All of lore.kernel.org
 help / color / mirror / Atom feed
From: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>
To: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>, Namhyung Kim <namhyung@kernel.org>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	linux-kernel <linux-kernel@vger.kernel.org>,
	Andi Kleen <ak@linux.intel.com>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Alexander Antonov <alexander.antonov@linux.intel.com>,
	Alexei Budankov <abudankov@huawei.com>,
	Riccardo Mancini <rickyman7@gmail.com>
Subject: [PATCH v12 01/16] perf record: Introduce thread affinity and mmap masks
Date: Tue, 23 Nov 2021 17:07:57 +0300	[thread overview]
Message-ID: <22ee51ee5430b51eee5f03301fb498d5d3e33d1e.1637675515.git.alexey.v.bayduraev@linux.intel.com> (raw)
In-Reply-To: <cover.1637675515.git.alexey.v.bayduraev@linux.intel.com>

Introduce affinity and mmap thread masks. Thread affinity mask
defines cpus that a thread is allowed to run on. Thread maps
mask defines mmap data buffers the thread serves to stream
profiling data from.

Acked-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Namhyung Kim <namhyung@gmail.com>
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/builtin-record.c | 129 ++++++++++++++++++++++++++++++++++++
 1 file changed, 129 insertions(+)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 0338b813585a..11537971ea3b 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -87,6 +87,11 @@ struct switch_output {
 	int		 cur_file;
 };
 
+struct thread_mask {
+	struct mmap_cpu_mask	maps;
+	struct mmap_cpu_mask	affinity;
+};
+
 struct record {
 	struct perf_tool	tool;
 	struct record_opts	opts;
@@ -111,6 +116,8 @@ struct record {
 	unsigned long long	samples;
 	struct mmap_cpu_mask	affinity_mask;
 	unsigned long		output_max_size;	/* = 0: unlimited */
+	int			nr_threads;
+	struct thread_mask	*thread_masks;
 };
 
 static volatile int done;
@@ -2197,6 +2204,54 @@ static int record__parse_affinity(const struct option *opt, const char *str, int
 	return 0;
 }
 
+static int record__mmap_cpu_mask_alloc(struct mmap_cpu_mask *mask, int nr_bits)
+{
+	mask->nbits = nr_bits;
+	mask->bits = bitmap_zalloc(mask->nbits);
+	if (!mask->bits) {
+		pr_err("Failed to allocate mmap_cpu mask\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void record__mmap_cpu_mask_free(struct mmap_cpu_mask *mask)
+{
+	bitmap_free(mask->bits);
+	mask->nbits = 0;
+}
+
+static void record__thread_mask_clear(struct thread_mask *mask)
+{
+	bitmap_zero(mask->maps.bits, mask->maps.nbits);
+	bitmap_zero(mask->affinity.bits, mask->affinity.nbits);
+}
+
+static int record__thread_mask_alloc(struct thread_mask *mask, int nr_bits)
+{
+	int ret = record__mmap_cpu_mask_alloc(&mask->maps, nr_bits);
+
+	if (ret) {
+		mask->affinity.bits = NULL;
+		return ret;
+	}
+
+	ret = record__mmap_cpu_mask_alloc(&mask->affinity, nr_bits);
+	if (ret) {
+		record__mmap_cpu_mask_free(&mask->maps);
+		mask->maps.bits = NULL;
+	}
+
+	return ret;
+}
+
+static void record__thread_mask_free(struct thread_mask *mask)
+{
+	record__mmap_cpu_mask_free(&mask->maps);
+	record__mmap_cpu_mask_free(&mask->affinity);
+}
+
 static int parse_output_max_size(const struct option *opt,
 				 const char *str, int unset)
 {
@@ -2668,6 +2723,72 @@ static struct option __record_options[] = {
 
 struct option *record_options = __record_options;
 
+static void record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_cpu_map *cpus)
+{
+	int c;
+
+	for (c = 0; c < cpus->nr; c++)
+		set_bit(cpus->map[c], mask->bits);
+}
+
+static void record__free_thread_masks(struct record *rec, int nr_threads)
+{
+	int t;
+
+	if (rec->thread_masks)
+		for (t = 0; t < nr_threads; t++)
+			record__thread_mask_free(&rec->thread_masks[t]);
+
+	zfree(&rec->thread_masks);
+}
+
+static int record__alloc_thread_masks(struct record *rec, int nr_threads, int nr_bits)
+{
+	int t, ret;
+
+	rec->thread_masks = zalloc(nr_threads * sizeof(*(rec->thread_masks)));
+	if (!rec->thread_masks) {
+		pr_err("Failed to allocate thread masks\n");
+		return -ENOMEM;
+	}
+
+	for (t = 0; t < nr_threads; t++) {
+		ret = record__thread_mask_alloc(&rec->thread_masks[t], nr_bits);
+		if (ret)
+			goto out_free;
+		record__thread_mask_clear(&rec->thread_masks[t]);
+	}
+
+	return 0;
+
+out_free:
+	record__free_thread_masks(rec, nr_threads);
+
+	return ret;
+}
+
+static int record__init_thread_default_masks(struct record *rec, struct perf_cpu_map *cpus)
+{
+	int ret;
+
+	ret = record__alloc_thread_masks(rec, 1, cpu__max_cpu());
+	if (ret)
+		return ret;
+
+	record__mmap_cpu_mask_init(&rec->thread_masks->maps, cpus);
+
+	rec->nr_threads = 1;
+
+	return 0;
+}
+
+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);
+}
+
 int cmd_record(int argc, const char **argv)
 {
 	int err;
@@ -2927,6 +3048,12 @@ int cmd_record(int argc, const char **argv)
 		goto out;
 	}
 
