[
https://issues.apache.org/jira/browse/HBASE-2945?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12904873#action_12904873
]
Jonathan Gray commented on HBASE-2945:
--------------------------------------
Also, we should review the high/low watermark values. I made those up rather
arbitrarily. With the current defaults, what I've seen in practice is under
heady read load there are very frequent evictions (ever few seconds) but each
is only evicting a small amount of memory (10% of total block cache size).
Considering the evictions are non-blocking and do seem to keep up regardless,
would evicting 2-3X as much each time yield better or worse GC performance?
Ideal behavior, performance/gc aside, I think would be to have as little
evicted each time as possible.
More discussion about changing the block cache lru is over on HBASE-2663.
> stop using string for block name in LRU block cache/hfile
> ---------------------------------------------------------
>
> Key: HBASE-2945
> URL: https://issues.apache.org/jira/browse/HBASE-2945
> Project: HBase
> Issue Type: Bug
> Affects Versions: 0.89.20100621
> Reporter: ryan rawson
>
> all my profiling runs indicate there is a large number of string/char[]
> objects and string manipulation is taking a long time in profiling runs.
> These come from the LRU block cache, block id. Also we should support the
> eviction of blocks belonging to particular hfiles, and the current code
> doesn't help with that right now.
> Let's do something better. Whatever that might be.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
