Skip to contentSkip to conversation

perf metric: Fix metric_leader

PATCH Applied Ian Rogers 3 participants 3 messages Jan 15, 2022 – Jan 17, 2022 perf events

lore
Share & tools
lore

Ian Rogers

author reviewer
#0 lore raw

PATCH 1/1 perf metric: Fix metric_leader

Multiple events may have a metric_leader to aggregate into. This happens for uncore events where, for example, uncore_imc is expanded into uncore_imc_0, uncore_imc_1, etc. Such events all have the same metric_id and should aggregate into the first event. The change introducing metric_ids had a bug where the metric_id was compared to itself, creating an always true condition. Correct this by comparing the event in the metric_evlist and the metric_leader.

Fixes ec5c5b3d2c21 ("perf metric: Encode and use metric-id as qualifier")
---
 tools/perf/util/metricgroup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/util/metricgroup.c +1 -1
index 51c99cb08abf..1f1b78b0388f 100644
@@ -314,7 +314,7 @@ static int setup_metric_events(struct hashmap *ids,
 		 */
 		metric_id = evsel__metric_id(ev);
 		evlist__for_each_entry_continue(metric_evlist, ev) {
-			if (!strcmp(evsel__metric_id(metric_events[i]), metric_id))
+			if (!strcmp(evsel__metric_id(ev), metric_id))
 				ev->metric_leader = metric_events[i];
 		}
 	}
Signature · 1 line
2.34.1.703.g22d0c6ccf7-goog
maintainer Applied
#1 lore raw

Em Fri, Jan 14, 2022 at 10:28:52PM -0800, Ian Rogers escreveu:

Quoted 7 lines

Multiple events may have a metric_leader to aggregate into. This happens for uncore events where, for example, uncore_imc is expanded into uncore_imc_0, uncore_imc_1, etc. Such events all have the same metric_id and should aggregate into the first event. The change introducing metric_ids had a bug where the metric_id was compared to itself, creating an always true condition. Correct this by comparing the event in the metric_evlist and the metric_leader.

Thanks, applied.

- Arnaldo

Quoted 21 lines
Fixes ec5c5b3d2c21 ("perf metric: Encode and use metric-id as qualifier")
---
 tools/perf/util/metricgroup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/util/metricgroup.c +1 -1
index 51c99cb08abf..1f1b78b0388f 100644
@@ -314,7 +314,7 @@ static int setup_metric_events(struct hashmap *ids,
 		 */
 		metric_id = evsel__metric_id(ev);
 		evlist__for_each_entry_continue(metric_evlist, ev) {
-			if (!strcmp(evsel__metric_id(metric_events[i]), metric_id))
+			if (!strcmp(evsel__metric_id(ev), metric_id))
 				ev->metric_leader = metric_events[i];
 		}
 	}
Signature · 1 line
2.34.1.703.g22d0c6ccf7-goog
Signature · 1 line
- Arnaldo
Reviewed-by on v1 1/1
#2 lore raw
In reply to Ian Rogers
Quoted 11 lines · Ian Rogers

Multiple events may have a metric_leader to aggregate into. This happens for uncore events where, for example, uncore_imc is expanded into uncore_imc_0, uncore_imc_1, etc. Such events all have the same metric_id and should aggregate into the first event. The change introducing metric_ids had a bug where the metric_id was compared to itself, creating an always true condition. Correct this by comparing the event in the metric_evlist and the metric_leader.

Fixes ec5c5b3d2c21 ("perf metric: Encode and use metric-id as qualifier")

---

Looks ok and I quickly tested it: