diff options
author | Ian Rogers <irogers@google.com> | 2023-05-27 00:22:05 -0700 |
---|---|---|
committer | Arnaldo Carvalho de Melo <acme@redhat.com> | 2023-05-27 09:42:00 -0300 |
commit | 9d6a1df9b2eef52ad03a594b1237a16dbbe34e83 (patch) | |
tree | 9131930b207cb97a28f01e40694fa542a9f177a1 /tools/perf/bench | |
parent | 15c57a8037c9683fb5c09ecc576a333c02d6f105 (diff) | |
download | linux-9d6a1df9b2eef52ad03a594b1237a16dbbe34e83.tar.gz linux-9d6a1df9b2eef52ad03a594b1237a16dbbe34e83.tar.bz2 linux-9d6a1df9b2eef52ad03a594b1237a16dbbe34e83.zip |
perf pmus: Allow just core PMU scanning
Scanning all PMUs is expensive as all PMUs sysfs entries are loaded,
benchmarking shows more than 4x the cost:
```
$ perf bench internals pmu-scan -i 1000
Computing performance of sysfs PMU event scan for 1000 times
Average core PMU scanning took: 989.231 usec (+- 1.535 usec)
Average PMU scanning took: 4309.425 usec (+- 74.322 usec)
```
Add new perf_pmus__scan_core routine that scans just core
PMUs. Replace perf_pmus__scan calls with perf_pmus__scan_core when
non-core PMUs are being ignored.
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ali Saidi <alisaidi@amazon.com>
Cc: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Cc: Dmitrii Dolgov <9erthalion6@gmail.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kang Minchul <tegongkang@gmail.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Ming Wang <wangming01@loongson.cn>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Cc: Sandipan Das <sandipan.das@amd.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Cc: coresight@lists.linaro.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20230527072210.2900565-30-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Diffstat (limited to 'tools/perf/bench')
-rw-r--r-- | tools/perf/bench/pmu-scan.c | 50 |
1 files changed, 29 insertions, 21 deletions
diff --git a/tools/perf/bench/pmu-scan.c b/tools/perf/bench/pmu-scan.c index 51cae2d03353..c7d207f8e13c 100644 --- a/tools/perf/bench/pmu-scan.c +++ b/tools/perf/bench/pmu-scan.c @@ -22,6 +22,7 @@ struct pmu_scan_result { int nr_aliases; int nr_formats; int nr_caps; + bool is_core; }; static const struct option options[] = { @@ -53,6 +54,7 @@ static int save_result(void) r = results + nr_pmus; r->name = strdup(pmu->name); + r->is_core = pmu->is_core; r->nr_caps = pmu->nr_caps; r->nr_aliases = 0; @@ -72,7 +74,7 @@ static int save_result(void) return 0; } -static int check_result(void) +static int check_result(bool core_only) { struct pmu_scan_result *r; struct perf_pmu *pmu; @@ -81,6 +83,9 @@ static int check_result(void) for (int i = 0; i < nr_pmus; i++) { r = &results[i]; + if (core_only && !r->is_core) + continue; + pmu = perf_pmus__find(r->name); if (pmu == NULL) { pr_err("Cannot find PMU %s\n", r->name); @@ -130,7 +135,6 @@ static int run_pmu_scan(void) struct timeval start, end, diff; double time_average, time_stddev; u64 runtime_us; - unsigned int i; int ret; init_stats(&stats); @@ -142,26 +146,30 @@ static int run_pmu_scan(void) return -1; } - for (i = 0; i < iterations; i++) { - gettimeofday(&start, NULL); - perf_pmus__scan(NULL); - gettimeofday(&end, NULL); - - timersub(&end, &start, &diff); - runtime_us = diff.tv_sec * USEC_PER_SEC + diff.tv_usec; - update_stats(&stats, runtime_us); - - ret = check_result(); - perf_pmus__destroy(); - if (ret < 0) - break; + for (int j = 0; j < 2; j++) { + bool core_only = (j == 0); + + for (unsigned int i = 0; i < iterations; i++) { + gettimeofday(&start, NULL); + if (core_only) + perf_pmus__scan_core(NULL); + else + perf_pmus__scan(NULL); + gettimeofday(&end, NULL); + timersub(&end, &start, &diff); + runtime_us = diff.tv_sec * USEC_PER_SEC + diff.tv_usec; + update_stats(&stats, runtime_us); + + ret = check_result(core_only); + perf_pmus__destroy(); + if (ret < 0) + break; + } + time_average = avg_stats(&stats); + time_stddev = stddev_stats(&stats); + pr_info(" Average%s PMU scanning took: %.3f usec (+- %.3f usec)\n", + core_only ? " core" : "", time_average, time_stddev); } - - time_average = avg_stats(&stats); - time_stddev = stddev_stats(&stats); - pr_info(" Average PMU scanning took: %.3f usec (+- %.3f usec)\n", - time_average, time_stddev); - delete_result(); return 0; } |