Uploaded image for project: 'Hadoop Common'
  1. Hadoop Common
  2. HADOOP-6713

The RPC server Listener thread is a scalability bottleneck

    Details

    • Type: Improvement
    • Status: Closed
    • Priority: Major
    • Resolution: Fixed
    • Affects Version/s: 0.21.0
    • Fix Version/s: 0.21.0
    • Component/s: ipc
    • Labels:
      None
    • Hadoop Flags:
      Reviewed

      Description

      The Hadoop RPC Server implementation has a single Listener thread that reads data from the socket and puts them into a call queue. This means that this single thread can pull RPC requests off the network only as fast as a single CPU can execute. This is a scalability bottlneck in our cluster.

        Attachments

        1. HADOOP-6713-rel20.patch
          13 kB
          Bharath Mundlapudi
        2. HADOOP-6713-rel20.3.patch
          13 kB
          Bharath Mundlapudi
        3. HADOOP-6713-rel20.2.patch
          12 kB
          Bharath Mundlapudi
        4. HADOOP-6713.patch
          10 kB
          Dmytro Molkov
        5. HADOOP-6713.2.patch
          11 kB
          Dmytro Molkov

          Issue Links

            Activity

              People

              • Assignee:
                dms Dmytro Molkov
                Reporter:
                dhruba dhruba borthakur
              • Votes:
                0 Vote for this issue
                Watchers:
                19 Start watching this issue

                Dates

                • Created:
                  Updated:
                  Resolved: