Details

    • Type: Improvement
    • Status: Patch Available
    • Priority: Major
    • Resolution: Unresolved
    • Affects Version/s: None
    • Fix Version/s: None
    • Component/s: datanode, performance
    • Labels:
      None

      Description

      In benchmarking HDFS-941 I noticed that for the random read workload, the FSDataset lock is highly contended. After converting it to a ReentrantReadWriteLock, I saw a ~25% improvement on both latency and ops/second.

        Attachments

        1. hdfs-1148-old.txt
          12 kB
          Todd Lipcon
        2. patch-HDFS-1148-rel0.20.2.txt
          12 kB
          Dave Thompson
        3. hdfs-1148-trunk.txt
          46 kB
          Todd Lipcon
        4. HDFS-1148.001.patch
          55 kB
          Yong Zhang
        5. HDFS-1148.002.patch
          55 kB
          Yong Zhang
        6. HDFS-1148.003.patch
          55 kB
          Yong Zhang

          Issue Links

            Activity

              People

              • Assignee:
                zhangyongxyz Yong Zhang
                Reporter:
                tlipcon Todd Lipcon
              • Votes:
                0 Vote for this issue
                Watchers:
                27 Start watching this issue

                Dates

                • Created:
                  Updated: