apex-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Francis Fernandes (JIRA)" <j...@apache.org>
Subject [jira] [Created] (APEXMALHAR-2374) Recursive support for AbstractFileInputOperator
Date Wed, 21 Dec 2016 11:35:58 GMT
Francis Fernandes created APEXMALHAR-2374:
---------------------------------------------

             Summary: Recursive support for AbstractFileInputOperator
                 Key: APEXMALHAR-2374
                 URL: https://issues.apache.org/jira/browse/APEXMALHAR-2374
             Project: Apache Apex Malhar
          Issue Type: Improvement
    Affects Versions: 3.6.0
            Reporter: Francis Fernandes
            Assignee: Francis Fernandes


Add recursive support to AbstractFileInputOperator. Curently it fails with FileNotFoundException
when the input directory contains sub directories inside it.

{code}
ERROR com.datatorrent.lib.io.fs.AbstractFileInputOperator: FS reader error
java.io.FileNotFoundException: Path is not a file: /user/dttbc/DATASETS/a/b
	at org.apache.hadoop.hdfs.server.namenode.INodeFile.valueOf(INodeFile.java:70)
	at org.apache.hadoop.hdfs.server.namenode.INodeFile.valueOf(INodeFile.java:56)
	at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocationsUpdateTimes(FSNamesystem.java:1932)
	at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocationsInt(FSNamesystem.java:1873)
	at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocations(FSNamesystem.java:1853)
	at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocations(FSNamesystem.java:1825)
	at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.getBlockLocations(NameNodeRpcServer.java:559)
	at org.apache.hadoop.hdfs.server.namenode.AuthorizationProviderProxyClientProtocol.getBlockLocations(AuthorizationProviderProxyClientProtocol.java:87)
	at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.getBlockLocations(ClientNamenodeProtocolServerSideTranslatorPB.java:363)
	at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java)
	at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:619)
	at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:1060)
	at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2044)
	at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2040)
	at java.security.AccessController.doPrivileged(Native Method)
	at javax.security.auth.Subject.doAs(Subject.java:415)
	at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1671)
	at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2038)
	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.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:1215)
	at org.apache.hadoop.hdfs.DFSClient.getLocatedBlocks(DFSClient.java:1203)
	at org.apache.hadoop.hdfs.DFSClient.getLocatedBlocks(DFSClient.java:1193)
	at org.apache.hadoop.hdfs.DFSInputStream.fetchLocatedBlocksAndGetLastBlockLength(DFSInputStream.java:299)
	at org.apache.hadoop.hdfs.DFSInputStream.openInfo(DFSInputStream.java:265)
	at org.apache.hadoop.hdfs.DFSInputStream.<init>(DFSInputStream.java:257)
	at org.apache.hadoop.hdfs.DFSClient.open(DFSClient.java:1492)
	at org.apache.hadoop.hdfs.DistributedFileSystem$3.doCall(DistributedFileSystem.java:302)
	at org.apache.hadoop.hdfs.DistributedFileSystem$3.doCall(DistributedFileSystem.java:298)
	at org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81)
	at org.apache.hadoop.hdfs.DistributedFileSystem.open(DistributedFileSystem.java:298)
	at org.apache.hadoop.fs.FileSystem.open(FileSystem.java:766)
	at com.datatorrent.lib.io.fs.AbstractFileInputOperator.openFile(AbstractFileInputOperator.java:773)
	at com.example.fileIO.BytesFileReader.openFile(BytesFileReader.java:87)
	at com.datatorrent.lib.io.fs.AbstractFileInputOperator.emitTuples(AbstractFileInputOperator.java:642)
	at com.example.fileIO.BytesFileReader.emitTuples(BytesFileReader.java:77)
	at com.datatorrent.stram.engine.InputNode.run(InputNode.java:91)
	at com.datatorrent.stram.engine.StreamingContainer$2.run(StreamingContainer.java:1415)
Caused by: org.apache.hadoop.ipc.RemoteException(java.io.FileNotFoundException): Path is not
a file: /user/dttbc/DATASETS/a/b
	at org.apache.hadoop.hdfs.server.namenode.INodeFile.valueOf(INodeFile.java:70)
	at org.apache.hadoop.hdfs.server.namenode.INodeFile.valueOf(INodeFile.java:56)
	at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocationsUpdateTimes(FSNamesystem.java:1932)
	at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocationsInt(FSNamesystem.java:1873)
	at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocations(FSNamesystem.java:1853)
	at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocations(FSNamesystem.java:1825)
	at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.getBlockLocations(NameNodeRpcServer.java:559)
	at org.apache.hadoop.hdfs.server.namenode.AuthorizationProviderProxyClientProtocol.getBlockLocations(AuthorizationProviderProxyClientProtocol.java:87)
	at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.getBlockLocations(ClientNamenodeProtocolServerSideTranslatorPB.java:363)
	at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java)
	at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:619)
	at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:1060)
	at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2044)
	at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2040)
	at java.security.AccessController.doPrivileged(Native Method)
	at javax.security.auth.Subject.doAs(Subject.java:415)
	at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1671)
	at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2038)
	at org.apache.hadoop.ipc.Client.call(Client.java:1468)
	at org.apache.hadoop.ipc.Client.call(Client.java:1399)
	at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:232)
	at com.sun.proxy.$Proxy14.getBlockLocations(Unknown Source)
	at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.getBlockLocations(ClientNamenodeProtocolTranslatorPB.java:254)
	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.$Proxy15.getBlockLocations(Unknown Source)
	at org.apache.hadoop.hdfs.DFSClient.callGetBlockLocations(DFSClient.java:1213)
	... 17 more
{code}



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

Mime
View raw message