Uploaded image for project: 'Hadoop Common'
  1. Hadoop Common
  2. HADOOP-14407

DistCp - Introduce a configurable copy buffer size

    XMLWordPrintableJSON

Details

    • Improvement
    • Status: Resolved
    • Major
    • Resolution: Fixed
    • 2.9.0
    • 2.9.0, 3.0.0-alpha4
    • tools/distcp
    • None
    • Reviewed
    • The copy buffer size can be configured via the new parameter <copybuffersize>. By default the <copybuffersize> is set to 8KB.

    Description

      Currently, the RetriableFileCopyCommand has a fixed copy buffer size of just 8KB. We have noticed in our performance tests that with bigger buffer sizes we saw upto ~3x performance boost. Hence, making the copy buffer size a configurable setting via the new parameter <copybuffersize>.

      Attachments

        1. HADOOP-14407.001.patch
          11 kB
          Omkar Aradhya K S
        2. HADOOP-14407.002.patch
          11 kB
          Yongjun Zhang
        3. HADOOP-14407.002.patch
          11 kB
          Omkar Aradhya K S
        4. HADOOP-14407.003.patch
          12 kB
          Omkar Aradhya K S
        5. HADOOP-14407.004.branch2.patch
          12 kB
          Omkar Aradhya K S
        6. HADOOP-14407.004.patch
          12 kB
          Omkar Aradhya K S
        7. HADOOP-14407.004.patch
          12 kB
          Omkar Aradhya K S
        8. HADOOP-14407.branch2.002.patch
          13 kB
          Yongjun Zhang
        9. TotalTime-vs-CopyBufferSize.jpg
          40 kB
          Omkar Aradhya K S

        Activity

          People

            omkarksa Omkar Aradhya K S
            omkarksa Omkar Aradhya K S
            Votes:
            0 Vote for this issue
            Watchers:
            8 Start watching this issue

            Dates

              Created:
              Updated:
              Resolved: