All of lore.kernel.org
 help / color / mirror / Atom feed
From: Alexey Budankov <alexey.budankov@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>,
	Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>,
	Alexander Antonov <alexander.antonov@linux.intel.com>
Subject: [PATCH v3 06/12] perf record: introduce data file at mmap buffer object
Date: Mon, 16 Nov 2020 15:18:50 +0300	[thread overview]
Message-ID: <c439c1f5-de40-8f6b-d494-39082092f3b4@linux.intel.com> (raw)
In-Reply-To: <7d197a2d-56e2-896d-bf96-6de0a4db1fb8@linux.intel.com>


Introduce data file and compressor objects into mmap object so
they could be used to process and store data stream from the
corresponding kernel data buffer. Introduce bytes_transferred
and bytes_compressed stats so they would capture statistics for
the related data buffer transfers. Make use of the introduced
per mmap file, compressor and stats when they are initialized
and available.

Signed-off-by: Alexey Budankov <alexey.budankov@linux.intel.com>
---
 tools/perf/builtin-record.c | 64 +++++++++++++++++++++++++++++--------
 tools/perf/util/mmap.c      |  6 ++++
 tools/perf/util/mmap.h      |  6 ++++
 3 files changed, 63 insertions(+), 13 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 13773739bedc..779676531edf 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -188,11 +188,19 @@ static int record__write(struct record *rec, struct mmap *map __maybe_unused,
 {
 	struct perf_data_file *file = &rec->session->data->file;
 
+	if (map && map->file)
+		file = map->file;
+
 	if (perf_data_file__write(file, bf, size) < 0) {
 		pr_err("failed to write perf data, error: %m\n");
 		return -1;
 	}
 
+	if (map && map->file) {
+		map->bytes_written += size;
+		return 0;
+	}
+
 	rec->bytes_written += size;
 
 	if (record__output_max_size_exceeded(rec) && !done) {
@@ -210,8 +218,8 @@ static int record__write(struct record *rec, struct mmap *map __maybe_unused,
 
 static int record__aio_enabled(struct record *rec);
 static int record__comp_enabled(struct record *rec);
-static size_t zstd_compress(struct perf_session *session, void *dst, size_t dst_size,
-			    void *src, size_t src_size);
+static size_t zstd_compress(struct zstd_data *data,
+			    void *dst, size_t dst_size, void *src, size_t src_size);
 
 #ifdef HAVE_AIO_SUPPORT
 static int record__aio_write(struct aiocb *cblock, int trace_fd,
@@ -345,9 +353,13 @@ static int record__aio_pushfn(struct mmap *map, void *to, void *buf, size_t size
 	 */
 
 	if (record__comp_enabled(aio->rec)) {
-		size = zstd_compress(aio->rec->session, aio->data + aio->size,
-				     mmap__mmap_len(map) - aio->size,
+		struct zstd_data *zstd_data = &aio->rec->session->zstd_data;
+
+		aio->rec->session->bytes_transferred += size;
+		size = zstd_compress(zstd_data,
+				     aio->data + aio->size, mmap__mmap_len(map) - aio->size,
 				     buf, size);
+		aio->rec->session->bytes_compressed += size;
 	} else {
 		memcpy(aio->data + aio->size, buf, size);
 	}
@@ -572,8 +584,22 @@ static int record__pushfn(struct mmap *map, void *to, void *bf, size_t size)
 	struct record *rec = to;
 
 	if (record__comp_enabled(rec)) {
-		size = zstd_compress(rec->session, map->data, mmap__mmap_len(map), bf, size);
+		struct zstd_data *zstd_data = &rec->session->zstd_data;
+
+		if (map->file) {
+			zstd_data = &map->zstd_data;
+			map->bytes_transferred += size;
+		} else {
+			rec->session->bytes_transferred += size;
+		}
+
+		size = zstd_compress(zstd_data, map->data, mmap__mmap_len(map), bf, size);
 		bf   = map->data;
+
+		if (map->file)
+			map->bytes_compressed += size;
+		else
+			rec->session->bytes_compressed += size;
 	}
 
 	thread->samples++;
@@ -1291,18 +1317,15 @@ static size_t process_comp_header(void *record, size_t increment)
 	return size;
 }
 
-static size_t zstd_compress(struct perf_session *session, void *dst, size_t dst_size,
+static size_t zstd_compress(struct zstd_data *zstd_data, void *dst, size_t dst_size,
 			    void *src, size_t src_size)
 {
 	size_t compressed;
 	size_t max_record_size = PERF_SAMPLE_MAX_SIZE - sizeof(struct perf_record_compressed) - 1;
 
-	compressed = zstd_compress_stream_to_records(&session->zstd_data, dst, dst_size, src, src_size,
+	compressed = zstd_compress_stream_to_records(zstd_data, dst, dst_size, src, src_size,
 						     max_record_size, process_comp_header);
 
-	session->bytes_transferred += src_size;
-	session->bytes_compressed  += compressed;
-
 	return compressed;
 }
 
@@ -1959,8 +1982,9 @@ static int record__start_threads(struct record *rec)
 
 static int record__stop_threads(struct record *rec, unsigned long *waking)
 {
-	int t;
+	int t, tm;
 	struct thread_data *thread_data = rec->thread_data;
+	u64 bytes_written = 0, bytes_transferred = 0, bytes_compressed = 0;
 
 	for (t = 1; t < rec->nr_threads; t++)
 		record__terminate_thread(&thread_data[t]);
@@ -1968,9 +1992,23 @@ static int record__stop_threads(struct record *rec, unsigned long *waking)
 	for (t = 0; t < rec->nr_threads; t++) {
 		rec->samples += thread_data[t].samples;
 		*waking += thread_data[t].waking;
-		pr_debug("threads[%d]: samples=%lld, wakes=%ld, trasferred=%ld, compressed=%ld\n",
+		for (tm = 0; tm < thread_data[t].nr_mmaps; tm++) {
+			if (thread_data[t].maps) {
+				bytes_transferred += thread_data[t].maps[tm]->bytes_transferred;
+				bytes_compressed += thread_data[t].maps[tm]->bytes_compressed;
+				bytes_written += thread_data[t].maps[tm]->bytes_written;
+			}
+			if (thread_data[t].overwrite_maps) {
+				bytes_transferred += thread_data[t].overwrite_maps[tm]->bytes_transferred;
+				bytes_compressed += thread_data[t].overwrite_maps[tm]->bytes_compressed;
+				bytes_written += thread_data[t].overwrite_maps[tm]->bytes_written;
+			}
+		}
+		rec->session->bytes_transferred += bytes_transferred;
+		rec->session->bytes_compressed += bytes_compressed;
+		pr_debug("threads[%d]: samples=%lld, wakes=%ld, trasferred=%ld, compressed=%ld, written=%ld\n",
 			 thread_data[t].tid, thread_data[t].samples, thread_data[t].waking,
-			 rec->session->bytes_transferred, rec->session->bytes_compressed);
+			 bytes_transferred, bytes_compressed, bytes_written);
 	}
 
 	return 0;
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index ab7108d22428..a2c5e4237592 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -230,6 +230,8 @@ void mmap__munmap(struct mmap *map)
 {
 	bitmap_free(map->affinity_mask.bits);
 
+	zstd_fini(&map->zstd_data);
+
 	perf_mmap__aio_munmap(map);
 	if (map->data != NULL) {
 		munmap(map->data, mmap__mmap_len(map));
@@ -291,6 +293,10 @@ int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu)
 	map->core.flush = mp->flush;
 
 	map->comp_level = mp->comp_level;
+	if (zstd_init(&map->zstd_data, map->comp_level)) {
+		pr_debug2("failed to init mmap commpressor, error %d\n", errno);
+		return -1;
+	}
 
 	if (map->comp_level && !perf_mmap__aio_enabled(map)) {
 		map->data = mmap(NULL, mmap__mmap_len(map), PROT_READ|PROT_WRITE,
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index 9d5f589f02ae..c04ca4b5adf5 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -13,6 +13,7 @@
 #endif
 #include "auxtrace.h"
 #include "event.h"
+#include "util/compress.h"
 
 struct aiocb;
 
@@ -43,6 +44,11 @@ struct mmap {
 	struct mmap_cpu_mask	affinity_mask;
 	void		*data;
 	int		comp_level;
+	struct perf_data_file *file;
+	struct zstd_data      zstd_data;
+	u64		      bytes_transferred;
+	u64		      bytes_compressed;
+	u64		      bytes_written;
 };
 
 struct mmap_params {
-- 
2.24.1



  parent reply	other threads:[~2020-11-16 12:38 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-11-16 12:12 [PATCH v3 00/12] Introduce threaded trace streaming for basic perf record operation Alexey Budankov
2020-11-16 12:14 ` [PATCH v3 01/12] perf record: introduce thread affinity and mmap masks Alexey Budankov
2020-11-20 10:01   ` Namhyung Kim
2020-11-16 12:15 ` [PATCH v3 02/12] perf record: introduce thread specific data array Alexey Budankov
2020-11-20 10:14   ` Namhyung Kim
2020-11-16 12:16 ` [PATCH v3 03/12] perf record: introduce thread local variable Alexey Budankov
2020-11-20 10:20   ` Namhyung Kim
2020-11-16 12:17 ` [PATCH v3 04/12] perf record: stop threads in the end of trace streaming Alexey Budankov
2020-11-16 12:18 ` [PATCH v3 05/12] perf record: start threads in the beginning " Alexey Budankov
2020-11-16 12:18 ` Alexey Budankov [this message]
2020-11-20 10:28   ` [PATCH v3 06/12] perf record: introduce data file at mmap buffer object Namhyung Kim
2020-11-16 12:19 ` [PATCH v3 07/12] perf record: init " Alexey Budankov
2020-11-20 10:49   ` Namhyung Kim
2021-03-01 11:16     ` Bayduraev, Alexey V
2021-03-01 11:44       ` Namhyung Kim
2021-03-01 13:33         ` Bayduraev, Alexey V
2021-03-01 14:20           ` Namhyung Kim
2020-11-16 12:20 ` [PATCH v3 08/12] perf record: introduce --threads=<spec> command line option Alexey Budankov
2020-11-20 11:09   ` Namhyung Kim
2020-11-16 12:21 ` [PATCH v3 09/12] perf record: document parallel data streaming mode Alexey Budankov
2020-11-16 12:22 ` [PATCH v3 10/12] perf report: output data file name in raw trace dump Alexey Budankov
2020-11-16 12:22 ` [PATCH v3 11/12] perf session: load data directory files for analysis Alexey Budankov
2020-11-16 12:25 ` [PATCH v3 12/12] perf session: use reader functions to load perf data file Alexey Budankov
2020-11-20  9:45 ` [PATCH v3 00/12] Introduce threaded trace streaming for basic perf record operation Namhyung Kim
2020-12-15 15:05   ` Alexei Budankov

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=c439c1f5-de40-8f6b-d494-39082092f3b4@linux.intel.com \
    --to=alexey.budankov@linux.intel.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=alexey.v.bayduraev@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 \
    /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.