[ 
https://issues.apache.org/jira/browse/YARN-4794?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
 ]

Sumana Sathish updated YARN-4794:
---------------------------------
    Description: 
Distributed shell app gets stuck on stopping containers after App completes 
with the following exception
{code:title = app log}
16/03/10 23:19:41 WARN ipc.Client: Exception encountered while connecting to 
the server : 
java.nio.channels.ClosedByInterruptException
at 
java.nio.channels.spi.AbstractInterruptibleChannel.end(AbstractInterruptibleChannel.java:202)
at sun.nio.ch.SocketChannelImpl.read(SocketChannelImpl.java:407)
at 
org.apache.hadoop.net.SocketInputStream$Reader.performIO(SocketInputStream.java:57)
at org.apache.hadoop.net.SocketIOWithTimeout.doIO(SocketIOWithTimeout.java:142)
at org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:161)
at org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:131)
at java.io.FilterInputStream.read(FilterInputStream.java:133)
at java.io.BufferedInputStream.fill(BufferedInputStream.java:246)
at java.io.BufferedInputStream.read(BufferedInputStream.java:265)
at java.io.DataInputStream.readInt(DataInputStream.java:387)
at org.apache.hadoop.security.SaslRpcClient.saslConnect(SaslRpcClient.java:367)
at org.apache.hadoop.ipc.Client$Connection.setupSaslConnection(Client.java:558)
at org.apache.hadoop.ipc.Client$Connection.access$1800(Client.java:373)
at org.apache.hadoop.ipc.Client$Connection$2.run(Client.java:727)
at org.apache.hadoop.ipc.Client$Connection$2.run(Client.java:723)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:422)
at 
org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1657)
at org.apache.hadoop.ipc.Client$Connection.setupIOstreams(Client.java:722)
at org.apache.hadoop.ipc.Client$Connection.access$2800(Client.java:373)
at org.apache.hadoop.ipc.Client.getConnection(Client.java:1493)
at org.apache.hadoop.ipc.Client.call(Client.java:1397)
at org.apache.hadoop.ipc.Client.call(Client.java:1358)
at 
org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:229)
at com.sun.proxy.$Proxy30.startContainers(Unknown Source)
at 
org.apache.hadoop.yarn.api.impl.pb.client.ContainerManagementProtocolPBClientImpl.startContainers(ContainerManagementProtocolPBClientImpl.java:96)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at 
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:497)
at 
org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:252)
at 
org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:104)
at com.sun.proxy.$Proxy31.startContainers(Unknown Source)
at 
org.apache.hadoop.yarn.client.api.impl.NMClientImpl.startContainer(NMClientImpl.java:205)
at 
org.apache.hadoop.yarn.client.api.async.impl.NMClientAsyncImpl$StatefulContainer$StartContainerTransition.transition(NMClientAsyncImpl.java:382)
at 
org.apache.hadoop.yarn.client.api.async.impl.NMClientAsyncImpl$StatefulContainer$StartContainerTransition.transition(NMClientAsyncImpl.java:368)
at 
org.apache.hadoop.yarn.state.StateMachineFactory$MultipleInternalArc.doTransition(StateMachineFactory.java:385)
at 
org.apache.hadoop.yarn.state.StateMachineFactory.doTransition(StateMachineFactory.java:302)
at 
org.apache.hadoop.yarn.state.StateMachineFactory.access$300(StateMachineFactory.java:46)
at 
org.apache.hadoop.yarn.state.StateMachineFactory$InternalStateMachine.doTransition(StateMachineFactory.java:448)
at 
org.apache.hadoop.yarn.client.api.async.impl.NMClientAsyncImpl$StatefulContainer.handle(NMClientAsyncImpl.java:503)
at 
org.apache.hadoop.yarn.client.api.async.impl.NMClientAsyncImpl$ContainerEventProcessor.run(NMClientAsyncImpl.java:562)
at 
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at 
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
{code}

  was:
Distributed shell app gets stuck on stopping containers after App completes 
with the following exception
{code:title = app log}
16/03/10 23:19:41 INFO distributedshell.ApplicationMaster: Application 
completed. Stopping running containers
16/03/10 23:19:41 INFO impl.NMClientAsyncImpl: NM Client is being stopped.
16/03/10 23:19:41 INFO impl.NMClientAsyncImpl: Waiting for 
eventDispatcherThread to be interrupted.
16/03/10 23:19:41 INFO impl.NMClientAsyncImpl: eventDispatcherThread exited.
16/03/10 23:19:41 INFO impl.NMClientAsyncImpl: Stopping NM client.
16/03/10 23:19:41 INFO impl.NMClientImpl: Clean up running containers on stop.
