[
https://issues.apache.org/jira/browse/YARN-624?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13737246#comment-13737246
]
Robert Joseph Evans commented on YARN-624:
------------------------------------------
Carlo,
I do have to be total honest here too. Gang scheduling is an interesting
feature, but it is not the highest on my priority list. In the short to medium
term I am fine with launching containers and letting them wait until there are
enough to run the entire topology. I am also fine if I have to configure my
queues appropriately to avoid deadlock/preemption in the short to medium term.
If it is too difficult to have preemption be gang aware we can skip it, and ask
users to configure the queue appropriately. I just want to be sure that
whatever route we start down does not lock us into a model that will prevent me
from getting to my end goal.
> Support gang scheduling in the AM RM protocol
> ---------------------------------------------
>
> Key: YARN-624
> URL: https://issues.apache.org/jira/browse/YARN-624
> Project: Hadoop YARN
> Issue Type: Sub-task
> Components: api, scheduler
> Affects Versions: 2.0.4-alpha
> Reporter: Sandy Ryza
> Assignee: Sandy Ryza
>
> Per discussion on YARN-392 and elsewhere, gang scheduling, in which a
> scheduler runs a set of tasks when they can all be run at the same time,
> would be a useful feature for YARN schedulers to support.
> Currently, AMs can approximate this by holding on to containers until they
> get all the ones they need. However, this lends itself to deadlocks when
> different AMs are waiting on the same containers.
--
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
