[PATCH v10 12/24] perf record: Introduce --threads command line option

[Alexey Bayduraev]

Provide --threads option in perf record command line interface.
The option creates a data streaming thread for each cpu in the system.
Document --threads option in Documentation/perf-record.txt.

Signed-off-by: Alexey Bayduraev <alexey.v.bayduraev@xxxxxxxxxxxxxxx>
---
 tools/perf/Documentation/perf-record.txt |  4 +++
 tools/perf/builtin-record.c              | 44 +++++++++++++++++++++++-
 2 files changed, 47 insertions(+), 1 deletion(-)

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index d71bac847936..ca2771b80fd5 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -695,6 +695,10 @@ measurements:
  wait -n ${perf_pid}
  exit $?
 
+--threads::
+Write collected trace data into several data files using parallel threads.
+The option creates a data streaming thread for each cpu in the system.
+
 include::intel-hybrid.txt[]
 
 SEE ALSO
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 791926ddc0b0..65e2d1837bec 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -122,6 +122,11 @@ static const char *thread_msg_tags[THREAD_MSG__MAX] = {
 	"UNDEFINED", "READY"
 };
 
+enum thread_spec {
+	THREAD_SPEC__UNDEFINED = 0,
+	THREAD_SPEC__CPU,
+};
+
 struct record {
 	struct perf_tool	tool;
 	struct record_opts	opts;
@@ -2811,6 +2816,16 @@ static void record__thread_mask_free(struct thread_mask *mask)
 	record__mmap_cpu_mask_free(&mask->affinity);
 }
 
+static int record__parse_threads(const struct option *opt, const char *str, int unset)
+{
+	struct record_opts *opts = opt->value;
+
+	if (unset || !str || !strlen(str))
+		opts->threads_spec = THREAD_SPEC__CPU;
+
+	return 0;
+}
+
 static int parse_output_max_size(const struct option *opt,
 				 const char *str, int unset)
 {
@@ -3254,6 +3269,9 @@ static struct option __record_options[] = {
 		     "\t\t\t  Optionally send control command completion ('ack\\n') to ack-fd descriptor.\n"
 		     "\t\t\t  Alternatively, ctl-fifo / ack-fifo will be opened and used as ctl-fd / ack-fd.",
 		      parse_control_option),
+	OPT_CALLBACK_OPTARG(0, "threads", &record.opts, NULL, "spec",
+			    "write collected trace data into several data files using parallel threads",
+			    record__parse_threads),
 	OPT_END()
 };
 
@@ -3303,6 +3321,27 @@ static int record__alloc_thread_masks(struct record *rec, int nr_threads, int nr
 	return ret;
 }
 
+static int record__init_thread_cpu_masks(struct record *rec, struct perf_cpu_map *cpus)
+{
+	int t, ret, nr_cpus = perf_cpu_map__nr(cpus);
+
+	ret = record__alloc_thread_masks(rec, nr_cpus, cpu__max_cpu());
+	if (ret)
+		return ret;
+
+	rec->nr_threads = nr_cpus;
+	pr_debug("threads: nr_threads=%d\n", rec->nr_threads);
+
+	for (t = 0; t < rec->nr_threads; t++) {
+		set_bit(cpus->map[t], rec->thread_masks[t].maps.bits);
+		pr_debug("thread_masks[%d]: maps mask [%d]\n", t, cpus->map[t]);
+		set_bit(cpus->map[t], rec->thread_masks[t].affinity.bits);
+		pr_debug("thread_masks[%d]: affinity mask [%d]\n", t, cpus->map[t]);
+	}
+
+	return 0;
+}
+
 static int record__init_thread_default_masks(struct record *rec, struct perf_cpu_map *cpus)
 {
 	int ret;
@@ -3322,7 +3361,10 @@ static int record__init_thread_masks(struct record *rec)
 {
 	struct perf_cpu_map *cpus = rec->evlist->core.cpus;
 
-	return record__init_thread_default_masks(rec, cpus);
+	if (!record__threads_enabled(rec))
+		return record__init_thread_default_masks(rec, cpus);
+
+	return record__init_thread_cpu_masks(rec, cpus);
 }
 
 static void record__fini_thread_masks(struct record *rec)
-- 
2.19.0