[
https://issues.apache.org/jira/browse/FLINK-13484?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Gary Yao updated FLINK-13484:
-----------------------------
Fix Version/s: 1.9.1
> ConnectedComponents end-to-end test instable with NoResourceAvailableException
> ------------------------------------------------------------------------------
>
> Key: FLINK-13484
> URL: https://issues.apache.org/jira/browse/FLINK-13484
> Project: Flink
> Issue Type: Bug
> Components: Test Infrastructure
> Reporter: Tzu-Li (Gordon) Tai
> Assignee: Gary Yao
> Priority: Blocker
> Labels: pull-request-available
> Fix For: 1.9.0, 1.9.1
>
> Time Spent: 10m
> Remaining Estimate: 0h
>
> The {{ConnectedComponents iterations with high parallelism}} e2e test seems
> to fail sporadically with {{NoResourceAvailableException}}.
> https://api.travis-ci.org/v3/job/564894454/log.txt
> {code}
> 2019-07-29 18:10:37,294 INFO
> org.apache.flink.runtime.executiongraph.ExecutionGraph - Map (Map at
> main(HighParallelismIterationsTestProgram.java:50)) (9/25)
> (84f306767dabaa104d215bb429797833) switched from SCHEDULED to FAILED.
> org.apache.flink.runtime.jobmanager.scheduler.NoResourceAvailableException:
> Could not allocate enough slots to run the job. Please make sure that the
> cluster has enough resources.
> at
> org.apache.flink.runtime.executiongraph.Execution.lambda$scheduleForExecution$0(Execution.java:459)
> at
> java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:760)
> at
> java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:736)
> at
> java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:474)
> at
> java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:1977)
> at
> org.apache.flink.runtime.jobmaster.slotpool.SchedulerImpl.lambda$internalAllocateSlot$0(SchedulerImpl.java:190)
> at
> java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:760)
> at
> java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:736)
> at
> java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:474)
> at
> java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:1977)
> at
> org.apache.flink.runtime.jobmaster.slotpool.SlotSharingManager$SingleTaskSlot.release(SlotSharingManager.java:694)
> at
> org.apache.flink.runtime.jobmaster.slotpool.SlotSharingManager$MultiTaskSlot.release(SlotSharingManager.java:482)
> at
> org.apache.flink.runtime.jobmaster.slotpool.SlotSharingManager$MultiTaskSlot.lambda$new$0(SlotSharingManager.java:378)
> at
> java.util.concurrent.CompletableFuture.uniHandle(CompletableFuture.java:822)
> at
> java.util.concurrent.CompletableFuture$UniHandle.tryFire(CompletableFuture.java:797)
> at
> java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:474)
> at
> java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:1977)
> at
> org.apache.flink.runtime.concurrent.FutureUtils$Timeout.run(FutureUtils.java:943)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRunAsync(AkkaRpcActor.java:397)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:190)
> at
> org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:74)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:152)
> at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26)
> at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21)
> at scala.PartialFunction.applyOrElse(PartialFunction.scala:123)
> at scala.PartialFunction.applyOrElse$(PartialFunction.scala:122)
> at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21)
> at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
> at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172)
> at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172)
> at akka.actor.Actor.aroundReceive(Actor.scala:517)
> at akka.actor.Actor.aroundReceive$(Actor.scala:515)
> 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$WorkQueue.runTask(ForkJoinPool.java:1339)
> at akka.dispatch.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
> at
> akka.dispatch.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
> 2019-07-29 18:10:37,299 INFO
> org.apache.flink.runtime.executiongraph.failover.AdaptedRestartPipelinedRegionStrategyNG
> - Fail to pass the restart strategy validation in region failover. Fallback
> to fail global.
> 2019-07-29 18:10:37,299 INFO
> org.apache.flink.runtime.executiongraph.ExecutionGraph - Job Flink
> Java Job at Mon Jul 29 18:05:26 UTC 2019 (2fd5c4d1583d85fb81ad98ea1176f9b4)
> switched from state RUNNING to FAILING.
> org.apache.flink.runtime.jobmanager.scheduler.NoResourceAvailableException:
> Could not allocate enough slots to run the job. Please make sure that the
> cluster has enough resources.
> at
> org.apache.flink.runtime.executiongraph.Execution.lambda$scheduleForExecution$0(Execution.java:459)
> at
> java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:760)
> at
> java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:736)
> at
> java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:474)
> at
> java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:1977)
> at
> org.apache.flink.runtime.jobmaster.slotpool.SchedulerImpl.lambda$internalAllocateSlot$0(SchedulerImpl.java:190)
> at
> java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:760)
> at
> java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:736)
> at
> java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:474)
> at
> java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:1977)
> at
> org.apache.flink.runtime.jobmaster.slotpool.SlotSharingManager$SingleTaskSlot.release(SlotSharingManager.java:694)
> at
> org.apache.flink.runtime.jobmaster.slotpool.SlotSharingManager$MultiTaskSlot.release(SlotSharingManager.java:482)
> at
> org.apache.flink.runtime.jobmaster.slotpool.SlotSharingManager$MultiTaskSlot.lambda$new$0(SlotSharingManager.java:378)
> at
> java.util.concurrent.CompletableFuture.uniHandle(CompletableFuture.java:822)
> at
> java.util.concurrent.CompletableFuture$UniHandle.tryFire(CompletableFuture.java:797)
> at
> java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:474)
> at
> java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:1977)
> at
> org.apache.flink.runtime.concurrent.FutureUtils$Timeout.run(FutureUtils.java:943)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRunAsync(AkkaRpcActor.java:397)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:190)
> at
> org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:74)
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:152)
> at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26)
> at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21)
> at scala.PartialFunction.applyOrElse(PartialFunction.scala:123)
> at scala.PartialFunction.applyOrElse$(PartialFunction.scala:122)
> at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21)
> at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
> at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172)
> at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172)
> at akka.actor.Actor.aroundReceive(Actor.scala:517)
> at akka.actor.Actor.aroundReceive$(Actor.scala:515)
> 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)
> {code}
--
This message was sent by Atlassian JIRA
(v7.6.14#76016)
