Messages in this thread | | | Date | Tue, 26 Apr 2011 02:00:10 +0800 | Subject | Re: [generalized cache events] Re: [PATCH 1/1] perf tools: Add missing user space support for config1/config2 | From | Dehao Chen <> |
| |
On Tue, Apr 26, 2011 at 1:41 AM, Ingo Molnar <mingo@elte.hu> wrote: > > * Andi Kleen <ak@linux.intel.com> wrote: > > > > You're so skilled at not actually saying anything useful. Are you > > > perchance referring to the fact that the IP reported in the PEBS data is > > > exactly _one_ instruction off? Something that is demonstrated to be > > > fixable? > > > > It's one instruction off the instruction that was retired when the PEBS > > interrupt was ready, but not one instruction off the instruction that caused > > the event. There's still skid in triggering the interrupt. > > Peter answered this in the other mail: > > | > | Sure, but who cares? So your period isn't exactly what you specified, but > | the effective period will have an average and a fairly small stdev (assuming > | the initial period is much larger than the relatively few cycles it takes to > | arm the PEBS assist), therefore you still get a fairly uniform spread. > | > > ... and the resulting low level of noise in the average period length is what > matters. The instruction itself will still be one of the hotspot instructions, > statistically.
Not true. This skid will lead to some aggregation and shadow effects on some certain instructions. To make things worse, these effects are deterministic and cannot be removed by either sampling for multiple times or by averaging among instructions within a basic block. As a result, some actual "hot spot" are not sampled at all. You can simply try to collect a basic block level CPI, and you'll get a very misleading profile.
Dehao
> > Thanks, > > Ingo > -- > To unsubscribe from this list: send the line "unsubscribe linux-kernel" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html > Please read the FAQ at http://www.tux.org/lkml/ -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |