hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "ramkrishna.s.vasudevan (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HBASE-16417) In-Memory MemStore Policy for Flattening and Compactions
Date Tue, 06 Dec 2016 11:11:35 GMT

    [ https://issues.apache.org/jira/browse/HBASE-16417?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15725126#comment-15725126
] 

ramkrishna.s.vasudevan commented on HBASE-16417:
------------------------------------------------

Thanks for the details report. Its great and well written.
bq.IMHO, these must be explored before setting chunk pool to on by default in 2.0. 
So do you advocate reverting this change for now?
Interesting fact is that in eager compaction (that is data compaction) you seem to perform
better  in 3 node cluster and not so well in single node cluster. Why do you think that is
happening?
My main question is that in these results are you generating lot of duplicatest such that
eager compaction is reducing the duplicates? If there are not much duplicates then the amount
of flushes/compaction should be same right? 

> 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
>            Assignee: Eshcar Hillel
>             Fix For: 2.0.0
>
>         Attachments: HBASE-16417-benchmarkresults-20161101.pdf, HBASE-16417-benchmarkresults-20161110.pdf,
HBASE-16417-benchmarkresults-20161123.pdf, HBASE-16417-benchmarkresults-20161205.pdf
>
>




--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Mime
View raw message