Uploaded image for project: 'Hadoop Common'
  1. Hadoop Common
  2. HADOOP-318

Progress in writing a DFS file does not count towards Job progress and can make the task timeout

    XMLWordPrintableJSON

Details

    • Bug
    • Status: Closed
    • Major
    • Resolution: Fixed
    • 0.3.2
    • 0.4.0
    • None
    • None
    • all, but especially on big busy clusters

    Description

      When a task writes to DFS file, depending on how busy the cluster is, it can timeout after 10 minutes by default, because the progress towards writing a DFS file does not count as progress of the task. The solution (patch is forthcoming) is to provide a way to callback reporter to report task progress from DFSOutputStream.

      Attachments

        1. hadoop-latency-latest.patch
          49 kB
          Milind Barve

        Activity

          People

            milindb Milind Barve
            milindb Milind Barve
            Votes:
            0 Vote for this issue
            Watchers:
            0 Start watching this issue

            Dates

              Created:
              Updated:
              Resolved: