[
https://issues.apache.org/jira/browse/HBASE-9857?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14004397#comment-14004397
]
Andrew Purtell commented on HBASE-9857:
---------------------------------------
Thanks for noticing the missing header. Will add it.
I'm on the phone so don't have the patch in front of me. I think cancel() is
not needed because we remove the entry for the prefetch upon exception but will
double check tomorrow.
> Blockcache prefetch option
> --------------------------
>
> Key: HBASE-9857
> URL: https://issues.apache.org/jira/browse/HBASE-9857
> Project: HBase
> Issue Type: Improvement
> Reporter: Andrew Purtell
> Assignee: Andrew Purtell
> Priority: Minor
> Fix For: 0.99.0, 0.98.3
>
> Attachments: 9857.patch, 9857.patch, HBASE-9857-0.98.patch,
> HBASE-9857-trunk.patch, HBASE-9857-trunk.patch
>
>
> Attached patch implements a prefetching function for HFile (v3) blocks, if
> indicated by a column family or regionserver property. The purpose of this
> change is to as rapidly after region open as reasonable warm the blockcache
> with all the data and index blocks of (presumably also in-memory) table data,
> without counting those block loads as cache misses. Great for fast reads and
> keeping the cache hit ratio high. Can tune the IO impact versus time until
> all data blocks are in cache. Works a bit like CompactSplitThread. Makes some
> effort not to stampede.
> I have been using this for setting up various experiments and thought I'd
> polish it up a bit and throw it out there. If the data to be preloaded will
> not fit in blockcache, or if as a percentage of blockcache it is large, this
> is not a good idea, will just blow out the cache and trigger a lot of useless
> GC activity. Might be useful as an expert tuning option though. Or not.
--
This message was sent by Atlassian JIRA
(v6.2#6252)
