[
https://issues.apache.org/jira/browse/YARN-3091?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16243089#comment-16243089
]
Daniel Templeton commented on YARN-3091:
----------------------------------------
I've been doing some performance testing lately as part of the resource types
(YARN-3926) work, and I'm not sure the idea of using read/write locks to
*improve* performance is sound. See:
https://stackoverflow.com/questions/34611106/synchronized-vs-readwritelock-performance
Read/write locks are slower in scenarios where there isn't a significant
amount of contention, which we don't have. My testing shows that by replacing
the read/write locks with a simple reentrant lock, I can get a notable
performance boost. I'm looking at reverting the read/write lock changes within
the fair scheduler at least. Thoughts?
> [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
(v6.4.14#64029)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
