Uploaded image for project: 'Hadoop Distributed Data Store'
  1. Hadoop Distributed Data Store
  2. HDDS-372

There are three buffer copies in BlockOutputStream

    XMLWordPrintableJSON

    Details

    • Type: Improvement
    • Status: Resolved
    • Priority: Major
    • Resolution: Fixed
    • Affects Version/s: None
    • Fix Version/s: 0.4.1
    • Component/s: Ozone Client
    • Labels:
      None
    • Target Version/s:
    • Sprint:
      Done

      Description

      Currently, there are three buffer copies in ChunkOutputStream

      1. from byte[] to ByteBuffer, and
      2. from ByteBuffer to ByteString.
      3. from ByteString to ByteBuffer for checskum computation

      We should eliminate the ByteBuffer in the middle.

      For zero copy io, we should support WritableByteChannel instead of OutputStream. It won't be done in this JIRA.

        Attachments

        1. HDDS-372.001.patch
          39 kB
          Shashikant Banerjee
        2. HDDS-372.002.patch
          33 kB
          Shashikant Banerjee
        3. HDDS-372.003.patch
          37 kB
          Shashikant Banerjee
        4. HDDS-372.004.patch
          23 kB
          Shashikant Banerjee
        5. HDDS-372.005.patch
          23 kB
          Shashikant Banerjee
        6. HDDS-372.20180829.patch
          27 kB
          Tsz-wo Sze

          Issue Links

          contains

          Improvement - An improvement or enhancement to an existing feature or task. HDDS-1227 Avoid extra buffer copy during checksum computation in write Path

          • Major - Major loss of function.
          • Resolved

            Activity

              People

              • Assignee:
                shashikant Shashikant Banerjee
                Reporter:
                szetszwo Tsz-wo Sze
              • Votes:
                0 Vote for this issue
                Watchers:
                7 Start watching this issue

                Dates

                • Created:
                  Updated:
                  Resolved: