[jira] [Commented] (YARN-1712) Admission Control: plan follower

["Wangda Tan (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/YARN-1712?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14119933#comment-14119933 ] 

Wangda Tan commented on YARN-1712:
----------------------------------

Hi [~curino],
Thanks for working on this patch,
I'm not sure if I completely understand the logic of {{synchronizePlan}} correctly , please correct me if I was wrong,
1) Get total resource of currentReservations, 
2) If sum(currentReservations) > {{planResources}}, shrink will happen
3) Make sure default queue added
4) Get expired reservations,
If getMoveOnExpiry(): move them to default queue
Else: kill them
Question: Why not do 2) after 4)? Is it better to do shrink after excluded expired reservations?

5) Set all entitlements of expired queue to 0, and remove such queues
6) Sort all reservations, from less to more satisfied, and set their new entitlement.
Question: Is it possible {{totalAssignedCapacity}} > 1? Could you please explain how to avoid it happen?

7) Set rest capacity to default queue

One comment is,
Current compare and sort reservation is comparing (allocatedResource - guaranteedResource), one feeling at top of my mind is, this may make larger queue can get resource easier than small queue. Is it possible an app can get more resource than other by lying to RM that it needs more resource when fierce competition on resource?

Thanks,
Wangda


> Admission Control: plan follower
> --------------------------------
>
>                 Key: YARN-1712
>                 URL: https://issues.apache.org/jira/browse/YARN-1712
>             Project: Hadoop YARN
>          Issue Type: Sub-task
>          Components: capacityscheduler, resourcemanager
>            Reporter: Carlo Curino
>            Assignee: Carlo Curino
>              Labels: reservations, scheduler
>         Attachments: YARN-1712.1.patch, YARN-1712.patch
>
>
> This JIRA tracks a thread that continuously propagates the current state of an inventory subsystem to the scheduler. As the inventory subsystem store the "plan" of how the resources should be subdivided, the work we propose in this JIRA realizes such plan by dynamically instructing the CapacityScheduler to add/remove/resize queues to follow the plan.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)