Uploaded image for project: 'Hadoop HDFS'
  1. Hadoop HDFS
  2. HDFS-200

In HDFS, sync() not yet guarantees data available to the new readers

    Details

    • Type: New Feature
    • Status: Closed
    • Priority: Blocker
    • Resolution: Fixed
    • Affects Version/s: 0.20-append
    • Fix Version/s: 0.20-append, 0.20.205.0
    • Component/s: None
    • Labels:
      None
    • Tags:
      hbase

      Description

      In the append design doc (https://issues.apache.org/jira/secure/attachment/12370562/Appends.doc), it says

      • A reader is guaranteed to be able to read data that was 'flushed' before the reader opened the file

      However, this feature is not yet implemented. Note that the operation 'flushed' is now called "sync".

        Attachments

        1. 4379_20081010TC3.java
          4 kB
          Tsz Wo Nicholas Sze
        2. checkLeases-fix-1.txt
          0.7 kB
          sam rash
        3. checkLeases-fix-unit-test-1.txt
          4 kB
          sam rash
        4. fsyncConcurrentReaders.txt
          14 kB
          dhruba borthakur
        5. fsyncConcurrentReaders11_20.txt
          14 kB
          dhruba borthakur
        6. fsyncConcurrentReaders12_20.txt
          14 kB
          dhruba borthakur
        7. fsyncConcurrentReaders13_20.txt
          15 kB
          dhruba borthakur
        8. fsyncConcurrentReaders14_20.txt
          17 kB
          dhruba borthakur
        9. fsyncConcurrentReaders15_20.txt
          18 kB
          dhruba borthakur
        10. fsyncConcurrentReaders16_20.txt
          18 kB
          dhruba borthakur
        11. fsyncConcurrentReaders3.patch
          14 kB
          dhruba borthakur
        12. fsyncConcurrentReaders4.patch
          15 kB
          dhruba borthakur
        13. fsyncConcurrentReaders5.txt
          15 kB
          dhruba borthakur
        14. fsyncConcurrentReaders6.patch
          15 kB
          dhruba borthakur
        15. fsyncConcurrentReaders9.patch
          19 kB
          dhruba borthakur
        16. hadoop-stack-namenode-aa0-000-12.u.powerset.com.log.gz
          86 kB
          stack
        17. HDFS-200.20-security.1.patch
          18 kB
          Jitendra Nath Pandey
        18. hdfs-200-ryan-existing-file-fail.txt
          13 kB
          ryan rawson
        19. hypertable-namenode.log.gz
          33 kB
          Doug Judd
        20. namenode.log
          2.51 MB
          Jim Kellerman
        21. namenode.log
          95 kB
          Jim Kellerman
        22. Reader.java
          2 kB
          dhruba borthakur
        23. Reader.java
          1 kB
          Jim Kellerman
        24. reopen_test.sh
          0.3 kB
          Doug Judd
        25. ReopenProblem.java
          7 kB
          Doug Judd
        26. Writer.java
          2 kB
          dhruba borthakur
        27. Writer.java
          2 kB
          Jim Kellerman

          Issue Links

            Activity

              People

              • Assignee:
                dhruba dhruba borthakur
                Reporter:
                szetszwo Tsz Wo Nicholas Sze
              • Votes:
                8 Vote for this issue
                Watchers:
                40 Start watching this issue

                Dates

                • Created:
                  Updated:
                  Resolved: