[
https://issues.apache.org/jira/browse/HBASE-9399?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13850194#comment-13850194
]
Matt Corgan commented on HBASE-9399:
------------------------------------
oops - yep, i've chatted with Todd about this before. I guess what made me
think of it in this context is that we could be flushing the memstore into the
block cache rather than into its own fenced off area of memory. Mixing the
memory pools together into a single big pool would provide more fluid
auto-tuning, reducing everything down to a unified eviction algorithm. Perhaps
the memstoreLAB blocks could go in as well, and it could be renamed from block
cache to block pool.
> 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)
