Re: [PATCH 3/6] perf, tools, stat: Support metrics in --per-core/socket mode

[Jiri Olsa]

On Mon, Feb 22, 2016 at 05:52:02PM +0100, Andi Kleen wrote:
> On Sun, Feb 21, 2016 at 06:15:35PM +0100, Jiri Olsa wrote:
> > On Wed, Feb 17, 2016 at 02:44:02PM -0800, Andi Kleen wrote:
> > 
> > SNIP
> > 
> > > @@ -892,7 +908,10 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
> > >  	struct perf_stat_output_ctx out;
> > >  	struct outstate os = {
> > >  		.fh = stat_config.output,
> > > -		.prefix = prefix ? prefix : ""
> > > +		.prefix = prefix ? prefix : "",
> > > +		.id = id,
> > > +		.nr = nr,
> > > +		.evsel = counter,
> > >  	};
> > >  	print_metric_t pm = print_metric_std;
> > >  	void (*nl)(void *);
> > > @@ -962,15 +981,38 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
> > >  
> > >  	perf_stat__print_shadow_stats(counter, uval,
> > >  				stat_config.aggr_mode == AGGR_GLOBAL ? 0 :
> > > -				cpu_map__id_to_cpu(id),
> > > +				first_shadow_cpu(counter, id),
> > 
> > hum, IIUC you need to handle AGGR_NONE in here as well?
> 
> AFAIK it works. aggr_get_id in first_shadow_cpu and cpu_map__id_to_cpu
> handle this case, right?

it does not look like.. however it'll be more clear once
there's the doc/comment about used cpus for aggr modes
I asked for in here:

  http://marc.info/?l=linux-kernel&m=145607533503803&w=2

thanks,
jirka