[
https://issues.apache.org/jira/browse/HDFS-17688?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17905508#comment-17905508
]
ASF GitHub Bot commented on HDFS-17688:
---------------------------------------
huangzhaobo99 opened a new pull request, #7225:
URL: https://github.com/apache/hadoop/pull/7225
### Description of PR
With https://github.com/apache/hadoop/pull/7120 Similarly.
It is used to limit the number of nodes that exceed the cluster average but
are below threshold.
During each round of balancer operation, sometimes does not focus on nodes
that are greater than the average value(AboveAvgUtilized), but instead
prioritizes processing nodes that exceed the threshold(OverUtilized), we can
set 'limitAboveAvgUtilizedNum' value to 0.
### How was this patch tested?
Add UT
> Add Option to limit Balancer aboveAvgUtilized nodes num in each iteration.
> --------------------------------------------------------------------------
>
> Key: HDFS-17688
> URL: https://issues.apache.org/jira/browse/HDFS-17688
> Project: Hadoop HDFS
> Issue Type: New Feature
> Reporter: Zhaobo Huang
> Assignee: Zhaobo Huang
> Priority: Major
>
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: hdfs-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org
