Uploaded image for project: 'Spark'
  1. Spark
  2. SPARK-12948

Consider reducing size of broadcasts in OrcRelation

    XMLWordPrintableJSON

Details

    • Improvement
    • Status: Resolved
    • Major
    • Resolution: Won't Fix
    • None
    • None
    • SQL
    • None

    Description

      Size of broadcasted data in OrcRelation was significantly higher when running query with large number of partitions (e.g TPC-DS). Consider reducing the size of the broadcasted data in OrcRelation, as it has an impact on the job runtime.

      Attachments

        1. SPARK-12948.mem.prof.snapshot.png
          338 kB
          Rajesh Balamohan
        2. SPARK-12948_cpuProf.png
          216 kB
          Rajesh Balamohan

        Activity

          People

            Unassigned Unassigned
            rajesh.balamohan Rajesh Balamohan
            Votes:
            0 Vote for this issue
            Watchers:
            3 Start watching this issue

            Dates

              Created:
              Updated:
              Resolved: