Uploaded image for project: 'IMPALA'
  1. IMPALA
  2. IMPALA-7872 Extended health checks to mark node as down
  3. IMPALA-10477

Mark executor node as down if it repeatedly failed to startup fragment instance

    XMLWordPrintableJSON

Details

    • Sub-task
    • Status: Open
    • Major
    • Resolution: Unresolved
    • None
    • None
    • None
    • None
    • ghx-label-2

    Description

      If an executor node notices that it is somehow unhealthy and repeatedly gets failures during fragment instance startup, it should report its unhealthy state to statestore so that the node could be removed from executor group and coordinators would not schedule new tasks on the unhealthy node.  

       

      Attachments

        Issue Links

          Activity

            People

              wzhou Wenzhe Zhou
              wzhou Wenzhe Zhou
              Votes:
              0 Vote for this issue
              Watchers:
              2 Start watching this issue

              Dates

                Created:
                Updated: