PVT Re: [PATCH 07/13] perf hists: Add support for showing relative percentage

From: Arnaldo Carvalho de Melo
Date: Fri Mar 07 2014 - 09:39:37 EST


Em Fri, Mar 07, 2014 at 11:37:07AM -0300, Arnaldo Carvalho de Melo escreveu:
> Em Mon, Mar 03, 2014 at 10:14:08AM +0900, Namhyung Kim escreveu:
> > When filtering by thread, dso or symbol on TUI it also update total
> > period so that the output shows different result than no filter - the
> > percentage changed to relative to filtered entries only. Sometimes
> > this is not desired since users might expect same results with filter.
> >
> > So new filtered_* fields to hists->stats to count them separately.
> > They'll be controlled/used by user later.
> >
> > Acked-by: Jiri Olsa <jolsa@xxxxxxxxxx>
> > Signed-off-by: Namhyung Kim <namhyung@xxxxxxxxxx>
> > ---
> > tools/perf/builtin-report.c | 6 ++++++
> > tools/perf/util/hist.c | 19 +++++++++++++++----
> > tools/perf/util/hist.h | 2 ++
> > 3 files changed, 23 insertions(+), 4 deletions(-)
> >
> > diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
> > index 5f7f1a332186..3f8478603d51 100644
> > --- a/tools/perf/builtin-report.c
> > +++ b/tools/perf/builtin-report.c
> > @@ -121,6 +121,8 @@ static int report__add_mem_hist_entry(struct report *rep, struct addr_location *
> >
> > evsel->hists.stats.total_period += cost;
> > hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
> > + if (!he->filtered)
> > + evsel->hists.stats.nr_filtered_samples++;
>
>
> Huh? I read the above as "if not filtered, increment the number of
> filtered samples", isn't this reversed?
>
> I.e. I understand "filtered" as entries that the filter applied to, so
> will not be considered, and you use this meaning for he->filtered, but
> not for stats_nr_filtered_samples, right?

Since I had to stop here, could you try reworking that other patch to
avoid aligning the \ at the end of the line and renaming the above to
some other name that makes he->filtered match in meaning what
stats_nr_filtered_samples means?

Perhaps stats_nr_non_filtered_samples?

> - Arnaldo
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/