[YARN-8897] LoadBasedRouterPolicy throws NPE in case of sub cluster unavailability

• Type: Bug
• Status: Resolved
• Priority: Minor
• Resolution: Fixed
• Fix Version/s: 3.3.0
• Component/s: federation, router
• Assignee: Bilwa S T
• Reporter: Akshay Agarwal
• Created: 17/Oct/18 06:06
• Updated: 03/Nov/18 15:02
• Resolved: 02/Nov/18 18:28

Description

If no sub clusters are available for "Load Based Router Policy" with cluster weight as 1  in Router Based Federation Setup , throwing "NullPointerException".

 

Exception Details:

java.lang.NullPointerException: java.lang.NullPointerException
 at org.apache.hadoop.yarn.server.federation.policies.router.LoadBasedRouterPolicy.getHomeSubcluster(LoadBasedRouterPolicy.java:99)
 at org.apache.hadoop.yarn.server.federation.policies.RouterPolicyFacade.getHomeSubcluster(RouterPolicyFacade.java:204)
 at org.apache.hadoop.yarn.server.router.clientrm.FederationClientInterceptor.submitApplication(FederationClientInterceptor.java:362)
 at org.apache.hadoop.yarn.server.router.clientrm.RouterClientRMService.submitApplication(RouterClientRMService.java:218)
 at org.apache.hadoop.yarn.api.impl.pb.service.ApplicationClientProtocolPBServiceImpl.submitApplication(ApplicationClientProtocolPBServiceImpl.java:282)
 at org.apache.hadoop.yarn.proto.ApplicationClientProtocol$ApplicationClientProtocolService$2.callBlockingMethod(ApplicationClientProtocol.java:579)
 at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:523)
 at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:991)
 at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:872)
 at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:818)
 at java.security.AccessController.doPrivileged(Native Method)
 at javax.security.auth.Subject.doAs(Subject.java:422)
 at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1729)
 at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2678)

at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
 at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
 at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
 at java.lang.reflect.Constructor.newInstance(Constructor.java:423)
 at org.apache.hadoop.yarn.ipc.RPCUtil.instantiateException(RPCUtil.java:53)
 at org.apache.hadoop.yarn.ipc.RPCUtil.instantiateRuntimeException(RPCUtil.java:85)
 at org.apache.hadoop.yarn.ipc.RPCUtil.unwrapAndThrowException(RPCUtil.java:122)
 at org.apache.hadoop.yarn.api.impl.pb.client.ApplicationClientProtocolPBClientImpl.submitApplication(ApplicationClientProtocolPBClientImpl.java:297)
 at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
 at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
 at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
 at java.lang.reflect.Method.invoke(Method.java:498)
 at org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:422)
 at org.apache.hadoop.io.retry.RetryInvocationHandler$Call.invokeMethod(RetryInvocationHandler.java:165)
 at org.apache.hadoop.io.retry.RetryInvocationHandler$Call.invoke(RetryInvocationHandler.java:157)
 at org.apache.hadoop.io.retry.RetryInvocationHandler$Call.invokeOnce(RetryInvocationHandler.java:95)
 at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:359)
 at com.sun.proxy.$Proxy15.submitApplication(Unknown Source)
 at org.apache.hadoop.yarn.client.api.impl.YarnClientImpl.submitApplication(YarnClientImpl.java:288)
 at org.apache.hadoop.mapred.ResourceMgrDelegate.submitApplication(ResourceMgrDelegate.java:300)
 at org.apache.hadoop.mapred.YARNRunner.submitJob(YARNRunner.java:331)
 at org.apache.hadoop.mapreduce.JobSubmitter.submitJobInternal(JobSubmitter.java:254)
 at org.apache.hadoop.mapreduce.Job$11.run(Job.java:1570)
 at org.apache.hadoop.mapreduce.Job$11.run(Job.java:1567)
 at java.security.AccessController.doPrivileged(Native Method)
 at javax.security.auth.Subject.doAs(Subject.java:422)
 at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1729)
 at org.apache.hadoop.mapreduce.Job.submit(Job.java:1567)
 at org.apache.hadoop.mapreduce.Job.waitForCompletion(Job.java:1588)
 at org.apache.hadoop.examples.QuasiMonteCarlo.estimatePi(QuasiMonteCarlo.java:307)
 at org.apache.hadoop.examples.QuasiMonteCarlo.run(QuasiMonteCarlo.java:360)
 at org.apache.hadoop.util.ToolRunner.run(ToolRunner.java:76)
 at org.apache.hadoop.examples.QuasiMonteCarlo.main(QuasiMonteCarlo.java:368)
 at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
 at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
 at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
 at java.lang.reflect.Method.invoke(Method.java:498)
 at org.apache.hadoop.util.ProgramDriver$ProgramDescription.invoke(ProgramDriver.java:71)
 at org.apache.hadoop.util.ProgramDriver.run(ProgramDriver.java:144)
 at org.apache.hadoop.examples.ExampleDriver.main(ExampleDriver.java:74)
 at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
 at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
 at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
 at java.lang.reflect.Method.invoke(Method.java:498)
 at org.apache.hadoop.util.RunJar.run(RunJar.java:318)
 at org.apache.hadoop.util.RunJar.main(RunJar.java:232)
 Caused by: org.apache.hadoop.ipc.RemoteException(java.lang.NullPointerException): java.lang.NullPointerException
 at org.apache.hadoop.yarn.server.federation.policies.router.LoadBasedRouterPolicy.getHomeSubcluster(LoadBasedRouterPolicy.java:99)
 at org.apache.hadoop.yarn.server.federation.policies.RouterPolicyFacade.getHomeSubcluster(RouterPolicyFacade.java:204)
 at org.apache.hadoop.yarn.server.router.clientrm.FederationClientInterceptor.submitApplication(FederationClientInterceptor.java:362)
 at org.apache.hadoop.yarn.server.router.clientrm.RouterClientRMService.submitApplication(RouterClientRMService.java:218)
 at org.apache.hadoop.yarn.api.impl.pb.service.ApplicationClientProtocolPBServiceImpl.submitApplication(ApplicationClientProtocolPBServiceImpl.java:282)
 at org.apache.hadoop.yarn.proto.ApplicationClientProtocol$ApplicationClientProtocolService$2.callBlockingMethod(ApplicationClientProtocol.java:579)
 at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:523)
 at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:991)
 at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:872)
 at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:818)
 at java.security.AccessController.doPrivileged(Native Method)
 at javax.security.auth.Subject.doAs(Subject.java:422)
 at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1729)
 at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2678)

Issue Links

• is related to: YARN-5324 Stateless Federation router policies implementation