Re: [PATCH v1 8/9] perf stat: Remove --per-thread pid/tid limitation

[Jin, Yao]

On 11/21/2017 11:18 PM, Jiri Olsa wrote:
> On Mon, Nov 20, 2017 at 10:43:43PM +0800, Jin Yao wrote:
>
> SNIP
>
> > diff --git a/tools/perf/util/target.h b/tools/perf/util/target.h
> > index 446aa7a..6ef01a8 100644
> > --- a/tools/perf/util/target.h
> > +++ b/tools/perf/util/target.h
> > @@ -64,6 +64,11 @@ static inline bool target__none(struct target *target)
> >   	return !target__has_task(target) && !target__has_cpu(target);
> >   }
> >   
> > +static inline bool target__has_per_thread(struct target *target)
> > +{
> > +	return target->system_wide && target->per_thread;
> > +}
>
> this is confusing.. has_per_thread depends on system_wide?

This patch series only supports to get per-thread data for the whole system.

So I add checking of system_wide here.

> > +
> >   static inline bool target__uses_dummy_map(struct target *target)
> >   {
> >   	bool use_dummy = false;
> > @@ -73,6 +78,8 @@ static inline bool target__uses_dummy_map(struct target *target)
> >   	else if (target__has_task(target) ||
> >   	         (!target__has_cpu(target) && !target->uses_mmap))
> >   		use_dummy = true;
> > +	else if (target__has_per_thread(target))
> > +		use_dummy = true;
>
> why do we need dummy_map for this? please comment

We need dummy_map here. That's similar to the processing of 
'--per-thread -p -t'.

We need a dummy map to help us to aggregate counts per-thread.

Thanks
Jin Yao

> thanks,
> jirka