You are viewing a plain text version of this content. The canonical link for it is here.
Posted to yarn-issues@hadoop.apache.org by "Yufei Gu (JIRA)" <ji...@apache.org> on 2017/08/18 20:46:00 UTC
[jira] [Comment Edited] (YARN-4090) Make Collections.sort() more
efficient by caching resource usage
[ https://issues.apache.org/jira/browse/YARN-4090?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16133595#comment-16133595 ]
Yufei Gu edited comment on YARN-4090 at 8/18/17 8:45 PM:
---------------------------------------------------------
Uploaded patch v7. To cache the resource usage in queues. We should recalculate resource usage for each queue and it parents in following situation. Patch v7 covers all of them.
- allocate, which increases resource usage
- moveApplication, which increases resource usage in a queue and decrease
resource usage in another queue
- container completed, which decreases resource usage
- preemption, which decreases resource usage when track resource to preempted for a job.
- add a node -> recover containers on a node -> increase resource usage
- remove a node -> complete a container -> decrease resource usage
was (Author: yufeigu):
Uploaded patch v7. To cache the resource usage in queues. We should recalculate resource usage for each queue and it parents in following situation. Patch v7 covers all of them.
- allocate, which increase resource usage
- moveApplication, which increase resource usage in a queue and decrease
resource usage in another queue
- container completed, which decrease resource usage
- preemption
- add a node -> recover containers on a node -> increase resource usage
- remove a node -> complete a container -> decrease resource usage
> Make Collections.sort() more efficient by caching resource usage
> ----------------------------------------------------------------
>
> Key: YARN-4090
> URL: https://issues.apache.org/jira/browse/YARN-4090
> Project: Hadoop YARN
> Issue Type: Sub-task
> Components: fairscheduler
> Reporter: Xianyin Xin
> Assignee: zhangshilong
> Attachments: sampling1.jpg, sampling2.jpg, YARN-4090.001.patch, YARN-4090.002.patch, YARN-4090.003.patch, YARN-4090.004.patch, YARN-4090.005.patch, YARN-4090.006.patch, YARN-4090.007.patch, YARN-4090-preview.patch, YARN-4090-TestResult.pdf
>
>
> Collections.sort() consumes too much time in a scheduling round.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
---------------------------------------------------------------------
To unsubscribe, e-mail: yarn-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: yarn-issues-help@hadoop.apache.org