perf-stat has supported some aggregation modes, such as --per-core,
--per-socket and etc. While for hybrid event, it may only available
on part of cpus. So for --per-core, we need to filter out the
unavailable cores, for --per-socket, filter out the unavailable
sockets, and so on.
Before:
root@ssp-pwrt-002:~# ./perf stat --per-core -e cpu_core/cycles/ -a -- sleep 1
Performance counter stats for 'system wide':
S0-D0-C0 2 1,604,426,524 cpu_core/cycles/
S0-D0-C4 2 1,604,408,224 cpu_core/cycles/
S0-D0-C8 2 1,605,995,644 cpu_core/cycles/
S0-D0-C12 2 1,628,056,554 cpu_core/cycles/
S0-D0-C16 2 1,611,488,734 cpu_core/cycles/
S0-D0-C20 2 1,616,314,761 cpu_core/cycles/
S0-D0-C24 2 1,603,558,295 cpu_core/cycles/
S0-D0-C28 2 1,603,541,128 cpu_core/cycles/
S0-D0-C32 0 <not counted> cpu_core/cycles/
S0-D0-C33 0 <not counted> cpu_core/cycles/
S0-D0-C34 0 <not counted> cpu_core/cycles/
S0-D0-C35 0 <not counted> cpu_core/cycles/
S0-D0-C36 0 <not counted> cpu_core/cycles/
S0-D0-C37 0 <not counted> cpu_core/cycles/
S0-D0-C38 0 <not counted> cpu_core/cycles/
S0-D0-C39 0 <not counted> cpu_core/cycles/
After:
root@ssp-pwrt-002:~# ./perf stat --per-core -e cpu_core/cycles/ -a -- sleep 1
Performance counter stats for 'system wide':
S0-D0-C0 2 1,621,781,943 cpu_core/cycles/
S0-D0-C4 2 1,621,755,088 cpu_core/cycles/
S0-D0-C8 2 1,604,276,920 cpu_core/cycles/
S0-D0-C12 2 1,603,446,963 cpu_core/cycles/
S0-D0-C16 2 1,604,231,725 cpu_core/cycles/
S0-D0-C20 2 1,603,435,286 cpu_core/cycles/
S0-D0-C24 2 1,603,387,250 cpu_core/cycles/
S0-D0-C28 2 1,604,173,183 cpu_core/cycles/
Signed-off-by: Jin Yao <yao....@linux.intel.com>
---
tools/perf/util/stat-display.c | 20 ++++++++++++++++++++
1 file changed, 20 insertions(+)
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index ed37d8e7ea1a..2db7c36a03ad 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -634,6 +634,20 @@ static void aggr_cb(struct perf_stat_config *config,
}
}
+static bool aggr_id_hybrid_matched(struct perf_stat_config *config,
+ struct evsel *counter, struct aggr_cpu_id id)
+{
+ struct aggr_cpu_id s;
+
+ for (int i = 0; i < evsel__nr_cpus(counter); i++) {
+ s = config->aggr_get_id(config, evsel__cpus(counter), i);
+ if (cpu_map__compare_aggr_cpu_id(s, id))
+ return true;
+ }
+
+ return false;
+}
+
static void print_counter_aggrdata(struct perf_stat_config *config,
struct evsel *counter, int s,
char *prefix, bool metric_only,
@@ -647,6 +661,12 @@ static void print_counter_aggrdata(struct perf_stat_config
*config,
double uval;
ad.id = id = config->aggr_map->map[s];
+
+ if (perf_pmu__hybrid_exist() &&
+ !aggr_id_hybrid_matched(config, counter, id)) {
+ return;
+ }
+
ad.val = ad.ena = ad.run = 0;
ad.nr = 0;
if (!collect_data(config, counter, aggr_cb, &ad))
--
2.17.1
