[
https://issues.apache.org/jira/browse/HBASE-11323?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14031616#comment-14031616
]
Andrew Purtell commented on HBASE-11323:
----------------------------------------
We have various results that all indicate _some_ penalty for using the bucket
cache, with commensurate improvement in GC related metrics. It can be a trade
off well worth making but should not be a global decision. I think we should
make combined LRU cache + bucket cache the default, but only if we can have the
default placement for data blocks still be on heap and plumb down schema level
selection of block placement off heap. Then you can have, on a per CF basis,
such strategies as large warm data off heap with block encoding (trade scanning
CPU for serde/copying costs) and smaller hot data on heap with no encoding. At
a future time we could have a few caching strategies like this automatically
managed by ergonomics.
> BucketCache all the time!
> -------------------------
>
> Key: HBASE-11323
> URL: https://issues.apache.org/jira/browse/HBASE-11323
> Project: HBase
> Issue Type: Sub-task
> Components: io
> Reporter: stack
> Fix For: 0.99.0
>
> Attachments: ReportBlockCache.pdf
>
>
> One way to realize the parent issue is to just enable bucket cache all the
> time; i.e. always have offheap enabled. Would have to do some work to make
> it drop-dead simple on initial setup (I think it doable).
> So, upside would be the offheap upsides (less GC, less likely to go away and
> never come back because of full GC when heap is large, etc.).
> Downside is higher latency. In Nick's BlockCache 101 there is little to no
> difference between onheap and offheap. In a basic compare doing scans and
> gets -- details to follow -- I have BucketCache deploy about 20% less ops
> than LRUBC when all incache and maybe 10% less ops when falling out of cache.
> I can't tell difference in means and 95th and 99th are roughly same (more
> stable with BucketCache). GC profile is much better with BucketCache -- way
> less. BucketCache uses about 7% more user CPU.
> More detail on comparison to follow.
> I think the numbers disagree enough we should probably do the [~lhofhansl]
> suggestion, that we allow you to have a table sit in LRUBC, something the
> current bucket cache layout does not do.
--
This message was sent by Atlassian JIRA
(v6.2#6252)
