public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Ian Rogers <irogers@google.com>
To: Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Mark Rutland <mark.rutland@arm.com>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Jiri Olsa <jolsa@kernel.org>, Namhyung Kim <namhyung@kernel.org>,
	Ian Rogers <irogers@google.com>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Nick Terrell <terrelln@fb.com>,
	Kan Liang <kan.liang@linux.intel.com>,
	Andi Kleen <ak@linux.intel.com>, Leo Yan <leo.yan@linaro.org>,
	Song Liu <song@kernel.org>, Sandipan Das <sandipan.das@amd.com>,
	James Clark <james.clark@arm.com>,
	Anshuman Khandual <anshuman.khandual@arm.com>,
	Miguel Ojeda <ojeda@kernel.org>,
	Liam Howlett <liam.howlett@oracle.com>,
	Yang Jihong <yangjihong1@huawei.com>,
	Athira Rajeev <atrajeev@linux.vnet.ibm.com>,
	Kajol Jain <kjain@linux.ibm.com>,
	K Prateek Nayak <kprateek.nayak@amd.com>,
	Sean Christopherson <seanjc@google.com>,
	Yanteng Si <siyanteng@loongson.cn>,
	Ravi Bangoria <ravi.bangoria@amd.com>,
	German Gomez <german.gomez@arm.com>,
	Changbin Du <changbin.du@huawei.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	Masami Hiramatsu <mhiramat@kernel.org>,
	liuwenyu <liuwenyu7@huawei.com>,
	linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org
Subject: [PATCH v3 14/50] perf mmap: Lazily initialize zstd streams
Date: Tue, 24 Oct 2023 15:23:17 -0700	[thread overview]
Message-ID: <20231024222353.3024098-15-irogers@google.com> (raw)
In-Reply-To: <20231024222353.3024098-1-irogers@google.com>

Zstd streams create dictionaries that can require significant RAM,
especially when there is one per-CPU. Tools like perf record won't use
the streams without the -z option, and so the creation of the streams
is pure overhead. Switch to creating the streams on first use.

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/builtin-record.c | 26 ++++++++++-----
 tools/perf/util/compress.h  |  6 ++--
 tools/perf/util/mmap.c      |  5 ++-
 tools/perf/util/mmap.h      |  1 -
 tools/perf/util/zstd.c      | 63 +++++++++++++++++++------------------
 5 files changed, 58 insertions(+), 43 deletions(-)

diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 8ec818568662..9b4f3805ca92 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -270,7 +270,7 @@ 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, struct mmap *map,
+static ssize_t zstd_compress(struct perf_session *session, struct mmap *map,
 			    void *dst, size_t dst_size, void *src, size_t src_size);
 
 #ifdef HAVE_AIO_SUPPORT
@@ -405,9 +405,13 @@ 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, NULL, aio->data + aio->size,
-				     mmap__mmap_len(map) - aio->size,
-				     buf, size);
+		ssize_t compressed = zstd_compress(aio->rec->session, NULL, aio->data + aio->size,
+						   mmap__mmap_len(map) - aio->size,
+						   buf, size);
+		if (compressed < 0)
+			return (int)compressed;
+
+		size = compressed;
 	} else {
 		memcpy(aio->data + aio->size, buf, size);
 	}
@@ -633,7 +637,13 @@ 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, map->data, mmap__mmap_len(map), bf, size);
+		ssize_t compressed = zstd_compress(rec->session, map, map->data,
+						   mmap__mmap_len(map), bf, size);
+
+		if (compressed < 0)
+			return (int)compressed;
+
+		size = compressed;
 		bf   = map->data;
 	}
 
@@ -1527,10 +1537,10 @@ static size_t process_comp_header(void *record, size_t increment)
 	return size;
 }
 
-static size_t zstd_compress(struct perf_session *session, struct mmap *map,
+static ssize_t zstd_compress(struct perf_session *session, struct mmap *map,
 			    void *dst, size_t dst_size, void *src, size_t src_size)
 {
-	size_t compressed;
+	ssize_t compressed;
 	size_t max_record_size = PERF_SAMPLE_MAX_SIZE - sizeof(struct perf_record_compressed) - 1;
 	struct zstd_data *zstd_data = &session->zstd_data;
 
@@ -1539,6 +1549,8 @@ static size_t zstd_compress(struct perf_session *session, struct mmap *map,
 
 	compressed = zstd_compress_stream_to_records(zstd_data, dst, dst_size, src, src_size,
 						     max_record_size, process_comp_header);
+	if (compressed < 0)
+		return compressed;
 
 	if (map && map->file) {
 		thread->bytes_transferred += src_size;
diff --git a/tools/perf/util/compress.h b/tools/perf/util/compress.h
index 0cd3369af2a4..9eb6eb5bf038 100644
--- a/tools/perf/util/compress.h
+++ b/tools/perf/util/compress.h
@@ -3,6 +3,7 @@
 #define PERF_COMPRESS_H
 
 #include <stdbool.h>
+#include <stdlib.h>
 #ifdef HAVE_ZSTD_SUPPORT
 #include <zstd.h>
 #endif
@@ -21,6 +22,7 @@ struct zstd_data {
 #ifdef HAVE_ZSTD_SUPPORT
 	ZSTD_CStream	*cstream;
 	ZSTD_DStream	*dstream;
+	int comp_level;
 #endif
 };
 
@@ -29,7 +31,7 @@ struct zstd_data {
 int zstd_init(struct zstd_data *data, int level);
 int zstd_fini(struct zstd_data *data);
 
-size_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size,
+ssize_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size,
 				       void *src, size_t src_size, size_t max_record_size,
 				       size_t process_header(void *record, size_t increment));
 
@@ -48,7 +50,7 @@ static inline int zstd_fini(struct zstd_data *data __maybe_unused)
 }
 
 static inline
-size_t zstd_compress_stream_to_records(struct zstd_data *data __maybe_unused,
+ssize_t zstd_compress_stream_to_records(struct zstd_data *data __maybe_unused,
 				       void *dst __maybe_unused, size_t dst_size __maybe_unused,
 				       void *src __maybe_unused, size_t src_size __maybe_unused,
 				       size_t max_record_size __maybe_unused,
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 49093b21ee2d..122ee198a86e 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -295,15 +295,14 @@ int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, struct perf_cpu
 
 	map->core.flush = mp->flush;
 
-	map->comp_level = mp->comp_level;
 #ifndef PYTHON_PERF
-	if (zstd_init(&map->zstd_data, map->comp_level)) {
+	if (zstd_init(&map->zstd_data, mp->comp_level)) {
 		pr_debug2("failed to init mmap compressor, error %d\n", errno);
 		return -1;
 	}
 #endif
 
-	if (map->comp_level && !perf_mmap__aio_enabled(map)) {
+	if (mp->comp_level && !perf_mmap__aio_enabled(map)) {
 		map->data = mmap(NULL, mmap__mmap_len(map), PROT_READ|PROT_WRITE,
 				 MAP_PRIVATE|MAP_ANONYMOUS, 0, 0);
 		if (map->data == MAP_FAILED) {
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index f944c3cd5efa..0df6e1621c7e 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -39,7 +39,6 @@ struct mmap {
 #endif
 	struct mmap_cpu_mask	affinity_mask;
 	void		*data;
-	int		comp_level;
 	struct perf_data_file *file;
 	struct zstd_data      zstd_data;
 };
diff --git a/tools/perf/util/zstd.c b/tools/perf/util/zstd.c
index 48dd2b018c47..57027e0ac7b6 100644
--- a/tools/perf/util/zstd.c
+++ b/tools/perf/util/zstd.c
@@ -7,35 +7,9 @@
 
