pack-bitmap: gracefully handle missing BTMP chunks

In 0fea6b73f1 (Merge branch 'tb/multi-pack-verbatim-reuse', 2024-01-12)
we have introduced multi-pack verbatim reuse of objects. This series has
introduced a new BTMP chunk, which encodes information about bitmapped
objects in the multi-pack index. Starting with dab60934e3 (pack-bitmap:
pass `bitmapped_pack` struct to pack-reuse functions, 2023-12-14) we use
this information to figure out objects which we can reuse from each of
the packfiles.

One thing that we glossed over though is backwards compatibility with
repositories that do not yet have BTMP chunks in their multi-pack index.
In that case, `nth_bitmapped_pack()` would return an error, which causes
us to emit a warning followed by another error message. These warnings
are visible to users that fetch from a repository:

```
$ git fetch
...
remote: error: MIDX does not contain the BTMP chunk
remote: warning: unable to load pack: 'pack-f6bb7bd71d345ea9fe604b60cab9ba9ece54ffbe.idx', disabling pack-reuse
remote: Enumerating objects: 40, done.
remote: Counting objects: 100% (40/40), done.
remote: Compressing objects: 100% (39/39), done.
remote: Total 40 (delta 5), reused 0 (delta 0), pack-reused 0 (from 0)
...
```

While the fetch succeeds the user is left wondering what they did wrong.
Furthermore, as visible both from the warning and from the reuse stats,
pack-reuse is completely disabled in such repositories.

What is quite interesting is that this issue can even be triggered in
case `pack.allowPackReuse=single` is set, which is the default value.
One could have expected that in this case we fall back to the old logic,
which is to use the preferred packfile without consulting BTMP chunks at
all. But either we fail with the above error in case they are missing,
or we use the first pack in the multi-pack-index. The former case
disables pack-reuse altogether, whereas the latter case may result in
reusing objects from a suboptimal packfile.

Fix this issue by partially reverting the logic back to what we had
before this patch series landed. Namely, in the case where we have no
BTMP chunks or when `pack.allowPackReuse=single` are set, we use the
preferred pack instead of consulting the BTMP chunks.

Helped-by: Taylor Blau <me@ttaylorr.com>
Signed-off-by: Patrick Steinhardt <ps@pks.im>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

3 files changed, 42 insertions, 23 deletions

diff --git a/midx.c b/midx.c
index 85e1c2cd12..d2e357fa0f 100644
--- a/midx.c
+++ b/midx.c
@@ -198,9 +198,10 @@ struct multi_pack_index *load_multi_pack_index(const char *object_dir, int local
 
 	pair_chunk(cf, MIDX_CHUNKID_LARGEOFFSETS, &m->chunk_large_offsets,
 		   &m->chunk_large_offsets_len);
-	pair_chunk(cf, MIDX_CHUNKID_BITMAPPEDPACKS,
-		   (const unsigned char **)&m->chunk_bitmapped_packs,
-		   &m->chunk_bitmapped_packs_len);
+	if (git_env_bool("GIT_TEST_MIDX_READ_BTMP", 1))
+		pair_chunk(cf, MIDX_CHUNKID_BITMAPPEDPACKS,
+			   (const unsigned char **)&m->chunk_bitmapped_packs,
+			   &m->chunk_bitmapped_packs_len);
 
 	if (git_env_bool("GIT_TEST_MIDX_READ_RIDX", 1))
 		pair_chunk(cf, MIDX_CHUNKID_REVINDEX, &m->chunk_revindex,
diff --git a/pack-bitmap.c b/pack-bitmap.c
index 229a11fb00..b314f912c9 100644
--- a/pack-bitmap.c
+++ b/pack-bitmap.c
@@ -2056,7 +2056,10 @@ void reuse_partial_packfile_from_bitmap(struct bitmap_index *bitmap_git,
 
 	load_reverse_index(r, bitmap_git);
 
-	if (bitmap_is_midx(bitmap_git)) {
+	if (!bitmap_is_midx(bitmap_git) || !bitmap_git->midx->chunk_bitmapped_packs)
+		multi_pack_reuse = 0;
+
+	if (multi_pack_reuse) {
 		for (i = 0; i < bitmap_git->midx->num_packs; i++) {
 			struct bitmapped_pack pack;
 			if (nth_bitmapped_pack(r, bitmap_git->midx, &pack, i) < 0) {
@@ -2069,34 +2072,32 @@ void reuse_partial_packfile_from_bitmap(struct bitmap_index *bitmap_git,
 			if (!pack.bitmap_nr)
 				continue;
 
-			if (!multi_pack_reuse && pack.bitmap_pos) {
-				/*
-				 * If we're only reusing a single pack, skip
-				 * over any packs which are not positioned at
-				 * the beginning of the MIDX bitmap.
-				 *
-				 * This is consistent with the existing
-				 * single-pack reuse behavior, which only reuses
-				 * parts of the MIDX's preferred pack.
-				 */
-				continue;
-			}
-
 			ALLOC_GROW(packs, packs_nr + 1, packs_alloc);
 			memcpy(&packs[packs_nr++], &pack, sizeof(pack));
 
 			objects_nr += pack.p->num_objects;
-
-			if (!multi_pack_reuse)
-				break;
 		}
 
 		QSORT(packs, packs_nr, bitmapped_pack_cmp);
 	} else {
-		ALLOC_GROW(packs, packs_nr + 1, packs_alloc);
+		struct packed_git *pack;
+
+		if (bitmap_is_midx(bitmap_git)) {
+			uint32_t preferred_pack_pos;
+
+			if (midx_preferred_pack(bitmap_git->midx, &preferred_pack_pos) < 0) {
+				warning(_("unable to compute preferred pack, disabling pack-reuse"));
+				return;
+			}
 
-		packs[packs_nr].p = bitmap_git->pack;
-		packs[packs_nr].bitmap_nr = bitmap_git->pack->num_objects;
+			pack = bitmap_git->midx->packs[preferred_pack_pos];
+		} else {
+			pack = bitmap_git->pack;
+		}
+
+		ALLOC_GROW(packs, packs_nr + 1, packs_alloc);
+		packs[packs_nr].p = pack;
+		packs[packs_nr].bitmap_nr = pack->num_objects;
 		packs[packs_nr].bitmap_pos = 0;
 
 		objects_nr = packs[packs_nr++].bitmap_nr;
diff --git a/t/t5326-multi-pack-bitmaps.sh b/t/t5326-multi-pack-bitmaps.sh
index 70d1b58709..5d7d321840 100755
--- a/t/t5326-multi-pack-bitmaps.sh
+++ b/t/t5326-multi-pack-bitmaps.sh
@@ -513,4 +513,21 @@ test_expect_success 'corrupt MIDX with bitmap causes fallback' '
 	)
 '
 
+for allow_pack_reuse in single multi
+do
+	test_expect_success "reading MIDX without BTMP chunk does not complain with $allow_pack_reuse pack reuse" '
+		test_when_finished "rm -rf midx-without-btmp" &&
+		git init midx-without-btmp &&
+		(
+			cd midx-without-btmp &&
+			test_commit initial &&
+
+			git repack -Adbl --write-bitmap-index --write-midx &&
+			GIT_TEST_MIDX_READ_BTMP=false git -c pack.allowPackReuse=$allow_pack_reuse \
+				pack-objects --all --use-bitmap-index --stdout </dev/null >/dev/null 2>err &&
+			test_must_be_empty err
+		)
+	'
+done
+
 test_done