[
https://issues.apache.org/jira/browse/FLINK-19141?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17191044#comment-17191044
]
Yunhui commented on FLINK-19141:
--------------------------------
Thanks for your suggestion [~ShawnHx] . But it works for flink-1.10.1
> Flink Job Submitted on Yarn Does not Work
> -----------------------------------------
>
> Key: FLINK-19141
> URL: https://issues.apache.org/jira/browse/FLINK-19141
> Project: Flink
> Issue Type: Bug
> Components: Client / Job Submission
> Affects Versions: 1.11.1
> Reporter: Yunhui
> Priority: Major
>
> I first launch a cluster on yarn.
> {code:java}
> $flink_path/bin/yarn-session.sh \
> -qu dev \
> -d -nm flink_cluster_1.11 \
> -jm 8192 \
> -tm 12288 \
> -s 2 \
> -D taskmanager.memory.framework.off-heap.size=2048m \
> -D taskmanager.memory.managed.size=0{code}
> Then I submit my job with the following command
> {code:java}
> $flink_path/bin/flink run \
> -d -m $host_port \
> -c MyMainClass \
> my-jar.jar{code}
> It take a long time to schedule. And it ended with the following Exception.
> But it works for flink-1.10.1
> {code:java}
> org.apache.flink.runtime.jobmanager.scheduler.NoResourceAvailableException:
> Could not allocate the required slot within slot request timeout. Please make
> sure that the cluster has enough resources. at
> org.apache.flink.runtime.scheduler.DefaultScheduler.maybeWrapWithNoResourceAvailableException(DefaultScheduler.java:441)
> ~[flink-dist_2.11-1.11.1.jar:1.11.1] at
> org.apache.flink.runtime.scheduler.DefaultScheduler.lambda$assignResourceOrHandleError$6(DefaultScheduler.java:422)
> ~[flink-dist_2.11-1.11.1.jar:1.11.1] at
> java.util.concurrent.CompletableFuture.uniHandle(CompletableFuture.java:822)
> ~[?:1.8.0_77] at
> java.util.concurrent.CompletableFuture$UniHandle.tryFire(CompletableFuture.java:797)
> ~[?:1.8.0_77] at
> java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:474)
> ~[?:1.8.0_77] at
> java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:1977)
> ~[?:1.8.0_77] at
> org.apache.flink.runtime.jobmaster.slotpool.SchedulerImpl.lambda$internalAllocateSlot$0(SchedulerImpl.java:168)
> ~[flink-dist_2.11-1.11.1.jar:1.11.1] at
> java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:760)
> ~[?:1.8.0_77] at
> java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:736)
> ~[?:1.8.0_77] at
> java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:474)
> ~[?:1.8.0_77] at
> java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:1977)
> ~[?:1.8.0_77] at
> org.apache.flink.runtime.jobmaster.slotpool.SlotSharingManager$SingleTaskSlot.release(SlotSharingManager.java:726)
> ~[flink-dist_2.11-1.11.1.jar:1.11.1] at
> org.apache.flink.runtime.jobmaster.slotpool.SlotSharingManager$MultiTaskSlot.release(SlotSharingManager.java:537)
> ~[flink-dist_2.11-1.11.1.jar:1.11.1] at
> org.apache.flink.runtime.jobmaster.slotpool.SlotSharingManager$MultiTaskSlot.lambda$new$0(SlotSharingManager.java:432)
> ~[flink-dist_2.11-1.11.1.jar:1.11.1] at
> java.util.concurrent.CompletableFuture.uniHandle(CompletableFuture.java:822)
> ~[?:1.8.0_77] at
> java.util.concurrent.CompletableFuture$UniHandle.tryFire(CompletableFuture.java:797)
> ~[?:1.8.0_77] at
> java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:474)
> ~[?:1.8.0_77] at
> java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:1977)
> ~[?:1.8.0_77] at
> org.apache.flink.runtime.concurrent.FutureUtils.lambda$forwardTo$21(FutureUtils.java:1120)
> ~[flink-dist_2.11-1.11.1.jar:1.11.1] at
> java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:760)
> ~[?:1.8.0_77] at
> java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:736)
> ~[?:1.8.0_77] at
> java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:474)
> ~[?:1.8.0_77] at
> java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:1977)
> ~[?:1.8.0_77] at
> org.apache.flink.runtime.concurrent.FutureUtils$Timeout.run(FutureUtils.java:1036)
> ~[flink-dist_2.11-1.11.1.jar:1.11.1] at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRunAsync(AkkaRpcActor.java:402)
> ~[flink-dist_2.11-1.11.1.jar:1.11.1] at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:195)
> ~[flink-dist_2.11-1.11.1.jar:1.11.1] at
> org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:74)
> ~[flink-dist_2.11-1.11.1.jar:1.11.1] at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:152)
> ~[flink-dist_2.11-1.11.1.jar:1.11.1] at
> akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26)
> [flink-dist_2.11-1.11.1.jar:1.11.1] at
> akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21)
> [flink-dist_2.11-1.11.1.jar:1.11.1] at
> scala.PartialFunction$class.applyOrElse(PartialFunction.scala:123)
> [flink-dist_2.11-1.11.1.jar:1.11.1] at
> akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21)
> [flink-dist_2.11-1.11.1.jar:1.11.1] at
> scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:170)
> [flink-dist_2.11-1.11.1.jar:1.11.1] at
> scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
> [flink-dist_2.11-1.11.1.jar:1.11.1] at
> scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
> [flink-dist_2.11-1.11.1.jar:1.11.1] at
> akka.actor.Actor$class.aroundReceive(Actor.scala:517)
> [flink-dist_2.11-1.11.1.jar:1.11.1] at
> akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:225)
> [flink-dist_2.11-1.11.1.jar:1.11.1] at
> akka.actor.ActorCell.receiveMessage(ActorCell.scala:592)
> [flink-dist_2.11-1.11.1.jar:1.11.1] at
> akka.actor.ActorCell.invoke(ActorCell.scala:561)
> [flink-dist_2.11-1.11.1.jar:1.11.1] at
> akka.dispatch.Mailbox.processMailbox(Mailbox.scala:258)
> [flink-dist_2.11-1.11.1.jar:1.11.1] at
> akka.dispatch.Mailbox.run(Mailbox.scala:225)
> [flink-dist_2.11-1.11.1.jar:1.11.1] at
> akka.dispatch.Mailbox.exec(Mailbox.scala:235)
> [flink-dist_2.11-1.11.1.jar:1.11.1] at
> akka.dispatch.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
> [flink-dist_2.11-1.11.1.jar:1.11.1] at
> akka.dispatch.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
> [flink-dist_2.11-1.11.1.jar:1.11.1] at
> akka.dispatch.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
> [flink-dist_2.11-1.11.1.jar:1.11.1] at
> akka.dispatch.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
> [flink-dist_2.11-1.11.1.jar:1.11.1]Caused by:
> java.util.concurrent.CompletionException:
> java.util.concurrent.TimeoutException at
> java.util.concurrent.CompletableFuture.encodeThrowable(CompletableFuture.java:292)
> ~[?:1.8.0_77] at
> java.util.concurrent.CompletableFuture.completeThrowable(CompletableFuture.java:308)
> ~[?:1.8.0_77] at
> java.util.concurrent.CompletableFuture.uniApply(CompletableFuture.java:593)
> ~[?:1.8.0_77] at
> java.util.concurrent.CompletableFuture$UniApply.tryFire(CompletableFuture.java:577)
> ~[?:1.8.0_77] ... 25 moreCaused by: java.util.concurrent.TimeoutException
> ... 23 more
> {code}
>
--
This message was sent by Atlassian Jira
(v8.3.4#803005)