hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Nicolas Liochon (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HBASE-9855) evictBlocksByHfileName improvement for bucket cache
Date Mon, 04 Nov 2013 13:53:22 GMT

    [ https://issues.apache.org/jira/browse/HBASE-9855?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13812839#comment-13812839
] 

Nicolas Liochon commented on HBASE-9855:
----------------------------------------

On 0.96, mvn test -Dtest=TestHRegion#testParallelAppendWithMemStoreFlush is now flaky.
I've ran 50 tests on the previous commit, it works. With this commit in, it fails 20% of the
time:

Failed tests:   testParallelAppendWithMemStoreFlush(org.apache.hadoop.hbase.regionserver.TestHRegion):
array lengths differed, expected.length=2000 actual.length=1996

I didn't test on trunk.

> evictBlocksByHfileName improvement for bucket cache
> ---------------------------------------------------
>
>                 Key: HBASE-9855
>                 URL: https://issues.apache.org/jira/browse/HBASE-9855
>             Project: HBase
>          Issue Type: Improvement
>          Components: regionserver
>    Affects Versions: 0.98.0
>            Reporter: Liang Xie
>            Assignee: Liang Xie
>             Fix For: 0.98.0, 0.96.1
>
>         Attachments: HBase-9855-v4.txt
>
>
> In deed, it comes from fb's l2 cache by [~avf]'s nice work,  i just did a simple backport
here. It could improve a linear-time search through the whole cache map into a log-access-time
map search.
> I did a small bench, showed it brings a bit gc overhead, but considering the evict on
close triggered by frequent compaction activity, seems reasonable?
> and i thought bring a "evictOnClose" config  into BucketCache ctor and only put/remove
the new index map while evictOnClose is true, seems this value could be set by each family
schema, but BucketCache is a global instance not per each family, so just ignore it rightnow...



--
This message was sent by Atlassian JIRA
(v6.1#6144)

Mime
View raw message