Uploaded image for project: 'Hadoop HDFS'
  1. Hadoop HDFS
  2. HDFS-2379

0.20: Allow block reports to proceed without holding FSDataset lock

    XMLWordPrintableJSON

Details

    • Bug
    • Status: Closed
    • Critical
    • Resolution: Fixed
    • 1.0.0
    • 1.0.1
    • datanode
    • None
    • Reviewed

    Description

      As disks are getting larger and more plentiful, we're seeing DNs with multiple millions of blocks on a single machine. When page cache space is tight, block reports can take multiple minutes to generate. Currently, during the scanning of the data directories to generate a report, the FSVolumeSet lock is held. This causes writes and reads to block, timeout, etc, causing big problems especially for clients like HBase.

      This JIRA is to explore some of the ideas originally discussed in HADOOP-4584 for the 0.20.20x series.

      Attachments

        1. hdfs-2379.txt
          11 kB
          Todd Lipcon
        2. hdfs-2379.txt
          31 kB
          Todd Lipcon
        3. hdfs-2379.txt
          32 kB
          Todd Lipcon
        4. hdfs-2379.txt
          32 kB
          Todd Lipcon
        5. hdfs-2379.txt
          32 kB
          Todd Lipcon
        6. hdfs-2379.txt
          32 kB
          Todd Lipcon

        Issue Links

          Activity

            People

              tlipcon Todd Lipcon
              tlipcon Todd Lipcon
              Votes:
              0 Vote for this issue
              Watchers:
              17 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: