All of lore.kernel.org
 help / color / mirror / Atom feed
From: Ian Rogers <irogers@google.com>
To: Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	 Arnaldo Carvalho de Melo <acme@kernel.org>,
	Namhyung Kim <namhyung@kernel.org>, Jiri Olsa <jolsa@kernel.org>,
	 Ian Rogers <irogers@google.com>,
	Adrian Hunter <adrian.hunter@intel.com>,
	 James Clark <james.clark@linaro.org>
Cc: linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH v3 29/30] perf script: Display metrics for perf stat record data
Date: Fri, 20 Nov 2026 14:13:30 -0800	[thread overview]
Message-ID: <20261120221332.2245191-30-irogers@google.com> (raw)
In-Reply-To: <20261120221332.2245191-1-irogers@google.com>

perf script displays the counts of each stat round read from a perf stat
record perf.data file. Also display, after each round, the metrics
requested on the perf stat record command line (or all matching metrics
when --all-metrics or stat.all-metrics=true is used), computed from the
counts aggregated across CPUs and threads, for example:

  $ perf stat record -M insn_per_cycle -a sleep 1
  $ perf script
  CPU THREAD         VAL         ENA         RUN        TIME EVENT
  ...
  cpu_atom/cpu-cycles/  metric:      0.7 instructions  insn_per_cycle
  cpu_core/cpu-cycles/  metric:      1.3 instructions  insn_per_cycle

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/Documentation/perf-script.txt |   6 ++
 tools/perf/builtin-script.c              | 107 ++++++++++++++++++++++-
 2 files changed, 110 insertions(+), 3 deletions(-)

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index f0228e784ced..bfd69d411996 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -468,6 +468,12 @@ include::itrace.txt[]
 	default behavior.  If you want to see separate CALLCHAIN_DEFERRED
 	records for some reason, use --no-merge-callchains explicitly.
 
+--all-metrics::
+	Display all metrics that match the recorded stat events in the perf data
+	file, rather than only the metrics requested on the 'perf stat record'
+	command line. Default setting can be changed with
+	"perf config stat.all-metrics=true".
+
 :GMEXAMPLECMD: script
 :GMEXAMPLESUBCMD:
 include::guest-files.txt[]
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index afed2353ef80..135ec34494bd 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -2334,8 +2334,13 @@ static void script_print_metric(struct perf_stat_config *config __maybe_unused,
 
 	if (!fmt)
 		return;
-	perf_sample__fprintf_start(NULL, mctx->sample, mctx->thread, mctx->evsel,
-				   PERF_RECORD_SAMPLE, mctx->fp);
+	if (mctx->sample) {
+		perf_sample__fprintf_start(NULL, mctx->sample, mctx->thread, mctx->evsel,
+					   PERF_RECORD_SAMPLE, mctx->fp);
+	} else {
+		/* Metric computed from the counts of a perf stat record round. */
+		fputs(evsel__name(mctx->evsel), mctx->fp);
+	}
 	fputs("\tmetric: ", mctx->fp);
 	if (color)
 		color_fprintf(mctx->fp, color, fmt, val);
@@ -3795,26 +3800,112 @@ static void script__setup_sample_type(struct perf_script *script)
 	}
 }
 