16/03/10 23:19:41 INFO impl.NMClientImpl: Stopping 
container_e05_1457650296862_0046_01_000008
16/03/10 23:19:41 INFO impl.NMClientImpl: ok, stopContainerInternal.. 
container_e05_1457650296862_0046_01_000008
16/03/10 23:19:41 INFO impl.ContainerManagementProtocolProxy: Opening proxy : 
yarn-sumana-1.novalocal:25454
16/03/10 23:19:41 WARN ipc.Client: Exception encountered while connecting to 
the server : 
java.nio.channels.ClosedByInterruptException
        at 
java.nio.channels.spi.AbstractInterruptibleChannel.end(AbstractInterruptibleChannel.java:202)
        at sun.nio.ch.SocketChannelImpl.read(SocketChannelImpl.java:407)
        at 
org.apache.hadoop.net.SocketInputStream$Reader.performIO(SocketInputStream.java:57)
        at 
org.apache.hadoop.net.SocketIOWithTimeout.doIO(SocketIOWithTimeout.java:142)
        at 
org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:161)
        at 
org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:131)
        at java.io.FilterInputStream.read(FilterInputStream.java:133)
        at java.io.BufferedInputStream.fill(BufferedInputStream.java:246)
        at java.io.BufferedInputStream.read(BufferedInputStream.java:265)
        at java.io.DataInputStream.readInt(DataInputStream.java:387)
        at 
org.apache.hadoop.security.SaslRpcClient.saslConnect(SaslRpcClient.java:367)
        at 
org.apache.hadoop.ipc.Client$Connection.setupSaslConnection(Client.java:558)
        at org.apache.hadoop.ipc.Client$Connection.access$1800(Client.java:373)
        at org.apache.hadoop.ipc.Client$Connection$2.run(Client.java:727)
        at org.apache.hadoop.ipc.Client$Connection$2.run(Client.java:723)
        at java.security.AccessController.doPrivileged(Native Method)
        at javax.security.auth.Subject.doAs(Subject.java:422)
        at 
org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1657)
        at 
org.apache.hadoop.ipc.Client$Connection.setupIOstreams(Client.java:722)
        at org.apache.hadoop.ipc.Client$Connection.access$2800(Client.java:373)
        at org.apache.hadoop.ipc.Client.getConnection(Client.java:1493)
        at org.apache.hadoop.ipc.Client.call(Client.java:1397)
        at org.apache.hadoop.ipc.Client.call(Client.java:1358)
        at 
org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:229)
        at com.sun.proxy.$Proxy30.startContainers(Unknown Source)
        at 
org.apache.hadoop.yarn.api.impl.pb.client.ContainerManagementProtocolPBClientImpl.startContainers(ContainerManagementProtocolPBClientImpl.java:96)
        at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
        at 
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
        at 
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
        at java.lang.reflect.Method.invoke(Method.java:497)
        at 
org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:252)
        at 
org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:104)
        at com.sun.proxy.$Proxy31.startContainers(Unknown Source)
        at 
org.apache.hadoop.yarn.client.api.impl.NMClientImpl.startContainer(NMClientImpl.java:205)
        at 
org.apache.hadoop.yarn.client.api.async.impl.NMClientAsyncImpl$StatefulContainer$StartContainerTransition.transition(NMClientAsyncImpl.java:382)
        at 
org.apache.hadoop.yarn.client.api.async.impl.NMClientAsyncImpl$StatefulContainer$StartContainerTransition.transition(NMClientAsyncImpl.java:368)
        at 
org.apache.hadoop.yarn.state.StateMachineFactory$MultipleInternalArc.doTransition(StateMachineFactory.java:385)
        at 
org.apache.hadoop.yarn.state.StateMachineFactory.doTransition(StateMachineFactory.java:302)
        at 
org.apache.hadoop.yarn.state.StateMachineFactory.access$300(StateMachineFactory.java:46)
        at 
org.apache.hadoop.yarn.state.StateMachineFactory$InternalStateMachine.doTransition(StateMachineFactory.java:448)
        at 
org.apache.hadoop.yarn.client.api.async.impl.NMClientAsyncImpl$StatefulContainer.handle(NMClientAsyncImpl.java:503)
        at 
org.apache.hadoop.yarn.client.api.async.impl.NMClientAsyncImpl$ContainerEventProcessor.run(NMClientAsyncImpl.java:562)
        at 
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
        at 
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
        at java.lang.Thread.run(Thread.java:745)
16/03/10 23:19:41 INFO impl.NMClientImpl: Stopping 
container_e05_1457650296862_0046_01_000007
16/03/10 23:19:41 INFO impl.NMClientImpl: ok, stopContainerInternal.. 
