各位好:

    Flink1.10.0版本发现偶发任务失败后但是web ui仍然挂着该任务并没有停止,日志如下:

    请问有遇到一样的情况的嘛

[INFO] 2020-07-28 16:34:00.938  - [taskAppId=TASK-38-97-193]:[106] -  -> 
2020-07-28 16:33:52,863 INFO  org.apache.flink.yarn.YarnClusterDescriptor       
            - Submitting application master application_1571540269403_52656

2020-07-28 16:33:52,895 INFO  
org.apache.hadoop.yarn.client.api.impl.YarnClientImpl         - Submitted 
application application_1571540269403_52656

2020-07-28 16:33:52,895 INFO  org.apache.flink.yarn.YarnClusterDescriptor       
            - Waiting for the cluster to be allocated

2020-07-28 16:33:52,897 INFO  org.apache.flink.yarn.YarnClusterDescriptor       
            - Deploying cluster, current state ACCEPTED

2020-07-28 16:34:00,938 INFO  org.apache.flink.yarn.YarnClusterDescriptor       
            - YARN application has been deployed successfully.

[INFO] 2020-07-28 16:36:04.622  - [taskAppId=TASK-38-97-193]:[106] -  -> 
2020-07-28 16:34:00,941 INFO  org.apache.flink.yarn.YarnClusterDescriptor       
            - Found Web Interface nb-bdh-hadoop.slave14:21913 of application 
'application_1571540269403_52656'.

Job has been submitted with JobID 54ac0f3db08f29022d9f3d51d797a724

[INFO] 2020-07-28 16:36:04.623  - [taskAppId=TASK-38-97-193]:[106] -  -> 
------------------------------------------------------------

The program finished with the following exception:

org.apache.flink.client.program.ProgramInvocationException: The main method 
caused an error: 
org.apache.flink.runtime.concurrent.FutureUtils$RetryException: Could not 
complete the operation. Number of retries has been exhausted.

at 
org.apache.flink.client.program.PackagedProgram.callMainMethod(PackagedProgram.java:335)

at 
org.apache.flink.client.program.PackagedProgram.invokeInteractiveModeForExecution(PackagedProgram.java:205)

at org.apache.flink.client.ClientUtils.executeProgram(ClientUtils.java:138)

at org.apache.flink.client.cli.CliFrontend.executeProgram(CliFrontend.java:664)

at org.apache.flink.client.cli.CliFrontend.run(CliFrontend.java:213)

at org.apache.flink.client.cli.CliFrontend.parseParameters(CliFrontend.java:895)

at org.apache.flink.client.cli.CliFrontend.lambda$main$10(CliFrontend.java:968)

at java.security.AccessController.doPrivileged(Native Method)

at javax.security.auth.Subject.doAs(Subject.java:422)

at 
org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1836)

at 
org.apache.flink.runtime.security.HadoopSecurityContext.runSecured(HadoopSecurityContext.java:41)

at org.apache.flink.client.cli.CliFrontend.main(CliFrontend.java:968)

Caused by: java.util.concurrent.ExecutionException: 
org.apache.flink.runtime.concurrent.FutureUtils$RetryException: Could not 
complete the operation. Number of retries has been exhausted.

at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:357)

at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:1908)

at 
org.apache.flink.streaming.api.environment.StreamContextEnvironment.execute(StreamContextEnvironment.java:83)

at 
org.apache.flink.streaming.api.environment.StreamExecutionEnvironment.execute(StreamExecutionEnvironment.java:1620)

at 
org.apache.flink.streaming.api.scala.StreamExecutionEnvironment.execute(StreamExecutionEnvironment.scala:678)

at com.nequal.bdh.cdp.IDMappingLauncher$.main(IDMappingLauncher.scala:140)

at com.nequal.bdh.cdp.IDMappingLauncher.main(IDMappingLauncher.scala)

at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)

at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)

at 
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)

at java.lang.reflect.Method.invoke(Method.java:498)

at 
org.apache.flink.client.program.PackagedProgram.callMainMethod(PackagedProgram.java:321)

... 11 more

Caused by: org.apache.flink.runtime.concurrent.FutureUtils$RetryException: 
Could not complete the operation. Number of retries has been exhausted.

