Re: [PATCH 3/9] perf, tools, stat: Move noise/running printing into printout

[Andi Kleen]

On Sat, Jan 23, 2016 at 05:19:58PM +0100, Jiri Olsa wrote:
> On Sat, Jan 23, 2016 at 04:43:05AM +0100, Andi Kleen wrote:
> > > > -		if (run == 0 || ena == 0) {
> > > > -			fprintf(output, "CPU%*d%s%*s%s",
> > > > -				csv_output ? 0 : -4,
> > > > -				perf_evsel__cpus(counter)->map[cpu], csv_sep,
> > > > -				csv_output ? 0 : 18,
> > > > -				counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
> > > > -				csv_sep);
> > > 
> > > this hunk is not preserved in the new code.. I guess the output is
> > > different for -A if counter wasn't meassure?
> > 
> > The code for this is common in printout() now.
> 
> but what will be printed for -A not counted counters?
> not the "CPU%*d%s%*s%s" ...


CPU0       <not supported>      stalled-cycles-backend                                      
CPU1       <not supported>      stalled-cycles-backend                                      
CPU2       <not supported>      stalled-cycles-backend                                      
CPU3       <not supported>      stalled-cycles-backend                                      
CPU4       <not supported>      stalled-cycles-backend                                      
CPU5       <not supported>      stalled-cycles-backend                                      
CPU6       <not supported>      stalled-cycles-backend                                      
CPU7       <not supported>      stalled-cycles-backend                                      
CPU8       <not supported>      stalled-cycles-backend                                      
CPU9       <not supported>      stalled-cycles-backend                                      
CPU10      <not supported>      stalled-cycles-backend                                      
CPU11      <not supported>      stalled-cycles-backend                                      

-Andi