[
https://issues.apache.org/jira/browse/FLINK-8266?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16325899#comment-16325899
]
ASF GitHub Bot commented on FLINK-8266:
---------------------------------------
Github user shuai-xu commented on the issue:
https://github.com/apache/flink/pull/5170
@tillrohrmann sorry, the conflict is resolved now
> Add network memory to ResourceProfile
> -------------------------------------
>
> Key: FLINK-8266
> URL: https://issues.apache.org/jira/browse/FLINK-8266
> Project: Flink
> Issue Type: Improvement
> Components: Cluster Management
> Reporter: shuai.xu
> Assignee: shuai.xu
> Priority: Major
> Labels: flip-6
>
> In task manager side, it should allocated the network buffer pool according
> to the input channel and output sub partition number, but when allocating a
> worker, the resource profile doesn't contain the information about these
> memory.
> So I suggest add a network memory filed to ResourceProfile and job master
> should calculate it when scheduling a task and then resource manager can
> allocating a container with the resource profile.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
