Uploaded image for project: 'Hadoop Common'
  1. Hadoop Common
  2. HADOOP-11827

Speed-up distcp buildListing() using threadpool

    Details

    • Type: Improvement
    • Status: Resolved
    • Priority: Major
    • Resolution: Fixed
    • Affects Version/s: 2.7.0, 2.7.1
    • Fix Version/s: 2.8.0, 3.0.0-alpha1
    • Component/s: tools/distcp
    • Labels:
      None
    • Target Version/s:

      Description

      For very large source trees on s3 distcp is taking long time to build file listing (client code, before starting mappers). For a dataset I used (1.5M files, 50K dirs) it was taking 65 minutes before my fix in HADOOP-11785 and 36 minutes after the fix).

        Attachments

        1. HADOOP-11827.patch
          37 kB
          Zoran Dimitrijevic
        2. HADOOP-11827-02.patch
          37 kB
          Zoran Dimitrijevic
        3. HADOOP-11827-03.patch
          38 kB
          Zoran Dimitrijevic
        4. HADOOP-11827-04.patch
          38 kB
          Ravi Prakash

          Issue Links

            Activity

              People

              • Assignee:
                3opan Zoran Dimitrijevic
                Reporter:
                3opan Zoran Dimitrijevic
              • Votes:
                0 Vote for this issue
                Watchers:
                6 Start watching this issue

                Dates

                • Due:
                  Created:
                  Updated:
                  Resolved:

                  Time Tracking

                  Estimated:
                  Original Estimate - 24h
                  24h
                  Remaining:
                  Remaining Estimate - 24h
                  24h
                  Logged:
                  Time Spent - Not Specified
                  Not Specified