pack-objects: only perform verbatim reuse on the preferred pack

When reusing objects from source pack(s), write_reused_pack_verbatim()
is responsible for reusing objects whole eword_t's at a time. It works
by taking the longest continuous run of objects from the beginning of
each source pack that the caller wants, and reuses the entirety of that
section from each pack.

This is based on the assumption that we don't have any gaps within the
region. This assumption relieves us from having to patch any
OFS_DELTAs, since we know that there aren't any gaps between any delta
and its base in that region.

To illustrate why this assumption is necessary, suppose we have some
pack P, which has objects X, Y, and Z. If the MIDX's copy of Y was
selected from a pack other than P, then the bit corresponding to object
Y will appear earlier in the bitmap than the bits corresponding to X and
Z.

If pack-objects already has or will use the copy of Y from the pack it
was selected from in the MIDX, then it is an error to reuse all objects
between X and Z in the source pack. Doing so will cause us to reuse Y
from a different pack than the one which represents Y in the MIDX,
causing us to either:

 - include the object twice, assuming that the caller wants Y in the
   pack, or

 - include the object once, resulting in us packing more objects than
   necessary.

This regression comes from ca0fd69 (pack-objects: prepare
`write_reused_pack_verbatim()` for multi-pack reuse, 2023-12-14), which
incorrectly assumed that there would be no gaps in reusable regions of
non-preferred packs.

Instead, we can only safely perform the whole-word reuse optimization on
the preferred pack, where we know with certainty that no gaps exist in
that region of the bitmap. We can still reuse objects from non-preferred
packs, but we have to inspect them individually in write_reused_pack()
to ensure that any gaps that may exist are accounted for.

This allows us to simplify the implementation of
write_reused_pack_verbatim() back to almost its pre-multi-pack reuse
form, since we can now assume that the beginning of the pack appears at
the beginning of the bitmap, meaning that we don't have to account for
any bits up to the first word boundary (like we had to special case in
ca0fd69).

The only significant changes from the pre-ca0fd69e37 implementation are:

 - that we can no longer inspect words up to the end of
   reuse_packfile_bitmap->word_alloc, since we only want to look at
   words whose bits all correspond to objects in the given packfile, and

 - that we return early when given a reuse_packfile which is not
   preferred, making the call a noop.

In the future, it might be possible to restore this optimization if we
could guarantee that some reuse packs don't contain any gaps by
construction (similar to the "disjoint packs" idea in very early
versions of multi-pack reuse).

Helped-by: Jeff King <[email protected]>
Signed-off-by: Taylor Blau <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: ttaylorr

builtin/pack-objects.c

@@ -1100,78 +1100,64 @@ static void write_reused_pack_one(struct packed_git *reuse_packfile,
 
 static size_t write_reused_pack_verbatim(struct bitmapped_pack *reuse_packfile,
 					 struct hashfile *out,
-					 off_t pack_start,
 					 struct pack_window **w_curs)
 {
-	size_t pos = reuse_packfile->bitmap_pos;
+	size_t pos = 0;
 	size_t end;
 
-	if (pos % BITS_IN_EWORD) {
-		size_t word_pos = (pos / BITS_IN_EWORD);
-		size_t offset = pos % BITS_IN_EWORD;
-		size_t last;
-		eword_t word = reuse_packfile_bitmap->words[word_pos];
-
-		if (offset + reuse_packfile->bitmap_nr < BITS_IN_EWORD)
-			last = offset + reuse_packfile->bitmap_nr;
-		else
-			last = BITS_IN_EWORD;
-
-		for (; offset < last; offset++) {
-			if (word >> offset == 0)
-				return word_pos;
-			if (!bitmap_get(reuse_packfile_bitmap,
-					word_pos * BITS_IN_EWORD + offset))
-				return word_pos;
-		}
-
-		pos += BITS_IN_EWORD - (pos % BITS_IN_EWORD);
+	if (reuse_packfile->bitmap_pos) {
+		/*
+		 * We can't reuse whole chunks verbatim out of
+		 * non-preferred packs since we can't guarantee that
+		 * all duplicate objects were resolved in favor of
+		 * that pack.
+		 *
+		 * Even if we have a whole eword_t worth of bits that
+		 * could be reused, there may be objects between the
+		 * objects corresponding to the first and last bit of
+		 * that word which were selected from a different
+		 * pack, causing us to send duplicate or unwanted
+		 * objects.
+		 *
+		 * Handle non-preferred packs from within
+		 * write_reused_pack(), which inspects and reuses
+		 * individual bits.
+		 */
+		return reuse_packfile->bitmap_pos / BITS_IN_EWORD;
 	}
 
 	/*
-	 * Now we're going to copy as many whole eword_t's as possible.
-	 * "end" is the index of the last whole eword_t we copy, but
-	 * there may be additional bits to process. Those are handled
-	 * individually by write_reused_pack().
+	 * Only read through the last word whose bits all correspond
+	 * to objects in the given packfile, since we must stop at a
+	 * word boundary.
 	 *
-	 * Begin by advancing to the first word boundary in range of the
-	 * bit positions occupied by objects in "reuse_packfile". Then
-	 * pick the last word boundary in the same range. If we have at
-	 * least one word's worth of bits to process, continue on.
+	 * If there is no whole word to read (i.e. the packfile
+	 * contains fewer than BITS_IN_EWORD objects), then we'll
+	 * inspect bits one-by-one in write_reused_pack().
 	 */
-	end = reuse_packfile->bitmap_pos + reuse_packfile->bitmap_nr;
-	if (end % BITS_IN_EWORD)
-		end -= end % BITS_IN_EWORD;
-	if (pos >= end)
-		return reuse_packfile->bitmap_pos / BITS_IN_EWORD;
-
-	while (pos < end &&
-	       reuse_packfile_bitmap->words[pos / BITS_IN_EWORD] == (eword_t)~0)
-		pos += BITS_IN_EWORD;
+	end = reuse_packfile->bitmap_nr / BITS_IN_EWORD;
+	if (reuse_packfile_bitmap->word_alloc < end)
+		BUG("fewer words than expected in reuse_packfile_bitmap");
 
-	if (pos > end)
-		pos = end;
+	while (pos < end && reuse_packfile_bitmap->words[pos] == (eword_t)~0)
+		pos++;
 
-	if (reuse_packfile->bitmap_pos < pos) {
-		off_t pack_start_off = pack_pos_to_offset(reuse_packfile->p, 0);
-		off_t pack_end_off = pack_pos_to_offset(reuse_packfile->p,
-							pos - reuse_packfile->bitmap_pos);
+	if (pos) {
+		off_t to_write;
 
-		written += pos - reuse_packfile->bitmap_pos;
+		written = (pos * BITS_IN_EWORD);
+		to_write = pack_pos_to_offset(reuse_packfile->p, written)
+			- sizeof(struct pack_header);
 
 		/* We're recording one chunk, not one object. */
-		record_reused_object(pack_start_off,
-				     pack_start_off - (hashfile_total(out) - pack_start));
+		record_reused_object(sizeof(struct pack_header), 0);
 		hashflush(out);
 		copy_pack_data(out, reuse_packfile->p, w_curs,
-			pack_start_off, pack_end_off - pack_start_off);
+			sizeof(struct pack_header), to_write);
 
 		display_progress(progress_state, written);
 	}
-	if (pos % BITS_IN_EWORD)
-		BUG("attempted to jump past a word boundary to %"PRIuMAX,
-		    (uintmax_t)pos);
-	return pos / BITS_IN_EWORD;
+	return pos;
 }
 
 static void write_reused_pack(struct bitmapped_pack *reuse_packfile,
@@ -1183,8 +1169,7 @@ static void write_reused_pack(struct bitmapped_pack *reuse_packfile,
 	struct pack_window *w_curs = NULL;
 
 	if (allow_ofs_delta)
-		i = write_reused_pack_verbatim(reuse_packfile, f, pack_start,
-					       &w_curs);
+		i = write_reused_pack_verbatim(reuse_packfile, f, &w_curs);
 
 	for (; i < reuse_packfile_bitmap->word_alloc; ++i) {
 		eword_t word = reuse_packfile_bitmap->words[i];

t/t5332-multi-pack-reuse.sh

@@ -259,7 +259,7 @@ test_expect_success 'duplicate objects' '
 	)
 '
 
-test_expect_failure 'duplicate objects with verbatim reuse' '
+test_expect_success 'duplicate objects with verbatim reuse' '
 	git init duplicate-objects-verbatim &&
 	(
 		cd duplicate-objects-verbatim &&