Uploaded image for project: 'Spark'
  1. Spark
  2. SPARK-451

Ranges of Longs don't get split properly by SparkContext.parallelize

    XMLWordPrintableJSON

Details

    • Bug
    • Status: Resolved
    • Resolution: Fixed
    • None
    • None
    • None

    Description

      We wanted Ranges to be split into smaller Range objects to avoid shipping the integers in them over the network, but Scala 2.9's Long ranges don't get matched as a Range by the ParallelCollection code and thus get converted to arrays, costing a lot of RAM.

      Attachments

        Activity

          People

            Unassigned Unassigned
            matei Matei Alexandru Zaharia
            Votes:
            0 Vote for this issue
            Watchers:
            0 Start watching this issue

            Dates

              Created:
              Updated:
              Resolved: