Uploaded image for project: 'HBase'
  1. HBase
  2. HBASE-11209

Increase the default value for hbase.hregion.memstore.block.multipler from 2 to 4

    XMLWordPrintableJSON

    Details

    • Type: Brainstorming
    • Status: Closed
    • Priority: Major
    • Resolution: Fixed
    • Affects Version/s: 0.99.0, 0.98.2
    • Fix Version/s: 0.99.0, 0.98.3
    • Component/s: regionserver
    • Labels:
      None
    • Hadoop Flags:
      Reviewed

      Description

      On a YCSB test, I saw a 33% performance increase, both on the max latency and on the throughput. I'm convinced enough that this value is better that I think it makes sense to change it on 0.98 as well.

      More fundamentally, but outside of the scope of this patch, I think this parameter should be changed to something at the region server level: today, we have:

      • global memstore check: if we're other 40%, we flush the biggest memstore
      • local: no more than 2 (proposed: 4) memstore size per region.

      But if we have enough memory and a spike on a region, there is no reason for not taking the write.

        Attachments

        1. HBASE-11209.patch
          0.6 kB
          Andrew Kyle Purtell

          Activity

            People

            • Assignee:
              nkeywal Nicolas Liochon
              Reporter:
              nkeywal Nicolas Liochon
            • Votes:
              0 Vote for this issue
              Watchers:
              8 Start watching this issue

              Dates

              • Created:
                Updated:
                Resolved: