Uploaded image for project: 'Hadoop Common'
  1. Hadoop Common
  2. HADOOP-5883

TaskMemoryMonitorThread might shoot down tasks even if their processes momentarily exceed the requested memory

    XMLWordPrintableJSON

    Details

    • Type: Bug
    • Status: Resolved
    • Priority: Major
    • Resolution: Fixed
    • Affects Version/s: None
    • Fix Version/s: 0.20.1
    • Component/s: None
    • Labels:
      None
    • Hadoop Flags:
      Reviewed

      Description

      Currently the TaskMemoryMonitorThread kills tasks as soon as it detects they are consuming more memory than the max value specified. There are valid cases (see HADOOP-5059) where if a program is executed from the task, it might momentarily occupy twice the amount of memory for a short time. Ideally the monitoring thread should handle this case.

        Attachments

        1. HADOOP-5883.patch
          29 kB
          Hemanth Yamijala
        2. HADOOP-5883.patch
          29 kB
          Hemanth Yamijala
        3. HADOOP-5883.patch
          28 kB
          Hemanth Yamijala
        4. HADOOP-5883-20.patch
          29 kB
          Hemanth Yamijala
        5. HADOOP-5883-20.patch
          29 kB
          Hemanth Yamijala

          Issue Links

          is blocked by

          Bug - A problem which impairs or prevents the functions of the product. HADOOP-5881 Simplify configuration related to task-memory-monitoring and memory-based scheduling

          • Major - Major loss of function.
          • Resolved

            Activity

              People

              • Assignee:
                yhemanth Hemanth Yamijala
                Reporter:
                yhemanth Hemanth Yamijala
              • Votes:
                0 Vote for this issue
                Watchers:
                7 Start watching this issue

                Dates

                • Created:
                  Updated:
                  Resolved: