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")
Reported-by: "Khalil, Amiri" <[email protected]>
Reviewed-by: Ian Rogers <[email protected]>
Signed-off-by: Kan Liang <[email protected]>
Cc: [email protected]
---
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(+)
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 3466aa952442..6bb975e46de3 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -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;
--
2.35.1
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.
>
> Fixes: 0a57b910807a ("perf stat: Use counts rather than saved_value")
> Reported-by: "Khalil, Amiri" <[email protected]>
> Reviewed-by: Ian Rogers <[email protected]>
> Signed-off-by: Kan Liang <[email protected]>
> Cc: [email protected]
Acked-by: Namhyung Kim <[email protected]>
Thanks,
Namhyung
> ---
>
> 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(+)
>
> diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
> index 3466aa952442..6bb975e46de3 100644
> --- a/tools/perf/util/stat-shadow.c
> +++ b/tools/perf/util/stat-shadow.c
> @@ -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;
> --
> 2.35.1
>