Uploaded image for project: 'HBase'
  1. HBase
  2. HBASE-2480

Smarter load-balancing

Log workAgile BoardRank to TopRank to BottomAttach filesAttach ScreenshotBulk Copy AttachmentsBulk Move AttachmentsVotersWatch issueWatchersCreate sub-taskConvert to sub-taskMoveLinkCloneLabelsUpdate Comment AuthorReplace String in CommentUpdate Comment VisibilityDelete Comments
    XMLWordPrintableJSON

Details

    • Improvement
    • Status: Closed
    • Major
    • Resolution: Won't Fix
    • None
    • 0.90.0
    • None
    • None

    Description

      Balancer is really basic; it just looks at counts of regions at the moment. It also as it currently works has loads of issues (See the linked issues) including a lack of testibility. This issue acts as the umbrella issue to collect all balancer improvements under.

      Attachments

        Issue Links

        incorporates

        Bug - A problem which impairs or prevents the functions of the product. HBASE-1419 Assignment and balance need to coordinate; assigner gives out up to 10 regions at a time unbalancing a balanced cluster making for churn, etc.

        • Major - Major loss of function.
        • Closed

        Bug - A problem which impairs or prevents the functions of the product. HBASE-1676 load balancing on a large cluster doesn't work very well

        • Major - Major loss of function.
        • Closed

        Bug - A problem which impairs or prevents the functions of the product. HBASE-1909 Balancer assigns to most loaded server when assigning a single region

        • Major - Major loss of function.
        • Closed

        Bug - A problem which impairs or prevents the functions of the product. HBASE-2240 Balancer should not reassign (because of overloading) a region that was just opened

        • Minor - Minor loss of function, or other problem where easy workaround is present.
        • Closed
        relates to

        Sub-task - The sub-task of the issue HBASE-2699 Reimplement load balancing to be a background process and to not use heartbeats

        • Critical - Crashes, loss of data, severe memory leak.
        • Closed

        Improvement - An improvement or enhancement to an existing feature or task. HBASE-2510 [performance] make hbase splits run even faster still

        • Major - Major loss of function.
        • Closed

        Improvement - An improvement or enhancement to an existing feature or task. HBASE-2802 Stop daughter regions both being assigned same server

        • Major - Major loss of function.
        • Closed

        Improvement - An improvement or enhancement to an existing feature or task. HBASE-3373 Allow regions to be load-balanced by table

        • Major - Major loss of function.
        • Closed

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

          People

            Unassigned Unassigned Assign to me
            stack Michael Stack
            Votes:
            0 Vote for this issue
            Watchers:
            4 Start watching this issue

            Dates

              Created:
              Updated:
              Resolved:

              Slack

                Issue deployment