container_e05_1457650296862_0046_01_000007
16/03/10 23:19:41 INFO impl.ContainerManagementProtocolProxy: Opening proxy : 
yarn-sumana-5.novalocal:25454
16/03/10 23:19:41 INFO impl.NMClientImpl: Stopping 
container_e05_1457650296862_0046_01_000009
{code}


> Distributed shell app gets stuck on stopping containers after App completes
> ---------------------------------------------------------------------------
>
>                 Key: YARN-4794
>                 URL: https://issues.apache.org/jira/browse/YARN-4794
>             Project: Hadoop YARN
>          Issue Type: Bug
>            Reporter: Sumana Sathish
>            Assignee: Jian He
>            Priority: Critical
>
> Distributed shell app gets stuck on stopping containers after App completes 
> with the following exception
> {code:title = app log}
> 16/03/10 23:19:41 WARN ipc.Client: Exception encountered while connecting to 
> the server : 
> java.nio.channels.ClosedByInterruptException
> at 
> java.nio.channels.spi.AbstractInterruptibleChannel.end(AbstractInterruptibleChannel.java:202)
> at sun.nio.ch.SocketChannelImpl.read(SocketChannelImpl.java:407)
> at 
> org.apache.hadoop.net.SocketInputStream$Reader.performIO(SocketInputStream.java:57)
> at 
> org.apache.hadoop.net.SocketIOWithTimeout.doIO(SocketIOWithTimeout.java:142)
> at org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:161)
> at org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:131)
> at java.io.FilterInputStream.read(FilterInputStream.java:133)
> at java.io.BufferedInputStream.fill(BufferedInputStream.java:246)
> at java.io.BufferedInputStream.read(BufferedInputStream.java:265)
> at java.io.DataInputStream.readInt(DataInputStream.java:387)
> at 
> org.apache.hadoop.security.SaslRpcClient.saslConnect(SaslRpcClient.java:367)
> at 
> org.apache.hadoop.ipc.Client$Connection.setupSaslConnection(Client.java:558)
> at org.apache.hadoop.ipc.Client$Connection.access$1800(Client.java:373)
> at org.apache.hadoop.ipc.Client$Connection$2.run(Client.java:727)
> at org.apache.hadoop.ipc.Client$Connection$2.run(Client.java:723)
> at java.security.AccessController.doPrivileged(Native Method)
> at javax.security.auth.Subject.doAs(Subject.java:422)
> at 
> org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1657)
> at org.apache.hadoop.ipc.Client$Connection.setupIOstreams(Client.java:722)
> at org.apache.hadoop.ipc.Client$Connection.access$2800(Client.java:373)
> at org.apache.hadoop.ipc.Client.getConnection(Client.java:1493)
> at org.apache.hadoop.ipc.Client.call(Client.java:1397)
> at org.apache.hadoop.ipc.Client.call(Client.java:1358)
> at 
> org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:229)
> at com.sun.proxy.$Proxy30.startContainers(Unknown Source)
> at 
> org.apache.hadoop.yarn.api.impl.pb.client.ContainerManagementProtocolPBClientImpl.startContainers(ContainerManagementProtocolPBClientImpl.java:96)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at 
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
> at 
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:497)
> at 
> org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:252)
> at 
> org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:104)
> at com.sun.proxy.$Proxy31.startContainers(Unknown Source)
> at 
> org.apache.hadoop.yarn.client.api.impl.NMClientImpl.startContainer(NMClientImpl.java:205)
> at 
> org.apache.hadoop.yarn.client.api.async.impl.NMClientAsyncImpl$StatefulContainer$StartContainerTransition.transition(NMClientAsyncImpl.java:382)
> at 
> org.apache.hadoop.yarn.client.api.async.impl.NMClientAsyncImpl$StatefulContainer$StartContainerTransition.transition(NMClientAsyncImpl.java:368)
> at 
> org.apache.hadoop.yarn.state.StateMachineFactory$MultipleInternalArc.doTransition(StateMachineFactory.java:385)
> at 
> org.apache.hadoop.yarn.state.StateMachineFactory.doTransition(StateMachineFactory.java:302)
> at 
> org.apache.hadoop.yarn.state.StateMachineFactory.access$300(StateMachineFactory.java:46)
> at 
> org.apache.hadoop.yarn.state.StateMachineFactory$InternalStateMachine.doTransition(StateMachineFactory.java:448)
> at 
> org.apache.hadoop.yarn.client.api.async.impl.NMClientAsyncImpl$StatefulContainer.handle(NMClientAsyncImpl.java:503)
> at 
> org.apache.hadoop.yarn.client.api.async.impl.NMClientAsyncImpl$ContainerEventProcessor.run(NMClientAsyncImpl.java:562)
> at 
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
> at 
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
> at java.lang.Thread.run(Thread.java:745)
> {code}



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Reply via email to