Uploaded image for project: 'Hadoop YARN'
  1. Hadoop YARN
  2. YARN-4105

Capacity Scheduler headroom for DRF is wrong

Log workAgile BoardRank to TopRank to BottomAttach filesAttach ScreenshotVotersWatch issueWatchersCreate sub-taskConvert to sub-taskMoveLinkCloneLabelsUpdate Comment AuthorReplace String in CommentUpdate Comment VisibilityDelete Comments
    XMLWordPrintableJSON

    Details

    • Target Version/s:
    • Hadoop Flags:
      Reviewed

      Description

      relate to the problem discussed in YARN-1857. But the min method is flawed when we are using DRC. Have run into a real scenario in production where queueCapacity: <memory:1056256, vCores:3750>, qconsumed: <memory:1054720, vCores:361>, consumed: <memory:125952, vCores:170> limit: <memory:214016, vCores:755>. headRoom calculation returns 88064 where there is only 1536 left in the queue because DRC effectively compare by vcores. It then caused deadlock because RMcontainer allocator thought there is still space for mapper and won't preempt a reducer in a full queue to schedule a mapper. Propose fix with componentwiseMin.

        Attachments

        1. YARN-4105.2.patch
          7 kB
          Chang Li
        2. YARN-4105.3.patch
          7 kB
          Chang Li
        3. YARN-4105.4.patch
          7 kB
          Chang Li
        4. YARN-4105.patch
          7 kB
          Chang Li

          Activity

          $i18n.getText('security.level.explanation', $currentSelection) Viewable by All Users
          Cancel

            People

              Dates

              • Created:
                Updated:
                Resolved:

                Issue deployment