hbase-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Jean-Daniel Cryans (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HBASE-887) Fix a hotspot in scanners
Date Tue, 23 Sep 2008 01:36:44 GMT

    [ https://issues.apache.org/jira/browse/HBASE-887?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12633591#action_12633591
] 

Jean-Daniel Cryans commented on HBASE-887:
------------------------------------------

@stack

Regards hbase-defaults, will do. Regards default value, I think 30 would be great as the test
shows. Ok for final. Regards scannerCaching, not sure of what you mean when saying "in the
one go".

@ Dogacan

1- Good question regards versionID, I'm not sure myself so thanks for pointing out.

2- It would seem yes.

3- It will not read anymore anyways :

{code}
if (cache.size() == 0 && this.closed) {
  return null;
}
if (cache.size() == 0) {
...
{code}

So it will empty the cache and then (cache.size() == 0 && this.closed) will be true.

Thank you both for the review, this is really appreciated!

> Fix a hotspot in scanners
> -------------------------
>
>                 Key: HBASE-887
>                 URL: https://issues.apache.org/jira/browse/HBASE-887
>             Project: Hadoop HBase
>          Issue Type: Improvement
>          Components: client, regionserver
>            Reporter: Jean-Daniel Cryans
>            Assignee: Jean-Daniel Cryans
>             Fix For: 0.19.0
>
>         Attachments: 877-chart.jpg, hbase-887-v1.patch
>
>
> When scanning, we do a lot of RPCs and this has a huge performance hit. I propose that
we add a way to fetch more rows during next() and put them in cache. This should be configurable.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.


Mime
View raw message