You are viewing a plain text version of this content. The canonical link for it is here.
Posted to yarn-issues@hadoop.apache.org by "yinghua_zh (Jira)" <ji...@apache.org> on 2019/09/19 08:55:00 UTC
[jira] [Comment Edited] (YARN-5040) CPU Isolation with CGroups
triggers kernel panics on Centos 7.1/7.2 when
yarn.nodemanager.resource.percentage-physical-cpu-limit < 100
[ https://issues.apache.org/jira/browse/YARN-5040?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16933167#comment-16933167 ]
yinghua_zh edited comment on YARN-5040 at 9/19/19 8:54 AM:
-----------------------------------------------------------
I also encountered the same problem. When CGroup is enabled and a big task is running, after a period of time, the operating system kernel crash,But not every time. My version information is as follows:
Hadoop:2.7.2
OS: CentOS Linux release 7.3.1611
OS kernel: 3.10.0-514.el7.x86_64
How did you solve the problem?[~vvasudev] [~sidharta-s] [~Tao Jie] [~ecwpp] [~cheersyang]@
was (Author: yinghua_zh):
I also encountered the same problem. When CGroup is enabled and a big task is running, after a period of time, the operating system kernel crash, My version information is as follows:
Hadoop:2.7.2
OS: CentOS Linux release 7.3.1611
OS kernel: 3.10.0-514.el7.x86_64
How did you solve the problem?[~vvasudev] [~sidharta-s] [~Tao Jie] [~ecwpp] @
> CPU Isolation with CGroups triggers kernel panics on Centos 7.1/7.2 when yarn.nodemanager.resource.percentage-physical-cpu-limit < 100
> --------------------------------------------------------------------------------------------------------------------------------------
>
> Key: YARN-5040
> URL: https://issues.apache.org/jira/browse/YARN-5040
> Project: Hadoop YARN
> Issue Type: Bug
> Affects Versions: 2.9.0
> Reporter: Sidharta Seethana
> Assignee: Varun Vasudev
> Priority: Major
>
> /cc [~vvasudev]
> We have been running some benchmarks internally with resource isolation enabled. We have consistently run into kernel panics when running a large job ( a large pi job, terasort ). These kernel panics wen't away when we set yarn.nodemanager.resource.percentage-physical-cpu-limit=100 . Anything less than 100 triggers different behavior in YARN's CPU resource handler which seems to cause these issues. Looking at the kernel crash dumps, the backtraces were different - sometimes pointing to java processes, sometimes not.
> Kernel versions used : 3.10.0-229.14.1.el7.x86_64 and 3.10.0-327.13.1.el7.x86_64 .
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: yarn-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: yarn-issues-help@hadoop.apache.org