Am 17.12.21 um 12:26 schrieb Han Xin:
> From: Han Xin <hanxin.hx@xxxxxxxxxxxxxxx>
>
> In dry_run mode, "get_data()" is used to verify the inflation of data,
> and the returned buffer will not be used at all and will be freed
> immediately. Even in dry_run mode, it is dangerous to allocate a
> full-size buffer for a large blob object. Therefore, only allocate a
> low memory footprint when calling "get_data()" in dry_run mode.
Clever. Looks good to me.
For some reason I was expecting this patch to have some connection to
one of the earlier ones (perhaps because get_data() was mentioned),
but it is technically independent.
>
> Suggested-by: Jiang Xin <zhiyou.jx@xxxxxxxxxxxxxxx>
> Signed-off-by: Han Xin <hanxin.hx@xxxxxxxxxxxxxxx>
> ---
> builtin/unpack-objects.c | 23 +++++++++++++++++------
> 1 file changed, 17 insertions(+), 6 deletions(-)
>
> diff --git a/builtin/unpack-objects.c b/builtin/unpack-objects.c
> index 4a9466295b..c4a17bdb44 100644
> --- a/builtin/unpack-objects.c
> +++ b/builtin/unpack-objects.c
> @@ -96,15 +96,21 @@ static void use(int bytes)
> display_throughput(progress, consumed_bytes);
> }
>
> -static void *get_data(unsigned long size)
> +static void *get_data(unsigned long size, int dry_run)
> {
> git_zstream stream;
> - void *buf = xmallocz(size);
> + unsigned long bufsize;
> + void *buf;
>
> memset(&stream, 0, sizeof(stream));
> + if (dry_run && size > 8192)
> + bufsize = 8192;
> + else
> + bufsize = size;
> + buf = xmallocz(bufsize);
>
> stream.next_out = buf;
> - stream.avail_out = size;
> + stream.avail_out = bufsize;
> stream.next_in = fill(1);
> stream.avail_in = len;
> git_inflate_init(&stream);
> @@ -124,6 +130,11 @@ static void *get_data(unsigned long size)
> }
> stream.next_in = fill(1);
> stream.avail_in = len;
> + if (dry_run) {
> + /* reuse the buffer in dry_run mode */
> + stream.next_out = buf;
> + stream.avail_out = bufsize;
> + }
> }
> git_inflate_end(&stream);
> return buf;
> @@ -323,7 +334,7 @@ static void added_object(unsigned nr, enum object_type type,
> static void unpack_non_delta_entry(enum object_type type, unsigned long size,
> unsigned nr)
> {
> - void *buf = get_data(size);
> + void *buf = get_data(size, dry_run);
>
> if (!dry_run && buf)
> write_object(nr, type, buf, size);
> @@ -357,7 +368,7 @@ static void unpack_delta_entry(enum object_type type, unsigned long delta_size,
> if (type == OBJ_REF_DELTA) {
> oidread(&base_oid, fill(the_hash_algo->rawsz));
> use(the_hash_algo->rawsz);
> - delta_data = get_data(delta_size);
> + delta_data = get_data(delta_size, dry_run);
> if (dry_run || !delta_data) {
> free(delta_data);
> return;
> @@ -396,7 +407,7 @@ static void unpack_delta_entry(enum object_type type, unsigned long delta_size,
> if (base_offset <= 0 || base_offset >= obj_list[nr].offset)
> die("offset value out of bound for delta base object");
>
> - delta_data = get_data(delta_size);
> + delta_data = get_data(delta_size, dry_run);
> if (dry_run || !delta_data) {
> free(delta_data);
> return;
