[MAPREDUCE-6273] HistoryFileManager should check whether summaryFile exists to avoid FileNotFoundException causing HistoryFileInfo into MOVE_FAILED state

• Type: Bug
• Status: Closed
• Priority: Minor
• Resolution: Fixed
• Fix Version/s: 2.8.0, 2.7.2, 2.6.3, 3.0.0-alpha1
• Component/s: jobhistoryserver
• Target Version/s: 2.8.0
• Hadoop Flags: Reviewed
• Assignee: Zhihai Xu
• Reporter: Zhihai Xu
• Created: 12/Mar/15 05:03
• Updated: 01/Dec/16 23:22
• Resolved: 15/May/15 07:06

Description

HistoryFileManager should check whether summaryFile exists to avoid FileNotFoundException causing HistoryFileInfo into MOVE_FAILED state,
I saw the following error message:

2015-02-17 19:13:45,198 ERROR org.apache.hadoop.mapreduce.v2.hs.HistoryFileManager: Error while trying to move a job to done
java.io.FileNotFoundException: File does not exist: /user/history/done_intermediate/agd_laci-sluice/job_1423740288390_1884.summary
	at org.apache.hadoop.hdfs.server.namenode.INodeFile.valueOf(INodeFile.java:65)
	at org.apache.hadoop.hdfs.server.namenode.INodeFile.valueOf(INodeFile.java:55)
	at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocationsUpdateTimes(FSNamesystem.java:1878)
	at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocationsInt(FSNamesystem.java:1819)
	at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocations(FSNamesystem.java:1799)
	at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocations(FSNamesystem.java:1771)
	at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.getBlockLocations(NameNodeRpcServer.java:527)
	at org.apache.hadoop.hdfs.server.namenode.AuthorizationProviderProxyClientProtocol.getBlockLocations(AuthorizationProviderProxyClientProtocol.java:85)
	at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.getBlockLocations(ClientNamenodeProtocolServerSideTranslatorPB.java:356)
	at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java)
	at org.apache.hadoop.ipc.ProtobufRpcEngine$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)

	at sun.reflect.GeneratedConstructorAccessor29.newInstance(Unknown Source)
	at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
	at java.lang.reflect.Constructor.newInstance(Constructor.java:526)
	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.DFSClient.callGetBlockLocations(DFSClient.java:1181)
	at org.apache.hadoop.hdfs.DFSClient.getLocatedBlocks(DFSClient.java:1169)
	at org.apache.hadoop.hdfs.DFSClient.getLocatedBlocks(DFSClient.java:1159)
	at org.apache.hadoop.hdfs.DFSInputStream.fetchLocatedBlocksAndGetLastBlockLength(DFSInputStream.java:270)
	at org.apache.hadoop.hdfs.DFSInputStream.openInfo(DFSInputStream.java:237)
	at org.apache.hadoop.hdfs.DFSInputStream.<init>(DFSInputStream.java:230)
	at org.apache.hadoop.hdfs.DFSClient.open(DFSClient.java:1457)
	at org.apache.hadoop.fs.Hdfs.open(Hdfs.java:318)
	at org.apache.hadoop.fs.Hdfs.open(Hdfs.java:59)
	at org.apache.hadoop.fs.AbstractFileSystem.open(AbstractFileSystem.java:621)
	at org.apache.hadoop.fs.FileContext$6.next(FileContext.java:789)
	at org.apache.hadoop.fs.FileContext$6.next(FileContext.java:785)
	at org.apache.hadoop.fs.FSLinkResolver.resolve(FSLinkResolver.java:90)
	at org.apache.hadoop.fs.FileContext.open(FileContext.java:785)
	at org.apache.hadoop.mapreduce.v2.hs.HistoryFileManager.getJobSummary(HistoryFileManager.java:953)
	at org.apache.hadoop.mapreduce.v2.hs.HistoryFileManager.access$400(HistoryFileManager.java:82)
	at org.apache.hadoop.mapreduce.v2.hs.HistoryFileManager$HistoryFileInfo.moveToDone(HistoryFileManager.java:370)
	at org.apache.hadoop.mapreduce.v2.hs.HistoryFileManager$HistoryFileInfo.access$1400(HistoryFileManager.java:295)
	at org.apache.hadoop.mapreduce.v2.hs.HistoryFileManager$1.run(HistoryFileManager.java:843)
	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
	at java.lang.Thread.run(Thread.java:745)
Caused by: org.apache.hadoop.ipc.RemoteException(java.io.FileNotFoundException): File does not exist: /user/history/done_intermediate/agd_laci-sluice/job_1423740288390_1884.summary
	at org.apache.hadoop.hdfs.server.namenode.INodeFile.valueOf(INodeFile.java:65)
	at org.apache.hadoop.hdfs.server.namenode.INodeFile.valueOf(INodeFile.java:55)
	at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocationsUpdateTimes(FSNamesystem.java:1878)
	at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocationsInt(FSNamesystem.java:1819)
	at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocations(FSNamesystem.java:1799)
	at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocations(FSNamesystem.java:1771)
	at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.getBlockLocations(NameNodeRpcServer.java:527)
	at org.apache.hadoop.hdfs.server.namenode.AuthorizationProviderProxyClientProtocol.getBlockLocations(AuthorizationProviderProxyClientProtocol.java:85)
	at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.getBlockLocations(ClientNamenodeProtocolServerSideTranslatorPB.java:356)
	at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java)
	at org.apache.hadoop.ipc.ProtobufRpcEngine$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)

	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$Invoker.invoke(ProtobufRpcEngine.java:206)
	at com.sun.proxy.$Proxy13.getBlockLocations(Unknown Source)
	at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.getBlockLocations(ClientNamenodeProtocolTranslatorPB.java:246)
	at sun.reflect.GeneratedMethodAccessor5.invoke(Unknown Source)
	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.$Proxy14.getBlockLocations(Unknown Source)
	at org.apache.hadoop.hdfs.DFSClient.callGetBlockLocations(DFSClient.java:1179)
	... 21 more

We should avoid this error by checking whether summaryFile exists before call getJobSummary, otherwise we will see this error happen every time scanIntermediateDirectory is called.