Uploaded image for project: 'Hadoop Map/Reduce'
  1. Hadoop Map/Reduce
  2. MAPREDUCE-2187

map tasks timeout during sorting

    XMLWordPrintableJSON

Details

    • Bug
    • Status: Closed
    • Major
    • Resolution: Fixed
    • 0.20.2, 0.20.205.0
    • 0.20.205.0
    • None
    • None
    • I just committed this. Thanks Anupam!

    Description

      During the execution of a large job, the map tasks timeout:

      INFO mapred.JobClient: Task Id : attempt_201010290414_60974_m_000057_1, Status : FAILED
      Task attempt_201010290414_60974_m_000057_1 failed to report status for 609 seconds. Killing!
      

      The bug is in the fact that the mapper has already finished, and, according to the logs, the timeout occurs during the merge sort phase.
      The intermediate data generated by the map task is quite large. So I think this is the problem.

      The logs show that the merge-sort was running for 10 minutes when the task was killed.
      I think the mapred.Merger should call Reporter.progress() somewhere.

      Attachments

        1. MAPREDUCE-2187-20-security.patch
          6 kB
          Anupam Seth
        2. MAPREDUCE-2187-20-security-v2.patch
          7 kB
          Anupam Seth
        3. MAPREDUCE-2187-22.patch
          6 kB
          Anupam Seth
        4. MAPREDUCE-2187-branch-MR-279.patch
          7 kB
          Anupam Seth
        5. MAPREDUCE-2187-MR-279-v2.patch
          8 kB
          Anupam Seth
        6. MAPREDUCE-2187-trunk.patch
          6 kB
          Anupam Seth
        7. MAPREDUCE-2187-trunk-v2.patch
          7 kB
          Anupam Seth
        8. MAPREDUCE-2187-trunk-v3.patch
          8 kB
          Anupam Seth

        Issue Links

          Activity

            People

              anupamseth Anupam Seth
              azaroth Gianmarco De Francisci Morales
              Votes:
              1 Vote for this issue
              Watchers:
              9 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: