On Tue, Apr 22, 2014 at 05:49:46PM +0900, Namhyung Kim wrote:
SNIP
> index f955ae5a41c5..883340d7d43e 100644
> --- a/tools/perf/util/hist.c
> +++ b/tools/perf/util/hist.c
> @@ -333,6 +333,19 @@ void hists__inc_nr_events(struct hists *hists, u32 type)
> __events_stats__add(&hists->stats, type, 1);
> }
>
> +void hists__inc_dump_events(struct hists *hists)
> +{
> + if (!dump_trace)
> + return;
> +
> + /*
> + * If dump_trace is enabled, perf will exit before accounting
> + * sample events during hists__output_resort(). Thus it needs to
> + * be done separately.
> + */
> + __events_stats__add(&hists->stats, PERF_RECORD_SAMPLE, 1);
> +}
hum, we already clear all the stats before resorting for output so why done
we call hists__inc_nr_entries from add_hist_entry? (at out label)
jirka
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
