Re: [PATCH v4 3/4] perf stat: Copy counts from prev_raw_counts to evsel->counts

[Jin, Yao]

Hi Jiri,

On 5/13/2020 11:31 PM, Jiri Olsa wrote:
> On Fri, May 08, 2020 at 03:58:16PM +0800, Jin Yao wrote:
> > It would be useful to support the overall statistics for perf-stat
> > interval mode. For example, report the summary at the end of
> > "perf-stat -I" output.
> >
> > But since perf-stat can support many aggregation modes, such as
> > --per-thread, --per-socket, -M and etc, we need a solution which
> > doesn't bring much complexity.
> >
> > The idea is to use 'evsel->prev_raw_counts' which is updated in
> > each interval and it's saved with the latest counts. Before reporting
> > the summary, we copy the counts from evsel->prev_raw_counts to
> > evsel->counts, and next we just follow non-interval processing.
> >
> > In evsel__compute_deltas, this patch saves counts to the member
> > [cpu0,thread0] of perf_counts for AGGR_GLOBAL.
> >
> > That's because after copying evsel->prev_raw_counts to evsel->counts,
> > perf_counts(evsel->counts, cpu, thread) are all 0 for AGGR_GLOBAL.
> > Once we go to process_counter_maps again, all members of perf_counts
> > are 0.
> >
> > So this patch uses a trick that saves the previous aggr value to
> > the member [cpu0,thread0] of perf_counts, then aggr calculation
> > in process_counter_values can work correctly.
> >
> >   v4:
> >   ---
> >   Change the commit message.
> >   No functional change.
> >
> > Signed-off-by: Jin Yao <yao.jin@xxxxxxxxxxxxxxx>
> > ---
> >   tools/perf/util/evsel.c |  1 +
> >   tools/perf/util/stat.c  | 24 ++++++++++++++++++++++++
> >   tools/perf/util/stat.h  |  1 +
> >   3 files changed, 26 insertions(+)
> >
> > diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> > index 28683b0eb738..6fae1ec28886 100644
> > --- a/tools/perf/util/evsel.c
> > +++ b/tools/perf/util/evsel.c
> > @@ -1283,6 +1283,7 @@ void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
> >   	if (cpu == -1) {
> >   		tmp = evsel->prev_raw_counts->aggr;
> >   		evsel->prev_raw_counts->aggr = *count;
> > +		*perf_counts(evsel->prev_raw_counts, 0, 0) = *count;
>
> ok, I think I understand that now.. it's only for AGGR_GLOBAL mode,
> because the perf_stat_process_counter will create aggr values from
> per cpu values
>
> but why do we need to do that all the time? can't we just set it up
> before you zero prev_raw_counts in next patch?
>
>
>          if (interval) {
>                  stat_config.interval = 0;
>                  stat_config.summary = true;
>                  perf_evlist__copy_prev_raw_counts(evsel_list);
>
> 	-> for AGGR_GLOBAL set the counts[0,0] to prev_raw_counts->aggr
>
>                  perf_evlist__reset_prev_raw_counts(evsel_list);
>                  runtime_stat_reset(&stat_config);
>                  perf_stat__reset_shadow_per_stat(&rt_stat);
>          }


Yes, I think that's a good idea.

Now in v5, I create a new patch "perf stat: Save aggr value to first member of 
prev_raw_counts" to save aggr value to first member of prev_raw_counts for 
AGGR_GLOBAL. Then next, perf_stat_process_counter can create aggr values from 
per cpu values successfully.

Thanks
Jin Yao

> thanks,
> jirka