hadoop-yarn-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Jian Fang (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (YARN-1680) availableResources sent to applicationMaster in heartbeat should exclude blacklistedNodes free memory.
Date Wed, 01 Oct 2014 18:21:34 GMT

    [ https://issues.apache.org/jira/browse/YARN-1680?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14155235#comment-14155235
] 

Jian Fang commented on YARN-1680:
---------------------------------

I may be wrong because I don't understand the logic fully. Seems your patch calculates the
blacklisted resource for each application. Please clarify for me whether the blacklisted node
is a cluster level concept or an application level one. What if multiple applications have
different sets of blacklisted nodes? If the blacklisted node is at the cluster level, the
blacklisted resource seems should be calculated at the cluster level, that is to say, you
need to get the blacklisted nodes from other applications as well. If it is only at the application
level, I wonder how the blacklist-task-tracker command works in hadoop one. 

> availableResources sent to applicationMaster in heartbeat should exclude blacklistedNodes
free memory.
> ------------------------------------------------------------------------------------------------------
>
>                 Key: YARN-1680
>                 URL: https://issues.apache.org/jira/browse/YARN-1680
>             Project: Hadoop YARN
>          Issue Type: Sub-task
>    Affects Versions: 2.2.0, 2.3.0
>         Environment: SuSE 11 SP2 + Hadoop-2.3 
>            Reporter: Rohith
>            Assignee: Chen He
>         Attachments: YARN-1680-WIP.patch, YARN-1680-v2.patch, YARN-1680-v2.patch, YARN-1680.patch
>
>
> There are 4 NodeManagers with 8GB each.Total cluster capacity is 32GB.Cluster slow start
is set to 1.
> Job is running reducer task occupied 29GB of cluster.One NodeManager(NM-4) is become
unstable(3 Map got killed), MRAppMaster blacklisted unstable NodeManager(NM-4). All reducer
task are running in cluster now.
> MRAppMaster does not preempt the reducers because for Reducer preemption calculation,
headRoom is considering blacklisted nodes memory. This makes jobs to hang forever(ResourceManager
does not assing any new containers on blacklisted nodes but returns availableResouce considers
cluster free memory). 



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

Mime
View raw message