hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Jean-Daniel Cryans (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HBASE-3681) Check the sloppiness of the region load before balancing
Date Tue, 22 Mar 2011 20:42:06 GMT

    [ https://issues.apache.org/jira/browse/HBASE-3681?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13009828#comment-13009828
] 

Jean-Daniel Cryans commented on HBASE-3681:
-------------------------------------------

This is the behavior we're trying to get to. The current problem is that every time the master
balances you'll have some disruption. You could instead set the balancer to run less often,
and have one big batch of regions moving at the same time while some region server may get
really unbalanced. Since the time to rebalance 5 regions can easily be the same as rebalancing
50 regions, the disruption ends up being almost the same.

To optimize that situation, we want to keep running the balancer often but first check against
some sloppiness.

> Check the sloppiness of the region load before balancing
> --------------------------------------------------------
>
>                 Key: HBASE-3681
>                 URL: https://issues.apache.org/jira/browse/HBASE-3681
>             Project: HBase
>          Issue Type: Improvement
>    Affects Versions: 0.90.1
>            Reporter: Jean-Daniel Cryans
>            Assignee: Ted Yu
>             Fix For: 0.92.0
>
>         Attachments: hbase-3681.txt
>
>
> Per our discussion at the hackathon today, it seems that it would be more helpful to
add a sloppiness check before doing the normal balancing.
> The current situation is that the balancer always tries to get the region load even,
meaning that there can be some very frequent regions movement.
> Setting the balancer to run less often (like every 4 hours) isn't much better since the
load could get out of whack easily.
> This is why running the normal balancer frequently, but first checking for some sloppiness
in the region load across the RS, seems like a more viable option.

--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira

Mime
View raw message