Karthik Kambatla commented on YARN-2448:

I am not sure I understand the usecase very well. The AM's requirements 
shouldn't change based on what the RM does internally. 

Shouldn't the application ask for all the resources that YARN supports? It is 
upto the scheduler (queue, user, app type etc.) to decide on what resources it 
would consider for scheduling. If the app doesn't specify any resources at all 
for a type, we can assume zero for that type (e.g. in clusters not configured 
to use a particular type). 

> RM should expose the name of the ResourceCalculator being used when AMs 
> register
> --------------------------------------------------------------------------------
>                 Key: YARN-2448
>                 URL: https://issues.apache.org/jira/browse/YARN-2448
>             Project: Hadoop YARN
>          Issue Type: Improvement
>            Reporter: Varun Vasudev
>            Assignee: Varun Vasudev
>         Attachments: apache-yarn-2448.0.patch, apache-yarn-2448.1.patch
> The RM should expose the name of the ResourceCalculator being used when AMs 
> register, as part of the RegisterApplicationMasterResponse.
> This will allow applications to make better decisions when scheduling. 
> MapReduce for example, only looks at memory when deciding it's scheduling, 
> even though the RM could potentially be using the DominantResourceCalculator.

This message was sent by Atlassian JIRA

Reply via email to