[ https://issues.apache.org/jira/browse/FLINK-23955?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Konstantin Knauf updated FLINK-23955: ------------------------------------- Fix Version/s: (was: 1.14.4) > submit flink sql job error when flink HA on yarn is configured > -------------------------------------------------------------- > > Key: FLINK-23955 > URL: https://issues.apache.org/jira/browse/FLINK-23955 > Project: Flink > Issue Type: Bug > Components: Table SQL / Client > Affects Versions: 1.13.0 > Reporter: Jun Zhang > Priority: Major > Fix For: 1.15.0, 1.14.5 > > > 1.when I configured the flink HA ,like this > {code:java} > high-availability: zookeeper > high-availability.storageDir: hdfs://xxx/flink/ha/ > high-availability.zookeeper.quorum: xxxxx:2181 > high-availability.zookeeper.path.root: /flink > {code} > 2. I start a flink session cluster > 3. I submit a flink sql job by flink sql client and set the > {code:java} > set execution.target = yarn-per-job; > {code} > then I get the error > > > {code:java} > 2021-08-25 10:40:39,500 INFO org.apache.flink.yarn.YarnClusterDescriptor > [] - Found Web Interface master3:38052 of application > 'application_1629858010528_0002'. > 2021-08-25 10:40:42,447 WARN > org.apache.flink.streaming.api.operators.collect.CollectResultFetcher [] - An > exception occurred when fetching query results > java.util.concurrent.ExecutionException: > org.apache.flink.runtime.rest.util.RestClientException: [Internal server > error., <Exception on server side: > org.apache.flink.runtime.messages.FlinkJobNotFoundException: Could not find > Flink job (2cc726b9ae70c95f128f6c1e55cf874c) > at > org.apache.flink.runtime.dispatcher.Dispatcher.getJobMasterGateway(Dispatcher.java:878) > at > org.apache.flink.runtime.dispatcher.Dispatcher.performOperationOnJobMasterGateway(Dispatcher.java:892) > at > org.apache.flink.runtime.dispatcher.Dispatcher.deliverCoordinationRequestToCoordinator(Dispatcher.java:712) > at sun.reflect.GeneratedMethodAccessor14.invoke(Unknown Source) > at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > at java.lang.reflect.Method.invoke(Method.java:498) > at > org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcInvocation(AkkaRpcActor.java:305) > at > org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:212) > at > org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:77) > at > org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:158) > 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)End > of exception on server side>] > at > java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:357) > ~[?:1.8.0_291] > at > java.util.concurrent.CompletableFuture.get(CompletableFuture.java:1908) > ~[?:1.8.0_291] > at > org.apache.flink.streaming.api.operators.collect.CollectResultFetcher.sendRequest(CollectResultFetcher.java:163) > ~[flink-dist_2.12-1.13.0.jar:1.13.0] > at > org.apache.flink.streaming.api.operators.collect.CollectResultFetcher.next(CollectResultFetcher.java:128) > ~[flink-dist_2.12-1.13.0.jar:1.13.0] > at > org.apache.flink.streaming.api.operators.collect.CollectResultIterator.nextResultFromFetcher(CollectResultIterator.java:106) > ~[flink-dist_2.12-1.13.0.jar:1.13.0] > at > org.apache.flink.streaming.api.operators.collect.CollectResultIterator.hasNext(CollectResultIterator.java:80) > ~[flink-dist_2.12-1.13.0.jar:1.13.0] > at > org.apache.iceberg.relocated.com.google.common.collect.Iterators.addAll(Iterators.java:355) > ~[iceberg-flink-runtime-77ea34e.dirty.jar:?] > at > org.apache.iceberg.relocated.com.google.common.collect.Lists.newArrayList(Lists.java:143) > ~[iceberg-flink-runtime-77ea34e.dirty.jar:?] > at > org.apache.iceberg.flink.source.RowDataRewriter.rewriteDataForTasks(RowDataRewriter.java:91) > ~[iceberg-flink-runtime-77ea34e.dirty.jar:?] > at > org.apache.iceberg.flink.actions.RewriteDataFilesAction.rewriteDataForTasks(RewriteDataFilesAction.java:56) > ~[iceberg-flink-runtime-77ea34e.dirty.jar:?] > at > org.apache.iceberg.actions.BaseRewriteDataFilesAction.execute(BaseRewriteDataFilesAction.java:240) > ~[iceberg-flink-runtime-77ea34e.dirty.jar:?] > at flink.test.RewriteTable.main(RewriteTable.java:52) > ~[iceberg-projects-1.0-SNAPSHOT.jar:?] > at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) > ~[?:1.8.0_291] > at > sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) > ~[?:1.8.0_291] > at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > ~[?:1.8.0_291] > at java.lang.reflect.Method.invoke(Method.java:498) ~[?:1.8.0_291] > at > org.apache.flink.client.program.PackagedProgram.callMainMethod(PackagedProgram.java:355) > ~[flink-clients_2.12-1.13.0.jar:1.13.0] > at > org.apache.flink.client.program.PackagedProgram.invokeInteractiveModeForExecution(PackagedProgram.java:222) > ~[flink-clients_2.12-1.13.0.jar:1.13.0] > at > org.apache.flink.client.ClientUtils.executeProgram(ClientUtils.java:114) > ~[flink-clients_2.12-1.13.0.jar:1.13.0] > at > org.apache.flink.client.cli.CliFrontend.executeProgram(CliFrontend.java:812) > ~[flink-clients_2.12-1.13.0.jar:1.13.0] > at org.apache.flink.client.cli.CliFrontend.run(CliFrontend.java:246) > ~[flink-clients_2.12-1.13.0.jar:1.13.0] > at > org.apache.flink.client.cli.CliFrontend.parseAndRun(CliFrontend.java:1054) > ~[flink-clients_2.12-1.13.0.jar:1.13.0] > at > org.apache.flink.client.cli.CliFrontend.lambda$main$10(CliFrontend.java:1132) > ~[flink-clients_2.12-1.13.0.jar:1.13.0] > at java.security.AccessController.doPrivileged(Native Method) > ~[?:1.8.0_291] > at javax.security.auth.Subject.doAs(Subject.java:422) [?:1.8.0_291] > at > org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1836) > [flink-shaded-hadoop2-uber-2.8.3-1.8.3.jar:2.8.3-1.8.3] > at > org.apache.flink.runtime.security.contexts.HadoopSecurityContext.runSecured(HadoopSecurityContext.java:41) > [flink-dist_2.12-1.13.0.jar:1.13.0] > at > org.apache.flink.client.cli.CliFrontend.main(CliFrontend.java:1132) > [flink-clients_2.12-1.13.0.jar:1.13.0] > Caused by: org.apache.flink.runtime.rest.util.RestClientException: [Internal > server error., <Exception on server side: > org.apache.flink.runtime.messages.FlinkJobNotFoundException: Could not find > Flink job (2cc726b9ae70c95f128f6c1e55cf874c) > at > org.apache.flink.runtime.dispatcher.Dispatcher.getJobMasterGateway(Dispatcher.java:878) > at > org.apache.flink.runtime.dispatcher.Dispatcher.performOperationOnJobMasterGateway(Dispatcher.java:892) > at > org.apache.flink.runtime.dispatcher.Dispatcher.deliverCoordinationRequestToCoordinator(Dispatcher.java:712) > at sun.reflect.GeneratedMethodAccessor14.invoke(Unknown Source) > at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > at java.lang.reflect.Method.invoke(Method.java:498) > at > org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcInvocation(AkkaRpcActor.java:305) > at > org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:212) > at > org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:77) > at > org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:158) > 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 (v8.20.1#820001)