Mailing-List: contact yarn-issues-help@hadoop.apache.org; run by ezmlm
Precedence: bulk
Reply-To: yarn-issues@hadoop.apache.org
Date: Thu, 21 Jan 2016 15:32:40 +0000 (UTC)
From: "Thomas Graves (JIRA)" <jira@apache.org>
To: yarn-issues@hadoop.apache.org
Message-ID: <JIRA.12932540.1453240252000.171689.1453390360174@Atlassian.JIRA>
In-Reply-To: <JIRA.12932540.1453240252000@Atlassian.JIRA>
References: <JIRA.12932540.1453240252000@Atlassian.JIRA>
 <JIRA.12932540.1453240252889@arcas>
Subject: [jira] [Commented] (YARN-4610) Reservations continue looking for
 one app causes other apps to starve
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit


    [ https://issues.apache.org/jira/browse/YARN-4610?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15110778#comment-15110778 ] 

Thomas Graves commented on YARN-4610:
-------------------------------------

+1 for branch 2.7.  After investigating this some more the original patch of setting it to none() works. The reason is that the parents limit is passed and it would be taken into account int he leaf calculation.  I think the latter patch is safer but either is fine with me.

The master patch I'm not sure about how its taking the max capacity into account so I'll have to look at that more, but the unit tests are passing and that would be a separate issue from this fix.  +1 on that patch as well.

> Reservations continue looking for one app causes other apps to starve
> ---------------------------------------------------------------------
>
>                 Key: YARN-4610
>                 URL: https://issues.apache.org/jira/browse/YARN-4610
>             Project: Hadoop YARN
>          Issue Type: Bug
>          Components: capacityscheduler
>    Affects Versions: 2.7.1
>            Reporter: Jason Lowe
>            Assignee: Jason Lowe
>            Priority: Blocker
>         Attachments: YARN-4610-branch-2.7.002.patch, YARN-4610.001.patch, YARN-4610.branch-2.7.001.patch
>
>
> CapacityScheduler's LeafQueue has "reservations continue looking" logic that allows an application to unreserve elsewhere to fulfil a container request on a node that has available space.  However in 2.7 that logic seems to break allocations for subsequent apps in the queue.  Once a user hits its user limit, subsequent apps in the queue for other users receive containers at a significantly reduced rate.


--
This message was sent by Atlassian JIRA
(v6.3.4#6332)