 int zstd_init(struct zstd_data *data, int level)
 {
-	size_t ret;
-
-	data->dstream = ZSTD_createDStream();
-	if (data->dstream == NULL) {
-		pr_err("Couldn't create decompression stream.\n");
-		return -1;
-	}
-
-	ret = ZSTD_initDStream(data->dstream);
-	if (ZSTD_isError(ret)) {
-		pr_err("Failed to initialize decompression stream: %s\n", ZSTD_getErrorName(ret));
-		return -1;
-	}
-
-	if (!level)
-		return 0;
-
-	data->cstream = ZSTD_createCStream();
-	if (data->cstream == NULL) {
-		pr_err("Couldn't create compression stream.\n");
-		return -1;
-	}
-
-	ret = ZSTD_initCStream(data->cstream, level);
-	if (ZSTD_isError(ret)) {
-		pr_err("Failed to initialize compression stream: %s\n", ZSTD_getErrorName(ret));
-		return -1;
-	}
-
+	data->comp_level = level;
+	data->dstream = NULL;
+	data->cstream = NULL;
 	return 0;
 }
 
@@ -54,7 +28,7 @@ int zstd_fini(struct zstd_data *data)
 	return 0;
 }
 
-size_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size,
+ssize_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t dst_size,
 				       void *src, size_t src_size, size_t max_record_size,
 				       size_t process_header(void *record, size_t increment))
 {
@@ -63,6 +37,21 @@ size_t zstd_compress_stream_to_records(struct zstd_data *data, void *dst, size_t
 	ZSTD_outBuffer output;
 	void *record;
 
+	if (!data->cstream) {
+		data->cstream = ZSTD_createCStream();
+		if (data->cstream == NULL) {
+			pr_err("Couldn't create compression stream.\n");
+			return -1;
+		}
+
+		ret = ZSTD_initCStream(data->cstream, data->comp_level);
+		if (ZSTD_isError(ret)) {
+			pr_err("Failed to initialize compression stream: %s\n",
+				ZSTD_getErrorName(ret));
+			return -1;
+		}
+	}
+
 	while (input.pos < input.size) {
 		record = dst;
 		size = process_header(record, 0);
@@ -96,6 +85,20 @@ size_t zstd_decompress_stream(struct zstd_data *data, void *src, size_t src_size
 	ZSTD_inBuffer input = { src, src_size, 0 };
 	ZSTD_outBuffer output = { dst, dst_size, 0 };
 
+	if (!data->dstream) {
+		data->dstream = ZSTD_createDStream();
+		if (data->dstream == NULL) {
+			pr_err("Couldn't create decompression stream.\n");
+			return 0;
+		}
+
+		ret = ZSTD_initDStream(data->dstream);
+		if (ZSTD_isError(ret)) {
+			pr_err("Failed to initialize decompression stream: %s\n",
+				ZSTD_getErrorName(ret));
+			return 0;
+		}
+	}
 	while (input.pos < input.size) {
 		ret = ZSTD_decompressStream(data->dstream, &output, &input);
 		if (ZSTD_isError(ret)) {
-- 
2.42.0.758.gaed0368e0e-goog


  parent reply	other threads:[~2023-10-24 22:25 UTC|newest]

