Uploaded image for project: 'Hadoop Common'
  1. Hadoop Common
  2. HADOOP-4565

MultiFileInputSplit can use data locality information to create splits

    XMLWordPrintableJSON

Details

    • Improvement
    • Status: Closed
    • Major
    • Resolution: Fixed
    • None
    • 0.20.0
    • None
    • None
    • Reviewed
    • Improved MultiFileInputFormat so that multiple blocks from the same node or same rack can be combined into a single split.

    Description

      The MultiFileInputFormat takes a set of paths and creates splits based on file sizes. Each splits contains a few files an each split are roughly equal in size. It would be efficient if we can extend this InputFormat to create splits such each all the blocks in one split and either node-local or rack-local.

      Attachments

        1. TestCombine.txt
          21 kB
          Dhruba Borthakur
        2. CombineMultiFile9.patch
          49 kB
          Dhruba Borthakur
        3. CombineMultiFile8.patch
          47 kB
          Dhruba Borthakur
        4. CombineMultiFile7.patch
          42 kB
          Dhruba Borthakur
        5. CombineMultiFile5.patch
          39 kB
          Dhruba Borthakur
        6. CombineMultiFile4.patch
          36 kB
          Dhruba Borthakur
        7. CombineMultiFile3.patch
          35 kB
          Dhruba Borthakur
        8. CombineMultiFile2.patch
          37 kB
          Dhruba Borthakur
        9. CombineMultiFile.patch
          19 kB
          Dhruba Borthakur

        Issue Links

          blocks

          Improvement - An improvement or enhancement to an existing feature or task. HIVE-74 Hive can use CombineFileInputFormat for when the input are many small files

          • Major - Major loss of function.
          • Closed
          duplicates

          Bug - A problem which impairs or prevents the functions of the product. HADOOP-2560 Processing multiple input splits per mapper task

          • Major - Major loss of function.
          • Resolved
          is blocked by

          Bug - A problem which impairs or prevents the functions of the product. HADOOP-3293 When an input split spans cross block boundary, the split location should be the host having most of bytes on it.

          • Major - Major loss of function.
          • Closed

          Improvement - An improvement or enhancement to an existing feature or task. HADOOP-4567 GetFileBlockLocations should return the NetworkTopology information of the machines that hosts those blocks

          • Major - Major loss of function.
          • Closed
          is depended upon by

          New Feature - A new feature of the product, which has yet to be developed. MAPREDUCE-214 Concrete implementation of MultiFileInputFormat

          • Major - Major loss of function.
          • Open

          Activity

            People

              dhruba Dhruba Borthakur
              dhruba Dhruba Borthakur
              Votes:
              0 Vote for this issue
              Watchers:
              7 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: