You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@kudu.apache.org by "Alexey Serbin (JIRA)" <ji...@apache.org> on 2018/12/12 23:57:00 UTC
[jira] [Commented] (KUDU-2637) Add a note about leadership
imbalance in the faq
[ https://issues.apache.org/jira/browse/KUDU-2637?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16719564#comment-16719564 ]
Alexey Serbin commented on KUDU-2637:
-------------------------------------
Probably, it makes sense to add some data-backed explanation to illustrate that actual leader-related overhead is not that big. Running {{kudu perf loadgen}} workload against a small Kudu cluster (even with all tablet servers at the same node) and capturing metrics like {{cpu_utime}}, {{cpu_stime}}, {{threads_running}} and a snapshot of the {{MALLOC}} section of the {{/memz}} page generated by embedded Web server might be good enough.
> Add a note about leadership imbalance in the faq
> ------------------------------------------------
>
> Key: KUDU-2637
> URL: https://issues.apache.org/jira/browse/KUDU-2637
> Project: Kudu
> Issue Type: Improvement
> Components: documentation
> Reporter: Grant Henke
> Priority: Minor
>
> There have been a few questions on leadership imbalance and whether or not it is important to monitor and fix. We should update the FAQ section to address this.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)