[PATCH v6 3/3] perf stat: Add no-affinity flag

[Ian Rogers <irogers@google.com>]

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>
---
 tools/perf/Documentation/perf-stat.txt | 4 ++++
 tools/perf/builtin-stat.c              | 6 ++++++
 tools/perf/util/evlist.c               | 6 +-----
 tools/perf/util/evlist.h               | 1 +
 4 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 1a766d4a2233..1ffb510606af 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -382,6 +382,10 @@ 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 affinities when iterating over CPUs. Disables
+an optimization aimed at minimizing interprocessor interrupts.
+
 STAT RECORD
 -----------
 Stores stat data into perf data file.
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index bb14268e7393..ddda0ea62eaf 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -2427,6 +2427,7 @@ 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"),
@@ -2555,6 +2556,8 @@ 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,
+			"don't allow affinity optimizations aimed at reducing 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)",
@@ -2612,6 +2615,9 @@ 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)
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d62b8bab8fa4..00fb3cf45bae 100644
--- a/tools/perf/util/evlist.c
+++ b/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;
 
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 30dff7484d3c..d17c3b57a409 100644
--- a/tools/perf/util/evlist.h
+++ b/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;
-- 
2.52.0.457.g6b5491de43-goog