repack: fix trying to use preferred pack in alternates

When doing a geometric repack with multi-pack-indices, then we ask
git-multi-pack-index(1) to use the largest packfile as the preferred
pack. It can happen though that the largest packfile is not part of the
main object database, but instead part of an alternate object database.
The result is that git-multi-pack-index(1) will not be able to find the
preferred pack and print a warning. It then falls back to use the first
packfile that the multi-pack-index shall reference.

Fix this bug by only considering packfiles as preferred pack that are
local. This is the right thing to do given that a multi-pack-index
should never reference packfiles borrowed from an alternate.

While at it, rename the function `get_largest_active_packfile()` to
`get_preferred_pack()` to better document its intent.

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

Author: pks-t

builtin/repack.c

@@ -444,8 +444,10 @@ static void split_pack_geometry(struct pack_geometry *geometry, int factor)
 	geometry->split = split;
 }
 
-static struct packed_git *get_largest_active_pack(struct pack_geometry *geometry)
+static struct packed_git *get_preferred_pack(struct pack_geometry *geometry)
 {
+	uint32_t i;
+
 	if (!geometry) {
 		/*
 		 * No geometry means either an all-into-one repack (in which
@@ -460,7 +462,21 @@ static struct packed_git *get_largest_active_pack(struct pack_geometry *geometry
 	}
 	if (geometry->split == geometry->pack_nr)
 		return NULL;
-	return geometry->pack[geometry->pack_nr - 1];
+
+	/*
+	 * The preferred pack is the largest pack above the split line. In
+	 * other words, it is the largest pack that does not get rolled up in
+	 * the geometric repack.
+	 */
+	for (i = geometry->pack_nr; i > geometry->split; i--)
+		/*
+		 * A pack that is not local would never be included in a
+		 * multi-pack index. We thus skip over any non-local packs.
+		 */
+		if (geometry->pack[i - 1]->pack_local)
+			return geometry->pack[i - 1];
+
+	return NULL;
 }
 
 static void clear_pack_geometry(struct pack_geometry *geometry)
@@ -587,7 +603,7 @@ static int write_midx_included_packs(struct string_list *include,
 {
 	struct child_process cmd = CHILD_PROCESS_INIT;
 	struct string_list_item *item;
-	struct packed_git *largest = get_largest_active_pack(geometry);
+	struct packed_git *preferred = get_preferred_pack(geometry);
 	FILE *in;
 	int ret;
 
@@ -608,9 +624,9 @@ static int write_midx_included_packs(struct string_list *include,
 	if (write_bitmaps)
 		strvec_push(&cmd.args, "--bitmap");
 
-	if (largest)
+	if (preferred)
 		strvec_pushf(&cmd.args, "--preferred-pack=%s",
-			     pack_basename(largest));
+			     pack_basename(preferred));
 
 	if (refs_snapshot)
 		strvec_pushf(&cmd.args, "--refs-snapshot=%s", refs_snapshot);

t/t7703-repack-geometric.sh

@@ -281,4 +281,36 @@ test_expect_success '--geometric with pack.packSizeLimit' '
 	)
 '
 
+test_expect_success '--geometric --write-midx with packfiles in main and alternate ODB' '
+	test_when_finished "rm -fr shared member" &&
+
+	# Create a shared repository that will serve as the alternate object
+	# database for the member linked to it. It has got some objects on its
+	# own that are packed into a single packfile.
+	git init shared &&
+	test_commit -C shared common-object &&
+	git -C shared repack -ad &&
+
+	# We create member so that its alternates file points to the shared
+	# repository. We then create a commit in it so that git-repack(1) has
+	# something to repack.
+	# of the shared object database.
+	git clone --shared shared member &&
+	test_commit -C member unique-object &&
+	git -C member repack --geometric=2 --write-midx 2>err &&
+	test_must_be_empty err &&
+
+	# We should see that a new packfile was generated.
+	find shared/.git/objects/pack -type f -name "*.pack" >packs &&
+	test_line_count = 1 packs &&
+
+	# We should also see a multi-pack-index. This multi-pack-index should
+	# never refer to any packfiles in the alternate object database.
+	test_path_is_file member/.git/objects/pack/multi-pack-index &&
+	test-tool read-midx member/.git/objects >packs.midx &&
+	grep "^pack-.*\.idx$" packs.midx | sort >actual &&
+	basename member/.git/objects/pack/pack-*.idx >expect &&
+	test_cmp expect actual
+'
+
 test_done