perf stat: Add no-affinity flag

Add flag that disables affinity behavior.

Using sched_setaffinity() to place a perf thread on a CPU can avoid
certain interprocessor interrupts but may introduce a delay due to the
scheduling, particularly on loaded machines.

Add a command line option to disable the behavior.

This behavior is less present in other tools like `perf record`, as it
uses a ring buffer and doesn't make repeated system calls.

Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Andres Freund <andres@anarazel.de>
Cc: Dapeng Mi <dapeng1.mi@linux.intel.com>
Cc: Dr. David Alan Gilbert <linux@treblig.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Falcon <thomas.falcon@intel.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Yang Li <yang.lee@linux.alibaba.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

Author: captain5050

tools/perf/Documentation/perf-stat.txt

@@ -382,6 +382,11 @@ color the metric's computed value.
 Don't print output, warnings or messages. This is useful with perf stat
 record below to only write data to the perf.data file.
 
+--no-affinity::
+Don't change scheduler CPU affinities when iterating over
+CPUs. Disables an optimization aimed at minimizing interprocessor
+interrupts.
+
 STAT RECORD
 -----------
 Stores stat data into perf data file.

tools/perf/builtin-stat.c

@@ -2426,6 +2426,7 @@ static int parse_tpebs_mode(const struct option *opt, const char *str,
 int cmd_stat(int argc, const char **argv)
 {
 	struct opt_aggr_mode opt_mode = {};
+	bool affinity = true, affinity_set = false;
 	struct option stat_options[] = {
 		OPT_BOOLEAN('T', "transaction", &transaction_run,
 			"hardware transaction statistics"),
@@ -2554,6 +2555,8 @@ int cmd_stat(int argc, const char **argv)
 			"don't print 'summary' for CSV summary output"),
 		OPT_BOOLEAN(0, "quiet", &quiet,
 			"don't print any output, messages or warnings (useful with record)"),
+		OPT_BOOLEAN_SET(0, "affinity", &affinity, &affinity_set,
+			"enable (default) or disable affinity optimizations to reduce IPIs"),
 		OPT_CALLBACK(0, "cputype", &evsel_list, "hybrid cpu type",
 			"Only enable events on applying cpu with this type "
 			"for hybrid platform (e.g. core or atom)",
@@ -2611,6 +2614,9 @@ int cmd_stat(int argc, const char **argv)
 	} else
 		stat_config.csv_sep = DEFAULT_SEPARATOR;
 
+	if (affinity_set)
+		evsel_list->no_affinity = !affinity;
+
 	if (argc && strlen(argv[0]) > 2 && strstarts("record", argv[0])) {
 		argc = __cmd_record(stat_options, &opt_mode, argc, argv);
 		if (argc < 0)

tools/perf/util/evlist.c

@@ -369,11 +369,7 @@ static bool evlist__use_affinity(struct evlist *evlist)
 	struct perf_cpu_map *used_cpus = NULL;
 	bool ret = false;
 
-	/*
-	 * With perf record core.user_requested_cpus is usually NULL.
-	 * Use the old method to handle this for now.
-	 */
-	if (!evlist->core.user_requested_cpus ||
+	if (evlist->no_affinity || !evlist->core.user_requested_cpus ||
 	    cpu_map__is_dummy(evlist->core.user_requested_cpus))
 		return false;
 

tools/perf/util/evlist.h

@@ -59,6 +59,7 @@ struct event_enable_timer;
 struct evlist {
 	struct perf_evlist core;
 	bool		 enabled;
+	bool		 no_affinity;
 	int		 id_pos;
 	int		 is_pos;
 	int		 nr_br_cntr;