hadoop-yarn-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Jason Lowe (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (YARN-3091) [Umbrella] Improve and fix locks of RM scheduler
Date Wed, 08 Nov 2017 15:48:01 GMT

    [ https://issues.apache.org/jira/browse/YARN-3091?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16244191#comment-16244191

Jason Lowe commented on YARN-3091:

bq. I'm looking at reverting the read/write lock changes within the fair scheduler at least.

+1, we've also seen a number of problems around the scheduler's read/write locks and have
done some short-term fixes to work around them like YARN-6680.  They are significantly more
expensive to acquire than a standard mutex if nobody is holding the lock, and there are lots
of places where the scheduler needs to acquire them during a scheduling pass.

> [Umbrella] Improve and fix locks of RM scheduler
> ------------------------------------------------
>                 Key: YARN-3091
>                 URL: https://issues.apache.org/jira/browse/YARN-3091
>             Project: Hadoop YARN
>          Issue Type: Task
>          Components: capacityscheduler, fairscheduler, resourcemanager, scheduler
>            Reporter: Wangda Tan
> In existing YARN RM scheduler, there're some issues of using locks. For example:
> - Many unnecessary synchronized locks, we have seen several cases recently that too frequent
access of scheduler makes scheduler hang. Which could be addressed by using read/write lock.
Components include scheduler, CS queues, apps
> - Some fields not properly locked (Like clusterResource)
> We can address them together in this ticket.
> (More details see comments below)

This message was sent by Atlassian JIRA

To unsubscribe, e-mail: yarn-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: yarn-issues-help@hadoop.apache.org

View raw message