Uploaded image for project: 'HBase'
  1. HBase
  2. HBASE-13109

Make better SEEK vs SKIP decisions during scanning

    XMLWordPrintableJSON

Details

    • Improvement
    • Status: Closed
    • Major
    • Resolution: Fixed
    • None
    • 1.0.1, 1.1.0, 0.98.12, 2.0.0
    • None
    • None
    • Reviewed

    Description

      I'm re-purposing this issue to add a heuristic as to when to SEEK and when to SKIP Cells. This has come up in various issues, and I think I have a way to finally fix this now. HBASE-9778, HBASE-12311, and friends are related.

      — Old description —

      This is a continuation of HBASE-9778.
      We've seen a scenario of a very slow scan over a region using a timerange that happens to fall after the ts of any Cell in the region.
      Turns out we spend a lot of time seeking.

      Tested with a 5 column table, and the scan is 5x faster when the timerange falls before all Cells' ts.
      We can use the lookahead hint introduced in HBASE-9778 to do opportunistic SKIPing before we actually seek.

      Attachments

        1. 13109-trunk.txt
          27 kB
          Lars Hofhansl
        2. 13109-trunk-v2.txt
          24 kB
          Lars Hofhansl
        3. 13109-trunk-v3.txt
          24 kB
          Lars Hofhansl
        4. 13109-trunk-v4.txt
          25 kB
          Lars Hofhansl
        5. nextIndexKVChange_new.patch
          6 kB
          ramkrishna.s.vasudevan
        6. 13109-0.98-v4.txt
          27 kB
          Lars Hofhansl
        7. 13109-trunk-v5.txt
          35 kB
          Lars Hofhansl
        8. 13109-0.98-v5.txt
          27 kB
          Lars Hofhansl

        Issue Links

          Activity

            People

              larsh Lars Hofhansl
              larsh Lars Hofhansl
              Votes:
              0 Vote for this issue
              Watchers:
              20 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: