Beckham007 commented on YARN-1856:

We had work on this for a few days. We will validate it in our production 
envriment, which has 4000 nodes.
We set memory.limit_in_bytes for /cgroup/memory/hadoop-yarn and set 
memory.soft_limit_in_byte for each container. Also, we use cgroup.event_control 
to handle oom event.
Mesos used the similar policy for memory isolation.

> cgroups based memory monitoring for containers
> ----------------------------------------------
>                 Key: YARN-1856
>                 URL: https://issues.apache.org/jira/browse/YARN-1856
>             Project: Hadoop YARN
>          Issue Type: Sub-task
>          Components: nodemanager
>    Affects Versions: 2.3.0
>            Reporter: Karthik Kambatla
>            Assignee: Karthik Kambatla

This message was sent by Atlassian JIRA

Reply via email to