Mailing-List: contact dev-help@hive.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@hive.apache.org
Date: Mon, 17 Jun 2013 19:01:26 +0000 (UTC)
From: "Alan Gates (JIRA)" <jira@apache.org>
To: hive-dev@hadoop.apache.org
Message-ID: <JIRA.12651479.1370553754323.127218.1371495686165@arcas>
In-Reply-To: <JIRA.12651479.1370553754323@arcas>
References: <JIRA.12651479.1370553754323@arcas>
Subject: [jira] [Updated] (HIVE-4679) WebHCat can deadlock Hadoop if the
 number of concurrently running tasks if higher or equal than the number of
 mappers
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit


     [ https://issues.apache.org/jira/browse/HIVE-4679?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Alan Gates updated HIVE-4679:
-----------------------------

    Status: Open  (was: Patch Available)
    
> WebHCat can deadlock Hadoop if the number of concurrently running tasks if higher or equal than the number of mappers
> ---------------------------------------------------------------------------------------------------------------------
>
>                 Key: HIVE-4679
>                 URL: https://issues.apache.org/jira/browse/HIVE-4679
>             Project: Hive
>          Issue Type: Bug
>          Components: HCatalog
>    Affects Versions: 0.10.0
>            Reporter: Eugene Koifman
>            Assignee: Eugene Koifman
>             Fix For: 0.12.0
>
>         Attachments: HIVE-4679.patch
>
>
> o In the current Templeton design, each time a Job is submitted thru the REST API (it can be Pig/Hive or MR job), it will consume one Hadoop map slot. Given that the number of map slots is finite in the cluster (16 node cluster will have 32 map slots), in some circumstances, a user can deadlock the cluster if Templeton job submission pipeline takes over all map slots (Templeton map tasks will wait for the actual underlying jobs to complete, what will never happen, given that Hadoop has no free map slots to schedule new tasks).
> o HCat queries use a different mechanism and do not contribute to the deadlock.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira