Re: get_cyclecount(9) deprecation

2011-03-18 Thread Jung-uk Kim
On Friday 18 March 2011 04:11 pm, Kostik Belousov wrote: > On Fri, Mar 18, 2011 at 02:09:58PM -0400, Jung-uk Kim wrote: > > On Friday 18 March 2011 01:05 pm, Bruce Evans wrote: > > > On Sat, 19 Mar 2011, Bruce Evans wrote: > > > > On Fri, 18 Mar 2011, Kostik Belousov wrote: > > > >> We definitely d

Re: get_cyclecount(9) deprecation

2011-03-18 Thread Kostik Belousov
On Fri, Mar 18, 2011 at 02:09:58PM -0400, Jung-uk Kim wrote: > On Friday 18 March 2011 01:05 pm, Bruce Evans wrote: > > On Sat, 19 Mar 2011, Bruce Evans wrote: > > > On Fri, 18 Mar 2011, Kostik Belousov wrote: > > >> We definitely do not support configurations with different > > >> models of CPUs i

Re: get_cyclecount(9) deprecation

2011-03-18 Thread Jung-uk Kim
On Friday 18 March 2011 01:05 pm, Bruce Evans wrote: > On Sat, 19 Mar 2011, Bruce Evans wrote: > > On Fri, 18 Mar 2011, Kostik Belousov wrote: > >> We definitely do not support configurations with different > >> models of CPUs in SMP, this is what Simmetric is about. > >> Different as in frequency

Re: get_cyclecount(9) deprecation

2011-03-18 Thread Bruce Evans
On Sat, 19 Mar 2011, Bruce Evans wrote: On Fri, 18 Mar 2011, Kostik Belousov wrote: We definitely do not support configurations with different models of CPUs in SMP, this is what Simmetric is about. Different as in frequency or stepping. ... Now there is even more asymmetry in core frequencie

Re: get_cyclecount(9) deprecation

2011-03-18 Thread Jung-uk Kim
On Friday 18 March 2011 12:15 pm, Kostik Belousov wrote: > On Fri, Mar 18, 2011 at 05:51:27PM +0200, Andriy Gapon wrote: > > on 18/03/2011 15:56 Kostik Belousov said the following: > > > On Fri, Mar 18, 2011 at 05:26:53PM +1100, Bruce Evans wrote: > > > ... > > > > > >> - set cputicker() has some d

Re: get_cyclecount(9) deprecation

2011-03-18 Thread Bruce Evans
On Fri, 18 Mar 2011, Kostik Belousov wrote: On Fri, Mar 18, 2011 at 05:26:53PM +1100, Bruce Evans wrote: ... - set cputicker() has some design bugs. It assumes that the tick frequency is the same across all CPUs, but the TSC is per-CPU. I have an old SMP system with CPUs of different freq

Re: get_cyclecount(9) deprecation

2011-03-18 Thread Kostik Belousov
On Fri, Mar 18, 2011 at 05:51:27PM +0200, Andriy Gapon wrote: > on 18/03/2011 15:56 Kostik Belousov said the following: > > On Fri, Mar 18, 2011 at 05:26:53PM +1100, Bruce Evans wrote: > > ... > >> - set cputicker() has some design bugs. It assumes that the tick frequency > >> is the same across

Re: get_cyclecount(9) deprecation

2011-03-18 Thread Andriy Gapon
on 18/03/2011 15:56 Kostik Belousov said the following: > On Fri, Mar 18, 2011 at 05:26:53PM +1100, Bruce Evans wrote: > ... >> - set cputicker() has some design bugs. It assumes that the tick frequency >> is the same across all CPUs, but the TSC is per-CPU. I have an old SMP >> system with C

Re: get_cyclecount(9) deprecation

2011-03-18 Thread Kostik Belousov
On Fri, Mar 18, 2011 at 05:26:53PM +1100, Bruce Evans wrote: ... > - set cputicker() has some design bugs. It assumes that the tick frequency > is the same across all CPUs, but the TSC is per-CPU. I have an old SMP > system with CPUs of different frequency that can demonstrate bugs from > t

Re: get_cyclecount(9) deprecation

2011-03-18 Thread Bruce Evans
On Thu, 17 Mar 2011, Jung-uk Kim wrote: Both get_cyclecount(9) and cpu_ticks() do almost exactly the same thing now assuming set_cputicker() is called with a correct function before get_cyclecount() is used, which is true for x86, at least. The only difference is get_cyclecount() may be inlined