Uploaded image for project: 'Hadoop HDFS'
  1. Hadoop HDFS
  2. HDFS-9752

Permanent write failures may happen to slow writers during datanode rolling upgrades

Log workAgile BoardRank to TopRank to BottomAttach filesAttach ScreenshotBulk Copy AttachmentsBulk Move AttachmentsVotersWatch issueWatchersCreate sub-taskConvert to sub-taskMoveLinkCloneLabelsUpdate Comment AuthorReplace String in CommentUpdate Comment VisibilityDelete Comments


    • Bug
    • Status: Closed
    • Critical
    • Resolution: Fixed
    • None
    • 2.8.0, 2.7.3, 2.6.5, 3.0.0-alpha1
    • None
    • None
    • Reviewed


      When datanodes are being upgraded, an out-of-band ack is sent upstream and the client does a pipeline recovery. The client may hit this multiple times as more nodes get upgraded. This normally does not cause any issue, but if the client is holding the stream open without writing any data during this time, a permanent write failure can occur.

      This is because there is a limit of 5 recovery trials for the same packet, which is tracked by "last acked sequence number". Since the empty heartbeat packets for an idle output stream does not increment the sequence number, the write will fail after it seeing 5 pipeline breakages by datanode upgrades.

      This check/limit was added to avoid spinning until running out of nodes in the cluster due to a corruption or any other irrecoverable conditions. The datanode upgrade-restart should be excluded from the count.


        1. HDFS-9752.01.patch
          7 kB
          Walter Su
        2. HdfsWriter.java
          2 kB
          Xiaobing Zhou
        3. HDFS-9752.02.patch
          7 kB
          Walter Su
        4. HDFS-9752.03.patch
          12 kB
          Walter Su
        5. HDFS-9752-branch-2.6.03.patch
          11 kB
          Walter Su
        6. HDFS-9752-branch-2.7.03.patch
          11 kB
          Walter Su


          This comment will be Viewable by All Users Viewable by All Users


            walter.k.su Walter Su Assign to me
            kihwal Kihwal Lee
            0 Vote for this issue
            16 Start watching this issue




                Issue deployment