hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Hudson (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HBASE-17462) Use sliding window for read/write request costs in StochasticLoadBalancer
Date Mon, 23 Jan 2017 07:45:27 GMT

    [ https://issues.apache.org/jira/browse/HBASE-17462?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15834015#comment-15834015
] 

Hudson commented on HBASE-17462:
--------------------------------

FAILURE: Integrated in Jenkins build HBase-Trunk_matrix #2369 (See [https://builds.apache.org/job/HBase-Trunk_matrix/2369/])
HBASE-17462 Use sliding window for read/write request costs in (tedyu: rev 7754a9620eff44d1d570fda534f9159a756310cd)
* (edit) hbase-server/src/test/java/org/apache/hadoop/hbase/master/balancer/TestStochasticLoadBalancer.java
* (edit) hbase-server/src/main/java/org/apache/hadoop/hbase/master/balancer/StochasticLoadBalancer.java


> Use sliding window for read/write request costs in StochasticLoadBalancer
> -------------------------------------------------------------------------
>
>                 Key: HBASE-17462
>                 URL: https://issues.apache.org/jira/browse/HBASE-17462
>             Project: HBase
>          Issue Type: Improvement
>            Reporter: Ted Yu
>            Assignee: Tim Brown
>              Labels: patch
>             Fix For: 2.0.0, 1.4.0
>
>         Attachments: after_changes.png, before_changes.png, HBASE-17462.patch, HBASE-17462-v2.patch
>
>
> In the thread, http://search-hadoop.com/m/HBase/YGbbyUZKXWALkX1, Timothy was asking whether
the read/write request costs in StochasticLoadBalancer should be calculated as rates.
> This makes sense since read / write load on region server tends to fluctuate over time.
Using sliding window would reflect more recent trend in read / write load.
> Some factors to consider:
> The data structure used by StochasticLoadBalancer should be concise. The
> number of regions in a cluster can be expected to approach 1 million. We
> cannot afford to store long history of read / write requests in master.
> Efficiency of cost calculation should be high - there're many cost
> functions the balancer goes through, it is expected for each cost function
> to return quickly. Otherwise we would not come up with proper region
> movement plan(s) in time.



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

Mime
View raw message