Merge branch 'tb/midx-repack-ignore-cruft-packs' into maint-2.38

"git multi-pack-index repack/expire" used to repack unreachable
cruft into a new pack, which have been corrected.
cf. <63a1c3d4-eff3-af10-4263-058c88e74594@github.com>

* tb/midx-repack-ignore-cruft-packs:
  midx.c: avoid cruft packs with non-zero `repack --batch-size`
  midx.c: remove unnecessary loop condition
  midx.c: replace `xcalloc()` with `CALLOC_ARRAY()`
  midx.c: avoid cruft packs with `repack --batch-size=0`
  midx.c: prevent `expire` from removing the cruft pack
  Documentation/git-multi-pack-index.txt: clarify expire behavior
  Documentation/git-multi-pack-index.txt: fix typo

3 files changed, 107 insertions, 6 deletions

diff --git a/Documentation/git-multi-pack-index.txt b/Documentation/git-multi-pack-index.txt
index a48c3d5ea6..3696506eb3 100644
--- a/Documentation/git-multi-pack-index.txt
+++ b/Documentation/git-multi-pack-index.txt
@@ -70,9 +70,10 @@ verify::
 	Verify the contents of the MIDX file.
 
 expire::
-	Delete the pack-files that are tracked 	by the MIDX file, but
-	have no objects referenced by the MIDX. Rewrite the MIDX file
-	afterward to remove all references to these pack-files.
+	Delete the pack-files that are tracked by the MIDX file, but
+	have no objects referenced by the MIDX (with the exception of
+	`.keep` packs and cruft packs). Rewrite the MIDX file afterward
+	to remove all references to these pack-files.
 
 repack::
 	Create a new pack-file containing objects in small pack-files
diff --git a/midx.c b/midx.c
index c27d0e5f15..3a8dcfe98e 100644
--- a/midx.c
+++ b/midx.c
@@ -1839,7 +1839,7 @@ int expire_midx_packs(struct repository *r, const char *object_dir, unsigned fla
 		if (prepare_midx_pack(r, m, i))
 			continue;
 
-		if (m->packs[i]->pack_keep)
+		if (m->packs[i]->pack_keep || m->packs[i]->is_cruft)
 			continue;
 
 		pack_name = xstrdup(m->packs[i]->pack_name);
@@ -1895,6 +1895,8 @@ static int fill_included_packs_all(struct repository *r,
 			continue;
 		if (!pack_kept_objects && m->packs[i]->pack_keep)
 			continue;
+		if (m->packs[i]->is_cruft)
+			continue;
 
 		include_pack[i] = 1;
 		count++;
@@ -1910,9 +1912,11 @@ static int fill_included_packs_batch(struct repository *r,
 {
 	uint32_t i, packs_to_repack;
 	size_t total_size;
-	struct repack_info *pack_info = xcalloc(m->num_packs, sizeof(struct repack_info));
+	struct repack_info *pack_info;
 	int pack_kept_objects = 0;
 
+	CALLOC_ARRAY(pack_info, m->num_packs);
+
 	repo_config_get_bool(r, "repack.packkeptobjects", &pack_kept_objects);
 
 	for (i = 0; i < m->num_packs; i++) {
@@ -1924,7 +1928,7 @@ static int fill_included_packs_batch(struct repository *r,
 		pack_info[i].mtime = m->packs[i]->mtime;
 	}
 
-	for (i = 0; batch_size && i < m->num_objects; i++) {
+	for (i = 0; i < m->num_objects; i++) {
 		uint32_t pack_int_id = nth_midxed_pack_int_id(m, i);
 		pack_info[pack_int_id].referenced_objects++;
 	}
@@ -1942,6 +1946,8 @@ static int fill_included_packs_batch(struct repository *r,
 			continue;
 		if (!pack_kept_objects && p->pack_keep)
 			continue;
+		if (p->is_cruft)
+			continue;
 		if (open_pack_index(p) || !p->num_objects)
 			continue;
 
diff --git a/t/t5319-multi-pack-index.sh b/t/t5319-multi-pack-index.sh
index afbe93f162..b5f9b10922 100755
--- a/t/t5319-multi-pack-index.sh
+++ b/t/t5319-multi-pack-index.sh
@@ -784,6 +784,70 @@ test_expect_success 'repack creates a new pack' '
 	)
 '
 
+test_expect_success 'repack (all) ignores cruft pack' '
+	git init repo &&
+	test_when_finished "rm -fr repo" &&
+	(
+		cd repo &&
+
+		test_commit base &&
+		test_commit --no-tag unreachable &&
+
+		git reset --hard base &&
+		git reflog expire --all --expire=all &&
+		git repack --cruft -d &&
+
+		git multi-pack-index write &&
+
+		find $objdir/pack | sort >before &&
+		git multi-pack-index repack --batch-size=0 &&
+		find $objdir/pack | sort >after &&
+
+		test_cmp before after
+	)
+'
+
+test_expect_success 'repack (--batch-size) ignores cruft pack' '
+	git init repo &&
+	test_when_finished "rm -fr repo" &&
+	(
+		cd repo &&
+
+		test_commit_bulk 5 &&
+		test_commit --no-tag unreachable &&
+
+		git reset --hard HEAD^ &&
+		git reflog expire --all --expire=all &&
+		git repack --cruft -d &&
+
+		test_commit four &&
+
+		find $objdir/pack -type f -name "*.pack" | sort >before &&
+		git repack -d &&
+		find $objdir/pack -type f -name "*.pack" | sort >after &&
+
+		pack="$(comm -13 before after)" &&
+		test_file_size "$pack" >sz &&
+		# Set --batch-size to twice the size of the pack created
+		# in the previous step, since this is enough to
+		# accommodate it and the cruft pack.
+		#
+		# This means that the MIDX machinery *could* combine the
+		# new and cruft packs together.
+		#
+		# We ensure that it does not below.
+		batch="$((($(cat sz) * 2)))" &&
+
+		git multi-pack-index write &&
+
+		find $objdir/pack | sort >before &&
+		git multi-pack-index repack --batch-size=$batch &&
+		find $objdir/pack | sort >after &&
+
+		test_cmp before after
+	)
+'
+
 test_expect_success 'expire removes repacked packs' '
 	(
 		cd dup &&
@@ -847,6 +911,36 @@ test_expect_success 'expire respects .keep files' '
 	)
 '
 
+test_expect_success 'expiring unreferenced cruft pack retains pack' '
+	git init repo &&
+	test_when_finished "rm -fr repo" &&
+	(
+		cd repo &&
+
+		test_commit base &&
+		test_commit --no-tag unreachable &&
+		unreachable=$(git rev-parse HEAD) &&
+
+		git reset --hard base &&
+		git reflog expire --all --expire=all &&
+		git repack --cruft -d &&
+		mtimes="$(ls $objdir/pack/pack-*.mtimes)" &&
+
+		echo "base..$unreachable" >in &&
+		pack="$(git pack-objects --revs --delta-base-offset \
+			$objdir/pack/pack <in)" &&
+
+		# Preferring the contents of "$pack" will leave the
+		# cruft pack unreferenced (ie., none of the objects
+		# contained in the cruft pack will have their MIDX copy
+		# selected from the cruft pack).
+		git multi-pack-index write --preferred-pack="pack-$pack.pack" &&
+		git multi-pack-index expire &&
+
+		test_path_is_file "$mtimes"
+	)
+'
+
 test_expect_success 'repack --batch-size=0 repacks everything' '
 	cp -r dup dup2 &&
 	(