Uploaded image for project: 'Hive'
  1. Hive
  2. HIVE-12492

MapJoin: 4 million unique integers seems to be a probe plateau

    XMLWordPrintableJSON

Details

    • Improvement
    • Status: Closed
    • Major
    • Resolution: Fixed
    • 1.2.1, 1.3.0, 2.0.0
    • 2.2.0
    • Query Planning

    Description

      After 4 million keys, the map-join implementation seems to suffer from a performance degradation.

      The hashtable build & probe time makes this very inefficient, even if the data is very compact (i.e 2 ints).

      Falling back onto the shuffle join or bucket map-join is useful after 2^22 items.

      (Note: this fixes a statsutil issue - due to the extra clone() in the column stats path)

      Attachments

        1. HIVE-12492.01.patch
          77 kB
          jcamachorodriguez
        2. HIVE-12492.02.patch
          39 kB
          jcamachorodriguez
        3. HIVE-12492.patch
          32 kB
          jcamachorodriguez

        Issue Links

          Activity

            People

              jcamacho Jesús Camacho Rodríguez
              gopalv Gopal Vijayaraghavan
              Votes:
              0 Vote for this issue
              Watchers:
              4 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: