Uploaded image for project: 'Hadoop HDFS'
  1. Hadoop HDFS
  2. HDFS-11742

Improve balancer usability after HDFS-8818

    XMLWordPrintableJSON

Details

    • Bug
    • Status: Resolved
    • Blocker
    • Resolution: Fixed
    • None
    • 2.9.0, 2.7.4, 3.0.0-beta1, 2.8.2
    • None
    • None

    Description

      We ran 2.8 balancer with HDFS-8818 on a 280-node and a 2,400-node cluster. In both cases, it would hang forever after two iterations. The two iterations were also moving things at a significantly lower rate. The hang itself is fixed by HDFS-11377, but the design limitation remains, so the balancer throughput ends up actually lower.

      Instead of reverting HDFS-8188 as originally suggested, I am making a small change to make it less error prone and more usable.

      Attachments

        1. balancer_fix.png
          28 kB
          Kihwal Lee
        2. balancer2.8.png
          23 kB
          Kihwal Lee
        3. HDFS-11742.branch-2.8.patch
          5 kB
          Kihwal Lee
        4. HDFS-11742.branch-2.patch
          5 kB
          Kihwal Lee
        5. HDFS-11742.trunk.patch
          5 kB
          Kihwal Lee
        6. HDFS-11742.v2.trunk.patch
          4 kB
          Kihwal Lee
        7. replaceBlockNumOps-8w.jpg
          89 kB
          Konstantin Shvachko

        Issue Links

          Activity

            People

              kihwal Kihwal Lee
              kihwal Kihwal Lee
              Votes:
              0 Vote for this issue
              Watchers:
              17 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: