[lkml]   [2011]   [Jun]   [15]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: REGRESSION: Performance regressions from switching anon_vma->lock to mutex

* Tim Chen <> wrote:

> On Wed, 2011-06-15 at 12:11 -0700, Linus Torvalds wrote:
> >
> > And it results in real problems. For example, if you use "perf record"
> > to see what the hell is up, the use of kernel threads for RCU
> > callbacks means that the RCU cost is never even seen. I don't know how
> > Tim did his profiling to figure out the costs, and I don't know how he
> > decided that the spinlock to semaphore conversion was the culprit, but
> > it is entirely possible that Tim didn't actually bisect the problem,
> > but instead used "perf record" on the exim task, saw that the
> > semaphore costs had gone up, and decided that it must be the
> > conversion.
> >
> Yes, I was using perf to do the profiling. I thought that the mutex
> conversion was the most likely culprit based on the change in
> profile.

have you used callgraph profiling (perf record -g) or flat profiling?
Flat profiling can be misleading when there's proxy work done.



 \ /
  Last update: 2011-06-15 22:21    [W:0.122 / U:13.252 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site