[PATCH] powerpc: perf: Fix frequency calculation for overflowing counters

[PATCH] powerpc: perf: Fix frequency calculation for overflowing counters

[Anton Blanchard]

When profiling a benchmark that is almost 100% userspace, I noticed some
wildly inaccurate profiles that showed almost all time spent in the kernel.
Closer examination shows we were programming a tiny number of cycles into
the PMU after each overflow (about ~200 away from the next overflow). This
gets us stuck in a loop which we eventually break out of by throttling the
PMU (there are regular throttle/unthrottle events in the log).

It looks like we aren't setting event->hw.last_period to something same
and the frequency to period calculations in perf are going haywire. With
the following patch we find the correct period after a few interrupts and
stay there. I also see no more throttle events.

Signed-off-by: Anton Blanchard <anton@samba.org>
---

diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c
index 5674807..ab6f6be 100644
--- a/arch/powerpc/kernel/perf_event.c
+++ b/arch/powerpc/kernel/perf_event.c
@@ -1212,6 +1212,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 			if (left <= 0)
 				left = period;
 			record = 1;
+			event->hw.last_period = event->hw.sample_period;
 		}
 		if (left < 0x80000000LL)
 			val = 0x80000000LL - left;

Re: [PATCH] powerpc: perf: Fix frequency calculation for overflowing counters

[Scott Wood]

On Mon, 17 Jan 2011 16:17:42 +1100
Anton Blanchard <anton@samba.org> wrote:

> 
> When profiling a benchmark that is almost 100% userspace, I noticed some
> wildly inaccurate profiles that showed almost all time spent in the kernel.
> Closer examination shows we were programming a tiny number of cycles into
> the PMU after each overflow (about ~200 away from the next overflow). This
> gets us stuck in a loop which we eventually break out of by throttling the
> PMU (there are regular throttle/unthrottle events in the log).
> 
> It looks like we aren't setting event->hw.last_period to something same
> and the frequency to period calculations in perf are going haywire. With
> the following patch we find the correct period after a few interrupts and
> stay there. I also see no more throttle events.
> 
> Signed-off-by: Anton Blanchard <anton@samba.org>
> ---
> 
> diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/perf_event.c
> index 5674807..ab6f6be 100644
> --- a/arch/powerpc/kernel/perf_event.c
> +++ b/arch/powerpc/kernel/perf_event.c
> @@ -1212,6 +1212,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
>  			if (left <= 0)
>  				left = period;
>  			record = 1;
> +			event->hw.last_period = event->hw.sample_period;
>  		}
>  		if (left < 0x80000000LL)
>  			val = 0x80000000LL - left;
> _______________________________________________
> Linuxppc-dev mailing list
> Linuxppc-dev@lists.ozlabs.org
> https://lists.ozlabs.org/listinfo/linuxppc-dev
> 

Does perf_event_fsl_emb.c need this as well (it has almost the same
record_and_restart code)?

-Scott

Re: [PATCH] powerpc: perf: Fix frequency calculation for overflowing counters

[Peter Zijlstra]

On Mon, 2011-01-17 at 11:32 -0600, Scott Wood wrote:
> > diff --git a/arch/powerpc/kernel/perf_event.c b/arch/powerpc/kernel/per=
f_event.c
> > index 5674807..ab6f6be 100644
> > --- a/arch/powerpc/kernel/perf_event.c
> > +++ b/arch/powerpc/kernel/perf_event.c
> > @@ -1212,6 +1212,7 @@ static void record_and_restart(struct perf_event =
*event, unsigned long val,
> >                       if (left <=3D 0)
> >                               left =3D period;
> >                       record =3D 1;
> > +                     event->hw.last_period =3D event->hw.sample_period=
;
> >               }
> >               if (left < 0x80000000LL)
> >                       val =3D 0x80000000LL - left;

> Does perf_event_fsl_emb.c need this as well (it has almost the same
> record_and_restart code)?=20

I would think so.

[PATCH] powerpc: perf: Fix frequency calculation for overflowing counters (FSL version)

[Anton Blanchard]

> > Does perf_event_fsl_emb.c need this as well (it has almost the same
> > record_and_restart code)? 
> 
> I would think so.

Good point:


When fixing the frequency calculations for perf on powerpc I forgot
to fix the FSL version.

If we dont set event->hw.last_period the frequency to period calculations
in perf go haywire and we continually throttle/unthrottle the PMU.

Signed-off-by: Anton Blanchard <anton@samba.org>
---

This is only compile tested.

Index: powerpc.git/arch/powerpc/kernel/perf_event_fsl_emb.c
===================================================================
--- powerpc.git.orig/arch/powerpc/kernel/perf_event_fsl_emb.c	2011-01-18 21:23:57.761644115 +1100
+++ powerpc.git/arch/powerpc/kernel/perf_event_fsl_emb.c	2011-01-18 21:25:28.994477247 +1100
@@ -596,6 +596,7 @@ static void record_and_restart(struct pe
 			if (left <= 0)
 				left = period;
 			record = 1;
+			event->hw.last_period = event->hw.sample_period;
 		}
 		if (left < 0x80000000LL)
 			val = 0x80000000LL - left;