[
https://issues.apache.org/jira/browse/HIVE-7627?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Chengxiang Li updated HIVE-7627:
--------------------------------
Attachment: HIVE-7627.5-spark.patch
> FSStatsPublisher does fit into Spark multi-thread task mode[Spark Branch]
> -------------------------------------------------------------------------
>
> Key: HIVE-7627
> URL: https://issues.apache.org/jira/browse/HIVE-7627
> Project: Hive
> Issue Type: Bug
> Components: Spark
> Reporter: Chengxiang Li
> Assignee: Chengxiang Li
> Labels: spark-m1
> Attachments: HIVE-7627.1-spark.patch, HIVE-7627.2-spark.patch,
> HIVE-7627.3-spark.patch, HIVE-7627.4-spark.patch, HIVE-7627.4-spark.patch,
> HIVE-7627.5-spark.patch
>
>
> Hive table statistic failed on FSStatsPublisher mode, with the following
> exception in Spark executor side:
> {noformat}
> 14/08/05 16:46:24 WARN hdfs.DFSClient: DataStreamer Exception
> java.io.FileNotFoundException: ID mismatch. Request id and saved id: 20277 ,
> 20278 for file
> /tmp/hive-root/8833d172-1edd-4508-86db-fdd7a1b0af17/hive_2014-08-05_16-46-03_013_6279446857294757772-1/-ext-10000/tmpstats-0
> at
> org.apache.hadoop.hdfs.server.namenode.INodeId.checkId(INodeId.java:53)
> at
> org.apache.hadoop.hdfs.server.namenode.FSNamesystem.checkLease(FSNamesystem.java:2952)
> at
> org.apache.hadoop.hdfs.server.namenode.FSNamesystem.analyzeFileState(FSNamesystem.java:2754)
> at
> org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getAdditionalBlock(FSNamesystem.java:2662)
> at
> org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.addBlock(NameNodeRpcServer.java:584)
> at
> org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.addBlock(ClientNamenodeProtocolServerSideTranslatorPB.java:440)
> at
> org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java)
> at
> org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:585)
> at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:928)
> at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2013)
> at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2009)
> at java.security.AccessController.doPrivileged(Native Method)
> at javax.security.auth.Subject.doAs(Subject.java:415)
> at
> org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1548)
> at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2007)
> 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:525)
> at
> org.apache.hadoop.ipc.RemoteException.instantiateException(RemoteException.java:106)
> at
> org.apache.hadoop.ipc.RemoteException.unwrapRemoteException(RemoteException.java:73)
> at
> org.apache.hadoop.hdfs.DFSOutputStream$DataStreamer.locateFollowingBlock(DFSOutputStream.java:1442)
> at
> org.apache.hadoop.hdfs.DFSOutputStream$DataStreamer.nextBlockOutputStream(DFSOutputStream.java:1261)
> at
> org.apache.hadoop.hdfs.DFSOutputStream$DataStreamer.run(DFSOutputStream.java:525)
> Caused by:
> org.apache.hadoop.ipc.RemoteException(java.io.FileNotFoundException): ID
> mismatch. Request id and saved id: 20277 , 20278 for file
> /tmp/hive-root/8833d172-1edd-4508-86db-fdd7a1b0af17/hive_2014-08-05_16-46-03_013_6279446857294757772-1/-ext-10000/tmpstats-0
> at
> org.apache.hadoop.hdfs.server.namenode.INodeId.checkId(INodeId.java:53)
> at
> org.apache.hadoop.hdfs.server.namenode.FSNamesystem.checkLease(FSNamesystem.java:2952)
> at
> org.apache.hadoop.hdfs.server.namenode.FSNamesystem.analyzeFileState(FSNamesystem.java:2754)
> at
> org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getAdditionalBlock(FSNamesystem.java:2662)
> at
> org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.addBlock(NameNodeRpcServer.java:584)
> at
> org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.addBlock(ClientNamenodeProtocolServerSideTranslatorPB.java:440)
> at
> org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java)
> at
> org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:585)
> at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:928)
> at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2013)
> at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2009)
> at java.security.AccessController.doPrivileged(Native Method)
> at javax.security.auth.Subject.doAs(Subject.java:415)
> at
> org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1548)
> at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2007)
> at org.apache.hadoop.ipc.Client.call(Client.java:1410)
> at org.apache.hadoop.ipc.Client.call(Client.java:1363)
> at
> org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:206)
> at com.sun.proxy.$Proxy19.addBlock(Unknown Source)
> 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:601)
> at
> org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:190)
> at
> org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:103)
> at com.sun.proxy.$Proxy19.addBlock(Unknown Source)
> at
> org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.addBlock(ClientNamenodeProtocolTranslatorPB.java:361)
> at
> org.apache.hadoop.hdfs.DFSOutputStream$DataStreamer.locateFollowingBlock(DFSOutputStream.java:1439)
> ... 2 more
> {noformat}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
