Mailing-List: contact hbase-dev-help@hadoop.apache.org; run by ezmlm
Precedence: bulk
Reply-To: hbase-dev@hadoop.apache.org
Message-ID: <1385569648.1203980031310.JavaMail.jira@brutus>
Date: Mon, 25 Feb 2008 14:53:51 -0800 (PST)
From: "Bryan Duxbury (JIRA)" <jira@apache.org>
To: hbase-dev@hadoop.apache.org
Subject: [jira] Commented: (HBASE-71) [hbase] Master should rebalance region
 assignments periodically
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit


    [ https://issues.apache.org/jira/browse/HBASE-71?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12572294#action_12572294 ] 

Bryan Duxbury commented on HBASE-71:
------------------------------------

In a naive approach, the RegionManager decides that a regionserver is overloaded and tells it to close some of its regions, puts them back in the unassigned region list, and lets them get randomly reassigned. The problem with this approach is that during the time when it's being "transferred" (offline pending reassignment), the region will be unavailable. That would be sort of undesirable, since it would mean downtime and possibly a lot of retries for some consumers. 

Instead, maybe we could introduce a way for one regionserver to keep serving a region while another opens it read-only. Then, once the second server has it opened, we could switch who is assigned as the writer server. This would introduce a period of time where there might not be consistent state because of the memcache on the original writer. Not sure this would work, but it could help.

> [hbase] Master should rebalance region assignments periodically
> ---------------------------------------------------------------
>
>                 Key: HBASE-71
>                 URL: https://issues.apache.org/jira/browse/HBASE-71
>             Project: Hadoop HBase
>          Issue Type: Improvement
>          Components: master
>            Reporter: Bryan Duxbury
>            Assignee: Bryan Duxbury
>             Fix For: 0.2.0
>
>
> The master currently only does region assignments at startup or when there are splits or dead regionservers. This means that if you join a new regionserver to the cluster after startup, it does not get assigned a fair share of the already-served regions as you would expect. It only gets a share of new regions being served.
> The master should periodically check the balance of regions, based on whatever assignment function, instead of in reaction to the above listed events.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.