perf stat: Disable NMI watchdog message on hybrid
PATCH v2 1/1 perf stat: Disable NMI watchdog message on hybrid
If we run a single workload that only runs on big core, there is always a ugly message about disabling the NMI watchdog because the atom is not counted.
Before:
# ./perf stat true
Performance counter stats for 'true':
0.43 msec task-clock # 0.396 CPUs utilized
0 context-switches # 0.000 /sec
0 cpu-migrations # 0.000 /sec
45 page-faults # 103.918 K/sec
639,634 cpu_core/cycles/ # 1.477 G/sec
<not counted> cpu_atom/cycles/ (0.00%)
643,498 cpu_core/instructions/ # 1.486 G/sec
<not counted> cpu_atom/instructions/ (0.00%)
123,715 cpu_core/branches/ # 285.694 M/sec
<not counted> cpu_atom/branches/ (0.00%)
4,094 cpu_core/branch-misses/ # 9.454 M/sec
<not counted> cpu_atom/branch-misses/ (0.00%) 0.001092407 seconds time elapsed
0.001144000 seconds user
0.000000000 seconds sys Some events weren't counted. Try disabling the NMI watchdog:
echo 0 > /proc/sys/kernel/nmi_watchdog perf stat ...
echo 1 > /proc/sys/kernel/nmi_watchdog
# ./perf stat -e '{cpu_atom/cycles/,msr/tsc/}' truePerformance counter stats for 'true':
<not counted> cpu_atom/cycles/ (0.00%)
<not counted> msr/tsc/ (0.00%) 0.001904106 seconds time elapsed
0.001947000 seconds user
0.000000000 seconds sys Some events weren't counted. Try disabling the NMI watchdog:
echo 0 > /proc/sys/kernel/nmi_watchdog
perf stat ...
echo 1 > /proc/sys/kernel/nmi_watchdog
The events in group usually have to be from the same PMU. Try reorganizing the group.
Now we disable the NMI watchdog message on hybrid, otherwise there are too many false positives.
After:
# ./perf stat true
Performance counter stats for 'true':
0.79 msec task-clock # 0.419 CPUs utilized
0 context-switches # 0.000 /sec
0 cpu-migrations # 0.000 /sec
48 page-faults # 60.889 K/sec
777,692 cpu_core/cycles/ # 986.519 M/sec
<not counted> cpu_atom/cycles/ (0.00%)
669,147 cpu_core/instructions/ # 848.828 M/sec
<not counted> cpu_atom/instructions/ (0.00%)
128,635 cpu_core/branches/ # 163.176 M/sec
<not counted> cpu_atom/branches/ (0.00%)
4,089 cpu_core/branch-misses/ # 5.187 M/sec
<not counted> cpu_atom/branch-misses/ (0.00%) 0.001880649 seconds time elapsed
0.001935000 seconds user
0.000000000 seconds sys # ./perf stat -e '{cpu_atom/cycles/,msr/tsc/}' truePerformance counter stats for 'true':
<not counted> cpu_atom/cycles/ (0.00%)
<not counted> msr/tsc/ (0.00%) 0.000963319 seconds time elapsed
0.000999000 seconds user
0.000000000 seconds sys---
v2:
- If the group was mixed with hybrid event and non-hybrid event, the NMI watchdog message was still reported. V2 adds checking for hybrid event mixed group.
v1:
- Get ACK from Jiri.
tools/perf/util/stat-display.c | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-)
tools/perf/util/stat-display.c +19 -3
@@ -404,6 +404,19 @@ static bool is_mixed_hw_group(struct evsel *counter)return false; } +static bool is_mixed_hybrid_group (struct evsel *counter) +{ +struct evlist *evlist = counter->evlist; +struct evsel *pos; + +evlist__for_each_entry (evlist, pos) { +if (perf_pmu__is_hybrid (pos->pmu_name)) +return true; + } + +return false; +} + static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int nr, struct evsel *counter, double uval, char *prefix, u64 run, u64 ena, double noise,
@@ -465,9 +478,12 @@ static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int config->csv_sep);if (counter->supported) { - config->print_free_counters_hint =1 ; -if (is_mixed_hw_group (counter)) - config->print_mixed_hw_group_error =1 ; +if (!is_mixed_hybrid_group (counter)) { +if (!perf_pmu__is_hybrid (counter->pmu_name)) + config->print_free_counters_hint =1 ; +if (is_mixed_hw_group (counter)) + config->print_mixed_hw_group_error =1 ; + } } fprintf(config->output, "%-*s%s",
Signature · 1 line
2.17.1
Quoted 110 lines · Jin Yao
If we run a single workload that only runs on big core, there is always a ugly message about disabling the NMI watchdog because the atom is not counted.
Before:
# ./perf stat truePerformance counter stats for 'true':
0.43 msec task-clock # 0.396 CPUs utilized 0 context-switches # 0.000 /sec 0 cpu-migrations # 0.000 /sec 45 page-faults # 103.918 K/sec 639,634 cpu_core/cycles/ # 1.477 G/sec <not counted> cpu_atom/cycles/ (0.00%) 643,498 cpu_core/instructions/ # 1.486 G/sec <not counted> cpu_atom/instructions/ (0.00%) 123,715 cpu_core/branches/ # 285.694 M/sec <not counted> cpu_atom/branches/ (0.00%) 4,094 cpu_core/branch-misses/ # 9.454 M/sec <not counted> cpu_atom/branch-misses/ (0.00%)0.001092407 seconds time elapsed 0.001144000 seconds user 0.000000000 seconds sysSome events weren't counted. Try disabling the NMI watchdog:
echo 0 >/proc/sys/kernel/nmi_watchdogperf stat ...
echo 1 >/proc/sys/kernel/nmi_watchdog# ./perf stat -e '{cpu_atom/cycles/,msr/tsc/}' truePerformance counter stats for 'true':
<not counted> cpu_atom/cycles/ (0.00%) <not counted> msr/tsc/ (0.00%)0.001904106 seconds time elapsed 0.001947000 seconds user 0.000000000 seconds sysSome events weren't counted. Try disabling the NMI watchdog:
echo 0 >/proc/sys/kernel/nmi_watchdog
perf stat ...
echo 1 >/proc/sys/kernel/nmi_watchdog
The events in group usually have to be from the same PMU. Try reorganizing the group.Now we disable the NMI watchdog message on hybrid, otherwise there are too many false positives.
After:
# ./perf stat truePerformance counter stats for 'true':
0.79 msec task-clock # 0.419 CPUs utilized 0 context-switches # 0.000 /sec 0 cpu-migrations # 0.000 /sec 48 page-faults # 60.889 K/sec 777,692 cpu_core/cycles/ # 986.519 M/sec <not counted> cpu_atom/cycles/ (0.00%) 669,147 cpu_core/instructions/ # 848.828 M/sec <not counted> cpu_atom/instructions/ (0.00%) 128,635 cpu_core/branches/ # 163.176 M/sec <not counted> cpu_atom/branches/ (0.00%) 4,089 cpu_core/branch-misses/ # 5.187 M/sec <not counted> cpu_atom/branch-misses/ (0.00%)0.001880649 seconds time elapsed 0.001935000 seconds user 0.000000000 seconds sys# ./perf stat -e '{cpu_atom/cycles/,msr/tsc/}' truePerformance counter stats for 'true':
<not counted> cpu_atom/cycles/ (0.00%) <not counted> msr/tsc/ (0.00%)0.000963319 seconds time elapsed 0.000999000 seconds user 0.000000000 seconds sysSigned-off-by Jin Yao <[email protected]>---
v2:
- If the group was mixed with hybrid event and non-hybrid event, the NMI watchdog message was still reported. V2 adds checking for hybrid event mixed group.v1:
- Get ACK from Jiri.tools/perf/util/stat-display.c | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-)tools/perf/util/stat-display.c +0
-0@@ -404,6 +404,19 @@ static bool is_mixed_hw_group(struct evsel *counter)return false; }
tools/perf/util/stat-display.c static bool is_mixed_hw_group(struct evsel *counter) · line 415
Quoted 10 lines
tools/perf/util/stat-display.c +9
-0+static bool is_mixed_hybrid_group (struct evsel *counter) +{ +struct evlist *evlist = counter->evlist; +struct evsel *pos; + +evlist__for_each_entry (evlist, pos) { +if (perf_pmu__is_hybrid (pos->pmu_name)) +return true; + }
so we care if there's at least one hybrid event in the list right? it can be all full with just hybrid events, but the function name suggests it's mixed with normal events
jirka
Quoted 26 lines
tools/perf/util/stat-display.c +10
-3+ +return false; +} + static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int nr, struct evsel *counter, double uval, char *prefix, u64 run, u64 ena, double noise,@@ -465,9 +478,12 @@ static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int config->csv_sep);if (counter->supported) { - config->print_free_counters_hint =1 ; -if (is_mixed_hw_group (counter)) - config->print_mixed_hw_group_error =1 ; +if (!is_mixed_hybrid_group (counter)) { +if (!perf_pmu__is_hybrid (counter->pmu_name)) + config->print_free_counters_hint =1 ; +if (is_mixed_hw_group (counter)) + config->print_mixed_hw_group_error =1 ; + } } fprintf(config->output, "%-*s%s",Signature · 1 line
2.17.1
Hi Jiri,
Quoted 13 lines · Jiri Olsa
tools/perf/util/stat-display.c static bool is_mixed_hw_group(struct evsel *counter) · line 415
Quoted 9 lines
tools/perf/util/stat-display.c +9
-0+static bool is_mixed_hybrid_group (struct evsel *counter) +{ +struct evlist *evlist = counter->evlist; +struct evsel *pos; + +evlist__for_each_entry (evlist, pos) { +if (perf_pmu__is_hybrid (pos->pmu_name)) +return true; + }so we care if there's at least one hybrid event in the list right? it can be all full with just hybrid events, but the function name suggests it's mixed with normal events
Quoted 2 lines
jirka
Yes, that's right. We only care there is at least one hybrid event in the evlist.
So do we change the function name to evlist__has_hybrid_event?
Thanks
Jin Yao
Quoted 16 lines · Yao
Hi Jiri,
Quoted 13 lines · Jiri Olsa
tools/perf/util/stat-display.c static bool is_mixed_hw_group(struct evsel *counter) · line 415
Quoted 9 lines
tools/perf/util/stat-display.c +9
-0+static bool is_mixed_hybrid_group (struct evsel *counter) +{ +struct evlist *evlist = counter->evlist; +struct evsel *pos; + +evlist__for_each_entry (evlist, pos) { +if (perf_pmu__is_hybrid (pos->pmu_name)) +return true; + }so we care if there's at least one hybrid event in the list right? it can be all full with just hybrid events, but the function name suggests it's mixed with normal events
Quoted 6 lines
Quoted 2 lines
jirka
Yes, that's right. We only care there is at least one hybrid event in the evlist.
So do we change the function name to
evlist__has_hybrid_event?
sounds good, thanks
jirka
Quoted 4 lines
Thanks
Jin Yao