+	err = record__init_thread_masks(rec);
+	if (err) {
+		pr_err("record__init_thread_masks failed, error %d\n", err);
+		goto out;
+	}
+
 	if (rec->opts.nr_cblocks > nr_cblocks_max)
 		rec->opts.nr_cblocks = nr_cblocks_max;
 	pr_debug("nr_cblocks: %d\n", rec->opts.nr_cblocks);
@@ -2945,6 +3072,8 @@ int cmd_record(int argc, const char **argv)
 	symbol__exit();
 	auxtrace_record__free(rec->itr);
 out_opts:
+	record__free_thread_masks(rec, rec->nr_threads);
+	rec->nr_threads = 0;
 	evlist__close_control(rec->opts.ctl_fd, rec->opts.ctl_fd_ack, &rec->opts.ctl_fd_close);
 	return err;
 }
-- 
2.19.0


  reply	other threads:[~2021-11-23 14:08 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-11-23 14:07 [PATCH v12 00/16] Introduce threaded trace streaming for basic perf record operation Alexey Bayduraev
2021-11-23 14:07 ` Alexey Bayduraev [this message]
2021-12-05 15:13   ` [PATCH v12 01/16] perf record: Introduce thread affinity and mmap masks Jiri Olsa
2021-12-20 10:37     ` Bayduraev, Alexey V
2021-11-23 14:07 ` [PATCH v12 02/16] tools lib: Introduce fdarray duplicate function Alexey Bayduraev
2021-11-23 14:07 ` [PATCH v12 03/16] perf record: Introduce thread specific data array Alexey Bayduraev
2021-11-23 14:08 ` [PATCH v12 04/16] perf record: Introduce function to propagate control commands Alexey Bayduraev
2021-11-23 14:08 ` [PATCH v12 05/16] perf record: Introduce thread local variable Alexey Bayduraev
2021-12-05 15:14   ` Jiri Olsa
2021-12-20  9:49     ` Bayduraev, Alexey V
2021-11-23 14:08 ` [PATCH v12 06/16] perf record: Stop threads in the end of trace streaming Alexey Bayduraev
2021-11-23 14:08 ` [PATCH v12 07/16] perf record: Start threads in the beginning " Alexey Bayduraev
2021-11-23 14:08 ` [PATCH v12 08/16] perf record: Introduce data file at mmap buffer object Alexey Bayduraev
2021-12-05 15:14   ` Jiri Olsa
2021-11-23 14:08 ` [PATCH v12 09/16] perf record: Introduce bytes written stats Alexey Bayduraev
2021-12-05 15:14   ` Jiri Olsa
2021-12-06 11:22     ` Bayduraev, Alexey V
2021-11-23 14:08 ` [PATCH v12 10/16] perf record: Introduce compressor at mmap buffer object Alexey Bayduraev
2021-11-23 14:08 ` [PATCH v12 11/16] perf record: Introduce data transferred and compressed stats Alexey Bayduraev
2021-11-23 14:08 ` [PATCH v12 12/16] perf record: Introduce --threads command line option Alexey Bayduraev
2021-11-23 14:08 ` [PATCH v12 13/16] perf record: Extend " Alexey Bayduraev
2021-12-05 15:13   ` Jiri Olsa
2021-12-05 15:14   ` Jiri Olsa
2021-12-05 15:14   ` Jiri Olsa
2021-12-05 15:14   ` Jiri Olsa
2021-11-23 14:08 ` [PATCH v12 14/16] perf record: Implement compatibility checks Alexey Bayduraev
2021-11-23 14:08 ` [PATCH v12 15/16] perf session: Load data directory files for analysis Alexey Bayduraev
2021-11-23 14:08 ` [PATCH v12 16/16] perf report: Output data file name in raw trace dump Alexey Bayduraev
2021-12-05 15:15 ` [PATCH v12 00/16] Introduce threaded trace streaming for basic perf record operation Jiri Olsa
2021-12-09 17:56   ` Jiri Olsa

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=22ee51ee5430b51eee5f03301fb498d5d3e33d1e.1637675515.git.alexey.v.bayduraev@linux.intel.com \
    --to=alexey.v.bayduraev@linux.intel.com \
    --cc=abudankov@huawei.com \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=ak@linux.intel.com \
    --cc=alexander.antonov@linux.intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=jolsa@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=rickyman7@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.