You are viewing a plain text version of this content. The canonical link for it is here.
Posted to mapreduce-issues@hadoop.apache.org by "Hudson (JIRA)" <ji...@apache.org> on 2015/08/15 10:07:46 UTC
[jira] [Commented] (MAPREDUCE-6439) AM may fail instead of retrying
if RM shuts down during the allocate call
[ https://issues.apache.org/jira/browse/MAPREDUCE-6439?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14698169#comment-14698169 ]
Hudson commented on MAPREDUCE-6439:
-----------------------------------
FAILURE: Integrated in Hadoop-trunk-Commit #8310 (See [https://builds.apache.org/job/Hadoop-trunk-Commit/8310/])
MAPREDUCE-6439. AM may fail instead of retrying if RM shuts down during the allocate call. (Anubhav Dhoot via kasha) (kasha: rev 8dfec7a1979e8f70f8355c096874921d368342ef)
* hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/test/java/org/apache/hadoop/mapreduce/v2/app/rm/TestRMCommunicator.java
* hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/rm/RMContainerAllocationException.java
* hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/rm/RMContainerAllocator.java
* hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/test/java/org/apache/hadoop/mapreduce/v2/app/rm/TestRMContainerAllocator.java
* hadoop-mapreduce-project/CHANGES.txt
* hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-app/src/main/java/org/apache/hadoop/mapreduce/v2/app/rm/RMCommunicator.java
> AM may fail instead of retrying if RM shuts down during the allocate call
> -------------------------------------------------------------------------
>
> Key: MAPREDUCE-6439
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-6439
> Project: Hadoop Map/Reduce
> Issue Type: Bug
> Affects Versions: 2.7.1
> Reporter: Anubhav Dhoot
> Assignee: Anubhav Dhoot
> Priority: Critical
> Fix For: 2.7.2
>
> Attachments: MAPREDUCE-6439.001.patch, MAPREDUCE-6439.002.patch
>
>
> We are seeing cases where MR AM gets a YarnRuntimeException thats thrown in RM and gets sent back to AM causing it to think that it has exhausted the number of retries. Copying the error which causes the heartbeat thread to quit.
> {noformat}
> 2015-07-25 20:07:27,346 ERROR [RMCommunicator Allocator] org.apache.hadoop.mapreduce.v2.app.rm.RMContainerAllocator: Error communicating with RM: java.lang.InterruptedException
> at org.apache.hadoop.yarn.event.AsyncDispatcher$GenericEventHandler.handle(AsyncDispatcher.java:245)
> at org.apache.hadoop.yarn.server.resourcemanager.ApplicationMasterService.allocate(ApplicationMasterService.java:469)
> at org.apache.hadoop.yarn.api.impl.pb.service.ApplicationMasterProtocolPBServiceImpl.allocate(ApplicationMasterProtocolPBServiceImpl.java:60)
> at org.apache.hadoop.yarn.proto.ApplicationMasterProtocol$ApplicationMasterProtocolService$2.callBlockingMethod(ApplicationMasterProtocol.java:99)
> at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:587)
> at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:1026)
> at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2013)
> at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2009)
> at java.security.AccessController.doPrivileged(Native Method)
> at javax.security.auth.Subject.doAs(Subject.java:415)
> at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1642)
> at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2007)
> Caused by: java.lang.InterruptedException
> at java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireInterruptibly(AbstractQueuedSynchronizer.java:1219)
> at java.util.concurrent.locks.ReentrantLock.lockInterruptibly(ReentrantLock.java:340)
> at java.util.concurrent.LinkedBlockingQueue.put(LinkedBlockingQueue.java:338)
> at org.apache.hadoop.yarn.event.AsyncDispatcher$GenericEventHandler.handle(AsyncDispatcher.java:240)
> ... 11 more
> org.apache.hadoop.yarn.exceptions.YarnRuntimeException: java.lang.InterruptedException
> at org.apache.hadoop.yarn.event.AsyncDispatcher$GenericEventHandler.handle(AsyncDispatcher.java:245)
> at org.apache.hadoop.yarn.server.resourcemanager.ApplicationMasterService.allocate(ApplicationMasterService.java:469)
> at org.apache.hadoop.yarn.api.impl.pb.service.ApplicationMasterProtocolPBServiceImpl.allocate(ApplicationMasterProtocolPBServiceImpl.java:60)
> at org.apache.hadoop.yarn.proto.ApplicationMasterProtocol$ApplicationMasterProtocolService$2.callBlockingMethod(ApplicationMasterProtocol.java:99)
> at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:587)
> at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:1026)
> at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2013)
> at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2009)
> at java.security.AccessController.doPrivileged(Native Method)
> at javax.security.auth.Subject.doAs(Subject.java:415)
> at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1642)
> at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2007)
> Caused by: java.lang.InterruptedException
> at java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireInterruptibly(AbstractQueuedSynchronizer.java:1219)
> at java.util.concurrent.locks.ReentrantLock.lockInterruptibly(ReentrantLock.java:340)
> at java.util.concurrent.LinkedBlockingQueue.put(LinkedBlockingQueue.java:338)
> at org.apache.hadoop.yarn.event.AsyncDispatcher$GenericEventHandler.handle(AsyncDispatcher.java:240)
> ... 11 more
> at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
> at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:57)
> at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
> at java.lang.reflect.Constructor.newInstance(Constructor.java:526)
> at org.apache.hadoop.yarn.ipc.RPCUtil.instantiateException(RPCUtil.java:53)
> at org.apache.hadoop.yarn.ipc.RPCUtil.unwrapAndThrowException(RPCUtil.java:107)
> at org.apache.hadoop.yarn.api.impl.pb.client.ApplicationMasterProtocolPBClientImpl.allocate(ApplicationMasterProtocolPBClientImpl.java:79)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
> at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:606)
> at org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:187)
> at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:102)
> at com.sun.proxy.$Proxy36.allocate(Unknown Source)
> at org.apache.hadoop.mapreduce.v2.app.rm.RMContainerRequestor.makeRemoteRequest(RMContainerRequestor.java:188)
> at org.apache.hadoop.mapreduce.v2.app.rm.RMContainerAllocator.getResources(RMContainerAllocator.java:667)
> at org.apache.hadoop.mapreduce.v2.app.rm.RMContainerAllocator.heartbeat(RMContainerAllocator.java:244)
> at org.apache.hadoop.mapreduce.v2.app.rm.RMCommunicator$1.run(RMCommunicator.java:282)
> at java.lang.Thread.run(Thread.java:745)
> Caused by: org.apache.hadoop.ipc.RemoteException(org.apache.hadoop.yarn.exceptions.YarnRuntimeException): java.lang.InterruptedException
> at org.apache.hadoop.yarn.event.AsyncDispatcher$GenericEventHandler.handle(AsyncDispatcher.java:245)
> at org.apache.hadoop.yarn.server.resourcemanager.ApplicationMasterService.allocate(ApplicationMasterService.java:469)
> at org.apache.hadoop.yarn.api.impl.pb.service.ApplicationMasterProtocolPBServiceImpl.allocate(ApplicationMasterProtocolPBServiceImpl.java:60)
> at org.apache.hadoop.yarn.proto.ApplicationMasterProtocol$ApplicationMasterProtocolService$2.callBlockingMethod(ApplicationMasterProtocol.java:99)
> at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:587)
> at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:1026)
> at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2013)
> at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2009)
> at java.security.AccessController.doPrivileged(Native Method)
> at javax.security.auth.Subject.doAs(Subject.java:415)
> at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1642)
> at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2007)
> Caused by: java.lang.InterruptedException
> at java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireInterruptibly(AbstractQueuedSynchronizer.java:1219)
> at java.util.concurrent.locks.ReentrantLock.lockInterruptibly(ReentrantLock.java:340)
> at java.util.concurrent.LinkedBlockingQueue.put(LinkedBlockingQueue.java:338)
> at org.apache.hadoop.yarn.event.AsyncDispatcher$GenericEventHandler.handle(AsyncDispatcher.java:240)
> ... 11 more
> at org.apache.hadoop.ipc.Client.call(Client.java:1411)
> at org.apache.hadoop.ipc.Client.call(Client.java:1364)
> at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:206)
> at com.sun.proxy.$Proxy35.allocate(Unknown Source)
> at org.apache.hadoop.yarn.api.impl.pb.client.ApplicationMasterProtocolPBClientImpl.allocate(ApplicationMasterProtocolPBClientImpl.java:77)
> ... 12 more
> {noformat}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)