diff mbox series

[v6,6/6] unpack-objects: unpack_non_delta_entry() read data in a stream

Message ID 20211217112629.12334-7-chiyutianyi@gmail.com (mailing list archive)
State Superseded
Headers show
Series unpack large blobs in stream | expand

Commit Message

Han Xin Dec. 17, 2021, 11:26 a.m. UTC
From: Han Xin <hanxin.hx@alibaba-inc.com>

We used to call "get_data()" in "unpack_non_delta_entry()" to read the
entire contents of a blob object, no matter how big it is. This
implementation may consume all the memory and cause OOM.

By implementing a zstream version of input_stream interface, we can use
a small fixed buffer for "unpack_non_delta_entry()".

However, unpack non-delta objects from a stream instead of from an
entrie buffer will have 10% performance penalty. Therefore, only unpack
object larger than the "core.BigFileStreamingThreshold" in zstream. See
the following benchmarks:

    hyperfine \
      --setup \
      'if ! test -d scalar.git; then git clone --bare https://github.com/microsoft/scalar.git; cp scalar.git/objects/pack/*.pack small.pack; fi' \
      --prepare 'rm -rf dest.git && git init --bare dest.git'

    Summary
      './git -C dest.git -c core.bigfilethreshold=512m unpack-objects <small.pack' in 'origin/master'
        1.01 ± 0.04 times faster than './git -C dest.git -c core.bigfilethreshold=512m unpack-objects <small.pack' in 'HEAD~1'
        1.01 ± 0.04 times faster than './git -C dest.git -c core.bigfilethreshold=512m unpack-objects <small.pack' in 'HEAD~0'
        1.03 ± 0.10 times faster than './git -C dest.git -c core.bigfilethreshold=16k unpack-objects <small.pack' in 'origin/master'
        1.02 ± 0.07 times faster than './git -C dest.git -c core.bigfilethreshold=16k unpack-objects <small.pack' in 'HEAD~0'
        1.10 ± 0.04 times faster than './git -C dest.git -c core.bigfilethreshold=16k unpack-objects <small.pack' in 'HEAD~1'

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 <hanxin.hx@alibaba-inc.com>
---
 Documentation/config/core.txt       | 11 ++++
 builtin/unpack-objects.c            | 73 +++++++++++++++++++++++-
 cache.h                             |  1 +
 config.c                            |  5 ++
 environment.c                       |  1 +
 t/t5590-unpack-non-delta-objects.sh | 87 +++++++++++++++++++++++++++++
 6 files changed, 177 insertions(+), 1 deletion(-)
 create mode 100755 t/t5590-unpack-non-delta-objects.sh
diff mbox series

Patch

diff --git a/Documentation/config/core.txt b/Documentation/config/core.txt
index c04f62a54a..601b7a2418 100644
--- a/Documentation/config/core.txt
+++ b/Documentation/config/core.txt
@@ -424,6 +424,17 @@  be delta compressed, but larger binary media files won't be.
 +
 Common unit suffixes of 'k', 'm', or 'g' are supported.
 
+core.bigFileStreamingThreshold::
+	Files larger than this will be streamed out to a temporary
+	object file while being hashed, which will when be renamed
+	in-place to a loose object, particularly if the
+	`core.bigFileThreshold' setting dictates that they're always
+	written out as loose objects.
++
+Default is 128 MiB on all platforms.
++
+Common unit suffixes of 'k', 'm', or 'g' are supported.
+
 core.excludesFile::
 	Specifies the pathname to the file that contains patterns to
 	describe paths that are not meant to be tracked, in addition
diff --git a/builtin/unpack-objects.c b/builtin/unpack-objects.c
index c4a17bdb44..42e1033d85 100644
--- a/builtin/unpack-objects.c
+++ b/builtin/unpack-objects.c
@@ -331,11 +331,82 @@  static void added_object(unsigned nr, enum object_type type,
 	}
 }
 
+struct input_zstream_data {
+	git_zstream *zstream;
+	unsigned char buf[8192];
+	int status;
+};
+
+static const void *feed_input_zstream(const 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 (!len || data->status == Z_STREAM_END) {
+		*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);
+	use(len - zstream->avail_in);
+	*readlen = sizeof(data->buf) - zstream->avail_out;
+
+	return data->buf;
+}
+
+static void write_stream_blob(unsigned nr, unsigned long size)
+{
+	git_zstream zstream;
+	struct input_zstream_data data;
+	struct input_stream in_stream = {
+		.read = feed_input_zstream,
+		.data = &data,
+	};
+
+	memset(&zstream, 0, sizeof(zstream));
+	memset(&data, 0, sizeof(data));
+	data.zstream = &zstream;
+	git_inflate_init(&zstream);
+
+	if (write_object_file_flags(&in_stream, size,
+				    type_name(OBJ_BLOB),
+				    &obj_list[nr].oid,
+				    HASH_STREAM))
+		die(_("failed to write object in stream"));
+
+	if (zstream.total_out != size || data.status != Z_STREAM_END)
+		die(_("inflate returned %d"), data.status);
+	git_inflate_end(&zstream);
+
+	if (strict) {
+		struct blob *blob = lookup_blob(the_repository, &obj_list[nr].oid);
+		if (blob)
+			blob->object.flags |= FLAG_WRITTEN;
+		else
+			die(_("invalid blob object from stream"));
+	}
+	obj_list[nr].obj = NULL;
+}
+
 static void unpack_non_delta_entry(enum object_type type, unsigned long size,
 				   unsigned nr)
 {
-	void *buf = get_data(size, dry_run);
+	void *buf;
+
+	/* Write large blob in stream without allocating full buffer. */
+	if (!dry_run && type == OBJ_BLOB && size > big_file_streaming_threshold) {
+		write_stream_blob(nr, size);
+		return;
+	}
 
+	buf = get_data(size, dry_run);
 	if (!dry_run && buf)
 		write_object(nr, type, buf, size);
 	else
diff --git a/cache.h b/cache.h
index 6d68fd10a3..976f9cf656 100644
--- a/cache.h
+++ b/cache.h
@@ -975,6 +975,7 @@  extern size_t packed_git_window_size;
 extern size_t packed_git_limit;
 extern size_t delta_base_cache_limit;
 extern unsigned long big_file_threshold;
+extern unsigned long big_file_streaming_threshold;
 extern unsigned long pack_size_limit_cfg;
 
 /*
diff --git a/config.c b/config.c
index c5873f3a70..7b122a142a 100644
--- a/config.c
+++ b/config.c
@@ -1408,6 +1408,11 @@  static int git_default_core_config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 
+	if (!strcmp(var, "core.bigfilestreamingthreshold")) {
+		big_file_streaming_threshold = git_config_ulong(var, value);
+		return 0;
+	}
+
 	if (!strcmp(var, "core.packedgitlimit")) {
 		packed_git_limit = git_config_ulong(var, value);
 		return 0;
diff --git a/environment.c b/environment.c
index 0d06a31024..04bba593de 100644
--- a/environment.c
+++ b/environment.c
@@ -47,6 +47,7 @@  size_t packed_git_window_size = DEFAULT_PACKED_GIT_WINDOW_SIZE;
 size_t packed_git_limit = DEFAULT_PACKED_GIT_LIMIT;
 size_t delta_base_cache_limit = 96 * 1024 * 1024;
 unsigned long big_file_threshold = 512 * 1024 * 1024;
+unsigned long big_file_streaming_threshold = 128 * 1024 * 1024;
 int pager_use_color = 1;
 const char *editor_program;
 const char *askpass_program;
diff --git a/t/t5590-unpack-non-delta-objects.sh b/t/t5590-unpack-non-delta-objects.sh
new file mode 100755
index 0000000000..11c70e192c
--- /dev/null
+++ b/t/t5590-unpack-non-delta-objects.sh
@@ -0,0 +1,87 @@ 
+#!/bin/sh
+#
+# Copyright (c) 2021 Han Xin
+#
+
+test_description='Test unpack-objects when receive pack'
+
+GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME=main
+export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME
+
+. ./test-lib.sh
+
+prepare_dest () {
+	test_when_finished "rm -rf dest.git" &&
+	git init --bare dest.git &&
+	git -C dest.git config core.bigFileStreamingThreshold $1 &&
+	git -C dest.git config core.bigFileThreshold $1
+}
+
+test_expect_success "setup repo with big blobs (1.5 MB)" '
+	test-tool genrandom foo 1500000 >big-blob &&
+	test_commit --append foo big-blob &&
+	test-tool genrandom bar 1500000 >big-blob &&
+	test_commit --append bar big-blob &&
+	(
+		cd .git &&
+		find objects/?? -type f | sort
+	) >expect &&
+	PACK=$(echo main | git pack-objects --revs test)
+'
+
+test_expect_success 'setup env: GIT_ALLOC_LIMIT to 1MB' '
+	GIT_ALLOC_LIMIT=1m &&
+	export GIT_ALLOC_LIMIT
+'
+
+test_expect_success 'fail to unpack-objects: cannot allocate' '
+	prepare_dest 2m &&
+	test_must_fail git -C dest.git unpack-objects <test-$PACK.pack 2>err &&
+	grep "fatal: attempting to allocate" err &&
+	(
+		cd dest.git &&
+		find objects/?? -type f | sort
+	) >actual &&
+	test_file_not_empty actual &&
+	! test_cmp expect actual
+'
+
+test_expect_success 'unpack big object in stream' '
+	prepare_dest 1m &&
+	git -C dest.git unpack-objects <test-$PACK.pack &&
+	git -C dest.git fsck &&
+	(
+		cd dest.git &&
+		find objects/?? -type f | sort
+	) >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'unpack big object in stream with existing oids' '
+	prepare_dest 1m &&
+	git -C dest.git index-pack --stdin <test-$PACK.pack &&
+	(
+		cd dest.git &&
+		find objects/?? -type f | sort
+	) >actual &&
+	test_must_be_empty actual &&
+	git -C dest.git unpack-objects <test-$PACK.pack &&
+	git -C dest.git fsck &&
+	(
+		cd dest.git &&
+		find objects/?? -type f | sort
+	) >actual &&
+	test_must_be_empty actual
+'
+
+test_expect_success 'unpack-objects dry-run' '
+	prepare_dest 1m &&
+	git -C dest.git unpack-objects -n <test-$PACK.pack &&
+	(
+		cd dest.git &&
+		find objects/ -type f
+	) >actual &&
+	test_must_be_empty actual
+'
+
+test_done