On Thu, May 12, 2016 at 01:30:36PM +, Liang, Kan wrote:
>
>
> > ---
> > Subject: perf/core: don't find side-band event from all pmus
> > From: Kan Liang
> > Date: Wed, 23 Mar 2016 11:24:37 -0700
> >
> Hi Peter,
>
> Is there something wrong with the patch?
> The last time I saw this patch w
> ---
> Subject: perf/core: don't find side-band event from all pmus
> From: Kan Liang
> Date: Wed, 23 Mar 2016 11:24:37 -0700
>
Hi Peter,
Is there something wrong with the patch?
The last time I saw this patch was in your personal tree
(kernel/git/peterz/queue.git).
But now I cannot find it
; mi...@kernel.org; a...@redhat.com; jo...@redhat.com;
> alexander.shish...@linux.intel.com; ying.hu...@linux.intel.com; linux-
> ker...@vger.kernel.org
> Subject: Re: [PATCH V2 1/1] perf/core: don't find side-band event from all
> pmus
>
> On Thu, Mar 31, 2016 at 06:22:26PM +0200, P
On Thu, Mar 31, 2016 at 06:22:26PM +0200, Peter Zijlstra wrote:
> I'm an idiot; quilt refresh is needed..
>
> ---
> Subject: perf/core: don't find side-band event from all pmus
> From: Kan Liang
> Date: Wed, 23 Mar 2016 11:24:37 -0700
>
Kan, does this patch work for you?
On Thu, Mar 31, 2016 at 06:21:41PM +0200, Peter Zijlstra wrote:
> On Thu, Mar 31, 2016 at 04:56:21PM +0200, Peter Zijlstra wrote:
> > On Thu, Mar 31, 2016 at 11:44:39AM -0300, Arnaldo Carvalho de Melo wrote:
> > > It probably will cope, but can't we just emit one single record?
> >
> > I'll try an
On Thu, Mar 31, 2016 at 04:56:21PM +0200, Peter Zijlstra wrote:
> On Thu, Mar 31, 2016 at 11:44:39AM -0300, Arnaldo Carvalho de Melo wrote:
> > It probably will cope, but can't we just emit one single record?
>
> I'll try and figure something out...
less clever but probably good enough..
---
Sub
On Thu, Mar 31, 2016 at 11:44:39AM -0300, Arnaldo Carvalho de Melo wrote:
> It probably will cope, but can't we just emit one single record?
I'll try and figure something out...
Em Tue, Mar 29, 2016 at 02:06:09PM +0200, Peter Zijlstra escreveu:
> On Wed, Mar 23, 2016 at 11:24:37AM -0700, kan.li...@intel.com wrote:
> > The V2 patch is mainly based on Peter's suggestion. But I didn't rename
> > perf_event_aux to perf_event_sb. Because it looks there are many aux things
> > i
Em Thu, Mar 31, 2016 at 02:05:46PM +, Liang, Kan escreveu:
>
>
> > > +static void perf_event_sb_mask(unsigned int sb_mask,
> > > +perf_event_aux_output_cb output,
> > > +void *data)
> > > +{
> > > + int sb;
> > > +
> > > + for (sb = 0; sb < sb_n
> > +static void perf_event_sb_mask(unsigned int sb_mask,
> > + perf_event_aux_output_cb output,
> > + void *data)
> > +{
> > + int sb;
> > +
> > + for (sb = 0; sb < sb_nr; sb++) {
> > + if (!(sb_mask & (1 << sb)))
> > +
On Wed, Mar 23, 2016 at 11:24:37AM -0700, kan.li...@intel.com wrote:
> The V2 patch is mainly based on Peter's suggestion. But I didn't rename
> perf_event_aux to perf_event_sb. Because it looks there are many aux things
> in the codes, e.g. AUX area in ring buffer. I'm not sure if we need to chang
From: Kan Liang
perf_event_aux funciton goes through all pmus and all events in whatever
contexts to find the side-band event to output, which is unnecessary and
expensive.
For example, the brk test case in lkp triggers many mmap operations, at
the time, perf with cycles:pp is also running on th
12 matches
Mail list logo