hadoop-yarn-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Abhishek Kapoor (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (YARN-816) Implement AM recovery for distributed shell
Date Fri, 12 Jul 2013 05:46:05 GMT

    [ https://issues.apache.org/jira/browse/YARN-816?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13706667#comment-13706667
] 

Abhishek Kapoor commented on YARN-816:
--------------------------------------

Couldn't agree more [~vinodkv]

We can have state of AM communicated to RM.
When AM boots up, the state from RM should be communicated to AM for example whether its a
fresh start or a recovery and if its a recovery the state of the nodes app was running on,
should be communicated to AM by RM. 

The above use case might require communication protocol change between AM and RM ..

                
> Implement AM recovery for distributed shell
> -------------------------------------------
>
>                 Key: YARN-816
>                 URL: https://issues.apache.org/jira/browse/YARN-816
>             Project: Hadoop YARN
>          Issue Type: Improvement
>          Components: applications/distributed-shell
>            Reporter: Vinod Kumar Vavilapalli
>
> Simple recovery to just continue from where it left off is a good start.

--
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