Re: perf stat stddev reporting broken since "perf stat: Introduce read_counters function"

[Jiri Olsa]

On Tue, Jan 19, 2016 at 09:38:12AM +0000, Mel Gorman wrote:
> On Tue, Jan 19, 2016 at 09:16:23AM +0100, Jiri Olsa wrote:
> > On Tue, Jan 19, 2016 at 08:42:28AM +0100, Jiri Olsa wrote:
> > 
> > SNIP
> > 
> > > > 
> > > >  Performance counter stats for 'sleep 1' (5 runs):
> > > > 
> > > >           0.583178      task-clock (msec)         #    0.001 CPUs utilized
> > > >                  1      context-switches          #    0.002 M/sec
> > > >                  0      cpu-migrations            #    0.000 K/sec
> > > >                 67      page-faults               #    0.141 M/sec
> > > >          1,224,416      cycles                    #    2.585 GHz
> > > >    <not supported>      stalled-cycles-frontend
> > > >    <not supported>      stalled-cycles-backend
> > > >            892,568      instructions              #    0.68  insns per cycle
> > > >            184,975      branches                  #  390.554 M/sec
> > > >              8,512      branch-misses             #    4.57% of all branches
> > > > 
> > > >        1.000889249 seconds time elapsed                                          ( +-  0.01% )
> > > > 
> > > > I checked and current master in Linus' tree is also broken. Is this
> > > > change in documented perf stat behaviour intentional?
> > > 
> > > nope, not intentional.. I'll check on that, thanks for reporting
> > 
> > for some reason we initialized the stat every iteration,
> > (the call is also wrong because it's called only over the
> > first res_stats[0])
> > 
> > attached patch works for me, could you please test?
> > I'll run more tests and put it in my queue
> > 
> 
> That works for me too, thanks. Feel free to put this on the patch;
> 
> Tested-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
> 
> When you send it through, can you make sure it has the following please?
> 
> Cc: stable@xxxxxxxxxxxxxxx # v4.2+

will do, thanks

jirka