hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Lars Hofhansl (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HBASE-13291) Lift the scan ceiling
Date Fri, 27 Mar 2015 05:29:53 GMT

    [ https://issues.apache.org/jira/browse/HBASE-13291?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14383356#comment-14383356
] 

Lars Hofhansl commented on HBASE-13291:
---------------------------------------

Just ran a test with my setup. All local on one box.
I wrote 1m rows with 1 col of 1000 bytes each, i.e. ~1GB of data (verified the data size on
HDFS). I can scan through that (in 0.98) 0.4s with filtering all, so that's over 2m rows/s.
Is there anything different about P/E?


> Lift the scan ceiling
> ---------------------
>
>                 Key: HBASE-13291
>                 URL: https://issues.apache.org/jira/browse/HBASE-13291
>             Project: HBase
>          Issue Type: Improvement
>          Components: Scanners
>    Affects Versions: 1.0.0
>            Reporter: stack
>            Assignee: stack
>         Attachments: 13291.inlining.txt, Screen Shot 2015-03-26 at 12.12.13 PM.png, Screen
Shot 2015-03-26 at 3.39.33 PM.png, hack_to_bypass_bb.txt, nonBBposAndInineMvccVint.txt, q
(1).png, traces.7.svg, traces.filterall.svg, traces.nofilter.svg, traces.small2.svg, traces.smaller.svg
>
>
> Scanning medium sized rows with multiple concurrent scanners exhibits interesting 'ceiling'
properties. A server runs at about 6.7k ops a second using 450% of possible 1600% of CPUs
 when 4 clients each with 10 threads doing scan 1000 rows.  If I add '--filterAll' argument
(do not return results), then we run at 1450% of possible 1600% possible but we do 8k ops
a second.
> Let me attach flame graphs for two cases. Unfortunately, there is some frustrating dark
art going on. Let me try figure it... Filing issue in meantime to keep score in.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Mime
View raw message