Uploaded image for project: 'Hadoop HDFS'
  1. Hadoop HDFS
  2. HDFS-1028

INode.getPathNames could split more efficiently

    XMLWordPrintableJSON

Details

    • Improvement
    • Status: Resolved
    • Minor
    • Resolution: Fixed
    • None
    • 0.22.0
    • namenode
    • None
    • Reviewed

    Description

      INode.getPathnames uses String.split(String) which actually uses the full Java regex implementation. Since we're always splitting on a single char, we could implement a faster one like StringUtils.split() (except without the escape character). This takes a significant amount of CPU during FSImage loading so should be a worthwhile speedup.

      Attachments

        1. HDFS-split.patch
          2 kB
          Dmytro Molkov
        2. HDFS-split.2.patch
          0.8 kB
          Dmytro Molkov

        Issue Links

          is blocked by

          Improvement - An improvement or enhancement to an existing feature or task. HADOOP-6623 Add StringUtils.split for non-escaped single-character separator

          • Minor - Minor loss of function, or other problem where easy workaround is present.
          • Resolved

          Activity

            People

              dms Dmytro Molkov
              tlipcon Todd Lipcon
              Votes:
              0 Vote for this issue
              Watchers:
              7 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: