[
https://issues.apache.org/jira/browse/HBASE-16417?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15426121#comment-15426121
]
Anastasia Braginsky commented on HBASE-16417:
---------------------------------------------
Answering [~anoop.hbase] and [~ram_krish] from HBASE-14921
In HBASE-14921, we run YCSB small just to ensure the correctness. In this JIRA
we’ll resolve the performance issues.
So in YCSB we did: 10 cols, 20 threads, only writes. 1G data, but very small
heap - 1G, so in the sense of garbage collection we should be the same. The GC
is Concurrent Mark & Sweep and we do not see GC pauses. We run with
duplications and without. I will give a run now with more data.
> In-Memory MemStore Policy for Flattening and Compactions
> --------------------------------------------------------
>
> Key: HBASE-16417
> URL: https://issues.apache.org/jira/browse/HBASE-16417
> Project: HBase
> Issue Type: Sub-task
> Reporter: Anastasia Braginsky
>
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
