternalResource$1.evaluate(ExternalResource.java:54) 2022-05-25T12:16:09.2595864Z May 25 12:16:09 at org.junit.rules.RunRules.evaluate(RunRules.java:20) 2022-05-25T12:16:09.2596521Z May 25 12:16:09 at org.junit.runners.ParentRunner$3.evaluate(ParentRunner.java:306) 2022-05-25T12:16:09.2597144Z May 25 12:16:09 at org.junit.runners.ParentRunner.run(ParentRunner.java:413) 2022-05-25T12:16:09.2597703Z May 25 12:16:09 at org.junit.runner.JUnitCore.run(JUnitCore.java:137) 2022-05-25T12:16:09.2598247Z May 25 12:16:09 at org.junit.runner.JUnitCore.run(JUnitCore.java:115) 2022-05-25T12:16:09.2599004Z May 25 12:16:09 at org.junit.vintage.engine.execution.RunnerExecutor.execute(RunnerExecutor.java:42) 2022-05-25T12:16:09.2599696Z May 25 12:16:09 at org.junit.vintage.engine.VintageTestEngine.executeAllChildren(VintageTestEngine.java:80) 2022-05-25T12:16:09.2600397Z May 25 12:16:09 at org.junit.vintage.engine.VintageTestEngine.execute(VintageTestEngine.java:72) 2022-05-25T12:16:09.2601282Z May 25 12:16:09 at org.junit.platform.launcher.core.EngineExecutionOrchestrator.execute(EngineExecutionOrchestrator.java:107) 2022-05-25T12:16:09.2602529Z May 25 12:16:09 at org.junit.platform.launcher.core.EngineExecutionOrchestrator.execute(EngineExecutionOrchestrator.java:88) 2022-05-25T12:16:09.2603747Z May 25 12:16:09 at org.junit.platform.launcher.core.EngineExecutionOrchestrator.lambda$execute$0(EngineExecutionOrchestrator.java:54) 2022-05-25T12:16:09.2604776Z May 25 12:16:09 at org.junit.platform.launcher.core.EngineExecutionOrchestrator.withInterceptedStreams(EngineExecutionOrchestrator.java:67) 2022-05-25T12:16:09.2605611Z May 25 12:16:09 at org.junit.platform.launcher.core.EngineExecutionOrchestrator.execute(EngineExecutionOrchestrator.java:52) 2022-05-25T12:16:09.2606370Z May 25 12:16:09 at org.junit.platform.launcher.core.DefaultLauncher.execute(DefaultLauncher.java:114) 2022-05-25T12:16:09.2607054Z May 25 12:16:09 at org.junit.platform.launcher.core.DefaultLauncher.execute(DefaultLauncher.java:86) 2022-05-25T12:16:09.2607796Z May 25 12:16:09 at org.junit.platform.launcher.core.DefaultLauncherSession$DelegatingLauncher.execute(DefaultLauncherSession.java:86) 2022-05-25T12:16:09.2608922Z May 25 12:16:09 at org.junit.platform.launcher.core.SessionPerRequestLauncher.execute(SessionPerRequestLauncher.java:53) 2022-05-25T12:16:09.2609723Z May 25 12:16:09 at org.apache.maven.surefire.junitplatform.JUnitPlatformProvider.lambda$execute$1(JUnitPlatformProvider.java:199) 2022-05-25T12:16:09.2610414Z May 25 12:16:09 at java.util.Iterator.forEachRemaining(Iterator.java:116) 2022-05-25T12:16:09.2611062Z May 25 12:16:09 at org.apache.maven.surefire.junitplatform.JUnitPlatformProvider.execute(JUnitPlatformProvider.java:193) 2022-05-25T12:16:09.2611845Z May 25 12:16:09 at org.apache.maven.surefire.junitplatform.JUnitPlatformProvider.invokeAllTests(JUnitPlatformProvider.java:154) 2022-05-25T12:16:09.2612633Z May 25 12:16:09 at org.apache.maven.surefire.junitplatform.JUnitPlatformProvider.invoke(JUnitPlatformProvider.java:120) 2022-05-25T12:16:09.2613364Z May 25 12:16:09 at org.apache.maven.surefire.booter.ForkedBooter.runSuitesInProcess(ForkedBooter.java:428) 2022-05-25T12:16:09.2614471Z May 25 12:16:09 at org.apache.maven.surefire.booter.ForkedBooter.execute(ForkedBooter.java:162) 2022-05-25T12:16:09.2615277Z May 25 12:16:09 at org.apache.maven.surefire.booter.ForkedBooter.run(ForkedBooter.java:562) 2022-05-25T12:16:09.2615920Z May 25 12:16:09 at org.apache.maven.surefire.booter.ForkedBooter.main(ForkedBooter.java:548) 2022-05-25T12:16:09.2616568Z May 25 12:16:09 Caused by: org.apache.flink.runtime.JobException: Recovery is suppressed by NoRestartBackoffTimeStrategy 2022-05-25T12:16:09.2617347Z May 25 12:16:09 at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:138) 2022-05-25T12:16:09.2618418Z May 25 12:16:09 at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:82) 2022-05-25T12:16:09.2619771Z May 25 12:16:09 at org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:300) 2022-05-25T12:16:09.2620681Z May 25 12:16:09 at org.apache.flink.runtime.scheduler.DefaultScheduler.maybeHandleTaskFailure(DefaultScheduler.java:290) 2022-05-25T12:16:09.2621485Z May 25 12:16:09 at org.apache.flink.runtime.scheduler.DefaultScheduler.updateTaskExecutionStateInternal(DefaultScheduler.java:281) 2022-05-25T12:16:09.2622270Z May 25 12:16:09 at org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:716) 2022-05-25T12:16:09.2623125Z May 25 12:16:09 at org.apache.flink.runtime.scheduler.UpdateSchedulerNgOnInternalFailuresListener.notifyTaskFailure(UpdateSchedulerNgOnInternalFailuresListener.java:51) 2022-05-25T12:16:09.2624085Z May 25 12:16:09 at org.apache.flink.runtime.executiongraph.DefaultExecutionGraph.notifySchedulerNgAboutInternalTaskFailure(DefaultExecutionGraph.java:1546) 2022-05-25T12:16:09.2625042Z May 25 12:16:09 at org.apache.flink.runtime.executiongraph.Execution.processFail(Execution.java:1113) 2022-05-25T12:16:09.2625741Z May 25 12:16:09 at org.apache.flink.runtime.executiongraph.Execution.processFail(Execution.java:1053) 2022-05-25T12:16:09.2626437Z May 25 12:16:09 at org.apache.flink.runtime.executiongraph.Execution.markFailed(Execution.java:892) 2022-05-25T12:16:09.2627140Z May 25 12:16:09 at org.apache.flink.runtime.executiongraph.ExecutionVertex.markFailed(ExecutionVertex.java:463) 2022-05-25T12:16:09.2627931Z May 25 12:16:09 at org.apache.flink.runtime.scheduler.DefaultExecutionVertexOperations.markFailed(DefaultExecutionVertexOperations.java:42) 2022-05-25T12:16:09.2628817Z May 25 12:16:09 at org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskDeploymentFailure(DefaultScheduler.java:617) 2022-05-25T12:16:09.2629669Z May 25 12:16:09 at org.apache.flink.runtime.scheduler.DefaultScheduler.lambda$assignAllResourcesAndRegisterProducedPartitions$6(DefaultScheduler.java:493) 2022-05-25T12:16:09.2630461Z May 25 12:16:09 at java.util.concurrent.CompletableFuture.uniHandle(CompletableFuture.java:836) 2022-05-25T12:16:09.2631135Z May 25 12:16:09 at java.util.concurrent.CompletableFuture$UniHandle.tryFire(CompletableFuture.java:811) 2022-05-25T12:16:09.2631823Z May 25 12:16:09 at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488) 2022-05-25T12:16:09.2632521Z May 25 12:16:09 at java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:1990) 2022-05-25T12:16:09.2633238Z May 25 12:16:09 at org.apache.flink.runtime.scheduler.SharedSlot.cancelLogicalSlotRequest(SharedSlot.java:222) 2022-05-25T12:16:09.2634066Z May 25 12:16:09 at org.apache.flink.runtime.scheduler.SlotSharingExecutionSlotAllocator.cancelLogicalSlotRequest(SlotSharingExecutionSlotAllocator.java:164) 2022-05-25T12:16:09.2635023Z May 25 12:16:09 at org.apache.flink.runtime.scheduler.SharingPhysicalSlotRequestBulk.cancel(SharingPhysicalSlotRequestBulk.java:86) 2022-05-25T12:16:09.2635897Z May 25 12:16:09 at org.apache.flink.runtime.jobmaster.slotpool.PhysicalSlotRequestBulkWithTimestamp.cancel(PhysicalSlotRequestBulkWithTimestamp.java:66) 2022-05-25T12:16:09.2637677Z May 25 12:16:09 at org.apache.flink.runtime.jobmaster.slotpool.PhysicalSlotRequestBulkCheckerImpl.lambda$schedulePendingRequestBulkWithTimestampCheck$0(PhysicalSlotRequestBulkCheckerImpl.java:91) 2022-05-25T12:16:09.2639068Z May 25 12:16:09 at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:511) 2022-05-25T12:16:09.2639679Z May 25 12:16:09 at java.util.concurrent.FutureTask.run(FutureTask.java:266) 2022-05-25T12:16:09.2640340Z May 25 12:16:09 at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.lambda$handleRunAsync$4(AkkaRpcActor.java:443) 2022-05-25T12:16:09.2641124Z May 25 12:16:09 at org.apache.flink.runtime.concurrent.akka.ClassLoadingUtils.runWithContextClassLoader(ClassLoadingUtils.java:68) 2022-05-25T12:16:09.2641888Z May 25 12:16:09 at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRunAsync(AkkaRpcActor.java:443) 2022-05-25T12:16:09.2642593Z May 25 12:16:09 at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:213) 2022-05-25T12:16:09.2643320Z May 25 12:16:09 at org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:78) 2022-05-25T12:16:09.2644048Z May 25 12:16:09 at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:163) 2022-05-25T12:16:09.2644951Z May 25 12:16:09 at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:24) 2022-05-25T12:16:09.2645549Z May 25 12:16:09 at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:20) 