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-1757) Auxiliary service support for nodemanager recovery
Date Mon, 07 Apr 2014 21:01:42 GMT

    [ https://issues.apache.org/jira/browse/YARN-1757?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13962251#comment-13962251
] 

Jason Lowe commented on YARN-1757:
----------------------------------

bq. We are doing all of YARN-1336 on trunk/branch-2 and not on a feature branch, right? 

Yes, I was not planning on doing a feature branch.  Feature branches are easy to iterate on
but difficult to keep current and get the final merge done.  I think this feature can be broken
up into small enough pieces that they can be reviewed and committed on their own merits and
provide useful functionality in the interim.  There's usefulness in recovering just aux services
(e.g.: can keep shuffling for previous jobs) or just localized resources (don't have to relocalize
across an NM reboot).

> Auxiliary service support for nodemanager recovery
> --------------------------------------------------
>
>                 Key: YARN-1757
>                 URL: https://issues.apache.org/jira/browse/YARN-1757
>             Project: Hadoop YARN
>          Issue Type: Sub-task
>          Components: nodemanager
>    Affects Versions: 2.3.0
>            Reporter: Jason Lowe
>            Assignee: Jason Lowe
>         Attachments: YARN-1757-v2.patch, YARN-1757.patch, YARN-1757.patch
>
>
> There needs to be a mechanism for communicating to auxiliary services whether nodemanager
recovery is enabled and where they should store their state.



--
This message was sent by Atlassian JIRA
(v6.2#6252)

Mime
View raw message