Messages in this thread | | | Date | Fri, 25 Mar 2011 11:31:38 +0100 | From | Ingo Molnar <> | Subject | Re: [PATCH 2/2] mutex: Apply adaptive spinning on mutex_trylock() |
| |
* Tejun Heo <tj@kernel.org> wrote:
> Hello, > > On Thu, Mar 24, 2011 at 10:41:51AM +0100, Tejun Heo wrote: > > USER SYSTEM SIRQ CXTSW THROUGHPUT > > SIMPLE 61107 354977 217 8099529 845.100 MB/sec > > SPIN 63140 364888 214 6840527 879.077 MB/sec > > > > On various runs, the adaptive spinning trylock consistently posts > > higher throughput. The amount of difference varies but it outperforms > > consistently. > > I've been running more of these tests and am having doubts about the > consistency. It seems that, even on a fresh filesystem, some random > initial condition seems to have persistent effect on the whole run. > I'll run more tests and report back.
Ok, and there's the deadlock issue as well which Steve noticed.
I'll zap the patches from tip:core/urgent and lets do this via tip:core/locking with a .40 timeframe and plenty of time of testing.
Thanks,
Ingo
| |