Uploaded image for project: 'Hadoop HDFS'
  1. Hadoop HDFS
  2. HDFS-12943 Consistent Reads from Standby Node
  3. HDFS-13880

Add mechanism to allow certain RPC calls to bypass sync

    XMLWordPrintableJSON

Details

    • Sub-task
    • Status: Resolved
    • Major
    • Resolution: Fixed
    • None
    • HDFS-12943, 3.3.0
    • namenode
    • None

    Description

      Currently, every single call to NameNode will be synced, in the sense that NameNode will not process it until state id catches up. But in certain cases, we would like to bypass this check and allow the call to return immediately, even when the server id is not up to date. One case could be the to-be-added new API in HDFS-13749 that request for current state id. Others may include calls that do not promise real time responses such as getContentSummary. This Jira is to add the mechanism to allow certain calls to bypass sync.

      Attachments

        1. HDFS-13880-HDFS-12943.005.patch
          23 kB
          Chen Liang
        2. HDFS-13880-HDFS-12943.004.patch
          22 kB
          Chen Liang
        3. HDFS-13880-HDFS-12943.003.patch
          20 kB
          Chen Liang
        4. HDFS-13880-HDFS-12943.002.patch
          10 kB
          Chen Liang
        5. HDFS-13880-HDFS-12943.001.patch
          10 kB
          Chen Liang

        Issue Links

          duplicates

          Sub-task - The sub-task of the issue HDFS-13872 Only some protocol methods should perform msync wait

          • Major - Major loss of function.
          • Resolved

          Activity

            People

              vagarychen Chen Liang
              vagarychen Chen Liang
              Votes:
              0 Vote for this issue
              Watchers:
              5 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: