[
https://issues.apache.org/jira/browse/HBASE-12934?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14294475#comment-14294475
]
Devaraj Das commented on HBASE-12934:
-------------------------------------
bq. And as I stated, other parts are more obvious: finishing HBASE-5954 and
then place WALs on SSDs, or allow column families to be stored on SSDs for
random read load.
[~lhofhansl], agree on the fact that HBASE-5954 should be done in order to see
benefits that HBASE-12848 potentially brings in. But could you please clarify
on the "storing of column families" - what Ted did here would be a starting
point for that? I took a quick look at the patch and it seems it handles the
case of flushing but not compaction. Or, are you suggesting that we could
"promote" certain column families' files to SSDs when we see fit (manually /
automatically)..
bq. Then again compactions are tricky, since the write-amplification will wear
out the SSDs.
[~lhofhansl], did you have any material that talks about that. A quick search
on the web on this topic led me to some material but those were not conclusive.
I was chatting with [~sureshms] on this and we are both interested to hear more
this... ([~sureshms] feel free to chime in).
> Utilize Flash storage for flushing
> ----------------------------------
>
> Key: HBASE-12934
> URL: https://issues.apache.org/jira/browse/HBASE-12934
> Project: HBase
> Issue Type: Sub-task
> Reporter: Ted Yu
> Assignee: Ted Yu
> Attachments: 12934-001.txt
>
>
> Store flushing should be able to make use of hdfs storage policy.
> One option is to allow setting storage policy for the directory path of the
> specified column family.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
