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 "Amareshwari Sriramadasu (JIRA)" <ji...@apache.org> on 2015/06/12 08:10:01 UTC
[jira] [Commented] (YARN-3734) Force dirhandler.checkDirs() in
ResourceLocalizationService when there is a localization failure
[ https://issues.apache.org/jira/browse/YARN-3734?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14583005#comment-14583005 ]
Amareshwari Sriramadasu commented on YARN-3734:
-----------------------------------------------
[~lavkesh], Can you look at processing of checkdirs()? How much time can that take? Is it thread safe?
> Force dirhandler.checkDirs() in ResourceLocalizationService when there is a localization failure
> ------------------------------------------------------------------------------------------------
>
> Key: YARN-3734
> URL: https://issues.apache.org/jira/browse/YARN-3734
> Project: Hadoop YARN
> Issue Type: Bug
> Reporter: Lavkesh Lahngir
> Assignee: Lavkesh Lahngir
>
> This scenario happens when a disk goes bad in between node health checks. In that case all containers will be failing.
> Would that be okay to force a checkdirs() when there is an IOException while localizing a resource so that next container will not fail due to disk issues?
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)