at 
org.apache.flink.runtime.concurrent.FutureUtils.lambda$retryOperationWithDelay$8(FutureUtils.java:284)

at 
java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:774)

at 
java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:750)

at 
java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488)

at 
java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:1990)

at 
org.apache.flink.runtime.rest.RestClient.lambda$submitRequest$1(RestClient.java:342)

at 
org.apache.flink.shaded.netty4.io.netty.util.concurrent.DefaultPromise.notifyListener0(DefaultPromise.java:500)

at 
org.apache.flink.shaded.netty4.io.netty.util.concurrent.DefaultPromise.notifyListeners0(DefaultPromise.java:493)

at 
org.apache.flink.shaded.netty4.io.netty.util.concurrent.DefaultPromise.notifyListenersNow(DefaultPromise.java:472)

at 
org.apache.flink.shaded.netty4.io.netty.util.concurrent.DefaultPromise.notifyListeners(DefaultPromise.java:413)

at 
org.apache.flink.shaded.netty4.io.netty.util.concurrent.DefaultPromise.setValue0(DefaultPromise.java:538)

at 
org.apache.flink.shaded.netty4.io.netty.util.concurrent.DefaultPromise.setFailure0(DefaultPromise.java:531)

at 
org.apache.flink.shaded.netty4.io.netty.util.concurrent.DefaultPromise.tryFailure(DefaultPromise.java:111)

at 
org.apache.flink.shaded.netty4.io.netty.channel.nio.AbstractNioChannel$AbstractNioUnsafe.fulfillConnectPromise(AbstractNioChannel.java:323)

at 
org.apache.flink.shaded.netty4.io.netty.channel.nio.AbstractNioChannel$AbstractNioUnsafe.finishConnect(AbstractNioChannel.java:339)

at 
org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:685)

at 
org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:632)

at 
org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:549)

at 
org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:511)

at 
org.apache.flink.shaded.netty4.io.netty.util.concurrent.SingleThreadEventExecutor$5.run(SingleThreadEventExecutor.java:918)

at 
org.apache.flink.shaded.netty4.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74)

at java.lang.Thread.run(Thread.java:748)

Caused by: java.util.concurrent.CompletionException: 
org.apache.flink.shaded.netty4.io.netty.channel.AbstractChannel$AnnotatedConnectException:
 Connection timed out: nb-bdh-hadoop.slave14/10.10.5.14:21913

at 
java.util.concurrent.CompletableFuture.encodeThrowable(CompletableFuture.java:292)

at 
java.util.concurrent.CompletableFuture.completeThrowable(CompletableFuture.java:308)

at java.util.concurrent.CompletableFuture.uniCompose(CompletableFuture.java:957)

at 
java.util.concurrent.CompletableFuture$UniCompose.tryFire(CompletableFuture.java:940)

... 19 more

Caused by: 
org.apache.flink.shaded.netty4.io.netty.channel.AbstractChannel$AnnotatedConnectException:
 Connection timed out: nb-bdh-hadoop.slave14/10.10.5.14:21913

Caused by: java.net.ConnectException: Connection timed out

at sun.nio.ch.SocketChannelImpl.checkConnect(Native Method)

at sun.nio.ch.SocketChannelImpl.finishConnect(SocketChannelImpl.java:717)

at 
org.apache.flink.shaded.netty4.io.netty.channel.socket.nio.NioSocketChannel.doFinishConnect(NioSocketChannel.java:327)

[INFO] 2020-07-28 16:36:04.738  - [taskAppId=TASK-38-97-193]:[106] -  -> at 
org.apache.flink.shaded.netty4.io.netty.channel.nio.AbstractNioChannel$AbstractNioUnsafe.finishConnect(AbstractNioChannel.java:336)

at 
org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:685)

at 
org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:632)

at 
org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:549)

at 
org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:511)

at 
org.apache.flink.shaded.netty4.io.netty.util.concurrent.SingleThreadEventExecutor$5.run(SingleThreadEventExecutor.java:918)

at 
org.apache.flink.shaded.netty4.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74)

at java.lang.Thread.run(Thread.java:748)

回复