[
https://issues.apache.org/jira/browse/HDDS-3743?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
runzhiwang updated HDDS-3743:
-----------------------------
Description:
I start a ozone cluster with 1000 datanodes, and run two weeks with heavy
workload, and perf om.
You can find NetUtils.normalize cost 0.17% cpu, because it needs to do
Matcher.replaceAll, we need not to do this when getFromProtoBuf, So we can
avoid normalize by check the last character.
!screenshot-2.png!
was:
I start a ozone cluster with 1000 datanodes, and run two weeks with heavy
workload, and perf om.
You can find NetUtils.normalize cost 4.83% cpu, because it needs to do
Matcher.replaceAll, we need not to do this when getFromProtoBuf, scm can do
NetUtils.normalize and keep the result in memory, then pass the result to om.
!screenshot-1.png!
> Avoid NetUtils.normalize when get DatanodeDetails from proto
> ------------------------------------------------------------
>
> Key: HDDS-3743
> URL: https://issues.apache.org/jira/browse/HDDS-3743
> Project: Hadoop Distributed Data Store
> Issue Type: Sub-task
> Reporter: runzhiwang
> Assignee: runzhiwang
> Priority: Major
> Attachments: om.svg, screenshot-1.png, screenshot-2.png
>
>
> I start a ozone cluster with 1000 datanodes, and run two weeks with heavy
> workload, and perf om.
> You can find NetUtils.normalize cost 0.17% cpu, because it needs to do
> Matcher.replaceAll, we need not to do this when getFromProtoBuf, So we can
> avoid normalize by check the last character.
> !screenshot-2.png!
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
