[
https://issues.apache.org/jira/browse/HBASE-15480?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15248384#comment-15248384
]
Andrew Purtell commented on HBASE-15480:
----------------------------------------
bq. (Ted) Can you post improvement in performance with the patch ?
bq. (Walter) illustration of poor performance before change
I think we need before and after measurements to assess the impact of the
change. I found the screenshot grabbed from a profile fairly context free as
well. If you can use a respected microbenchmark harness like JMH to get before
and after numbers, and those numbers are favorable, I will commit this.
> Bloom Filter check needs to be more efficient for array
> -------------------------------------------------------
>
> Key: HBASE-15480
> URL: https://issues.apache.org/jira/browse/HBASE-15480
> Project: HBase
> Issue Type: Improvement
> Components: Performance
> Affects Versions: 1.0.3
> Reporter: Walter Koetke
> Assignee: Walter Koetke
> Fix For: 1.0.4
>
> Attachments: BloomFilterCheckOneByOne.tiff,
> HBASE-15480-branch-1.0.patch, HBASE-15480.patch
>
>
> It is currently inefficient to do lots of bloom filter checks. Each check has
> overhead like going to the block cache to retrieve the block and recording
> metrics. It would be good to have one bloom filter check api that does a
> bunch of checks without so much block retrieval and metrics updates.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
