Uploaded image for project: 'Hadoop HDFS'
  1. Hadoop HDFS
  2. HDFS-13183

Standby NameNode process getBlocks request to reduce Active load

    XMLWordPrintableJSON

    Details

    • Type: Improvement
    • Status: Open
    • Priority: Major
    • Resolution: Unresolved
    • Affects Version/s: 2.7.5, 3.1.0, 2.9.1, 2.8.4, 3.0.2
    • Fix Version/s: None
    • Component/s: balancer & mover, namenode
    • Labels:
      None

      Description

      The performance of Active NameNode could be impact when Balancer requests #getBlocks, since query blocks of overly full DNs performance is extremely inefficient currently. The main reason is NameNodeRpcServer#getBlocks hold read lock for long time. In extreme case, all handlers of Active NameNode RPC server are occupied by one reader NameNodeRpcServer#getBlocks and other write operation calls, thus Active NameNode enter a state of false death for number of seconds even for minutes.
      The similar performance concerns of Balancer have reported by HDFS-9412, HDFS-7967, etc.

      If Standby NameNode can shoulder #getBlocks heavy burden, it could speed up the progress of balancing and reduce performance impact to Active NameNode.

        Attachments

        1. HDFS-13183-trunk.001.patch
          0.9 kB
          Xiaoqiao He
        2. HDFS-13183-trunk.002.patch
          2 kB
          Xiaoqiao He
        3. HDFS-13183-trunk.003.patch
          13 kB
          Xiaoqiao He

          Issue Links

            Activity

              People

              • Assignee:
                hexiaoqiao Xiaoqiao He
                Reporter:
                hexiaoqiao Xiaoqiao He
              • Votes:
                1 Vote for this issue
                Watchers:
                17 Start watching this issue

                Dates

                • Created:
                  Updated: