[
https://issues.apache.org/jira/browse/HBASE-15205?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15159185#comment-15159185
]
stack commented on HBASE-15205:
-------------------------------
bq. Yes Stack as said in my earlier comments I was not able to directly pass it
to WALKey on construction.
I did not get that. My fault. When you said pass through to WALKey, I did not
get that it meant saving first to WALEntry and then at a later point passing it
through to WALKey.
Doing as you have in the patch means that replication scopes are serialized
twice, right? That is not on. Our WAL writes are already dripping with fat in
need of diet.
> Do not find the replication scope for every WAL#append()
> --------------------------------------------------------
>
> Key: HBASE-15205
> URL: https://issues.apache.org/jira/browse/HBASE-15205
> Project: HBase
> Issue Type: Sub-task
> Components: regionserver
> Reporter: ramkrishna.s.vasudevan
> Assignee: ramkrishna.s.vasudevan
> Priority: Minor
> Fix For: 2.0.0
>
> Attachments: HBASE-15204_6.patch, HBASE-15205.patch,
> HBASE-15205_1.patch, HBASE-15205_2.patch, HBASE-15205_3.patch,
> HBASE-15205_4.patch, HBASE-15205_6.patch, HBASE-15205_6.patch,
> HBASE-15205_7.patch, ScopeWALEdits.jpg, ScopeWALEdits_afterpatch.jpg
>
>
> After the byte[] and char[] the other top contributor for lot of GC (though
> it is only 2.86%) is the UTF_8.newDecoder.
> This happens because for every WAL append we try to calculate the replication
> scope associate with the families associated with the TableDescriptor. I
> think per WAL append doing this is very costly and creates lot of garbage.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
