Uploaded image for project: 'Hadoop Map/Reduce'
  1. Hadoop Map/Reduce
  2. MAPREDUCE-6302

Preempt reducers after a configurable timeout irrespective of headroom

    XMLWordPrintableJSON

Details

    • Bug
    • Status: Closed
    • Critical
    • Resolution: Fixed
    • 2.6.0
    • 2.8.0, 2.7.3, 2.6.5, 3.0.0-alpha1
    • None
    • None

    Description

      I submit a big job, which has 500 maps and 350 reduce, to a queue(fairscheduler) with 300 max cores. When the big mapreduce job is running 100% maps, the 300 reduces have occupied 300 max cores in the queue. And then, a map fails and retry, waiting for a core, while the 300 reduces are waiting for failed map to finish. So a deadlock occur. As a result, the job is blocked, and the later job in the queue cannot run because no available cores in the queue.
      I think there is the similar issue for memory of a queue .

      Attachments

        1. queue_with_max333cores.png
          13 kB
          Shurong Mai
        2. queue_with_max263cores.png
          15 kB
          Shurong Mai
        3. queue_with_max163cores.png
          14 kB
          Shurong Mai
        4. mr-6302-prelim.patch
          8 kB
          Karthik Kambatla
        5. mr-6302-7.patch
          23 kB
          Karthik Kambatla
        6. mr-6302-6.patch
          23 kB
          Karthik Kambatla
        7. mr-6302-5.patch
          23 kB
          Karthik Kambatla
        8. mr-6302-4.patch
          23 kB
          Karthik Kambatla
        9. mr-6302-3.patch
          22 kB
          Karthik Kambatla
        10. mr-6302-2.patch
          22 kB
          Karthik Kambatla
        11. mr-6302-1.patch
          20 kB
          Karthik Kambatla
        12. mr-6302_branch-2.patch
          24 kB
          Karthik Kambatla
        13. MAPREDUCE-6302.branch-2.7.0001.patch
          22 kB
          Wangda Tan
        14. MAPREDUCE-6302.branch-2.6.0001.patch
          22 kB
          Wangda Tan
        15. log.txt
          13 kB
          Benjamin Tortorelli
        16. AM_log_tail100000.txt.gz
          946 kB
          Shurong Mai
        17. AM_log_head100000.txt.gz
          830 kB
          Shurong Mai

        Issue Links

          Activity

            People

              kasha Karthik Kambatla
              shurong.mai Shurong Mai
              Votes:
              0 Vote for this issue
              Watchers:
              42 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: