[YARN-7009] TestNMClient.testNMClientNoCleanupOnStop is flaky by design

• Type: Bug
• Status: Resolved
• Priority: Major
• Resolution: Fixed
• Fix Version/s: 3.0.0
• Hadoop Flags: Reviewed
• Assignee: Miklos Szegedi
• Reporter: Miklos Szegedi
• Created: 14/Aug/17 18:33
• Updated: 06/Oct/17 00:20
• Resolved: 05/Oct/17 22:52

Description

The sleeps to wait for a transition to reinit and than back to running is not long enough, it can miss the reinit event.

java.lang.AssertionError: Exception is not expected: org.apache.hadoop.yarn.exceptions.YarnException: Cannot perform RE_INIT on [container_1502735389852_0001_01_000001]. Current state is [REINITIALIZING, isReInitializing=true].
	at org.apache.hadoop.yarn.server.nodemanager.containermanager.ContainerManagerImpl.preReInitializeOrLocalizeCheck(ContainerManagerImpl.java:1772)
	at org.apache.hadoop.yarn.server.nodemanager.containermanager.ContainerManagerImpl.reInitializeContainer(ContainerManagerImpl.java:1697)
	at org.apache.hadoop.yarn.server.nodemanager.containermanager.ContainerManagerImpl.reInitializeContainer(ContainerManagerImpl.java:1668)
	at org.apache.hadoop.yarn.api.impl.pb.service.ContainerManagementProtocolPBServiceImpl.reInitializeContainer(ContainerManagementProtocolPBServiceImpl.java:214)
	at org.apache.hadoop.yarn.proto.ContainerManagementProtocol$ContainerManagementProtocolService$2.callBlockingMethod(ContainerManagementProtocol.java:237)
	at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:523)
	at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:991)
	at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:869)
	at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:815)
	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:1962)
	at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2675)


	at org.apache.hadoop.yarn.client.api.impl.TestNMClient.testReInitializeContainer(TestNMClient.java:567)
	at org.apache.hadoop.yarn.client.api.impl.TestNMClient.testContainerManagement(TestNMClient.java:405)
	at org.apache.hadoop.yarn.client.api.impl.TestNMClient.testNMClientNoCleanupOnStop(TestNMClient.java:214)
	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.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:47)
	at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12)
	at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:44)
	at org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17)
	at org.junit.internal.runners.statements.FailOnTimeout$StatementThread.run(FailOnTimeout.java:74)
Caused by: org.apache.hadoop.yarn.exceptions.YarnException: Cannot perform RE_INIT on [container_1502735389852_0001_01_000001]. Current state is [REINITIALIZING, isReInitializing=true].
	at org.apache.hadoop.yarn.server.nodemanager.containermanager.ContainerManagerImpl.preReInitializeOrLocalizeCheck(ContainerManagerImpl.java:1772)
	at org.apache.hadoop.yarn.server.nodemanager.containermanager.ContainerManagerImpl.reInitializeContainer(ContainerManagerImpl.java:1697)
	at org.apache.hadoop.yarn.server.nodemanager.containermanager.ContainerManagerImpl.reInitializeContainer(ContainerManagerImpl.java:1668)
	at org.apache.hadoop.yarn.api.impl.pb.service.ContainerManagementProtocolPBServiceImpl.reInitializeContainer(ContainerManagementProtocolPBServiceImpl.java:214)
	at org.apache.hadoop.yarn.proto.ContainerManagementProtocol$ContainerManagementProtocolService$2.callBlockingMethod(ContainerManagementProtocol.java:237)
	at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:523)
	at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:991)
	at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:869)
	at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:815)
	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:1962)
	at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2675)

	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.instantiateYarnException(RPCUtil.java:75)
	at org.apache.hadoop.yarn.ipc.RPCUtil.unwrapAndThrowException(RPCUtil.java:116)
	at org.apache.hadoop.yarn.api.impl.pb.client.ContainerManagementProtocolPBClientImpl.reInitializeContainer(ContainerManagementProtocolPBClientImpl.java:237)
	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$Call.invokeOnce(RetryInvocationHandler.java:95)
	at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:359)
	at com.sun.proxy.$Proxy93.reInitializeContainer(Unknown Source)
	at org.apache.hadoop.yarn.client.api.impl.NMClientImpl.reInitializeContainer(NMClientImpl.java:322)
	at org.apache.hadoop.yarn.client.api.impl.TestNMClient.testReInitializeContainer(TestNMClient.java:561)
	... 11 more
Caused by: org.apache.hadoop.ipc.RemoteException(org.apache.hadoop.yarn.exceptions.YarnException): Cannot perform RE_INIT on [container_1502735389852_0001_01_000001]. Current state is [REINITIALIZING, isReInitializing=true].
	at org.apache.hadoop.yarn.server.nodemanager.containermanager.ContainerManagerImpl.preReInitializeOrLocalizeCheck(ContainerManagerImpl.java:1772)
	at org.apache.hadoop.yarn.server.nodemanager.containermanager.ContainerManagerImpl.reInitializeContainer(ContainerManagerImpl.java:1697)
	at org.apache.hadoop.yarn.server.nodemanager.containermanager.ContainerManagerImpl.reInitializeContainer(ContainerManagerImpl.java:1668)
	at org.apache.hadoop.yarn.api.impl.pb.service.ContainerManagementProtocolPBServiceImpl.reInitializeContainer(ContainerManagementProtocolPBServiceImpl.java:214)
	at org.apache.hadoop.yarn.proto.ContainerManagementProtocol$ContainerManagementProtocolService$2.callBlockingMethod(ContainerManagementProtocol.java:237)
	at org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:523)
	at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:991)
	at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:869)
	at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:815)
	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:1962)
	at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2675)

	at org.apache.hadoop.ipc.Client.getRpcResponse(Client.java:1490)
	at org.apache.hadoop.ipc.Client.call(Client.java:1436)
	at org.apache.hadoop.ipc.Client.call(Client.java:1346)
	at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:228)
	at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:116)
	at com.sun.proxy.$Proxy92.reInitializeContainer(Unknown Source)
	at org.apache.hadoop.yarn.api.impl.pb.client.ContainerManagementProtocolPBClientImpl.reInitializeContainer(ContainerManagementProtocolPBClientImpl.java:235)
	... 23 more