From: Namhyung Kim <namhyung@kernel.org>
To: Arnaldo Carvalho de Melo <acme@kernel.org>, Jiri Olsa <jolsa@kernel.org>
Cc: Ingo Molnar <mingo@kernel.org>,
Peter Zijlstra <peterz@infradead.org>,
LKML <linux-kernel@vger.kernel.org>,
Ian Rogers <irogers@google.com>,
Adrian Hunter <adrian.hunter@intel.com>,
linux-perf-users@vger.kernel.org,
Kan Liang <kan.liang@linux.intel.com>,
Leo Yan <leo.yan@linaro.org>, Andi Kleen <ak@linux.intel.com>,
Athira Rajeev <atrajeev@linux.vnet.ibm.com>,
James Clark <james.clark@arm.com>,
Xing Zhengjun <zhengjun.xing@linux.intel.com>
Subject: [PATCH 14/19] perf stat: Add perf_stat_merge_counters()
Date: Sun, 9 Oct 2022 22:35:55 -0700 [thread overview]
Message-ID: <20221010053600.272854-15-namhyung@kernel.org> (raw)
In-Reply-To: <20221010053600.272854-1-namhyung@kernel.org>
The perf_stat_merge_counters() is to aggregate the same events in different
PMUs like in case of uncore or hybrid. The same logic is in the stat-display
routines but I think it should be handled when it processes the event counters.
As it works on the aggr_counters, it doesn't change the output yet.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
tools/perf/builtin-stat.c | 2 +
tools/perf/util/stat.c | 96 +++++++++++++++++++++++++++++++++++++++
tools/perf/util/stat.h | 2 +
3 files changed, 100 insertions(+)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 49a7e290d778..f90e8f29cb23 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -486,6 +486,8 @@ static void process_counters(void)
pr_warning("failed to process counter %s\n", counter->name);
counter->err = 0;
}
+
+ perf_stat_merge_counters(&stat_config, evsel_list);
}
static void process_interval(void)
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 4edfc1c5dc07..1bb197782a34 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -575,6 +575,102 @@ int perf_stat_process_counter(struct perf_stat_config *config,
return 0;
}
+static int evsel__merge_aggr_counters(struct evsel *evsel, struct evsel *alias)
+{
+ struct perf_stat_evsel *ps_a = evsel->stats;
+ struct perf_stat_evsel *ps_b = alias->stats;
+ int i;
+
+ if (ps_a->aggr == NULL && ps_b->aggr == NULL)
+ return 0;
+
+ if (ps_a->nr_aggr != ps_b->nr_aggr) {
+ pr_err("Unmatched aggregation mode between aliases\n");
+ return -1;
+ }
+
+ for (i = 0; i < ps_a->nr_aggr; i++) {
+ struct perf_counts_values *aggr_counts_a = &ps_a->aggr[i].counts;
+ struct perf_counts_values *aggr_counts_b = &ps_b->aggr[i].counts;
+
+ /* NB: don't increase aggr.nr for aliases */
+
+ aggr_counts_a->val += aggr_counts_b->val;
+ aggr_counts_a->ena += aggr_counts_b->ena;
+ aggr_counts_a->run += aggr_counts_b->run;
+ }
+
+ return 0;
+}
+/* events should have the same name, scale, unit, cgroup but on different PMUs */
+static bool evsel__is_alias(struct evsel *evsel_a, struct evsel *evsel_b)
+{
+ if (strcmp(evsel__name(evsel_a), evsel__name(evsel_b)))
+ return false;
+
+ if (evsel_a->scale != evsel_b->scale)
+ return false;
+
+ if (evsel_a->cgrp != evsel_b->cgrp)
+ return false;
+
+ if (strcmp(evsel_a->unit, evsel_b->unit))
+ return false;
+
+ if (evsel__is_clock(evsel_a) != evsel__is_clock(evsel_b))
+ return false;
+
+ return !!strcmp(evsel_a->pmu_name, evsel_b->pmu_name);
+}
+
+static void evsel__merge_aliases(struct evsel *evsel)
+{
+ struct evlist *evlist = evsel->evlist;
+ struct evsel *alias;
+
+ alias = list_prepare_entry(evsel, &(evlist->core.entries), core.node);
+ list_for_each_entry_continue(alias, &evlist->core.entries, core.node) {
+ /* Merge the same events on different PMUs. */
+ if (evsel__is_alias(evsel, alias)) {
+ evsel__merge_aggr_counters(evsel, alias);
+ alias->merged_stat = true;
+ }
+ }
+}
+
+static bool evsel__should_merge_hybrid(struct evsel *evsel, struct perf_stat_config *config)
+{
+ struct perf_pmu *pmu;
+
+ if (!config->hybrid_merge)
+ return false;
+
+ pmu = evsel__find_pmu(evsel);
+ return pmu && pmu->is_hybrid;
+}
+
+static void evsel__merge_stats(struct evsel *evsel, struct perf_stat_config *config)
+{
+ /* this evsel is already merged */
+ if (evsel->merged_stat)
+ return;
+
+ if (evsel->auto_merge_stats || evsel__should_merge_hybrid(evsel, config))
+ evsel__merge_aliases(evsel);
+}
+
+/* merge the same uncore and hybrid events if requested */
+void perf_stat_merge_counters(struct perf_stat_config *config, struct evlist *evlist)
+{
+ struct evsel *evsel;
+
+ if (config->no_merge)
+ return;
+
+ evlist__for_each_entry(evlist, evsel)
+ evsel__merge_stats(evsel, config);
+}
+
int perf_event__process_stat_event(struct perf_session *session,
union perf_event *event)
{
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 3a876ad2870b..12cc60ab04e4 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -270,6 +270,8 @@ void evlist__reset_aggr_stats(struct evlist *evlist);
int perf_stat_process_counter(struct perf_stat_config *config,
struct evsel *counter);
+void perf_stat_merge_counters(struct perf_stat_config *config, struct evlist *evlist);
+
struct perf_tool;
union perf_event;
struct perf_session;
--
2.38.0.rc1.362.ged0d419d3c-goog
next prev parent reply other threads:[~2022-10-10 5:37 UTC|newest]
Thread overview: 63+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-10-10 5:35 [RFC/PATCHSET 00/19] perf stat: Cleanup counter aggregation (v1) Namhyung Kim
2022-10-10 5:35 ` [PATCH 01/19] perf tools: Save evsel->pmu in parse_events() Namhyung Kim
2022-10-10 22:21 ` Ian Rogers
2022-10-10 5:35 ` [PATCH 02/19] perf tools: Use pmu info in evsel__is_hybrid() Namhyung Kim
2022-10-10 22:31 ` Ian Rogers
2022-10-11 5:10 ` Namhyung Kim
2022-10-10 5:35 ` [PATCH 03/19] perf stat: Use evsel__is_hybrid() more Namhyung Kim
2022-10-10 22:32 ` Ian Rogers
2022-10-10 5:35 ` [PATCH 04/19] perf stat: Add aggr id for global mode Namhyung Kim
2022-10-10 22:46 ` Ian Rogers
2022-10-11 23:08 ` Namhyung Kim
2022-10-12 10:55 ` Jiri Olsa
2022-10-12 16:31 ` Namhyung Kim
2022-10-10 5:35 ` [PATCH 05/19] perf stat: Add cpu aggr id for no aggregation mode Namhyung Kim
2022-10-10 22:49 ` Ian Rogers
2022-10-12 10:40 ` Jiri Olsa
2022-10-12 16:27 ` Namhyung Kim
2022-10-10 5:35 ` [PATCH 06/19] perf stat: Add 'needs_sort' argument to cpu_aggr_map__new() Namhyung Kim
2022-10-10 22:53 ` Ian Rogers
2022-10-11 23:32 ` Namhyung Kim
2022-10-10 5:35 ` [PATCH 07/19] perf stat: Add struct perf_stat_aggr to perf_stat_evsel Namhyung Kim
2022-10-10 23:00 ` Ian Rogers
2022-10-11 23:37 ` Namhyung Kim
2022-10-10 5:35 ` [PATCH 08/19] perf stat: Allocate evsel->stats->aggr properly Namhyung Kim
2022-10-10 23:03 ` Ian Rogers
2022-10-11 23:38 ` Namhyung Kim
2022-10-10 5:35 ` [PATCH 09/19] perf stat: Aggregate events using evsel->stats->aggr Namhyung Kim
2022-10-10 23:11 ` Ian Rogers
2022-10-11 23:44 ` Namhyung Kim
2022-10-10 5:35 ` [PATCH 10/19] perf stat: Aggregate per-thread stats " Namhyung Kim
2022-10-10 23:17 ` Ian Rogers
2022-10-11 23:46 ` Namhyung Kim
2022-10-10 5:35 ` [PATCH 11/19] perf stat: Allocate aggr counts for recorded data Namhyung Kim
2022-10-10 23:18 ` Ian Rogers
2022-10-10 5:35 ` [PATCH 12/19] perf stat: Reset aggr counts for each interval Namhyung Kim
2022-10-10 23:20 ` Ian Rogers
2022-10-11 23:48 ` Namhyung Kim
2022-10-10 5:35 ` [PATCH 13/19] perf stat: Split process_counters() Namhyung Kim
2022-10-10 23:21 ` Ian Rogers
2022-10-10 5:35 ` Namhyung Kim [this message]
2022-10-10 23:31 ` [PATCH 14/19] perf stat: Add perf_stat_merge_counters() Ian Rogers
2022-10-11 23:55 ` Namhyung Kim
2022-10-10 5:35 ` [PATCH 15/19] perf stat: Add perf_stat_process_percore() Namhyung Kim
2022-10-10 23:32 ` Ian Rogers
2022-10-11 23:59 ` Namhyung Kim
2022-10-10 5:35 ` [PATCH 16/19] perf stat: Add perf_stat_process_shadow_stats() Namhyung Kim
2022-10-10 23:36 ` Ian Rogers
2022-10-10 5:35 ` [PATCH 17/19] perf stat: Display event stats using aggr counts Namhyung Kim
2022-10-10 23:38 ` Ian Rogers
2022-10-10 5:35 ` [PATCH 18/19] perf stat: Display percore events properly Namhyung Kim
2022-10-10 23:39 ` Ian Rogers
2022-10-10 5:36 ` [PATCH 19/19] perf stat: Remove unused perf_counts.aggr field Namhyung Kim
2022-10-10 23:40 ` Ian Rogers
2022-10-12 8:41 ` Jiri Olsa
2022-10-12 16:26 ` Namhyung Kim
2022-10-13 20:56 ` [PATCH] perf stat: Init aggr_map when reporting per-process stat Namhyung Kim
2022-10-11 0:25 ` [RFC/PATCHSET 00/19] perf stat: Cleanup counter aggregation (v1) Andi Kleen
2022-10-11 5:38 ` Namhyung Kim
2022-10-11 6:13 ` Ian Rogers
2022-10-12 3:55 ` Namhyung Kim
2022-10-11 11:57 ` Andi Kleen
2022-10-12 3:58 ` Namhyung Kim
-- strict thread matches above, loose matches on Subject: below --
2022-10-14 6:15 [PATCHSET 00/19] perf stat: Cleanup counter aggregation (v2) Namhyung Kim
2022-10-14 6:15 ` [PATCH 14/19] perf stat: Add perf_stat_merge_counters() Namhyung Kim
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20221010053600.272854-15-namhyung@kernel.org \
--to=namhyung@kernel.org \
--cc=acme@kernel.org \
--cc=adrian.hunter@intel.com \
--cc=ak@linux.intel.com \
--cc=atrajeev@linux.vnet.ibm.com \
--cc=irogers@google.com \
--cc=james.clark@arm.com \
--cc=jolsa@kernel.org \
--cc=kan.liang@linux.intel.com \
--cc=leo.yan@linaro.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=zhengjun.xing@linux.intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).