flink-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Johannes (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (FLINK-2213) Configure number of vcores
Date Mon, 09 Nov 2015 20:23:11 GMT

    [ https://issues.apache.org/jira/browse/FLINK-2213?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14997286#comment-14997286
] 

Johannes commented on FLINK-2213:
---------------------------------

What happens when the container exceed its resources is configurable

see [Nodemanager Cgroups|http://blog.cloudera.com/blog/2013/12/managing-multiple-resources-in-hadoop-2-with-yarn/]
^1^

The CPU allocation via cgroups should enforce that the cpu is throttled. When the memory exceeds
its limits, the container is killed.

{quote}
 Because memory is for the most part inelastic, we enforce memory limits by killing container
processes when they go over their memory allocation
{quote}

So probably the inital container in my setup was killed because of memory.

1. http://blog.cloudera.com/blog/2013/12/managing-multiple-resources-in-hadoop-2-with-yarn/

> Configure number of vcores
> --------------------------
>
>                 Key: FLINK-2213
>                 URL: https://issues.apache.org/jira/browse/FLINK-2213
>             Project: Flink
>          Issue Type: Improvement
>          Components: YARN Client
>    Affects Versions: 0.10
>            Reporter: Ufuk Celebi
>             Fix For: 1.0
>
>
> Currently, the number of vcores per YARN container is set to 1.
> It is desirable to allow configuring this value. As a simple heuristic it makes sense
to at least set it to the number of slots per container.



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

Mime
View raw message