[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20220831174926.579643-6-irogers@google.com>
Date: Wed, 31 Aug 2022 10:49:24 -0700
From: Ian Rogers <irogers@...gle.com>
To: Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...hat.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
Mark Rutland <mark.rutland@....com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Jiri Olsa <jolsa@...nel.org>,
Namhyung Kim <namhyung@...nel.org>,
Andi Kleen <ak@...ux.intel.com>,
Kan Liang <kan.liang@...ux.intel.com>,
Thomas Richter <tmricht@...ux.ibm.com>,
James Clark <james.clark@....com>,
Miaoqian Lin <linmq006@...il.com>,
John Garry <john.garry@...wei.com>,
Zhengjun Xing <zhengjun.xing@...ux.intel.com>,
Florian Fischer <florian.fischer@...q.space>,
linux-perf-users@...r.kernel.org, linux-kernel@...r.kernel.org,
perry.taylor@...el.com, caleb.biggers@...el.com,
kshipra.bopardikar@...el.com, ahmad.yasin@...el.com
Cc: Stephane Eranian <eranian@...gle.com>,
Ian Rogers <irogers@...gle.com>
Subject: [PATCH v2 5/7] perf stat: Delay metric parsing
Having metric parsing as part of argument processing causes issues as
flags like metric-no-group may be specified later. It also denies the
opportunity to optimize the events on SMT systems where fewer events
may be possible if we know the target is system-wide. Move metric
parsing to after command line option parsing. Because of how stat runs
this moves the parsing after record/report which fail to work with
metrics currently anyway.
Signed-off-by: Ian Rogers <irogers@...gle.com>
---
tools/perf/builtin-stat.c | 52 +++++++++++++++++++++++++----------
tools/perf/util/metricgroup.c | 3 +-
tools/perf/util/metricgroup.h | 2 +-
3 files changed, 39 insertions(+), 18 deletions(-)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 54cd29d07ca8..a59c23f4ffd2 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -191,6 +191,7 @@ static bool append_file;
static bool interval_count;
static const char *output_name;
static int output_fd;
+static char *metrics;
struct perf_stat {
bool record;
@@ -1148,14 +1149,23 @@ static int enable_metric_only(const struct option *opt __maybe_unused,
return 0;
}
-static int parse_metric_groups(const struct option *opt,
+static int append_metric_groups(const struct option *opt __maybe_unused,
const char *str,
int unset __maybe_unused)
{
- return metricgroup__parse_groups(opt, str,
- stat_config.metric_no_group,
- stat_config.metric_no_merge,
- &stat_config.metric_events);
+ if (metrics) {
+ char *tmp;
+
+ if (asprintf(&tmp, "%s,%s", metrics, str) < 0)
+ return -ENOMEM;
+ free(metrics);
+ metrics = tmp;
+ } else {
+ metrics = strdup(str);
+ if (!metrics)
+ return -ENOMEM;
+ }
+ return 0;
}
static int parse_control_option(const struct option *opt,
@@ -1299,7 +1309,7 @@ static struct option stat_options[] = {
"measure SMI cost"),
OPT_CALLBACK('M', "metrics", &evsel_list, "metric/metric group list",
"monitor specified metrics or metric groups (separated by ,)",
- parse_metric_groups),
+ append_metric_groups),
OPT_BOOLEAN_FLAG(0, "all-kernel", &stat_config.all_kernel,
"Configure all used events to run in kernel space.",
PARSE_OPT_EXCLUSIVE),
@@ -1792,11 +1802,9 @@ static int add_default_attributes(void)
* on an architecture test for such a metric name.
*/
if (metricgroup__has_metric("transaction")) {
- struct option opt = { .value = &evsel_list };
-
- return metricgroup__parse_groups(&opt, "transaction",
+ return metricgroup__parse_groups(evsel_list, "transaction",
stat_config.metric_no_group,
- stat_config.metric_no_merge,
+ stat_config.metric_no_merge,
&stat_config.metric_events);
}
@@ -2182,6 +2190,8 @@ static int __cmd_report(int argc, const char **argv)
input_name = "perf.data";
}
+ perf_stat__init_shadow_stats();
+
perf_stat.data.path = input_name;
perf_stat.data.mode = PERF_DATA_MODE_READ;
@@ -2261,8 +2271,6 @@ int cmd_stat(int argc, const char **argv)
argc = parse_options_subcommand(argc, argv, stat_options, stat_subcommands,
(const char **) stat_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
- perf_stat__collect_metric_expr(evsel_list);
- perf_stat__init_shadow_stats();
if (stat_config.csv_sep) {
stat_config.csv_output = true;
@@ -2429,6 +2437,23 @@ int cmd_stat(int argc, const char **argv)
target.system_wide = true;
}
+ if ((stat_config.aggr_mode == AGGR_THREAD) && (target.system_wide))
+ target.per_thread = true;
+
+ /*
+ * Metric parsing needs to be delayed as metrics may optimize events
+ * knowing the target is system-wide.
+ */
+ if (metrics) {
+ metricgroup__parse_groups(evsel_list, metrics,
+ stat_config.metric_no_group,
+ stat_config.metric_no_merge,
+ &stat_config.metric_events);
+ zfree(&metrics);
+ }
+ perf_stat__collect_metric_expr(evsel_list);
+ perf_stat__init_shadow_stats();
+
if (add_default_attributes())
goto out;
@@ -2448,9 +2473,6 @@ int cmd_stat(int argc, const char **argv)
}
}
- if ((stat_config.aggr_mode == AGGR_THREAD) && (target.system_wide))
- target.per_thread = true;
-
if (evlist__fix_hybrid_cpus(evsel_list, target.cpu_list)) {
pr_err("failed to use cpu list %s\n", target.cpu_list);
goto out;
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index b144c3e35264..9151346a16ab 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -1646,13 +1646,12 @@ static int parse_groups(struct evlist *perf_evlist, const char *str,
return ret;
}
-int metricgroup__parse_groups(const struct option *opt,
+int metricgroup__parse_groups(struct evlist *perf_evlist,
const char *str,
bool metric_no_group,
bool metric_no_merge,
struct rblist *metric_events)
{
- struct evlist *perf_evlist = *(struct evlist **)opt->value;
const struct pmu_events_table *table = pmu_events_table__find();
if (!table)
diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h
index 016b3b1a289a..af9ceadaec0f 100644
--- a/tools/perf/util/metricgroup.h
+++ b/tools/perf/util/metricgroup.h
@@ -64,7 +64,7 @@ struct metric_expr {
struct metric_event *metricgroup__lookup(struct rblist *metric_events,
struct evsel *evsel,
bool create);
-int metricgroup__parse_groups(const struct option *opt,
+int metricgroup__parse_groups(struct evlist *perf_evlist,
const char *str,
bool metric_no_group,
bool metric_no_merge,
--
2.37.2.672.g94769d06f0-goog
Powered by blists - more mailing lists