[
https://issues.apache.org/jira/browse/KUDU-3061?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17495988#comment-17495988
]
shenxingwuying edited comment on KUDU-3061 at 5/5/22 8:49 AM:
--------------------------------------------------------------
This work can assign to me. Now I am thinking do the work.
My basic idea is every tablet server leaders' number : replicas' number should
be 1: replica_refactor.
If needed , I can write a doc to describe my detail thought.
Adding another thread in master do the work, only leader can run the leader
rebalance.
The work should based on replica rebalances work enabled.
was (Author: shenxingwuying):
This work can assign to me. Now I am thinking do the work.
My basic idea is every tablet server leaders' number : replicas' number should
be 1:3.
If needed , I can write a doc to describe my detail thought.
Adding another thread in master do the work, only leader can run the leader
rebalance.
The work should based on replica rebalances work enabled.
> Balance tablet leaders across TServers
> --------------------------------------
>
> Key: KUDU-3061
> URL: https://issues.apache.org/jira/browse/KUDU-3061
> Project: Kudu
> Issue Type: New Feature
> Components: api, tablet
> Affects Versions: 1.11.1
> Reporter: Adam Voga
> Assignee: shenxingwuying
> Priority: Major
> Labels: performance, roadmap-candidate, scalability
>
> The number of leader tablets per tablet server can become imbalanced over
> time, putting additional pressure on a few nodes.
> A CLI tool or an extension to the existing balancer should be added to take
> care of this.
> Currently the only option is running leader_step_down manually.
--
This message was sent by Atlassian Jira
(v8.20.7#820007)