2022-05-25T12:16:09.2646138Z May 25 12:16:09 at scala.PartialFunction.applyOrElse(PartialFunction.scala:123) 2022-05-25T12:16:09.2646729Z May 25 12:16:09 at scala.PartialFunction.applyOrElse$(PartialFunction.scala:122) 2022-05-25T12:16:09.2647315Z May 25 12:16:09 at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:20) 2022-05-25T12:16:09.2647930Z May 25 12:16:09 at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171) 2022-05-25T12:16:09.2648543Z May 25 12:16:09 at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172) 2022-05-25T12:16:09.2649259Z May 25 12:16:09 at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172) 2022-05-25T12:16:09.2649838Z May 25 12:16:09 at akka.actor.Actor.aroundReceive(Actor.scala:537) 2022-05-25T12:16:09.2650370Z May 25 12:16:09 at akka.actor.Actor.aroundReceive$(Actor.scala:535) 2022-05-25T12:16:09.2650923Z May 25 12:16:09 at akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:220) 2022-05-25T12:16:09.2651505Z May 25 12:16:09 at akka.actor.ActorCell.receiveMessage(ActorCell.scala:580) 2022-05-25T12:16:09.2652066Z May 25 12:16:09 at akka.actor.ActorCell.invoke(ActorCell.scala:548) 2022-05-25T12:16:09.2652617Z May 25 12:16:09 at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:270) 2022-05-25T12:16:09.2653167Z May 25 12:16:09 at akka.dispatch.Mailbox.run(Mailbox.scala:231) 2022-05-25T12:16:09.2653680Z May 25 12:16:09 at akka.dispatch.Mailbox.exec(Mailbox.scala:243) 2022-05-25T12:16:09.2654223Z May 25 12:16:09 at java.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:289) 2022-05-25T12:16:09.2655018Z May 25 12:16:09 at java.util.concurrent.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1056) 2022-05-25T12:16:09.2655657Z May 25 12:16:09 at java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1692) 2022-05-25T12:16:09.2656290Z May 25 12:16:09 at java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:175) 2022-05-25T12:16:09.2657251Z May 25 12:16:09 Caused by: java.util.concurrent.CompletionException: java.util.concurrent.CompletionException: org.apache.flink.runtime.jobmanager.scheduler.NoResourceAvailableException: Slot request bulk is not fulfillable! Could not allocate the required slot within slot request timeout 2022-05-25T12:16:09.2658276Z May 25 12:16:09 at org.apache.flink.runtime.scheduler.DefaultScheduler.lambda$assignResource$8(DefaultScheduler.java:551) 2022-05-25T12:16:09.2658918Z May 25 12:16:09 ... 37 more 2022-05-25T12:16:09.2659648Z May 25 12:16:09 Caused by: java.util.concurrent.CompletionException: org.apache.flink.runtime.jobmanager.scheduler.NoResourceAvailableException: Slot request bulk is not fulfillable! Could not allocate the required slot within slot request timeout 2022-05-25T12:16:09.2660734Z May 25 12:16:09 at java.util.concurrent.CompletableFuture.encodeThrowable(CompletableFuture.java:292) 2022-05-25T12:16:09.2661412Z May 25 12:16:09 at java.util.concurrent.CompletableFuture.completeThrowable(CompletableFuture.java:308) 2022-05-25T12:16:09.2662091Z May 25 12:16:09 at java.util.concurrent.CompletableFuture.uniApply(CompletableFuture.java:607) 2022-05-25T12:16:09.2662756Z May 25 12:16:09 at java.util.concurrent.CompletableFuture$UniApply.tryFire(CompletableFuture.java:591) 2022-05-25T12:16:09.2663267Z May 25 12:16:09 ... 35 more 2022-05-25T12:16:09.2663902Z May 25 12:16:09 Caused by: org.apache.flink.runtime.jobmanager.scheduler.NoResourceAvailableException: Slot request bulk is not fulfillable! Could not allocate the required slot within slot request timeout 2022-05-25T12:16:09.2665137Z May 25 12:16:09 at org.apache.flink.runtime.jobmaster.slotpool.PhysicalSlotRequestBulkCheckerImpl.lambda$schedulePendingRequestBulkWithTimestampCheck$0(PhysicalSlotRequestBulkCheckerImpl.java:86) 2022-05-25T12:16:09.2665881Z May 25 12:16:09 ... 28 more 2022-05-25T12:16:09.2666328Z May 25 12:16:09 Caused by: java.util.concurrent.TimeoutException: Timeout has occurred: 300000 ms 2022-05-25T12:16:09.2666794Z May 25 12:16:09 ... 29 more {code} https://dev.azure.com/apache-flink/apache-flink/_build/results?buildId=36053&view=logs&j=0da23115-68bb-5dcd-192c-bd4c8adebde1&t=24c3384f-1bcb-57b3-224f-51bf973bbee8 -- This message was sent by Atlassian Jira (v8.20.7#820007)