[
https://issues.apache.org/jira/browse/YARN-2883?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Konstantinos Karanasos updated YARN-2883:
-----------------------------------------
Attachment: YARN-2883-trunk.012.patch
I am attaching a new version of the patch, in which I got rid of the
{{QueuingContainersMonitorImpl}}. The {{containersAllocation}} field is now
moved to the {{ContainersManagerImpl}}.
Give it a look, [~kasha] and [~asuresh].
What I don't like is that I had to expose a lot of new methods in the
{{ContainerManager}} interface, and also that I had to add a field (i.e., the
{{containersAllocation}}) to the {{ContainerManagerImpl}} that will not be
updated if queuing is not enabled.
That said, unless I am missing something (as in being able to access the
methods of the {{ContainersManagerImpl}} without exposing them to the
interface, which actually does not solve the second problem I mention above), I
prefer the previous version of the patch that had the
{{QueuingContainersMonitorImpl}}.
I agree though with moving the pickOpportunisticContainersToKill to the
{{QueuingContainerManagerImpl}}.
Let me know what you think.
> 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-trunk.009.patch,
> YARN-2883-trunk.010.patch, YARN-2883-trunk.011.patch,
> YARN-2883-trunk.012.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)
