@matheusbsbs / matheus-bagliano / commits / d1d701eb9c

pack-objects: keep track of `pack_start` for each reuse pack

When reusing objects from a pack, we keep track of a set of one or more `reused_chunk`s, corresponding to sections of one or more object(s) from a source pack that we are reusing. Each chunk contains two pieces of information: - the offset of the first object in the source pack (relative to the beginning of the source pack) - the difference between that offset, and the corresponding offset in the pack we're generating The purpose of keeping track of these is so that we can patch an OFS_DELTAs that cross over a section of the reuse pack that we didn't take. For instance, consider a hypothetical pack as shown below: (chunk #2) __________... / / +--------+---------+-------------------+---------+ ... | <base> | <other> | (unused) | <delta> | ... +--------+---------+-------------------+---------+ \ / \______________/ (chunk #1) Suppose that we are sending objects "base", "other", and "delta", and that the "delta" object is stored as an OFS_DELTA, and that its base is "base". If we don't send any objects in the "(unused)" range, we can't copy the delta'd object directly, since its delta offset includes a range of the pack that we didn't copy, so we have to account for that difference when patching and reassembling the delta. In order to compute this value correctly, we need to know not only where we are in the packfile we're assembling (with `hashfile_total(f)`) but also the position of the first byte of the packfile that we are currently reusing. Currently, this works just fine, since when reusing only a single pack those two values are always identical (because verbatim reuse is the first thing pack-objects does when enabled after writing the pack header). But when reusing multiple packs which have one or more gaps, we'll need to account for these two values diverging. Together, these two allow us to compute the reused chunk's offset difference relative to the start of the reused pack, as desired. Helped-by: Jeff King <peff@peff.net> Signed-off-by: Taylor Blau <me@ttaylorr.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>

Taylor Blau committed Dec 14, 2023 at 17:24 UTC d1d701eb9ce2293588aabf34c69335d49640f968

1 file changed +8 -3

builtin/pack-objects.c

+8 -3

@@ -1015,6 +1015,7 @@ static off_t find_reused_offset(off_t where)

1015

1016 static void write_reused_pack_one(struct packed_git *reuse_packfile,

1017 size_t pos, struct hashfile *out,

1018 + off_t pack_start,

1019 struct pack_window **w_curs)

1020 {

1021 off_t offset, next, cur;

@@ -1024,7 +1025,8 @@ static void write_reused_pack_one(struct packed_git *reuse_packfile,

1025 offset = pack_pos_to_offset(reuse_packfile, pos);

1026 next = pack_pos_to_offset(reuse_packfile, pos + 1);

1027

1027 - record_reused_object(offset, offset - hashfile_total(out));

1028 + record_reused_object(offset,

1029 + offset - (hashfile_total(out) - pack_start));

1030

1031 cur = offset;

1032 type = unpack_object_header(reuse_packfile, w_curs, &cur, &size);

@@ -1094,6 +1096,7 @@ static void write_reused_pack_one(struct packed_git *reuse_packfile,

1096

1097 static size_t write_reused_pack_verbatim(struct packed_git *reuse_packfile,

1098 struct hashfile *out,

1099 + off_t pack_start UNUSED,

1100 struct pack_window **w_curs)

1101 {

1102 size_t pos = 0;

@@ -1125,10 +1128,12 @@ static void write_reused_pack(struct packed_git *reuse_packfile,

1128 {

1129 size_t i = 0;

1130 uint32_t offset;

1131 + off_t pack_start = hashfile_total(f) - sizeof(struct pack_header);

1132 struct pack_window *w_curs = NULL;

1133

1134 if (allow_ofs_delta)

1131 - i = write_reused_pack_verbatim(reuse_packfile, f, &w_curs);

1135 + i = write_reused_pack_verbatim(reuse_packfile, f, pack_start,

1136 + &w_curs);

1137

1138 for (; i < reuse_packfile_bitmap->word_alloc; ++i) {

1139 eword_t word = reuse_packfile_bitmap->words[i];

@@ -1145,7 +1150,7 @@ static void write_reused_pack(struct packed_git *reuse_packfile,

1150 * for why.

1151 */

1152 write_reused_pack_one(reuse_packfile, pos + offset, f,

1148 - &w_curs);

1153 + pack_start, &w_curs);

1154 display_progress(progress_state, ++written);

1155 }

1156 }