Details

    • Type: Task
    • Status: Closed
    • Priority: Minor
    • Resolution: Fixed
    • Affects Version/s: None
    • Fix Version/s: 2.1.0-beta
    • Component/s: task
    • Labels:
      None
    • Hadoop Flags:
      Reviewed

      Description

      In the current implementation, Fetcher instances usually exit gracefully when the shuffle succeeds. When it fails, threads are interrupted, but may continue running harmlessly until the JVM shuts down.

      However, to generate consistent checkpoints, these threads should exit cleanly to quiesce the state of the shuffle.

        Attachments

        1. M5194.patch
          28 kB
          Chris Douglas
        2. M5194-1.patch
          25 kB
          Chris Douglas
        3. M5194-2.patch
          30 kB
          Chris Douglas

          Issue Links

            Activity

              People

              • Assignee:
                chris.douglas Chris Douglas
                Reporter:
                chris.douglas Chris Douglas
              • Votes:
                0 Vote for this issue
                Watchers:
                6 Start watching this issue

                Dates

                • Created:
                  Updated:
                  Resolved: