Uploaded image for project: 'Hadoop Map/Reduce'
  1. Hadoop Map/Reduce
  2. MAPREDUCE-3932

MR tasks failing and crashing the AM when available-resources/headRoom becomes zero

    XMLWordPrintableJSON

Details

    • Bug
    • Status: Closed
    • Critical
    • Resolution: Fixed
    • 0.23.0
    • 0.23.3, 2.0.2-alpha
    • mr-am, mrv2
    • None
    • Reviewed

    Description

      karams reported this offline. One reduce task gets preempted because of zero headRoom and crashes the AM.

      2012-02-23 11:30:15,956 INFO [RMCommunicator Allocator] org.apache.hadoop.mapreduce.v2.app.rm.RMContainerAllocator: After Scheduling: PendingReduces:377 ScheduledMaps:6 ScheduledReduces:23 AssignedMaps:0 AssignedReduces:0 completedMaps:4 completedReduces:0 containersAllocated:4 containersReleased:0 hostLocalAssigned:0 rackLocalAssigned:4 availableResources(headroom):memory: 44544
      2012-02-23 11:30:16,959 INFO [RMCommunicator Allocator] org.apache.hadoop.mapreduce.v2.app.rm.RMContainerAllocator: Before Scheduling: PendingReduces:377 ScheduledMaps:6 ScheduledReduces:23 AssignedMaps:0 AssignedReduces:0 completedMaps:4 completedReduces:0 containersAllocated:4 containersReleased:0 hostLocalAssigned:0 rackLocalAssigned:4 availableResources(headroom):memory: 44544
      2012-02-23 11:30:16,965 INFO [RMCommunicator Allocator] org.apache.hadoop.mapreduce.v2.app.rm.RMContainerAllocator: After Scheduling: PendingReduces:377 ScheduledMaps:6 ScheduledReduces:23 AssignedMaps:0 AssignedReduces:0 completedMaps:4 completedReduces:0 containersAllocated:4 containersReleased:0 hostLocalAssigned:0 rackLocalAssigned:4 availableResources(headroom):memory: 0
      2012-02-23 11:30:16,965 INFO [RMCommunicator Allocator] org.apache.hadoop.mapreduce.v2.app.rm.RMContainerAllocator: Before Assign: PendingReduces:377 ScheduledMaps:6 ScheduledReduces:23 AssignedMaps:0 AssignedReduces:0 completedMaps:4 completedReduces:0 containersAllocated:4 containersReleased:0 hostLocalAssigned:0 rackLocalAssigned:4 availableResources(headroom):memory: 0
      2012-02-23 11:30:16,965 INFO [RMCommunicator Allocator] org.apache.hadoop.mapreduce.v2.app.rm.RMContainerAllocator: Got allocated containers 3
      2012-02-23 11:30:16,965 INFO [RMCommunicator Allocator] org.apache.hadoop.mapreduce.v2.app.rm.RMContainerAllocator: Assigned to reduce
      2012-02-23 11:30:16,966 INFO [RMCommunicator Allocator] org.apache.hadoop.mapreduce.v2.app.rm.RMContainerAllocator: Assigned container container_1329995034628_0983_01_000006 to attempt_1329995034628_0983_r_000000_0
      2012-02-23 11:30:16,966 INFO [RMCommunicator Allocator] org.apache.hadoop.mapreduce.v2.app.rm.RMContainerAllocator: Assigned to reduce
      2012-02-23 11:30:16,966 INFO [RMCommunicator Allocator] org.apache.hadoop.mapreduce.v2.app.rm.RMContainerAllocator: Assigned container container_1329995034628_0983_01_000007 to attempt_1329995034628_0983_r_000001_0
      2012-02-23 11:30:16,966 INFO [RMCommunicator Allocator] org.apache.hadoop.mapreduce.v2.app.rm.RMContainerAllocator: Assigned to reduce
      2012-02-23 11:30:16,966 INFO [RMCommunicator Allocator] org.apache.hadoop.mapreduce.v2.app.rm.RMContainerAllocator: Assigned container container_1329995034628_0983_01_000008 to attempt_1329995034628_0983_r_000002_0
      2012-02-23 11:30:16,966 INFO [RMCommunicator Allocator] org.apache.hadoop.mapreduce.v2.app.rm.RMContainerAllocator: After Assign: PendingReduces:377 ScheduledMaps:6 ScheduledReduces:20 AssignedMaps:0 AssignedReduces:3 completedMaps:4 completedReduces:0 containersAllocated:7 containersReleased:0 hostLocalAssigned:0 rackLocalAssigned:4 availableResources(headroom):memory: 0
      2012-02-23 11:30:16,966 INFO [RMCommunicator Allocator] org.apache.hadoop.mapreduce.v2.app.rm.RMContainerAllocator: Ramping down all scheduled reduces:20
      2012-02-23 11:30:16,966 INFO [RMCommunicator Allocator] org.apache.hadoop.mapreduce.v2.app.rm.RMContainerAllocator: Going to preempt 2
      2012-02-23 11:30:16,966 INFO [RMCommunicator Allocator] org.apache.hadoop.mapreduce.v2.app.rm.RMContainerAllocator: Preempting attempt_1329995034628_0983_r_000002_0
      2012-02-23 11:30:16,966 INFO [RMCommunicator Allocator] org.apache.hadoop.mapreduce.v2.app.rm.RMContainerAllocator: Preempting attempt_1329995034628_0983_r_000001_0
      2012-02-23 11:30:16,966 INFO [RMCommunicator Allocator] org.apache.hadoop.mapreduce.v2.app.rm.RMContainerAllocator: Recalculating schedule...
      2012-02-23 11:30:16,966 INFO [RMCommunicator Allocator] org.apache.hadoop.mapreduce.v2.app.rm.RMContainerAllocator: completedMapPercent 0.4 totalMemLimit:4608 finalMapMemLimit:2765 finalReduceMemLimit:1843 netScheduledMapMem:9216 netScheduledReduceMem:4608
      2012-02-23 11:30:16,966 INFO [RMCommunicator Allocator] org.apache.hadoop.mapreduce.v2.app.rm.RMContainerAllocator: Ramping down 0
      2012-02-23 11:30:16,968 INFO [AsyncDispatcher event handler] org.apache.hadoop.yarn.util.RackResolver: Resolved $host6 to /$rack6
      2012-02-23 11:30:16,976 INFO [AsyncDispatcher event handler] org.apache.hadoop.mapreduce.v2.app.job.impl.TaskAttemptImpl: attempt_1329995034628_0983_r_000000_0 TaskAttempt Transitioned from UNASSIGNED to ASSIGNED
      2012-02-23 11:30:16,976 INFO [AsyncDispatcher event handler] org.apache.hadoop.yarn.util.RackResolver: Resolved $host1 to /$rack1
      2012-02-23 11:30:16,977 INFO [AsyncDispatcher event handler] org.apache.hadoop.mapreduce.v2.app.job.impl.TaskAttemptImpl: attempt_1329995034628_0983_r_000001_0 TaskAttempt Transitioned from UNASSIGNED to ASSIGNED
      2012-02-23 11:30:16,981 INFO [AsyncDispatcher event handler] org.apache.hadoop.yarn.util.RackResolver: Resolved $host9 to /$rack9
      2012-02-23 11:30:16,982 INFO [AsyncDispatcher event handler] org.apache.hadoop.mapreduce.v2.app.job.impl.TaskAttemptImpl: attempt_1329995034628_0983_r_000002_0 TaskAttempt Transitioned from UNASSIGNED to ASSIGNED
      2012-02-23 11:30:16,982 INFO [AsyncDispatcher event handler] org.apache.hadoop.mapreduce.v2.app.job.impl.TaskAttemptImpl: attempt_1329995034628_0983_r_000002_0 TaskAttempt Transitioned from ASSIGNED to KILL_CONTAINER_CLEANUP
      2012-02-23 11:30:16,983 INFO [AsyncDispatcher event handler] org.apache.hadoop.mapreduce.v2.app.job.impl.TaskAttemptImpl: attempt_1329995034628_0983_r_000001_0 TaskAttempt Transitioned from ASSIGNED to KILL_CONTAINER_CLEANUP
      2012-02-23 11:30:16,983 INFO [ContainerLauncher #8] org.apache.hadoop.mapreduce.v2.app.launcher.ContainerLauncherImpl: Processing the event EventType: CONTAINER_REMOTE_LAUNCH for taskAttempt attempt_1329995034628_0983_r_000000_0
      2012-02-23 11:30:16,983 INFO [ContainerLauncher #0] org.apache.hadoop.mapreduce.v2.app.launcher.ContainerLauncherImpl: Processing the event EventType: CONTAINER_REMOTE_LAUNCH for taskAttempt attempt_1329995034628_0983_r_000002_0
      2012-02-23 11:30:16,983 INFO [ContainerLauncher #8] org.apache.hadoop.mapreduce.v2.app.launcher.ContainerLauncherImpl: Launching attempt_1329995034628_0983_r_000000_0
      2012-02-23 11:30:16,984 INFO [ContainerLauncher #0] org.apache.hadoop.mapreduce.v2.app.launcher.ContainerLauncherImpl: Launching attempt_1329995034628_0983_r_000002_0
      2012-02-23 11:30:16,984 INFO [ContainerLauncher #1] org.apache.hadoop.mapreduce.v2.app.launcher.ContainerLauncherImpl: Processing the event EventType: CONTAINER_REMOTE_CLEANUP for taskAttempt attempt_1329995034628_0983_r_000002_0
      2012-02-23 11:30:16,984 INFO [ContainerLauncher #3] org.apache.hadoop.mapreduce.v2.app.launcher.ContainerLauncherImpl: Processing the event EventType: CONTAINER_REMOTE_CLEANUP for taskAttempt attempt_1329995034628_0983_r_000001_0
      2012-02-23 11:30:16,987 INFO [ContainerLauncher #9] org.apache.hadoop.mapreduce.v2.app.launcher.ContainerLauncherImpl: Processing the event EventType: CONTAINER_REMOTE_LAUNCH for taskAttempt attempt_1329995034628_0983_r_000001_0
      2012-02-23 11:30:16,988 INFO [ContainerLauncher #9] org.apache.hadoop.mapreduce.v2.app.launcher.ContainerLauncherImpl: Launching attempt_1329995034628_0983_r_000001_0
      2012-02-23 11:30:16,988 ERROR [ContainerLauncher #9] org.apache.hadoop.mapreduce.v2.app.launcher.ContainerLauncherImpl: Container was killed before it was launched
      2012-02-23 11:30:17,061 INFO [ContainerLauncher #8] org.apache.hadoop.mapreduce.v2.app.launcher.ContainerLauncherImpl: Shuffle port returned by ContainerManager for attempt_1329995034628_0983_r_000000_0 : 53990
      2012-02-23 11:30:17,077 INFO [AsyncDispatcher event handler] org.apache.hadoop.mapreduce.v2.app.job.impl.TaskAttemptImpl: attempt_1329995034628_0983_r_000001_0 TaskAttempt Transitioned from KILL_CONTAINER_CLEANUP to KILL_TASK_CLEANUP
      2012-02-23 11:30:17,077 INFO [AsyncDispatcher event handler] org.apache.hadoop.mapreduce.v2.app.job.impl.TaskAttemptImpl: Diagnostics report from attempt_1329995034628_0983_r_000001_0: Container was killed before it was launched
      2012-02-23 11:30:17,078 ERROR [AsyncDispatcher event handler] org.apache.hadoop.mapreduce.v2.app.job.impl.TaskAttemptImpl: Can't handle this event at current state for attempt_1329995034628_0983_r_000001_0
      org.apache.hadoop.yarn.state.InvalidStateTransitonException: Invalid event: TA_CONTAINER_LAUNCH_FAILED at KILL_TASK_CLEANUP
      	at org.apache.hadoop.yarn.state.StateMachineFactory.doTransition(StateMachineFactory.java:301)
      	at org.apache.hadoop.yarn.state.StateMachineFactory.access$300(StateMachineFactory.java:43)
      	at org.apache.hadoop.yarn.state.StateMachineFactory$InternalStateMachine.doTransition(StateMachineFactory.java:443)
      	at org.apache.hadoop.mapreduce.v2.app.job.impl.TaskAttemptImpl.handle(TaskAttemptImpl.java:926)
