You are viewing a plain text version of this content. The canonical link for it is here.
Posted to common-issues@hadoop.apache.org by "Allen Wittenauer (JIRA)" <ji...@apache.org> on 2016/05/31 16:38:12 UTC
[jira] [Commented] (HADOOP-13225) Allow java to be started with
numactl
[ https://issues.apache.org/jira/browse/HADOOP-13225?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15308059#comment-15308059 ]
Allen Wittenauer commented on HADOOP-13225:
-------------------------------------------
bq. I made a small mention in the description about this; I'm not sure how it would work with jsvc.
Sorry, I missed this. I'm not sure why one couldn't just use numactl to launch jsvc given the man page states:
numactl runs processes with a specific NUMA scheduling or memory placement policy. *The policy is set for command and inherited by all of its children.*
I'm fairly certain that the java DN process would be considered a child of jsvc in this context. Things get trickier if some other method is being used (e.g., HADOOP_SECURE_COMMAND is defined). Chances are good that those users are either non-Linux or are using function overrides anyway.
Also:
* Looks like you didn't have contributor set for HADOOP. Fixed.
* I've moved the JIRA for you.
* Coding rules for bash are generally covered here: https://wiki.apache.org/hadoop/UnixShellScriptProgrammingGuide
> Allow java to be started with numactl
> -------------------------------------
>
> Key: HADOOP-13225
> URL: https://issues.apache.org/jira/browse/HADOOP-13225
> Project: Hadoop Common
> Issue Type: New Feature
> Components: scripts
> Reporter: Dave Marion
> Assignee: Dave Marion
> Attachments: HDFS-10370-1.patch, HDFS-10370-2.patch, HDFS-10370-3.patch, HDFS-10370-branch-2.004.patch, HDFS-10370.004.patch
>
>
> Allow numactl constraints to be applied to the datanode process. The implementation I have in mind involves two environment variables (enable and parameters) in the datanode startup process. Basically, if enabled and numactl exists on the system, then start the java process using it. Provide a default set of parameters, and allow the user to override the default. Wiring this up for the non-jsvc use case seems straightforward. Not sure how this can be supported using jsvc.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: common-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: common-issues-help@hadoop.apache.org