Uploaded image for project: 'Hadoop HDFS'
  1. Hadoop HDFS
  2. HDFS-5535 Umbrella jira for improved HDFS rolling upgrades
  3. HDFS-5498

Improve datanode startup time

    XMLWordPrintableJSON

Details

    • Sub-task
    • Status: Resolved
    • Major
    • Resolution: Fixed
    • None
    • HDFS-5535 (Rolling upgrades)
    • None
    • None
    • Reviewed

    Description

      Similarly to HDFS-5027, an improvement can be made for getVomeMap(). This is the phase in which ReplicaMap.is populated. But it will be even better if datanode scans only once and do both.

      Attachments

        1. HDFS-5498.with_du_change.patch
          10 kB
          Kihwal Lee
        2. HDFS-5498.with_du_change.patch
          11 kB
          Kihwal Lee
        3. HDFS-5498_sh.patch
          9 kB
          Kihwal Lee

        Issue Links

          depends upon

          Improvement - An improvement or enhancement to an existing feature or task. HADOOP-10111 Allow DU to be initialized with an initial value

          • Major - Major loss of function.
          • Closed
          duplicates

          Sub-task - The sub-task of the issue HDFS-5586 Add quick-restart option for datanode

          • Major - Major loss of function.
          • Resolved
          is related to

          Improvement - An improvement or enhancement to an existing feature or task. HDFS-8710 Always read DU value from the cached "dfsUsed" file on datanode startup

          • Major - Major loss of function.
          • Resolved

          Improvement - An improvement or enhancement to an existing feature or task. HDFS-5027 On startup, DN should scan volumes in parallel

          • Major - Major loss of function.
          • Closed

          Activity

            People

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

              Dates

                Created:
                Updated:
                Resolved: