Messages in this thread | | | Subject | Re: [PATCH] perf stat: Fix uncore event mixed metric with workload error issue | From | "Jin, Yao" <> | Date | Wed, 29 Apr 2020 19:50:48 +0800 |
| |
Hi Jiri,
On 4/29/2020 4:16 PM, Jiri Olsa wrote: > On Tue, Apr 28, 2020 at 02:19:22PM -0700, Andi Kleen wrote: >>> I wonder this would break some expectations.. would it be >>> more safe to detect duration event and bypass it from the >>> decission? but maybe the case I'm worried about is not a >>> problem at all.. Andi? >> >> Don't see what it would break. >> >> Yes maybe we need to special case duration_time more, but that would >> be a much bigger patch. > > would below change work for you? if duration_time is the only > case, I'd rather go with the special case for it > > jirka > >
Just tested, for the case of DRAM_BW_Use, it can work.
root@lkp-csl-2sp5 ~# perf stat -M DRAM_BW_Use -- sleep 1
Performance counter stats for 'system wide':
9.54 MiB uncore_imc/cas_count_read/ 3.26 MiB uncore_imc/cas_count_write/ 1002109793 ns duration_time
1.002109793 seconds time elapsed
Thanks Jin Yao
> --- > diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c > index 9207b6c45475..2518204cffd1 100644 > --- a/tools/perf/builtin-stat.c > +++ b/tools/perf/builtin-stat.c > @@ -1853,6 +1853,8 @@ static void setup_system_wide(int forks) > struct evsel *counter; > > evlist__for_each_entry(evsel_list, counter) { > + if (counter->tool_event == PERF_TOOL_DURATION_TIME) > + continue; > if (!counter->core.system_wide) > return; > } >
| |