Arun Suresh updated YARN-2885:
    Attachment: YARN-2885_api_changes.patch

Attaching the API changes as a separate patch.

As suggested by [~leftnoteasy], Introducing a new 
*DistributedSchedulerProtocol* which extends the *ApplicationMasterProtocol* 
with two extra methods *registedApplicationMasterForDistScheduling* and 
*allocateForDistScheduling*. This would behave as follows :
# For NMs supporting Distributed Scheduling, the register and allocate calls 
made by the AM (via the AMProtocol) will be intercepted by the LocalRM, which 
will use the new *DistributedSchedulerProtocol* to talk to a coordinator on the 
RM. The coordinator will wrap the response with extra information (anything 
policy related) which the LocalRM on the NM will strip off before returning the 
response to the AM. This way, the AM will not see any protocol change.

> Create AMRMProxy request interceptor for distributed scheduling decisions for 
> queueable containers
> --------------------------------------------------------------------------------------------------
>                 Key: YARN-2885
>                 URL: https://issues.apache.org/jira/browse/YARN-2885
>             Project: Hadoop YARN
>          Issue Type: Sub-task
>          Components: nodemanager, resourcemanager
>            Reporter: Konstantinos Karanasos
>            Assignee: Arun Suresh
>         Attachments: YARN-2885-yarn-2877.001.patch, 
> YARN-2885_api_changes.patch
> We propose to add a Local ResourceManager (LocalRM) to the NM in order to 
> support distributed scheduling decisions. 
> Architecturally we leverage the RMProxy, introduced in YARN-2884. 
> The LocalRM makes distributed decisions for queuable containers requests. 
> Guaranteed-start requests are still handled by the central RM.

This message was sent by Atlassian JIRA

Reply via email to