[jira] [Commented] (YARN-2883) Queuing of container requests in the NM

["Karthik Kambatla (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/YARN-2883?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15221849#comment-15221849 ] 

Karthik Kambatla commented on YARN-2883:
----------------------------------------

Discussed this briefly with [~kkaranasos]. Our opinions appear to differ on the scope of {{ContainersMonitorImpl}} - my opinion is this class should monitor only running containers and shouldn't be aware of containers that have not running yet or play part in decision making of when containers should start running. It appears [~kkaranasos] believes this class should also monitor when the non-running containers should start running. 

IMO, expanding the scope of {{ContainersMonitorImpl}} makes the code hard to follow as we have communication going both ways between {{ContainersMonitorImpl}} and {{ContainersManagerImpl}}. Also, {{ContainersMonitorImpl}} will then have state that needs to be persisted for a work-preserving NM restart. Would like to hear others' thoughts. [~chris.douglas], [~asuresh] - what do you guys think? /cc [~jlowe]

> Queuing of container requests in the NM
> ---------------------------------------
>
>                 Key: YARN-2883
>                 URL: https://issues.apache.org/jira/browse/YARN-2883
>             Project: Hadoop YARN
>          Issue Type: Sub-task
>          Components: nodemanager, resourcemanager
>            Reporter: Konstantinos Karanasos
>            Assignee: Konstantinos Karanasos
>         Attachments: YARN-2883-trunk.004.patch, YARN-2883-trunk.005.patch, YARN-2883-trunk.006.patch, YARN-2883-trunk.007.patch, YARN-2883-trunk.008.patch, YARN-2883-yarn-2877.001.patch, YARN-2883-yarn-2877.002.patch, YARN-2883-yarn-2877.003.patch, YARN-2883-yarn-2877.004.patch
>
>
> We propose to add a queue in each NM, where queueable container requests can be held.
> Based on the available resources in the node and the containers in the queue, the NM will decide when to allow the execution of a queued container.
> In order to ensure the instantaneous start of a guaranteed-start container, the NM may decide to pre-empt/kill running queueable containers.



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