+/*
+ * Set up the computation of metrics whose events were all recorded by perf stat
+ * record. Counts are aggregated globally for the metrics.
+ */
+static bool script_stat_metrics_init(struct evlist *evlist)
+{
+	struct perf_thread_map *threads = evlist__core(evlist)->threads;
+	struct evsel *counter;
+
+	evlist__for_each_entry(evlist, counter) {
+		if (!counter->stats)
+			return false;
+	}
+	/* Metrics may use system_wide, such as for #target_cpu. */
+	stat_config.system_wide = !threads || perf_thread_map__nr(threads) < 1 ||
+				  perf_thread_map__pid(threads, /*idx=*/0) == -1;
+	metricgroup__add_recorded_metrics(evlist, /*metrics=*/NULL,
+					  /*pmu_filter=*/NULL,
+					  /*cputype_filter=*/false,
+					  stat_config.metric_no_group,
+					  stat_config.metric_no_merge,
+					  stat_config.metric_no_threshold,
+					  stat_config.all_metrics,
+					  stat_config.system_wide,
+					  /*default_metricgroup=*/false,
+					  /*metric_only=*/NULL);
+
+	if (rblist__empty(evlist__metric_events(evlist)))
+		return false;
+
+	if (!stat_config.aggr_map) {
+		stat_config.aggr_get_id = script_aggr_cpu_id_get;
+		stat_config.aggr_map =
+			cpu_aggr_map__new(evlist__core(evlist)->user_requested_cpus,
+					  aggr_cpu_id__global, /*data=*/NULL,
+					  /*needs_sort=*/false);
+		if (!stat_config.aggr_map)
+			return false;
+	}
+	/*
+	 * The aggregated stats may already have been allocated, with the
+	 * aggr_map, for metrics computed from samples.
+	 */
+	if (!evlist__first(evlist)->stats->aggr &&
+	    evlist__alloc_aggr_stats(evlist, stat_config.aggr_map->nr))
+		return false;
+
+	if (!stat_config.output)
+		stat_config.output = stdout;
+	stat_config.aggr_mode = AGGR_GLOBAL;
+	return true;
+}
+
+static void script_print_stat_metrics(struct evlist *evlist)
+{
+	struct evsel *counter;
+	int aggr_idx;
+
+	evlist__for_each_entry(evlist, counter) {
+		struct perf_stat_output_ctx ctx = {
+			.print_metric = script_print_metric,
+			.new_line = script_new_line,
+			.ctx = &(struct metric_ctx) {
+				.evsel = counter,
+				.fp = stdout,
+			},
+			.force_header = false,
+		};
+
+		cpu_aggr_map__for_each_idx(aggr_idx, stat_config.aggr_map)
+			perf_stat__print_shadow_stats(&stat_config, counter, aggr_idx, &ctx);
+	}
+}
+
 static int process_stat_round_event(const struct perf_tool *tool __maybe_unused,
 				    struct perf_session *session,
 				    union perf_event *event)
 {
 	struct perf_record_stat_round *round = &event->stat_round;
 	struct evsel *counter;
+	static int show_metrics = -1;
+
+	if (show_metrics < 0)
+		show_metrics = script_stat_metrics_init(session->evlist) ? 1 : 0;
+
+	if (show_metrics)
+		evlist__reset_aggr_stats(session->evlist);
 
 	evlist__for_each_entry(session->evlist, counter) {
 		perf_stat_process_counter(&stat_config, counter);
 		process_stat(counter, round->time);
 	}
 
+	if (show_metrics)
+		script_print_stat_metrics(session->evlist);
+
 	process_stat_interval(round->time);
 	return 0;
 }
 
 static int process_stat_config_event(const struct perf_tool *tool __maybe_unused,
-				     struct perf_session *session __maybe_unused,
+				     struct perf_session *session,
 				     union perf_event *event)
 {
+	struct evsel *counter;
+
 	perf_event__read_stat_config(&stat_config, &event->stat_config);
 
 	/*
@@ -3823,6 +3914,13 @@ static int process_stat_config_event(const struct perf_tool *tool __maybe_unused
 	 */
 	stat_config.aggr_mode = AGGR_NONE;
 
+	/*
+	 * Mark counters unsupported until a PERF_RECORD_STAT event is
+	 * processed for them by perf_event__process_stat_event().
+	 */
+	evlist__for_each_entry(session->evlist, counter)
+		counter->supported = false;
+
 	return 0;
 }
 
@@ -4206,6 +4304,8 @@ int cmd_script(int argc, const char **argv)
 		    "Enable LBR callgraph stitching approach"),
 	OPT_BOOLEAN('\0', "merge-callchains", &merge_deferred_callchains,
 		    "Enable merge deferred user callchains"),
+	OPT_BOOLEAN(0, "all-metrics", &stat_config.all_metrics,
+		    "Display all metrics matching recorded stat events"),
 	OPTS_EVSWITCH(&script.evswitch),
 	OPT_END()
 	};
@@ -4577,6 +4677,7 @@ int cmd_script(int argc, const char **argv)
 
 	zstd_fini(&(session->zstd_data));
 	evlist__free_stats(session->evlist);
+	zfree(&stat_config.aggr_map);
 	perf_session__delete(session);
 	perf_script__exit(&script);
 
-- 
2.56.1.750.gf70dc682cf-goog


  parent reply	other threads:[~2026-11-20 22:16 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-20 22:13 [PATCH v3 00/30] perf: Per-env PMUs, metric event sharing, and recorded event metrics Ian Rogers
2026-11-20 22:13 ` [PATCH v3 01/30] perf pmus: Don't skip core PMUs as duplicates Ian Rogers
2026-11-20 22:13 ` [PATCH v3 02/30] perf script: Fix metrics computed from samples Ian Rogers
2026-11-20 22:13 ` [PATCH v3 03/30] perf script: Don't drop metric samples for CPUs missing from the evsel Ian Rogers
2026-11-20 22:13 ` [PATCH v3 04/30] perf metricgroup: Don't prefer tool events for displaying a metric Ian Rogers
2026-11-20 22:13 ` [PATCH v3 05/30] perf env: Make lazy perf_env initialization thread-safe Ian Rogers
2026-11-20 22:13 ` [PATCH v3 06/30] perf env: Add host_env() singleton Ian Rogers
2026-11-20 22:13 ` [PATCH v3 07/30] perf pmu: Add from_env parameter to perf_pmu__init() Ian Rogers
2026-11-20 22:13 ` [PATCH v3 08/30] perf pmus: Introduce struct perf_pmus and perf_env__pmus() Ian Rogers
2026-11-20 22:13 ` [PATCH v3 09/30] perf pmus: Pass struct perf_pmus to find helpers Ian Rogers
2026-11-20 22:13 ` [PATCH v3 10/30] perf pmus: Pass struct perf_pmus to scan helpers Ian Rogers
2026-11-20 22:13 ` [PATCH v3 11/30] perf pmu-events: Add e_machine to struct pmu_events_map Ian Rogers
2026-11-20 22:13 ` [PATCH v3 12/30] perf pmu-events: Pass e_machine to find_core_*_table() Ian Rogers
2026-11-20 22:13 ` [PATCH v3 13/30] perf header: Pass e_machine to strcmp_cpuid_str() Ian Rogers
2026-11-20 22:13 ` [PATCH v3 14/30] perf header: Support CPUID matching across all architectures Ian Rogers
2026-11-20 22:13 ` [PATCH v3 15/30] perf test: Make the CPUID matching test architecture independent Ian Rogers
2026-11-20 22:13 ` [PATCH v3 16/30] perf test: Add CPUID matching tests for other architectures Ian Rogers
2026-11-20 22:13 ` [PATCH v3 17/30] perf dwarf-regs: Add e_machine__same_arch() Ian Rogers
2026-11-20 22:13 ` [PATCH v3 18/30] perf metricgroup: Pass struct perf_pmus to metricgroup__for_each_metric() Ian Rogers
2026-11-20 22:13 ` [PATCH v3 19/30] perf metricgroup: Move matching of metrics to recorded events from perf script Ian Rogers
2026-11-20 22:13 ` [PATCH v3 20/30] perf parse-events: Decode metric-id terms when adding events Ian Rogers
2026-11-20 22:13 ` [PATCH v3 21/30] perf evsel: Generalize metric_id to a set of metric_ids Ian Rogers
2026-11-20 22:13 ` [PATCH v3 22/30] perf pmu: Add perf_pmu__for_each_name_from_config() Ian Rogers
2026-11-20 22:13 ` [PATCH v3 23/30] perf metricgroup: Share metric events by their counter encoding Ian Rogers
2026-11-20 22:13 ` [PATCH v3 24/30] perf stat: Share events between metrics and command line events Ian Rogers
2026-11-20 22:13 ` [PATCH v3 25/30] perf pmus: Add perf_pmus__read_from_env() Ian Rogers
2026-11-20 22:42   ` sashiko-bot
2026-11-20 22:13 ` [PATCH v3 26/30] perf metricgroup: Improve matching of metrics to recorded events Ian Rogers
2026-11-20 22:13 ` [PATCH v3 27/30] perf metricgroup: Add metricgroup__add_recorded_metrics() Ian Rogers
2026-11-20 22:13 ` [PATCH v3 28/30] perf stat report: Display metrics for recorded events Ian Rogers
2026-11-20 22:13 ` Ian Rogers [this message]
2026-11-20 22:13 ` [PATCH v3 30/30] perf test: Add stat record metrics test Ian Rogers
2026-11-20 22:42 ` [PATCH v3 00/30] perf: Per-env PMUs, metric event sharing, and recorded event metrics sashiko-bot

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=20261120221332.2245191-30-irogers@google.com \
    --to=irogers@google.com \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=james.clark@linaro.org \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.