Re: [PATCH v7 5/5] unpack-objects: unpack_non_delta_entry() read data in a stream

> 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 | 36 +++++++++++++-
>  6 files changed, 125 insertions(+), 2 deletions(-)
>
> 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 9104eb48da..72d8616e00 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(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, size_t 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_stream_object_file(&in_stream, size, OBJ_BLOB, 0, 0,
> +				     &obj_list[nr].oid))

> +		die(_("failed to write object in stream"));
> 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
> index 48c4fb1ba3..8436cbf8db 100755
> --- a/t/t5590-unpack-non-delta-objects.sh
> +++ b/t/t5590-unpack-non-delta-objects.sh
> @@ -13,6 +13,11 @@ export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME
>  prepare_dest () {
>  	test_when_finished "rm -rf dest.git" &&
>  	git init --bare dest.git
> +	if test -n "$1"
> +	then
> +		git -C dest.git config core.bigFileStreamingThreshold $1
> +		git -C dest.git config core.bigFileThreshold $1
> +	fi