Uploaded image for project: 'Spark'
  1. Spark
  2. SPARK-13926

Automatically use Kryo serializer when shuffling RDDs with simple types

Log workAgile BoardRank to TopRank to BottomAttach filesAttach ScreenshotBulk Copy AttachmentsBulk Move AttachmentsVotersWatch issueWatchersCreate sub-taskConvert to sub-taskMoveLinkCloneLabelsUpdate Comment AuthorReplace String in CommentUpdate Comment VisibilityDelete CommentsDelete
    XMLWordPrintableJSON

Details

    • Improvement
    • Status: Resolved
    • Major
    • Resolution: Fixed
    • None
    • 2.0.0
    • Shuffle, Spark Core
    • None

    Description

      Because ClassTags are available when constructing ShuffledRDD we can use them to automatically use Kryo for shuffle serialization when the RDD's types are guaranteed to be compatible with Kryo (e.g. RDDs whose key, value, and/or combiner types are primitives, arrays of primitives, or strings). This is likely to result in a large performance gain for many RDD API workloads.

      Attachments

        Activity

          This comment will be Viewable by All Users Viewable by All Users
          Cancel

          People

            joshrosen Josh Rosen Assign to me
            joshrosen Josh Rosen
            Votes:
            0 Vote for this issue
            Watchers:
            3 Start watching this issue

            Dates

              Created:
              Updated:
              Resolved:

              Slack

                Issue deployment