Uploaded image for project: 'Spark'
  1. Spark
  2. SPARK-31856

Handle locality wait reset better when executors added

Attach filesAttach ScreenshotAdd voteVotersWatch issueWatchersCreate sub-taskLinkCloneUpdate Comment AuthorReplace String in CommentUpdate Comment VisibilityDelete Comments
    XMLWordPrintableJSON

Details

    • Improvement
    • Status: Open
    • Major
    • Resolution: Unresolved
    • 3.1.0
    • None
    • Scheduler
    • None

    Description

      We found a corner case with the new locality algorithm where we were not affectively resetting the locality when you started without executors.  See https://github.com/apache/spark/pull/28656/

      In that fix we reset the locality when a new executor is added and it changes the valid locality levels.  This could reset it when you don't want to. for instance if the task set has been around for quite a while and you have other executors it could put tasks on. Resetting it back to the most local locality level could cause delays in the tasks getting scheduled that have been waiting for more then the locality wait. 

      This goes back to the new algorithm tries to use heuristic on this but its not perfect.  Ideally I think we would still track per executor but that is a lot more change.

      Investigate to see if we can handle this better. 

      Attachments

        Activity

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

          People

            Unassigned Unassigned
            tgraves Thomas Graves

            Dates

              Created:
              Updated:

              Slack

                Issue deployment