Uploaded image for project: 'Spark'
  1. Spark
  2. SPARK-2926

Add MR-style (merge-sort) SortShuffleReader for sort-based shuffle

    XMLWordPrintableJSON

Details

    • Improvement
    • Status: Resolved
    • Major
    • Resolution: Incomplete
    • 1.1.0
    • None
    • Shuffle, Spark Core

    Description

      Currently Spark has already integrated sort-based shuffle write, which greatly improve the IO performance and reduce the memory consumption when reducer number is very large. But for the reducer side, it still adopts the implementation of hash-based shuffle reader, which neglects the ordering attributes of map output data in some situations.

      Here we propose a MR style sort-merge like shuffle reader for sort-based shuffle to better improve the performance of sort-based shuffle.

      Working in progress code and performance test report will be posted later when some unit test bugs are fixed.

      Any comments would be greatly appreciated.
      Thanks a lot.

      Attachments

        1. SortBasedShuffleRead.pdf
          56 kB
          Saisai Shao
        2. Spark Shuffle Test Report.pdf
          340 kB
          Saisai Shao
        3. Spark Shuffle Test Report(contd).pdf
          326 kB
          Saisai Shao
        4. SortBasedShuffleReader on Spark 2.x.pdf
          3.52 MB
          Yuanjian Li
        5. Spark Shuffle Test Report on Spark2.x.pdf
          186 kB
          Yuanjian Li

        Issue Links

          Activity

            People

              jerryshao Saisai Shao
              jerryshao Saisai Shao
              Votes:
              7 Vote for this issue
              Watchers:
              75 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: