Mailing-List: contact yarn-issues-help@hadoop.apache.org; run by ezmlm
Precedence: bulk
Reply-To: yarn-issues@hadoop.apache.org
Date: Wed, 10 Sep 2014 03:27:29 +0000 (UTC)
From: "Wangda Tan (JIRA)" <jira@apache.org>
To: yarn-issues@hadoop.apache.org
Message-ID: <JIRA.12736888.1409084149000.34367.1410319649670@Atlassian.JIRA>
In-Reply-To: <JIRA.12736888.1409084149000@Atlassian.JIRA>
References: <JIRA.12736888.1409084149000@Atlassian.JIRA>
 <JIRA.12736888.1409084149981@arcas>
Subject: [jira] [Commented] (YARN-2456) Possible deadlock in
 CapacityScheduler when RM is recovering apps
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit


    [ https://issues.apache.org/jira/browse/YARN-2456?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14127989#comment-14127989 ] 

Wangda Tan commented on YARN-2456:
----------------------------------

In addition, I suggest to change the {{deadlock}} of the title to be {{livelock}}, because no thread is locked here, it just a weird state preventing the state to make progress, instead of lock. See: http://en.wikipedia.org/wiki/Deadlock#Livelock

Wangda

> Possible deadlock in CapacityScheduler when RM is recovering apps
> -----------------------------------------------------------------
>
>                 Key: YARN-2456
>                 URL: https://issues.apache.org/jira/browse/YARN-2456
>             Project: Hadoop YARN
>          Issue Type: Sub-task
>          Components: resourcemanager
>            Reporter: Jian He
>            Assignee: Jian He
>         Attachments: YARN-2456.1.patch
>
>
> Consider this scenario:
> 1. RM is configured with a single queue and only one application can be active at a time.
> 2. Submit App1 which uses up the queue's whole capacity
> 3. Submit App2 which remains pending.
> 4. Restart RM.
> 5. App2 is recovered before App1, so App2 is added to the activeApplications list. Now App1 remains pending (because of max-active-app limit)
> 6. All containers of App1 are now recovered when NM registers, and use up the whole queue capacity again.
> 7. Since the queue is full, App2 cannot proceed to allocate AM container.
> 8. In the meanwhile, App1 cannot proceed to become active because of the max-active-app limit 


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