Uploaded image for project: 'Hadoop HDFS'
  1. Hadoop HDFS
  2. HDFS-2989

HA: Optimize quota tracking for HA

    XMLWordPrintableJSON

Details

    • Improvement
    • Status: Open
    • Minor
    • Resolution: Unresolved
    • 2.0.0-alpha
    • None
    • ha, namenode
    • None

    Description

      Currently after each segment we read in on the standby, we re-calculate all of the quota/usage information throughout the directory tree. This is inefficient. There are two potential optimizations: (a) we could maintain the quotas incrementally as edits are read, or (b) we could defer all quota computation until the node transitions to active mode. (b) is probably less bug-prone.

      This is not a crucial optimization since in the worst case it might just delay failover by a few extra seconds (the time to traverse the in-memory FSDirectory)

      Attachments

        Activity

          People

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

            Dates

              Created:
              Updated: