Uploaded image for project: 'Apache Tez'
  1. Apache Tez
  2. TEZ-3739

Fair CartesianProduct doesn't works well with huge difference in output size

    XMLWordPrintableJSON

Details

    • Bug
    • Status: Closed
    • Major
    • Resolution: Fixed
    • None
    • 0.9.0
    • None
    • None

    Description

      Specifically, the weighted factorization of initial parallelism goes crazy if #record of each side is too different. The formula works in real number, but not in integer.

      Attachments

        1. TEZ-3739.1.patch
          6 kB
          Zhiyuan Yang

        Issue Links

          is broken by

          Sub-task - The sub-task of the issue TEZ-3708 Improve parallelism and auto grouping of unpartitioned cartesian product

          • Major - Major loss of function.
          • Closed

          Activity

            People

              zhiyuany Zhiyuan Yang
              zhiyuany Zhiyuan Yang
              Votes:
              0 Vote for this issue
              Watchers:
              2 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: