unpack-objects: use stream_loose_object() to unpack large objects

Make use of the stream_loose_object() function introduced in the
preceding commit to unpack large objects. Before this we'd need to
malloc() the size of the blob before unpacking it, which could cause
OOM with very large blobs.

We could use the new streaming interface to unpack all blobs, but
doing so would be much slower, as demonstrated e.g. with this
benchmark using git-hyperfine[0]:

	rm -rf /tmp/scalar.git &&
	git clone --bare https://github.com/Microsoft/scalar.git /tmp/scalar.git &&
	mv /tmp/scalar.git/objects/pack/*.pack /tmp/scalar.git/my.pack &&
	git hyperfine \
		-r 2 --warmup 1 \
		-L rev origin/master,HEAD -L v "10,512,1k,1m" \
		-s 'make' \
		-p 'git init --bare dest.git' \
		-c 'rm -rf dest.git' \
		'./git -C dest.git -c core.bigFileThreshold={v} unpack-objects </tmp/scalar.git/my.pack'

Here we'll perform worse with lower core.bigFileThreshold settings
with this change in terms of speed, but we're getting lower memory use
in return:

	Summary
	  './git -C dest.git -c core.bigFileThreshold=10 unpack-objects </tmp/scalar.git/my.pack' in 'origin/master' ran
	    1.01 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1k unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
	    1.01 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1m unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
	    1.01 ± 0.02 times faster than './git -C dest.git -c core.bigFileThreshold=1m unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
	    1.02 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/scalar.git/my.pack' in 'origin/master'
	    1.09 ± 0.01 times faster than './git -C dest.git -c core.bigFileThreshold=1k unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
	    1.10 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'
	    1.11 ± 0.00 times faster than './git -C dest.git -c core.bigFileThreshold=10 unpack-objects </tmp/scalar.git/my.pack' in 'HEAD'

A better benchmark to demonstrate the benefits of that this one, which
creates an artificial repo with a 1, 25, 50, 75 and 100MB blob:

	rm -rf /tmp/repo &&
	git init /tmp/repo &&
	(
		cd /tmp/repo &&
		for i in 1 25 50 75 100
		do
			dd if=/dev/urandom of=blob.$i count=$(($i*1024)) bs=1024
		done &&
		git add blob.* &&
		git commit -mblobs &&
		git gc &&
		PACK=$(echo .git/objects/pack/pack-*.pack) &&
		cp "$PACK" my.pack
	) &&
	git hyperfine \
		--show-output \
		-L rev origin/master,HEAD -L v "512,50m,100m" \
		-s 'make' \
		-p 'git init --bare dest.git' \
		-c 'rm -rf dest.git' \
		'/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold={v} unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum'

Using this test we'll always use >100MB of memory on
origin/master (around ~105MB), but max out at e.g. ~55MB if we set
core.bigFileThreshold=50m.

The relevant "Maximum resident set size" lines were manually added
below the relevant benchmark:

  '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=50m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master' ran
        Maximum resident set size (kbytes): 107080
    1.02 ± 0.78 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master'
        Maximum resident set size (kbytes): 106968
    1.09 ± 0.79 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=100m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'origin/master'
        Maximum resident set size (kbytes): 107032
    1.42 ± 1.07 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=100m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
        Maximum resident set size (kbytes): 107072
    1.83 ± 1.02 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=50m unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
        Maximum resident set size (kbytes): 55704
    2.16 ± 1.19 times faster than '/usr/bin/time -v ./git -C dest.git -c core.bigFileThreshold=512 unpack-objects </tmp/repo/my.pack 2>&1 | grep Maximum' in 'HEAD'
        Maximum resident set size (kbytes): 4564

This shows that if you have enough memory this new streaming method is
slower the lower you set the streaming threshold, but the benefit is
more bounded memory use.

An earlier version of this patch introduced a new
"core.bigFileStreamingThreshold" instead of re-using the existing
"core.bigFileThreshold" variable[1]. As noted in a detailed overview
of its users in [2] using it has several different meanings.

Still, we consider it good enough to simply re-use it. While it's
possible that someone might want to e.g. consider objects "small" for
the purposes of diffing but "big" for the purposes of writing them
such use-cases are probably too obscure to worry about. We can always
split up "core.bigFileThreshold" in the future if there's a need for
that.

0. https://github.com/avar/git-hyperfine/
1. https://lore.kernel.org/git/20211210103435.83656-1-chiyutianyi@gmail.com/
2. https://lore.kernel.org/git/20220120112114.47618-5-chiyutianyi@gmail.com/

Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Helped-by: Derrick Stolee <stolee@gmail.com>
Helped-by: Jiang Xin <zhiyou.jx@alibaba-inc.com>
Signed-off-by: Han Xin <chiyutianyi@gmail.com>
Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 68 insertions, 1 deletions

diff --git a/builtin/unpack-objects.c b/builtin/unpack-objects.c
index 32e8b47059..43789b8ef2 100644
--- a/builtin/unpack-objects.c
+++ b/builtin/unpack-objects.c
@@ -351,6 +351,68 @@ static void unpack_non_delta_entry(enum object_type type, unsigned long size,
 		write_object(nr, type, buf, size);
 }
 
+struct input_zstream_data {
+	git_zstream *zstream;
+	unsigned char buf[8192];
+	int status;
+};
+
+static const void *feed_input_zstream(struct input_stream *in_stream,
+				      unsigned long *readlen)
+{
+	struct input_zstream_data *data = in_stream->data;
+	git_zstream *zstream = data->zstream;
+	void *in = fill(1);
+
+	if (in_stream->is_finished) {
+		*readlen = 0;
+		return NULL;
+	}
+
+	zstream->next_out = data->buf;
+	zstream->avail_out = sizeof(data->buf);
+	zstream->next_in = in;
+	zstream->avail_in = len;
+
+	data->status = git_inflate(zstream, 0);
+
+	in_stream->is_finished = data->status != Z_OK;
+	use(len - zstream->avail_in);
+	*readlen = sizeof(data->buf) - zstream->avail_out;
+
+	return data->buf;
+}
+
+static void stream_blob(unsigned long size, unsigned nr)
+{
+	git_zstream zstream = { 0 };
+	struct input_zstream_data data = { 0 };
+	struct input_stream in_stream = {
+		.read = feed_input_zstream,
+		.data = &data,
+	};
+	struct obj_info *info = &obj_list[nr];
+
+	data.zstream = &zstream;
+	git_inflate_init(&zstream);
+
+	if (stream_loose_object(&in_stream, size, &info->oid))
+		die(_("failed to write object in stream"));
+
+	if (data.status != Z_STREAM_END)
+		die(_("inflate returned (%d)"), data.status);
+	git_inflate_end(&zstream);
+
+	if (strict) {
+		struct blob *blob = lookup_blob(the_repository, &info->oid);
+
+		if (!blob)
+			die(_("invalid blob object from stream"));
+		blob->object.flags |= FLAG_WRITTEN;
+	}
+	info->obj = NULL;
+}
+
 static int resolve_against_held(unsigned nr, const struct object_id *base,
 				void *delta_data, unsigned long delta_size)
 {
@@ -483,9 +545,14 @@ static void unpack_one(unsigned nr)
 	}
 
 	switch (type) {
+	case OBJ_BLOB:
+		if (!dry_run && size > big_file_threshold) {
+			stream_blob(size, nr);
+			return;
+		}
+		/* fallthrough */
 	case OBJ_COMMIT:
 	case OBJ_TREE:
-	case OBJ_BLOB:
 	case OBJ_TAG:
 		unpack_non_delta_entry(type, size, nr);
 		return;