[
https://issues.apache.org/jira/browse/HBASE-9399?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13849635#comment-13849635
]
Lars Hofhansl commented on HBASE-9399:
--------------------------------------
I am starting to benchmark the memstore. What I found so far is that (not too
surprisingly) a lot of CPU time during an insert is spent in managing the CSLS.
Making that larger should have minimal impact (if any). Might get better IO,
since we're flushing larger initial files, even that should be negligible
unless we're IO bound on write.
For reads I almost want to flush sooner so that the data gets into the more
scan friendly block format.
> Up the memstore flush size
> --------------------------
>
> Key: HBASE-9399
> URL: https://issues.apache.org/jira/browse/HBASE-9399
> Project: HBase
> Issue Type: Task
> Components: regionserver
> Affects Versions: 0.98.0, 0.96.0
> Reporter: Elliott Clark
> Assignee: Elliott Clark
> Fix For: 0.98.0
>
>
> As heap sizes get bigger we are still recommending that users keep their
> number of regions to a minimum. This leads to lots of un-used memstore
> memory.
> For example I have a region server with 48 gigs of ram. 30 gigs are there
> for the region server. This with current defaults the global memstore size
> reserved is 8 gigs.
> The per region memstore size is 128mb right now. That means that I need 80
> regions actively taking writes to reach the global memstore size. That
> number is way out of line with what our split policies currently give users.
> They are given much fewer regions by default.
> We should up the hbase.hregion.memstore.flush.size size. Ideally we should
> auto tune everything. But until then I think something like 512mb would help
> a lot with our write throughput on clusters that don't have several hundred
> regions per RS.
--
This message was sent by Atlassian JIRA
(v6.1.4#6159)
