lkml.org 
[lkml]   [2021]   [Nov]   [23]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH v12 12/16] perf record: Introduce --threads command line option
Date
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.

Reviewed-by: Riccardo Mancini <rickyman7@gmail.com>
Tested-by: Riccardo Mancini <rickyman7@gmail.com>
Signed-off-by: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
---
tools/perf/Documentation/perf-record.txt | 4 ++
tools/perf/builtin-record.c | 48 +++++++++++++++++++++++-
2 files changed, 51 insertions(+), 1 deletion(-)

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 3cf7bac67239..c84cdb3d7ede 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -711,6 +711,10 @@ 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 67181102c18f..e9c9ae62f90b 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -125,6 +125,11 @@ 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;
@@ -2766,6 +2771,16 @@ 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)
{
@@ -3232,6 +3247,9 @@ static struct option __record_options[] = {
parse_control_option),
OPT_CALLBACK(0, "synth", &record.opts, "no|all|task|mmap|cgroup",
"Fine-tune event synthesis: default=all", parse_record_synth_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()
};

@@ -3281,6 +3299,31 @@ 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("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);
+ set_bit(cpus->map[t], rec->thread_masks[t].affinity.bits);
+ if (verbose) {
+ pr_debug("thread_masks[%d]: ", t);
+ mmap_cpu_mask__scnprintf(&rec->thread_masks[t].maps, "maps");
+ pr_debug("thread_masks[%d]: ", t);
+ mmap_cpu_mask__scnprintf(&rec->thread_masks[t].affinity, "affinity");
+ }
+ }
+
+ return 0;
+}
+
static int record__init_thread_default_masks(struct record *rec, struct perf_cpu_map *cpus)
{
int ret;
@@ -3300,7 +3343,10 @@ 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);
}

int cmd_record(int argc, const char **argv)
--
2.19.0
\
 
 \ /
  Last update: 2021-11-23 15:11    [W:0.201 / U:0.032 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site