hadoop-yarn-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Jason Lowe (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (YARN-415) Capture memory utilization at the app-level for chargeback
Date Fri, 20 Sep 2013 21:48:54 GMT

    [ https://issues.apache.org/jira/browse/YARN-415?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13773472#comment-13773472
] 

Jason Lowe commented on YARN-415:
---------------------------------

I think the accounting should be based on the RM's view of the cluster state, since it is
controlling which applications get the resources.  If the RM allocates a container for an
application, whether the application ultimately uses it or not, it is a resource that is unavailable
for other applications to use.  Similarly if an RM allocates a container but it takes a while
for the AM to heartbeat in to receive it, takes even longer for the AM to connect to the NM
to launch it, and takes even longer for the NM to report back that the container completed,
all of that is still time where the container's resources were unavailable to other applications.
 The RM was setting aside those resources on behalf of that application, therefore the application
should be accountable.

Bugs in the RM or scheduler may cause extraneous containers to be allocated, but they are
still allocated on behalf of a particular application and should be charged accordingly.
                
> Capture memory utilization at the app-level for chargeback
> ----------------------------------------------------------
>
>                 Key: YARN-415
>                 URL: https://issues.apache.org/jira/browse/YARN-415
>             Project: Hadoop YARN
>          Issue Type: New Feature
>          Components: resourcemanager
>    Affects Versions: 0.23.6
>            Reporter: Kendall Thrapp
>            Assignee: Andrey Klochkov
>         Attachments: YARN-415--n2.patch, YARN-415--n3.patch, YARN-415.patch
>
>
> For the purpose of chargeback, I'd like to be able to compute the cost of an
> application in terms of cluster resource usage.  To start out, I'd like to get the memory
utilization of an application.  The unit should be MB-seconds or something similar and, from
a chargeback perspective, the memory amount should be the memory reserved for the application,
as even if the app didn't use all that memory, no one else was able to use it.
> (reserved ram for container 1 * lifetime of container 1) + (reserved ram for
> container 2 * lifetime of container 2) + ... + (reserved ram for container n * lifetime
of container n)
> It'd be nice to have this at the app level instead of the job level because:
> 1. We'd still be able to get memory usage for jobs that crashed (and wouldn't appear
on the job history server).
> 2. We'd be able to get memory usage for future non-MR jobs (e.g. Storm).
> This new metric should be available both through the RM UI and RM Web Services REST API.

--
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

Mime
View raw message