Thread overview: 62+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-10-24 22:23 [PATCH v3 00/50] Improvements to memory use Ian Rogers
2023-10-24 22:23 ` [PATCH v3 01/50] perf rwsem: Add debug mode that uses a mutex Ian Rogers
2023-10-24 22:23 ` [PATCH v3 02/50] perf machine: Avoid out of bounds LBR memory read Ian Rogers
2023-10-24 22:23 ` [PATCH v3 03/50] libperf rc_check: Make implicit enabling work for GCC Ian Rogers
2023-10-24 22:23 ` [PATCH v3 04/50] libperf rc_check: Add RC_CHK_EQUAL Ian Rogers
2023-10-24 22:23 ` [PATCH v3 05/50] perf hist: Add missing puts to hist__account_cycles Ian Rogers
2023-10-24 22:23 ` [PATCH v3 06/50] perf threads: Remove unused dead thread list Ian Rogers
2023-10-24 22:23 ` [PATCH v3 07/50] perf offcpu: Add missed btf_free Ian Rogers
2023-10-24 22:23 ` [PATCH v3 08/50] perf callchain: Make display use of branch_type_stat const Ian Rogers
2023-10-24 22:23 ` [PATCH v3 09/50] perf callchain: Make brtype_stat in callchain_list optional Ian Rogers
2023-10-24 22:23 ` [PATCH v3 10/50] perf callchain: Minor layout changes to callchain_list Ian Rogers
2023-10-24 22:23 ` [PATCH v3 11/50] perf mem_info: Add and use map_symbol__exit and addr_map_symbol__exit Ian Rogers
2023-10-24 22:23 ` [PATCH v3 12/50] perf record: Lazy load kernel symbols Ian Rogers
2023-10-25 18:25   ` Namhyung Kim
2023-10-25 18:35     ` Adrian Hunter
2023-10-24 22:23 ` [PATCH v3 13/50] libperf: Lazily allocate mmap event copy Ian Rogers
2023-10-25  2:38   ` Yang Jihong
2023-10-25  3:28     ` Ian Rogers
2023-10-24 22:23 ` Ian Rogers [this message]
2023-10-24 22:23 ` [PATCH v3 15/50] perf machine thread: Remove exited threads by default Ian Rogers
2023-10-24 22:23 ` [PATCH v3 16/50] tools api fs: Switch filename__read_str to use io.h Ian Rogers
2023-10-24 22:23 ` [PATCH v3 17/50] tools api fs: Avoid reading whole file for a 1 byte bool Ian Rogers
2023-10-24 22:23 ` [PATCH v3 18/50] tools lib api: Add io_dir an allocation free readdir alternative Ian Rogers
2023-10-25 18:43   ` Namhyung Kim
2023-10-25 22:15     ` Ian Rogers
2023-10-24 22:23 ` [PATCH v3 19/50] perf maps: Switch modules tree walk to io_dir__readdir Ian Rogers
2023-10-24 22:23 ` [PATCH v3 20/50] perf record: Be lazier in allocating lost samples buffer Ian Rogers
2023-10-25  3:44   ` Yang Jihong
2023-10-25 17:00     ` Ian Rogers
2023-10-25 19:04       ` Namhyung Kim
2023-10-25 19:00   ` Namhyung Kim
2023-10-24 22:23 ` [PATCH v3 21/50] perf pmu: Switch to io_dir__readdir Ian Rogers
2023-10-24 22:23 ` [PATCH v3 22/50] perf bpf: Don't synthesize BPF events when disabled Ian Rogers
2023-10-24 22:23 ` [PATCH v3 23/50] perf header: Switch mem topology to io_dir__readdir Ian Rogers
2023-10-24 22:23 ` [PATCH v3 24/50] perf events: Remove scandir in thread synthesis Ian Rogers
2023-10-24 22:23 ` [PATCH v3 25/50] perf map: Simplify map_ip/unmap_ip and make map size smaller Ian Rogers
2023-10-24 22:23 ` [PATCH v3 26/50] perf maps: Move symbol maps functions to maps.c Ian Rogers
2023-10-24 22:23 ` [PATCH v3 27/50] perf thread: Add missing RC_CHK_ACCESS Ian Rogers
2023-10-24 22:23 ` [PATCH v3 28/50] perf maps: Add maps__for_each_map to call a function on each entry Ian Rogers
2023-10-24 22:23 ` [PATCH v3 29/50] perf maps: Add remove maps function to remove a map based on callback Ian Rogers
