Skip to contentSkip to conversation

perf stat: Fix the hard-coded metrics calculation on the hybrid

PATCH Applied [email protected] 2 participants 3 messages Jun 6, 2024 – Jun 24, 2024

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

PATCH v2 1/1 perf stat: Fix the hard-coded metrics calculation on the hybrid

From: Kan Liang <[email protected]>

The hard-coded metrics is wrongly calculated on the hybrid machine.

$ perf stat -e cycles,instructions -a sleep 1

Performance counter stats for 'system wide':

        18,205,487      cpu_atom/cycles/
         9,733,603      cpu_core/cycles/
         9,423,111      cpu_atom/instructions/     #  0.52  insn per cycle
         4,268,965      cpu_core/instructions/     #  0.23  insn per cycle

The insn per cycle for cpu_core should be 4,268,965 / 9,733,603 = 0.44.

When finding the metric events, the find_stat() doesn't take the PMU type into account. The cpu_atom/cycles/ is wrongly used to calculate the IPC of the cpu_core.

In the hard-coded metrics, the events from a different PMU are only SW_CPU_CLOCK and SW_TASK_CLOCK. They both have the stat type, STAT_NSECS. Except the SW CLOCK events, check the PMU type as well.

Fixes 0a57b910807a ("perf stat: Use counts rather than saved_value")

---

Changes since V1:
- Don't check the PMU of the SW CLOCK events

 tools/perf/util/stat-shadow.c | 7 +++++++
 1 file changed, 7 insertions(+)
tools/perf/util/stat-shadow.c +7 -0
index 3466aa952442..6bb975e46de3 100644
@@ -176,6 +176,13 @@ static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type
 		if (type != evsel__stat_type(cur))
 			continue;
 
+		/*
+		 * Except the SW CLOCK events,
+		 * ignore if not the PMU we're looking for.
+		 */
+		if ((type != STAT_NSECS) && (evsel->pmu != cur->pmu))
+			continue;
+
 		aggr = &cur->stats->aggr[aggr_idx];
 		if (type == STAT_NSECS)
 			return aggr->counts.val;
Signature · 1 line
2.35.1
maintainer Acked-by on v2 1/1
#1 lore raw
Quoted 23 lines · On Thu, Jun 06, 2024 at 11:03:16AM -0700, [email protected] wrote:

From: Kan Liang <[email protected]>

The hard-coded metrics is wrongly calculated on the hybrid machine.

$ perf stat -e cycles,instructions -a sleep 1

Performance counter stats for 'system wide':

        18,205,487      cpu_atom/cycles/
         9,733,603      cpu_core/cycles/
         9,423,111      cpu_atom/instructions/     #  0.52  insn per cycle
         4,268,965      cpu_core/instructions/     #  0.23  insn per cycle

The insn per cycle for cpu_core should be 4,268,965 / 9,733,603 = 0.44.

When finding the metric events, the find_stat() doesn't take the PMU type into account. The cpu_atom/cycles/ is wrongly used to calculate the IPC of the cpu_core.

In the hard-coded metrics, the events from a different PMU are only SW_CPU_CLOCK and SW_TASK_CLOCK. They both have the stat type, STAT_NSECS. Except the SW CLOCK events, check the PMU type as well.

Quoted 5 lines
Fixes 0a57b910807a ("perf stat: Use counts rather than saved_value")

Thanks,
Namhyung

Quoted 29 lines

---

Changes since V1:
- Don't check the PMU of the SW CLOCK events

 tools/perf/util/stat-shadow.c | 7 +++++++
 1 file changed, 7 insertions(+)
tools/perf/util/stat-shadow.c +7 -0
index 3466aa952442..6bb975e46de3 100644
@@ -176,6 +176,13 @@ static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type
 		if (type != evsel__stat_type(cur))
 			continue;
 
+		/*
+		 * Except the SW CLOCK events,
+		 * ignore if not the PMU we're looking for.
+		 */
+		if ((type != STAT_NSECS) && (evsel->pmu != cur->pmu))
+			continue;
+
 		aggr = &cur->stats->aggr[aggr_idx];
 		if (type == STAT_NSECS)
 			return aggr->counts.val;
Signature · 1 line
2.35.1
maintainer Applied
#2 lore raw
In reply to [email protected]
Quoted 4 lines · On Thu, 06 Jun 2024 11:03:16 -0700, [email protected] wrote:

The hard-coded metrics is wrongly calculated on the hybrid machine.

$ perf stat -e cycles,instructions -a sleep 1
Quoted 8 lines

Performance counter stats for 'system wide':

        18,205,487      cpu_atom/cycles/
         9,733,603      cpu_core/cycles/
         9,423,111      cpu_atom/instructions/     #  0.52  insn per cycle
         4,268,965      cpu_core/instructions/     #  0.23  insn per cycle

[...]

Applied to perf-tools-next, thanks!

Best regards,
Namhyung