hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "stack (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HBASE-3976) Disable Block Cache On Compactions
Date Sat, 18 Jun 2011 22:04:47 GMT

    [ https://issues.apache.org/jira/browse/HBASE-3976?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13051603#comment-13051603
] 

stack commented on HBASE-3976:
------------------------------

bq. If "hbase.rs.cacheblocksonwrite" is used sparingly...

My guess is that its not used at all, not at least until we commit fix for hbase-3417

bq.  It'd be nice though to have different knobs to turn block caching on for the "flush"
case as opposed to the "compaction" case, considering that the blocks in the snapshop being
flushed are probably hotter than those in the files being compacted.

Yes.  Good idea (IIRC, this idea or a version of it has come up before but I don't recall
the issue if any to implement -- we should make one).

> Disable Block Cache On Compactions
> ----------------------------------
>
>                 Key: HBASE-3976
>                 URL: https://issues.apache.org/jira/browse/HBASE-3976
>             Project: HBase
>          Issue Type: Improvement
>          Components: regionserver
>    Affects Versions: 0.90.3
>            Reporter: Karthick Sankarachary
>            Assignee: Nicolas Spiegelberg
>            Priority: Minor
>         Attachments: HBASE-3976-V3.patch, HBASE-3976-unconditional.patch, HBASE-3976.patch
>
>
> Is there a good reason to believe that caching blocks during compactions is beneficial?
Currently, if block cache is enabled on a certain family, then every time it's compacted,
we load all of its blocks into the (LRU) cache, at the expense of the legitimately hot ones.
> As a matter of fact, this concern was raised earlier in HBASE-1597, which rightly points
out that, "we should not bog down the LRU with unneccessary blocks" during compaction. Even
though that issue has been marked as "fixed", it looks like it ought to be reopened.
> Should we err on the side of caution and not cache blocks during compactions period (as
illustrated in the attached patch)? Or, can we be selectively aggressive about what blocks
do get cached during compaction (e.g., only cache those blocks from the recent files)?

--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira

        

Mime
View raw message