@lists.freedesktop.org
Subject: Re: [Intel-gfx] [RFC 04/10] drm/i915: Expose a PMU interface for perf
queries
On Tue, 2017-08-29 at 21:21 +0200, Peter Zijlstra wrote:
> On Tue, Aug 29, 2017 at 07:16:31PM +, Rogozhkin, Dmitry V wrote:
> > > Pretty strict, people tend to get fairly upset every
-gfx] [RFC 04/10] drm/i915: Expose a PMU interface for perf
queries
On Tue, 2017-08-29 at 21:21 +0200, Peter Zijlstra wrote:
> On Tue, Aug 29, 2017 at 07:16:31PM +, Rogozhkin, Dmitry V wrote:
> > > Pretty strict, people tend to get fairly upset every time we leak stuff.
> >
On Tue, 2017-08-29 at 21:21 +0200, Peter Zijlstra wrote:
> On Tue, Aug 29, 2017 at 07:16:31PM +, Rogozhkin, Dmitry V wrote:
> > > Pretty strict, people tend to get fairly upset every time we leak stuff.
> > > In fact Debian and Android carry a perf_event_paranoid patch that
> > > default disabl
On Tue, Aug 29, 2017 at 07:16:31PM +, Rogozhkin, Dmitry V wrote:
> > Pretty strict, people tend to get fairly upset every time we leak stuff.
> > In fact Debian and Android carry a perf_event_paranoid patch that
> > default disables _everything_ :-(
>
> Can you say more on that for Debian and
On Tue, 2017-08-29 at 11:30 +0200, Peter Zijlstra wrote:
> On Mon, Aug 28, 2017 at 10:43:17PM +, Rogozhkin, Dmitry V wrote:
>
> > Hi Peter,
> >
> > I have updated my fixes to Tvrtko's PMU, they are here:
> > https://patchwork.freedesktop.org/series/28842/, and I started to check
> > whether we
On Mon, Aug 28, 2017 at 10:43:17PM +, Rogozhkin, Dmitry V wrote:
> Hi Peter,
>
> I have updated my fixes to Tvrtko's PMU, they are here:
> https://patchwork.freedesktop.org/series/28842/, and I started to check
> whether we will be able to cover all the use cases for this PMU which we
> had in
On Wed, 2017-08-23 at 20:22 +0200, Peter Zijlstra wrote:
> On Wed, Aug 23, 2017 at 05:51:38PM +, Rogozhkin, Dmitry V wrote:
>
> > Anyhow, returning to the metrics i915 exposes. Some metrics are just
> > exposure of some counters supported already inside i915 PMU which do not
> > require any sp
On Wed, Aug 23, 2017 at 07:00:33PM +, Rogozhkin, Dmitry V wrote:
> On Wed, 2017-08-23 at 20:22 +0200, Peter Zijlstra wrote:
> > On Wed, Aug 23, 2017 at 05:51:38PM +, Rogozhkin, Dmitry V wrote:
> >
> > > Anyhow, returning to the metrics i915 exposes. Some metrics are just
> > > exposure of
On Wed, Aug 23, 2017 at 06:38:05PM +, Rogozhkin, Dmitry V wrote:
> On Wed, 2017-08-23 at 20:04 +0200, Peter Zijlstra wrote:
> > On Wed, Aug 23, 2017 at 05:51:38PM +, Rogozhkin, Dmitry V wrote:
> >
> > > > The above command tries to add an event 'i915/rcs0-busy/' to a task. How
> > > > are
On Wed, 2017-08-23 at 20:22 +0200, Peter Zijlstra wrote:
> On Wed, Aug 23, 2017 at 05:51:38PM +, Rogozhkin, Dmitry V wrote:
>
> > Anyhow, returning to the metrics i915 exposes. Some metrics are just
> > exposure of some counters supported already inside i915 PMU which do not
> > require any sp
On Wed, 2017-08-23 at 20:01 +0200, Peter Zijlstra wrote:
> On Wed, Aug 23, 2017 at 05:51:38PM +, Rogozhkin, Dmitry V wrote:
>
> > https://patchwork.freedesktop.org/patch/171953/. This patch makes 'perf
> > stat -e i915/rcs0-busy/' to error out and supports 'perf stat -e
> > i915/rcs0-busy/ -a
On Wed, 2017-08-23 at 20:04 +0200, Peter Zijlstra wrote:
> On Wed, Aug 23, 2017 at 05:51:38PM +, Rogozhkin, Dmitry V wrote:
>
> > > The above command tries to add an event 'i915/rcs0-busy/' to a task. How
> > > are i915 resource associated to any one particular task?
> >
> > Currently in no w
On Wed, Aug 23, 2017 at 05:51:38PM +, Rogozhkin, Dmitry V wrote:
> Anyhow, returning to the metrics i915 exposes. Some metrics are just
> exposure of some counters supported already inside i915 PMU which do not
> require any special sampling: at any given moment you can request the
> counter v
On Wed, Aug 23, 2017 at 05:51:38PM +, Rogozhkin, Dmitry V wrote:
> And there is another problem associated with the "perf stat -e
> -a": since 8 events are initialized, I get metric values multiplied by
> 8. How I am supposed to fix that? I suspect that this is somehow related
> to cpumask att
On Wed, Aug 23, 2017 at 05:51:38PM +, Rogozhkin, Dmitry V wrote:
> > The above command tries to add an event 'i915/rcs0-busy/' to a task. How
> > are i915 resource associated to any one particular task?
>
> Currently in no way, they are global.
Right. So no per DRM context things. Can you ha
On Wed, Aug 23, 2017 at 05:51:38PM +, Rogozhkin, Dmitry V wrote:
> https://patchwork.freedesktop.org/patch/171953/. This patch makes 'perf
> stat -e i915/rcs0-busy/' to error out and supports 'perf stat -e
> i915/rcs0-busy/ -a -C0'. I still think I miss something since 'perf stat
> -e i915/rcs
On Tue, 2017-08-22 at 20:17 +0200, Peter Zijlstra wrote:
> On Sat, Aug 12, 2017 at 02:15:13AM +, Rogozhkin, Dmitry V wrote:
> > $ perf stat -e instructions,i915/rcs0-busy/ workload.sh
> > <... wrokload.sh output...>
> >
> > Performance counter stats for 'workload.sh':
> > 1,204,616,268
On Sat, Aug 12, 2017 at 02:15:13AM +, Rogozhkin, Dmitry V wrote:
> $ perf stat -e instructions,i915/rcs0-busy/ workload.sh
> <... wrokload.sh output...>
>
> Performance counter stats for 'workload.sh':
> 1,204,616,268 instructions
> 0 i915/rcs0-busy/
>
>
Hi Peter,
We are trying to expose some software PMU events from the i915 driver.
Things like GPU engine busyness, power usage and similar.
There is quite a bit of opens regarding usage of the perf API and so on.
Would you be able to snoop around the below patch and help with
answering some
From: Chris Wilson
The first goal is to be able to measure GPU (and invidual ring) busyness
without having to poll registers from userspace. (Which not only incurs
holding the forcewake lock indefinitely, perturbing the system, but also
runs the risk of hanging the machine.) As an alternative we
20 matches
Mail list logo
