perf tool_pmu: Fix aggregation on duration_time
Ian Rogers
reviewerPATCH 1/1 perf tool_pmu: Fix aggregation on duration_time
evsel__count_has_error fails counters when the enabled or running time are 0. The duration_time event reads 0 when the cpu_map_idx != 0 to avoid aggregating time over CPUs. Change the enable and running time to always have a ratio of 100% so that evsel__count_has_error won't fail.
Before:
```
$ sudo /tmp/perf/perf stat --per-core -a -M UNCORE_FREQ sleep 1
Performance counter stats for 'system wide':
S0-D0-C0 1 2,615,819,485 UNC_CLOCK.SOCKET # 2.61 UNCORE_FREQ
S0-D0-C0 2 <not counted> duration_time
1.002111784 seconds time elapsed
```After:
```
$ perf stat --per-core -a -M UNCORE_FREQ sleep 1
Performance counter stats for 'system wide':
S0-D0-C0 1 758,160,296 UNC_CLOCK.SOCKET # 0.76 UNCORE_FREQ
S0-D0-C0 2 1,003,438,246 duration_time
1.002486017 seconds time elapsed
```Note: the metric reads the value a different way and isn't impacted.
--- tools/perf/util/tool_pmu.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)
tools/perf/util/tool_pmu.c +7 -1
@@ -486,8 +486,14 @@ int evsel__tool_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread) delta_start *=1000000000 / ticks_per_sec; } count->val = delta_start; - count->ena = count->run = delta_start; count->lost =0 ; +/* +* The values of enabled and running must make a ratio of 100%. The +* exact values don't matter as long as they are non-zero to avoid +* issues with evsel__count_has_error. +*/ + count->ena++; + count->run++;return 0 ; }
Signature · 1 line
2.49.0.805.g082f7c87e0-goog
Quoted 49 lines · Ian Rogers
evsel__count_has_errorfails counters when the enabled or running time are 0. Theduration_timeevent reads 0 when thecpu_map_idx!= 0 to avoid aggregating time over CPUs. Change the enable and running time to always have a ratio of 100% so thatevsel__count_has_errorwon't fail.Before:
``` $ sudo /tmp/perf/perf stat --per-core -a -M UNCORE_FREQ sleep 1 Performance counter stats for 'system wide': S0-D0-C0 1 2,615,819,485 UNC_CLOCK.SOCKET # 2.61 UNCORE_FREQ S0-D0-C0 2 <not counted> duration_time 1.002111784 seconds time elapsed ```After:
``` $ perf stat --per-core -a -M UNCORE_FREQ sleep 1 Performance counter stats for 'system wide': S0-D0-C0 1 758,160,296 UNC_CLOCK.SOCKET # 0.76 UNCORE_FREQ S0-D0-C0 2 1,003,438,246 duration_time 1.002486017 seconds time elapsed ```Note: the metric reads the value a different way and isn't impacted.
Reported-by Stephane Eranian <[email protected]>Fixes 240505b2d0ad ("perf tool_pmu: Factor tool events into their own PMU")Signed-off-by Ian Rogers <[email protected]>--- tools/perf/util/tool_pmu.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)tools/perf/util/tool_pmu.c +0
-1@@ -486,8 +486,14 @@ int evsel__tool_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread) delta_start *=1000000000 / ticks_per_sec; } count->val = delta_start; - count->ena = count->run = delta_start; count->lost =0 ;
tools/perf/util/tool_pmu.c int evsel__tool_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread) · line 499
Quoted 10 lines
tools/perf/util/tool_pmu.c +7
-0+/* +* The values of enabled and running must make a ratio of 100%. The +* exact values don't matter as long as they are non-zero to avoid +* issues with evsel__count_has_error. +*/ + count->ena++; + count->run++;return 0 ; }
Quoted 10 lines · James Clark
Quoted 10 lines
+++
b/tools/perf/util/tool_pmu.ctools/perf/util/tool_pmu.c +3
-1@@ -486,8 +486,14 @@ int evsel__tool_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread) delta_start *=1000000000 / ticks_per_sec; } count->val = delta_start; - count->ena = count->run = delta_start; count->lost =0 ; +/* +* The values of enabled and running must make a ratio of 100%. The +* exact values don't matter as long as they are non-zero to avoid
Quoted 8 lines
tools/perf/util/tool_pmu.c int evsel__tool_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread) · line 498
Quoted 6 lines
tools/perf/util/tool_pmu.c +4
-0+* issues with evsel__count_has_error. +*/ + count->ena++; + count->run++;return 0 ; }Reviewed-by James Clark <[email protected]>
Thanks, applied to perf-tools-next,
- Arnaldo