Uploaded image for project: 'Hadoop YARN'
  1. Hadoop YARN
  2. YARN-5677

RM should transition to standby when connection is lost for an extended period

VotersWatch issueWatchersCreate sub-taskLinkCloneUpdate Comment AuthorReplace String in CommentUpdate Comment VisibilityDelete Comments
    XMLWordPrintableJSON

Details

    • Bug
    • Status: Resolved
    • Critical
    • Resolution: Fixed
    • 2.8.0
    • 2.8.0, 3.0.0-alpha2
    • resourcemanager
    • None
    • Reviewed

    Description

      In trunk, there is no maximum number of retries that I see. It appears the connection will be retried forever, with the active never figuring out it's no longer active. In my testing, the active-active state lasted almost 2 hours with no sign of stopping before I killed it. The solution appears to be to cap the number of retries or amount of time spent retrying.

      This issue is significant because of the asynchronous nature of job submission. If the active doesn't know it's not active, it will buffer up job submissions until it finally realizes it has become the standby. Then it will fail all the job submissions in bulk. In high-volume workflows, that behavior can create huge mass job failures.

      This issue is also important because the node managers will not fail over to the new active until the old active realizes it's the standby. Workloads submitted after the old active loses contact with ZK will therefore fail to be executed regardless of which RM the clients contact.

      Attachments

        1. YARN-5677.branch-2.001.patch
          12 kB
          Daniel Templeton
        2. YARN-5677.005.patch
          12 kB
          Daniel Templeton
        3. YARN-5677.004.patch
          12 kB
          Daniel Templeton
        4. YARN-5677.003.patch
          10 kB
          Daniel Templeton
        5. YARN-5677.002.patch
          4 kB
          Daniel Templeton
        6. YARN-5677.001.patch
          4 kB
          Daniel Templeton

        Activity

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

          People

            templedf Daniel Templeton
            templedf Daniel Templeton
            Votes:
            0 Vote for this issue
            Watchers:
            13 Start watching this issue

            Dates

              Created:
              Updated:
              Resolved:

              Slack

                Issue deployment