[PATCH v11 10/24] perf record: Introduce data transferred and compressed stats

[Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com>]

Introduce bytes_transferred and bytes_compressed stats so they
would capture statistics for the related data buffer transfers.

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 | 68 +++++++++++++++++++++++++++++--------
 tools/perf/util/mmap.h      |  2 ++
 2 files changed, 56 insertions(+), 14 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index cb155f1ba979..d833095e73cb 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -246,8 +246,8 @@ 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,
@@ -381,9 +381,13 @@ 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);
 	}
@@ -608,8 +612,22 @@ 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++;
@@ -1396,18 +1414,15 @@ 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;
 }
 
@@ -2063,8 +2078,10 @@ 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 mmap *map, *overwrite_map;
 	struct record_thread *thread_data = rec->thread_data;
+	u64 bytes_written, bytes_transferred, bytes_compressed;
 
 	for (t = 1; t < rec->nr_threads; t++)
 		record__terminate_thread(&thread_data[t]);
@@ -2072,9 +2089,32 @@ 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",
-			 thread_data[t].tid, thread_data[t].samples, thread_data[t].waking,
-			 rec->session->bytes_transferred, rec->session->bytes_compressed);
+		bytes_transferred = 0;
+		bytes_compressed = 0;
+		bytes_written = t ? 0 : rec->bytes_written;
+		for (tm = 0; tm < thread_data[t].nr_mmaps; tm++) {
+			if (thread_data[t].maps) {
+				map = thread_data[t].maps[tm];
+				bytes_transferred += map->bytes_transferred;
+				bytes_compressed += map->bytes_compressed;
+				bytes_written += map->bytes_written;
+			}
+			if (thread_data[t].overwrite_maps) {
+				overwrite_map = thread_data[t].overwrite_maps[tm];
+				bytes_transferred += overwrite_map->bytes_transferred;
+				bytes_compressed += overwrite_map->bytes_compressed;
+				bytes_written += overwrite_map->bytes_written;
+			}
+		}
+		rec->session->bytes_transferred += bytes_transferred;
+		rec->session->bytes_compressed += bytes_compressed;
+		pr_debug("threads[%d]: samples=%lld, wakes=%ld, ",
+			 thread_data[t].tid, thread_data[t].samples, thread_data[t].waking);
+		if (bytes_compressed)
+			pr_debug("trasferred=%ld, compressed=%ld\n",
+				 bytes_transferred, bytes_compressed);
+		else
+			pr_debug("written=%ld\n", bytes_written);
 	}
 
 	return 0;
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index 67d41003d82e..f5e8c8a24e68 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -47,6 +47,8 @@ struct mmap {
 	struct perf_data_file *file;
 	struct zstd_data      zstd_data;
 	u64		      bytes_written;
+	u64		      bytes_transferred;
+	u64		      bytes_compressed;
 };
 
 struct mmap_params {
-- 
2.19.0