Uploaded image for project: 'Spark'
  1. Spark
  2. SPARK-4366 Aggregation Improvement
  3. SPARK-10100

Eliminate hash table lookup if there is no grouping key in aggregation.

    XMLWordPrintableJSON

Details

    • Sub-task
    • Status: Resolved
    • Major
    • Resolution: Fixed
    • 1.5.0
    • 1.5.0
    • SQL
    • None

    Description

      Update: The title of this jira has been changed to "Eliminate hash table lookup if there is no grouping key in aggregation.". For the Max and Min expressions, we can revisit them later if we find a better way to improve the performance and open a new jira.

      The original title of this JIRA is "AggregateFunction2's Max is slower than AggregateExpression1's MaxFunction". Below is the original description:
      Looks like Max (probably Min) implemented based on AggregateFunction2 is slower than the old MaxFunction.

      Attachments

        1. SPARK-10100.perf.test.scala
          1 kB
          Herman van Hövell

        Activity

          People

            rxin Reynold Xin
            yhuai Yin Huai
            Votes:
            0 Vote for this issue
            Watchers:
            3 Start watching this issue

            Dates

              Created:
              Updated:
              Resolved: