Gour Saha created YARN-8367:
-------------------------------
Summary: 2 components, one with placement constraint and one
without causes NPE in SingleConstraintAppPlacementAllocator
Key: YARN-8367
URL: https://issues.apache.org/jira/browse/YARN-8367
Project: Hadoop YARN
Issue Type: Bug
Components: scheduler
Affects Versions: 3.1.0
Reporter: Gour Saha
While testing the fix for YARN-8350, [~billie.rinaldi] encountered this NPE in
AM log. Filling this on her behalf -
{noformat}
2018-05-25 21:11:54,006 [AMRM Heartbeater thread] ERROR
impl.AMRMClientAsyncImpl - Exception on heartbeat
java.lang.NullPointerException: java.lang.NullPointerException
at
org.apache.hadoop.yarn.server.resourcemanager.scheduler.placement.SingleConstraintAppPlacementAllocator.validateAndSetSchedulingRequest(SingleConstraintAppPlacementAllocator.java:245)
at
org.apache.hadoop.yarn.server.resourcemanager.scheduler.placement.SingleConstraintAppPlacementAllocator.internalUpdatePendingAsk(SingleConstraintAppPlacementAllocator.java:193)
at
org.apache.hadoop.yarn.server.resourcemanager.scheduler.placement.SingleConstraintAppPlacementAllocator.updatePendingAsk(SingleConstraintAppPlacementAllocator.java:207)
at
org.apache.hadoop.yarn.server.resourcemanager.scheduler.AppSchedulingInfo.addSchedulingRequests(AppSchedulingInfo.java:269)
at
org.apache.hadoop.yarn.server.resourcemanager.scheduler.AppSchedulingInfo.updateSchedulingRequests(AppSchedulingInfo.java:240)
at
org.apache.hadoop.yarn.server.resourcemanager.scheduler.SchedulerApplicationAttempt.updateSchedulingRequests(SchedulerApplicationAttempt.java:469)
at
org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler.allocate(CapacityScheduler.java:1154)
at
org.apache.hadoop.yarn.server.resourcemanager.DefaultAMSProcessor.allocate(DefaultAMSProcessor.java:278)
at
org.apache.hadoop.yarn.server.resourcemanager.scheduler.constraint.processor.SchedulerPlacementProcessor.allocate(SchedulerPlacementProcessor.java:53)
at
org.apache.hadoop.yarn.server.resourcemanager.AMSProcessingChain.allocate(AMSProcessingChain.java:92)
at
org.apache.hadoop.yarn.server.resourcemanager.ApplicationMasterService.allocate(ApplicationMasterService.java:433)
at
org.apache.hadoop.yarn.api.impl.pb.service.ApplicationMasterProtocolPBServiceImpl.allocate(ApplicationMasterProtocolPBServiceImpl.java:60)
at
org.apache.hadoop.yarn.proto.ApplicationMasterProtocol$ApplicationMasterProtocolService$2.callBlockingMethod(ApplicationMasterProtocol.java:99)
at
org.apache.hadoop.ipc.ProtobufRpcEngine$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:1682)
at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2678)
at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
at
sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
at
sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
at java.lang.reflect.Constructor.newInstance(Constructor.java:423)
at
org.apache.hadoop.yarn.ipc.RPCUtil.instantiateException(RPCUtil.java:53)
at
org.apache.hadoop.yarn.ipc.RPCUtil.instantiateRuntimeException(RPCUtil.java:85)
at
org.apache.hadoop.yarn.ipc.RPCUtil.unwrapAndThrowException(RPCUtil.java:122)
at
org.apache.hadoop.yarn.api.impl.pb.client.ApplicationMasterProtocolPBClientImpl.allocate(ApplicationMasterProtocolPBClientImpl.java:79)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at
org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:422)
at
org.apache.hadoop.io.retry.RetryInvocationHandler$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.$Proxy48.allocate(Unknown Source)
at
org.apache.hadoop.yarn.client.api.impl.AMRMClientImpl.allocate(AMRMClientImpl.java:313)
at
org.apache.hadoop.yarn.client.api.async.impl.AMRMClientAsyncImpl$HeartbeatThread.run(AMRMClientAsyncImpl.java:305)
Caused by:
org.apache.hadoop.ipc.RemoteException(java.lang.NullPointerException):
java.lang.NullPointerException
at
org.apache.hadoop.yarn.server.resourcemanager.scheduler.placement.SingleConstraintAppPlacementAllocator.validateAndSetSchedulingRequest(SingleConstraintAppPlacementAllocator.java:245)
at
org.apache.hadoop.yarn.server.resourcemanager.scheduler.placement.SingleConstraintAppPlacementAllocator.internalUpdatePendingAsk(SingleConstraintAppPlacementAllocator.java:193)
at
org.apache.hadoop.yarn.server.resourcemanager.scheduler.placement.SingleConstraintAppPlacementAllocator.updatePendingAsk(SingleConstraintAppPlacementAllocator.java:207)
at
org.apache.hadoop.yarn.server.resourcemanager.scheduler.AppSchedulingInfo.addSchedulingRequests(AppSchedulingInfo.java:269)
at
org.apache.hadoop.yarn.server.resourcemanager.scheduler.AppSchedulingInfo.updateSchedulingRequests(AppSchedulingInfo.java:240)
at
org.apache.hadoop.yarn.server.resourcemanager.scheduler.SchedulerApplicationAttempt.updateSchedulingRequests(SchedulerApplicationAttempt.java:469)
at
org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler.allocate(CapacityScheduler.java:1154)
at
org.apache.hadoop.yarn.server.resourcemanager.DefaultAMSProcessor.allocate(DefaultAMSProcessor.java:278)
at
org.apache.hadoop.yarn.server.resourcemanager.scheduler.constraint.processor.SchedulerPlacementProcessor.allocate(SchedulerPlacementProcessor.java:53)
at
org.apache.hadoop.yarn.server.resourcemanager.AMSProcessingChain.allocate(AMSProcessingChain.java:92)
at
org.apache.hadoop.yarn.server.resourcemanager.ApplicationMasterService.allocate(ApplicationMasterService.java:433)
at
org.apache.hadoop.yarn.api.impl.pb.service.ApplicationMasterProtocolPBServiceImpl.allocate(ApplicationMasterProtocolPBServiceImpl.java:60)
at
org.apache.hadoop.yarn.proto.ApplicationMasterProtocol$ApplicationMasterProtocolService$2.callBlockingMethod(ApplicationMasterProtocol.java:99)
at
org.apache.hadoop.ipc.ProtobufRpcEngine$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:1682)
at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2678)
at org.apache.hadoop.ipc.Client.getRpcResponse(Client.java:1491)
at org.apache.hadoop.ipc.Client.call(Client.java:1437)
at org.apache.hadoop.ipc.Client.call(Client.java:1347)
at
org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:228)
at
org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:116)
at com.sun.proxy.$Proxy47.allocate(Unknown Source)
at
org.apache.hadoop.yarn.api.impl.pb.client.ApplicationMasterProtocolPBClientImpl.allocate(ApplicationMasterProtocolPBClientImpl.java:77)
... 12 more
{noformat}
The Yarnfile which can be used to reproduce this problem in a 3.1.0 hadoop
cluster is provided below -
{code:java}
{
"name": "test-aa",
"version": "1",
"components" :
[
{
"name": "comp-a",
"number_of_containers": 3,
"launch_command": "sleep 6000",
"resource": {
"cpus": 1,
"memory": "256"
},
"placement_policy": {
"constraints": [
{
"type": "ANTI_AFFINITY",
"scope": "NODE",
"target_tags": [
"comp-a"
]
}
]
}
},
{
"name": "comp-b",
"number_of_containers": 2,
"launch_command": "sleep 6000",
"resource": {
"cpus": 1,
"memory": "256"
},
"placement_policy": {
"constraints": [
]
}
}
]
}
{code}
The scheduler should support this mixed scenario where some components of an
application have placement constraints whereas some don't.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