      	at org.apache.hadoop.mapreduce.v2.app.job.impl.TaskAttemptImpl.handle(TaskAttemptImpl.java:135)
      	at org.apache.hadoop.mapreduce.v2.app.MRAppMaster$TaskAttemptEventDispatcher.handle(MRAppMaster.java:870)
      	at org.apache.hadoop.mapreduce.v2.app.MRAppMaster$TaskAttemptEventDispatcher.handle(MRAppMaster.java:862)
      	at org.apache.hadoop.yarn.event.AsyncDispatcher.dispatch(AsyncDispatcher.java:125)
      	at org.apache.hadoop.yarn.event.AsyncDispatcher$1.run(AsyncDispatcher.java:82)
      	at java.lang.Thread.run(Thread.java:619)
      2012-02-23 11:30:17,080 INFO [AsyncDispatcher event handler] org.apache.hadoop.mapreduce.v2.app.job.impl.TaskAttemptImpl: TaskAttempt: [attempt_1329995034628_0983_r_000000_0] using containerId: [container_1329995034628_0983_01_000006 on NM: [$host6:51529]
      2012-02-23 11:30:17,081 INFO [AsyncDispatcher event handler] org.apache.hadoop.mapreduce.v2.app.job.impl.TaskAttemptImpl: attempt_1329995034628_0983_r_000000_0 TaskAttempt Transitioned from ASSIGNED to RUNNING
      2012-02-23 11:30:17,207 INFO [ContainerLauncher #0] org.apache.hadoop.mapreduce.v2.app.launcher.ContainerLauncherImpl: Shuffle port returned by ContainerManager for attempt_1329995034628_0983_r_000002_0 : 47960
      2012-02-23 11:30:17,207 INFO [ContainerLauncher #1] org.apache.hadoop.mapreduce.v2.app.launcher.ContainerLauncherImpl: KILLING attempt_1329995034628_0983_r_000002_0
      2012-02-23 11:30:17,215 INFO [AsyncDispatcher event handler] org.apache.hadoop.mapreduce.v2.app.job.impl.JobImpl: job_1329995034628_0983Job Transitioned from RUNNING to ERROR
      2012-02-23 11:30:17,216 ERROR [AsyncDispatcher event handler] org.apache.hadoop.mapreduce.v2.app.job.impl.JobImpl: Can't handle this event at current state
      org.apache.hadoop.yarn.state.InvalidStateTransitonException: Invalid event: JOB_COUNTER_UPDATE at ERROR
      	at org.apache.hadoop.yarn.state.StateMachineFactory.doTransition(StateMachineFactory.java:301)
      	at org.apache.hadoop.yarn.state.StateMachineFactory.access$300(StateMachineFactory.java:43)
      	at org.apache.hadoop.yarn.state.StateMachineFactory$InternalStateMachine.doTransition(StateMachineFactory.java:443)
      	at org.apache.hadoop.mapreduce.v2.app.job.impl.JobImpl.handle(JobImpl.java:657)
      	at org.apache.hadoop.mapreduce.v2.app.job.impl.JobImpl.handle(JobImpl.java:111)
      	at org.apache.hadoop.mapreduce.v2.app.MRAppMaster$JobEventDispatcher.handle(MRAppMaster.java:848)
      	at org.apache.hadoop.mapreduce.v2.app.MRAppMaster$JobEventDispatcher.handle(MRAppMaster.java:844)
      	at org.apache.hadoop.yarn.event.AsyncDispatcher.dispatch(AsyncDispatcher.java:125)
      	at org.apache.hadoop.yarn.event.AsyncDispatcher$1.run(AsyncDispatcher.java:82)
      	at java.lang.Thread.run(Thread.java:619)
      
      

      Attachments

        1. MR-3932.txt
          13 kB
          Robert Joseph Evans
        2. MR-3932.txt
          13 kB
          Robert Joseph Evans

        Issue Links

          Activity

            People

              revans2 Robert Joseph Evans
              vinodkv Vinod Kumar Vavilapalli
              Votes:
              0 Vote for this issue
              Watchers:
              6 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: