Messages in this thread | | | Date | Sat, 7 May 2011 10:20:18 +0200 | From | Ingo Molnar <> | Subject | Re: [RFC] time: xtime_lock is held too long |
| |
* Andi Kleen <andi@firstfloor.org> wrote:
> > Then precise measurements have to be done on the source of cache misses, the > > total cost of the timer interrupt, etc. > > What we did was profiling the remote node cache misses > using raw offcore events, and the xtime code was high up. > I cannot share exact numbers for various reasons, but it was > an improvement on a hard to improve workload.
You could certainly share the profiling commands you typed, so that others can reproduce and double check your results.
Thanks,
Ingo
| |