Florian Schmidt created APEXCORE-776: ----------------------------------------
Summary: launch -originalAppId throws exception when trying to restart a killed app Key: APEXCORE-776 URL: https://issues.apache.org/jira/browse/APEXCORE-776 Project: Apache Apex Core Issue Type: Bug Reporter: Florian Schmidt Priority: Minor When launching an application, killing it immediately and trying to restart it with {-originalAppId}, the following stacktrace is shown. I *assume* that this is because the app never reached running state but was killed in submitted / accepted step. What I did expect: Better error message as to why this error occurs. {code} apex> launch apex-test/malhar-examples-highlevelapi-3.8.0-SNAPSHOT.apa 1. AutoComplete 2. CombinePerKeyExamples 3. DeDupExample 4. MaxPerKeyExamples 5. MinimalWordCount 6. StreamingWordExtract 7. TopWikipediaSessions 8. TrafficRoutes 9. TwitterAutoComplete 10. WindowedWordCount Choose application: 5 {"appId": "application_1499808956620_1492"} apex (application_1499808956620_1492) > kill-app Kill app requested apex> launch -originalAppId application_1499808956620_1492 java.io.FileNotFoundException: File does not exist: /user/dtadmin/datatorrent/apps/application_1499808956620_1492/meta.json at org.apache.hadoop.hdfs.server.namenode.INodeFile.valueOf(INodeFile.java:66) at org.apache.hadoop.hdfs.server.namenode.INodeFile.valueOf(INodeFile.java:56) at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocationsUpdateTimes(FSNamesystem.java:1963) at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocationsInt(FSNamesystem.java:1904) at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocations(FSNamesystem.java:1884) at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocations(FSNamesystem.java:1856) at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.getBlockLocations(NameNodeRpcServer.java:568) at org.apache.hadoop.hdfs.server.namenode.AuthorizationProviderProxyClientProtocol.getBlockLocations(AuthorizationProviderProxyClientProtocol.java:89) 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$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:617) at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:1073) at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2086) at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2082) at java.security.AccessController.doPrivileged(Native Method) at javax.security.auth.Subject.doAs(Subject.java:415) at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1693) at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2080) 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:1280) at org.apache.hadoop.hdfs.DFSClient.getLocatedBlocks(DFSClient.java:1265) at org.apache.hadoop.hdfs.DFSClient.getLocatedBlocks(DFSClient.java:1253) at org.apache.hadoop.hdfs.DFSInputStream.fetchLocatedBlocksAndGetLastBlockLength(DFSInputStream.java:305) at org.apache.hadoop.hdfs.DFSInputStream.openInfo(DFSInputStream.java:271) at org.apache.hadoop.hdfs.DFSInputStream.<init>(DFSInputStream.java:263) at org.apache.hadoop.hdfs.DFSClient.open(DFSClient.java:1584) at org.apache.hadoop.hdfs.DistributedFileSystem$3.doCall(DistributedFileSystem.java:309) at org.apache.hadoop.hdfs.DistributedFileSystem$3.doCall(DistributedFileSystem.java:305) at org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81) at org.apache.hadoop.hdfs.DistributedFileSystem.open(DistributedFileSystem.java:305) at org.apache.hadoop.fs.FileSystem.open(FileSystem.java:778) at com.datatorrent.stram.client.StramAppLauncher.init(StramAppLauncher.java:279) at com.datatorrent.stram.client.StramAppLauncher.<init>(StramAppLauncher.java:262) at com.datatorrent.stram.cli.ApexCli$LaunchCommand.execute(ApexCli.java:1922) at com.datatorrent.stram.cli.ApexCli$3.run(ApexCli.java:1520) Caused by: org.apache.hadoop.ipc.RemoteException(java.io.FileNotFoundException): File does not exist: /user/dtadmin/datatorrent/apps/application_1499808956620_1492/meta.json at org.apache.hadoop.hdfs.server.namenode.INodeFile.valueOf(INodeFile.java:66) at org.apache.hadoop.hdfs.server.namenode.INodeFile.valueOf(INodeFile.java:56) at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocationsUpdateTimes(FSNamesystem.java:1963) at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocationsInt(FSNamesystem.java:1904) at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocations(FSNamesystem.java:1884) at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getBlockLocations(FSNamesystem.java:1856) at org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.getBlockLocations(NameNodeRpcServer.java:568) at org.apache.hadoop.hdfs.server.namenode.AuthorizationProviderProxyClientProtocol.getBlockLocations(AuthorizationProviderProxyClientProtocol.java:89) at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.getBlockLocations(ClientNamenodeProtocolServerSideTranslatorPB.java:363) at org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java) at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:617) at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:1073) at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2086) at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2082) at java.security.AccessController.doPrivileged(Native Method) at javax.security.auth.Subject.doAs(Subject.java:415) at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1693) at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2080) at org.apache.hadoop.ipc.Client.call(Client.java:1471) at org.apache.hadoop.ipc.Client.call(Client.java:1408) at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:230) at com.sun.proxy.$Proxy16.getBlockLocations(Unknown Source) at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.getBlockLocations(ClientNamenodeProtocolTranslatorPB.java:256) at sun.reflect.GeneratedMethodAccessor19.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:256) at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:104) at com.sun.proxy.$Proxy17.getBlockLocations(Unknown Source) at org.apache.hadoop.hdfs.DFSClient.callGetBlockLocations(DFSClient.java:1278) ... 15 more {code} -- This message was sent by Atlassian JIRA (v6.4.14#64029)