Hadoop Map/Reduce
  1. Hadoop Map/Reduce
  2. MAPREDUCE-4587

Support fetch by key boundaries for memcmp types

    Details

    • Type: Improvement Improvement
    • Status: Open
    • Priority: Major Major
    • Resolution: Unresolved
    • Affects Version/s: None
    • Fix Version/s: None
    • Component/s: nodemanager, task
    • Labels:
      None
    • Target Version/s:

      Description

      Intermediate data addressable by key support not only restartable streams, but partitioning after the map output are written. With sampling of map output, a job can implement a total-order and tune the number of reduces around skew. It is possible to implement something similar for non-memcmp types, but it is significantly more complex.

        Issue Links

          Activity

            People

            • Assignee:
              Unassigned
              Reporter:
              Chris Douglas
            • Votes:
              0 Vote for this issue
              Watchers:
              3 Start watching this issue

              Dates

              • Created:
                Updated:

                Development