diff options
author | Namhyung Kim <namhyung@kernel.org> | 2022-10-18 04:02:23 +0200 |
---|---|---|
committer | Arnaldo Carvalho de Melo <acme@redhat.com> | 2022-10-27 21:37:25 +0200 |
commit | 1d6d2bea5b97359ff09a8d793674aab3e5f79023 (patch) | |
tree | 8cd2e82b7245d77f69181504ebe9913bd0303737 /tools/perf/util/stat.c | |
parent | perf stat: Add perf_stat_merge_counters() (diff) | |
download | linux-1d6d2bea5b97359ff09a8d793674aab3e5f79023.tar.xz linux-1d6d2bea5b97359ff09a8d793674aab3e5f79023.zip |
perf stat: Add perf_stat_process_percore()
The perf_stat_process_percore() is to aggregate counts for an event per-core
even if the aggr_mode is AGGR_NONE. This is enabled when user requested it
on the command line.
To handle that, it keeps the per-cpu counts at first. And then it aggregates
the counts that have the same core id in the aggr->counts and updates the
values for each cpu back.
Later, per-core events will skip one of the CPUs unless percore-show-thread
option is given. In that case, it can simply print all cpu stats with the
updated (per-core) values.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Link: https://lore.kernel.org/r/20221018020227.85905-17-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Diffstat (limited to 'tools/perf/util/stat.c')
-rw-r--r-- | tools/perf/util/stat.c | 71 |
1 files changed, 71 insertions, 0 deletions
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index aff1e7390585..26c48ef7ca92 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -691,6 +691,77 @@ void perf_stat_merge_counters(struct perf_stat_config *config, struct evlist *ev evsel__merge_stats(evsel, config); } +static void evsel__update_percore_stats(struct evsel *evsel, struct aggr_cpu_id *core_id) +{ + struct perf_stat_evsel *ps = evsel->stats; + struct perf_counts_values counts = { 0, }; + struct aggr_cpu_id id; + struct perf_cpu cpu; + int idx; + + /* collect per-core counts */ + perf_cpu_map__for_each_cpu(cpu, idx, evsel->core.cpus) { + struct perf_stat_aggr *aggr = &ps->aggr[idx]; + + id = aggr_cpu_id__core(cpu, NULL); + if (!aggr_cpu_id__equal(core_id, &id)) + continue; + + counts.val += aggr->counts.val; + counts.ena += aggr->counts.ena; + counts.run += aggr->counts.run; + } + + /* update aggregated per-core counts for each CPU */ + perf_cpu_map__for_each_cpu(cpu, idx, evsel->core.cpus) { + struct perf_stat_aggr *aggr = &ps->aggr[idx]; + + id = aggr_cpu_id__core(cpu, NULL); + if (!aggr_cpu_id__equal(core_id, &id)) + continue; + + aggr->counts.val = counts.val; + aggr->counts.ena = counts.ena; + aggr->counts.run = counts.run; + + aggr->used = true; + } +} + +/* we have an aggr_map for cpu, but want to aggregate the counters per-core */ +static void evsel__process_percore(struct evsel *evsel) +{ + struct perf_stat_evsel *ps = evsel->stats; + struct aggr_cpu_id core_id; + struct perf_cpu cpu; + int idx; + + if (!evsel->percore) + return; + + perf_cpu_map__for_each_cpu(cpu, idx, evsel->core.cpus) { + struct perf_stat_aggr *aggr = &ps->aggr[idx]; + + if (aggr->used) + continue; + + core_id = aggr_cpu_id__core(cpu, NULL); + evsel__update_percore_stats(evsel, &core_id); + } +} + +/* process cpu stats on per-core events */ +void perf_stat_process_percore(struct perf_stat_config *config, struct evlist *evlist) +{ + struct evsel *evsel; + + if (config->aggr_mode != AGGR_NONE) + return; + + evlist__for_each_entry(evlist, evsel) + evsel__process_percore(evsel); +} + int perf_event__process_stat_event(struct perf_session *session, union perf_event *event) { |