hadoop-yarn-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Varun Saxena (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (YARN-6156) AM blacklistdisableThreshold consider node partition count
Date Mon, 13 Feb 2017 08:01:41 GMT

    [ https://issues.apache.org/jira/browse/YARN-6156?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15863305#comment-15863305

Varun Saxena commented on YARN-6156:

[~bibinchundatt], actually my first comment was about not using getAmNodeLabelExpression.
We can use node label expression from AM request directly. Seems it wasnt clear. Hasn't been
handled in the patch. Can you handle this?

bq. However if some resource are obtained from any such node, we have to increase and update
nodes count to SimpleBlacklistManager and then decrease node count when resources are removed.
Agree. That is what I meant when I said we are not refreshing node count and do not update
when node is added or removed. But this is same as before. So probably can be done in another

> AM blacklistdisableThreshold  consider node partition count
> -----------------------------------------------------------
>                 Key: YARN-6156
>                 URL: https://issues.apache.org/jira/browse/YARN-6156
>             Project: Hadoop YARN
>          Issue Type: Sub-task
>            Reporter: Bibin A Chundatt
>            Assignee: Bibin A Chundatt
>         Attachments: YARN-6156.0001.patch, YARN-6156.0002.patch
> As per the current implementation for AM blacklisting disabling is based on completed
custer resource.
> Incase of partitioned cluster, nodes applicable for AM labels only should be considered
as total nodes.

This message was sent by Atlassian JIRA

To unsubscribe, e-mail: yarn-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: yarn-issues-help@hadoop.apache.org

View raw message