Mailing-List: contact yarn-issues-help@hadoop.apache.org; run by ezmlm
Precedence: bulk
Date: Wed, 22 Mar 2017 06:37:43 +0000 (UTC)
From: "Sunil G (JIRA)" <jira@apache.org>
To: yarn-issues@hadoop.apache.org
Message-ID: <JIRA.13021256.1479328337000.84974.1490164663692@Atlassian.JIRA>
In-Reply-To: <JIRA.13021256.1479328337000@Atlassian.JIRA>
References: <JIRA.13021256.1479328337000@Atlassian.JIRA> <JIRA.13021256.1479328337470@jira-lw-us.apache.org>
Subject: [jira] [Commented] (YARN-5892) Capacity Scheduler: Support
 user-specific minimum user limit percent
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit
archived-at: Wed, 22 Mar 2017 06:37:49 -0000


    [ https://issues.apache.org/jira/browse/YARN-5892?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15935823#comment-15935823 ] 

Sunil G commented on YARN-5892:
-------------------------------

Hi [~eepayne]
Thanks for working on this patch.

I have some doubts which are inline with Wangdas comments as well.

1. Do we need to store *localVersionOfUsersState* per user level. Currently we invalidate all user's limit if there is a semantic change (queue refresh, cluster resource change etc). Currently we invalidate per user level as per this patch, please correct me if I got that wrong. So if we invalidate per user level, how about other users in case of resource change/ config change etc.
2. I could see that *compureUserLimit* method internally consider the user's weight. Do we need to do this way? Is it possible to keep existing computation as it is, and then from external caller side, we can multiply with specific user's weight with computed user-limit.  

> Capacity Scheduler: Support user-specific minimum user limit percent
> --------------------------------------------------------------------
>
>                 Key: YARN-5892
>                 URL: https://issues.apache.org/jira/browse/YARN-5892
>             Project: Hadoop YARN
>          Issue Type: Improvement
>          Components: capacityscheduler
>            Reporter: Eric Payne
>            Assignee: Eric Payne
>         Attachments: Active users highlighted.jpg, YARN-5892.001.patch, YARN-5892.002.patch, YARN-5892.003.patch, YARN-5892.004.patch, YARN-5892.005.patch
>
>
> Currently, in the capacity scheduler, the {{minimum-user-limit-percent}} property is per queue. A cluster admin should be able to set the minimum user limit percent on a per-user basis within the queue.
> This functionality is needed so that when intra-queue preemption is enabled (YARN-4945 / YARN-2113), some users can be deemed as more important than other users, and resources from VIP users won't be as likely to be preempted.
> For example, if the {{getstuffdone}} queue has a MULP of 25 percent, but user {{jane}} is a power user of queue {{getstuffdone}} and needs to be guaranteed 75 percent, the properties for {{getstuffdone}} and {{jane}} would look like this:
> {code}
>   <property>
>     <name>yarn.scheduler.capacity.root.getstuffdone.minimum-user-limit-percent</name>
>     <value>25</value>
>   </property>
>   <property>
>     <name>yarn.scheduler.capacity.root.getstuffdone.jane.minimum-user-limit-percent</name>
>     <value>75</value>
>   </property>
> {code}


--
This message was sent by Atlassian JIRA
(v6.3.15#6346)

---------------------------------------------------------------------
To unsubscribe, e-mail: yarn-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: yarn-issues-help@hadoop.apache.org