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-16421) Introducing the CellChunkMap as a new additional index variant in the MemStore
Date Wed, 28 Dec 2016 06:05:58 GMT

    [ https://issues.apache.org/jira/browse/HBASE-16421?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15782169#comment-15782169
] 

ramkrishna.s.vasudevan commented on HBASE-16421:
------------------------------------------------

Ya this is the total GC time. My main aim is to show that CellChunkMap garbage is not a killer.
But I can wait for some more inputs in order to test in a bigger scale.
And as you said offheap memstore just runs with 12G space and onheap runs with 30G. The 12G
space has to anyway handle the garbage that occurs in the flush/compaction path. If you see
the mixed GC avg it is lesser than any other case for offheap memstore - particuarly the CellChunkMap
case.
If I run offheap with 30G space I will end up in much better GC profile too. 



> Introducing the CellChunkMap as a new additional index variant in the MemStore
> ------------------------------------------------------------------------------
>
>                 Key: HBASE-16421
>                 URL: https://issues.apache.org/jira/browse/HBASE-16421
>             Project: HBase
>          Issue Type: Umbrella
>            Reporter: Anastasia Braginsky
>         Attachments: CellChunkMapRevived.pdf, ChunkCell_creation.png, IntroductiontoNewFlatandCompactMemStore.pdf
>
>
> Follow up for HBASE-14921. This is going to be the umbrella JIRA to include all the parts
of integration of the CellChunkMap to the MemStore.



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

Mime
View raw message