[jira] [Created] (HBASE-11209) Increase the default value for hbase.hregion.memstore.block.multipler from 2 to 4

["Nicolas Liochon (JIRA)" <ji...@apache.org>]

Nicolas Liochon created HBASE-11209:
---------------------------------------

             Summary: Increase the default value for hbase.hregion.memstore.block.multipler from 2 to 4
                 Key: HBASE-11209
                 URL: https://issues.apache.org/jira/browse/HBASE-11209
             Project: HBase
          Issue Type: Brainstorming
          Components: regionserver
    Affects Versions: 0.98.2, 0.99.0
            Reporter: Nicolas Liochon
            Assignee: Nicolas Liochon
             Fix For: 0.99.0, 0.98.3


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.






--
This message was sent by Atlassian JIRA
(v6.2#6252)