Re: [PATCH] dcache: Translating dentry into pathname without takingrename_lock

[Waiman Long]

On 09/05/2013 09:29 AM, John Stoffel wrote:
> Can you then show the variation over multiple runs? I think you have a 
> good justification for larger boxes to make this change, I just worry 
> about smaller systems getting hit and losing performance. John 

Please see the attached PDF file for the performance level of the short 
workload at different number of users. You can see that there is quite a 
lot of run-to-run variation.

-Longman

Attachment: aim7-short-jpm-3.11.pdf
Description: Adobe PDF document