2023-10-24 22:23 ` [PATCH v3 30/50] perf debug: Expose debug file Ian Rogers
2023-10-24 22:23 ` [PATCH v3 31/50] perf maps: Refactor maps__fixup_overlappings Ian Rogers
2023-10-24 22:23 ` [PATCH v3 32/50] perf maps: Do simple merge if given map doesn't overlap Ian Rogers
2023-10-24 22:23 ` [PATCH v3 33/50] perf maps: Rename clone to copy from Ian Rogers
2023-10-24 22:23 ` [PATCH v3 34/50] perf maps: Add maps__load_first Ian Rogers
2023-10-24 22:23 ` [PATCH v3 35/50] perf maps: Add find next entry to give entry after the given map Ian Rogers
2023-10-24 22:23 ` [PATCH v3 36/50] perf maps: Reduce scope of map_rb_node and maps internals Ian Rogers
2023-10-24 22:23 ` [PATCH v3 37/50] perf maps: Fix up overlaps during fixup_end Ian Rogers
2023-10-24 22:23 ` [PATCH v3 38/50] perf maps: Switch from rbtree to lazily sorted array for addresses Ian Rogers
2023-10-24 22:23 ` [PATCH v3 39/50] perf maps: Get map before returning in maps__find Ian Rogers
2023-10-24 22:23 ` [PATCH v3 40/50] perf maps: Get map before returning in maps__find_by_name Ian Rogers
2023-10-24 22:23 ` [PATCH v3 41/50] perf maps: Get map before returning in maps__find_next_entry Ian Rogers
2023-10-24 22:23 ` [PATCH v3 42/50] perf maps: Hide maps internals Ian Rogers
2023-10-24 22:23 ` [PATCH v3 43/50] perf maps: Locking tidy up of nr_maps Ian Rogers
2023-10-24 22:23 ` [PATCH v3 44/50] perf dso: Reorder variables to save space in struct dso Ian Rogers
2023-10-24 22:23 ` [PATCH v3 45/50] perf report: Sort child tasks by tid Ian Rogers
2023-10-24 22:23 ` [PATCH v3 46/50] perf trace: Ignore thread hashing in summary Ian Rogers
2023-10-24 22:23 ` [PATCH v3 47/50] perf machine: Move fprintf to for_each loop and a callback Ian Rogers
2023-10-24 22:23 ` [PATCH v3 48/50] perf threads: Move threads to its own files Ian Rogers
2023-10-24 22:23 ` [PATCH v3 49/50] perf threads: Switch from rbtree to hashmap Ian Rogers
2023-10-24 22:23 ` [PATCH v3 50/50] perf threads: Reduce table size from 256 to 8 Ian Rogers
2023-10-26 17:11 ` (subset) [PATCH v3 00/50] Improvements to memory use Namhyung Kim

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=20231024222353.3024098-15-irogers@google.com \
    --to=irogers@google.com \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=ak@linux.intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=anshuman.khandual@arm.com \
    --cc=atrajeev@linux.vnet.ibm.com \
    --cc=changbin.du@huawei.com \
    --cc=german.gomez@arm.com \
    --cc=james.clark@arm.com \
    --cc=jolsa@kernel.org \
    --cc=kan.liang@linux.intel.com \
    --cc=kjain@linux.ibm.com \
    --cc=kprateek.nayak@amd.com \
    --cc=leo.yan@linaro.org \
    --cc=liam.howlett@oracle.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=liuwenyu7@huawei.com \
    --cc=mark.rutland@arm.com \
    --cc=mhiramat@kernel.org \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=ojeda@kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=peterz@infradead.org \
    --cc=ravi.bangoria@amd.com \
    --cc=sandipan.das@amd.com \
    --cc=seanjc@google.com \
    --cc=siyanteng@loongson.cn \
    --cc=song@kernel.org \
    --cc=terrelln@fb.com \
    --cc=yangjihong1@huawei.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox