[
https://issues.apache.org/jira/browse/HADOOP-2527?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12556152#action_12556152
]
Billy Pearson commented on HADOOP-2527:
---------------------------------------
not sure I have not looked at the code but I thank it works off load/request
load of the server for placement maybe when/if we decide to put some logic in
to the master to assign regions to nodes that have local copys of the data we
could put something in there to balance out the nodes more even.
Billy
> Poor distribution of regions
> ----------------------------
>
> Key: HADOOP-2527
> URL: https://issues.apache.org/jira/browse/HADOOP-2527
> Project: Hadoop
> Issue Type: Improvement
> Components: contrib/hbase
> Affects Versions: 0.15.0
> Environment: CentOS 5
> Reporter: Chris Kline
> Priority: Minor
>
> We get poor distribution of regions when we start up HBase. We have a total
> of 13 nodes and 898 regions, which should yield an average of 69 regions per
> node. Instead, one node has 173 regions and one node has 16 regions.
> Address Start Code Load
> 10.100.11.62:60020 1199406218912 requests: 0 regions: 63
> 10.100.11.59:60020 1199406219179 requests: 0 regions: 55
> 10.100.11.60:60020 1199406219062 requests: 0 regions: 90
> 10.100.11.61:60020 1199406219132 requests: 1 regions: 54
> 10.100.11.64:60020 1199406218817 requests: 0 regions: 173
> 10.100.11.31:60020 1199406219039 requests: 1 regions: 16
> 10.100.11.58:60020 1199406218895 requests: 0 regions: 89
> 10.100.11.56:60020 1199406219037 requests: 0 regions: 76
> 10.100.11.65:60020 1199406219135 requests: 0 regions: 56
> 10.100.11.57:60020 1199406219183 requests: 1 regions: 56
> 10.100.11.33:60020 1199406219174 requests: 1 regions: 56
> 10.100.11.32:60020 1199406218944 requests: 0 regions: 66
> 10.100.11.63:60020 1199406219182 requests: 0 regions: 48
> Total: servers: 13 requests: 4 regions: 898
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
