Merge branch 'tb/repack-max-cruft-size'

"git repack" learned "--max-cruft-size" to prevent cruft packs from
growing without bounds.

* tb/repack-max-cruft-size:
  repack: free existing_cruft array after use
  builtin/repack.c: avoid making cruft packs preferred
  builtin/repack.c: implement support for `--max-cruft-size`
  builtin/repack.c: parse `--max-pack-size` with OPT_MAGNITUDE
  t7700: split cruft-related tests to t7704

8 files changed, 645 insertions, 136 deletions

diff --git a/Documentation/config/gc.txt b/Documentation/config/gc.txt
index 466466d6cc..c6e3acc99d 100644
--- a/Documentation/config/gc.txt
+++ b/Documentation/config/gc.txt
@@ -86,6 +86,12 @@ gc.cruftPacks::
 	linkgit:git-repack[1]) instead of as loose objects. The default
 	is `true`.
 
+gc.maxCruftSize::
+	Limit the size of new cruft packs when repacking. When
+	specified in addition to `--max-cruft-size`, the command line
+	option takes priority. See the `--max-cruft-size` option of
+	linkgit:git-repack[1].
+
 gc.pruneExpire::
 	When 'git gc' is run, it will call 'prune --expire 2.weeks.ago'
 	(and 'repack --cruft --cruft-expiration 2.weeks.ago' if using
diff --git a/Documentation/git-gc.txt b/Documentation/git-gc.txt
index 90806fd26a..b5561c458a 100644
--- a/Documentation/git-gc.txt
+++ b/Documentation/git-gc.txt
@@ -59,6 +59,13 @@ be performed as well.
 	cruft pack instead of storing them as loose objects. `--cruft`
 	is on by default.
 
+--max-cruft-size=<n>::
+	When packing unreachable objects into a cruft pack, limit the
+	size of new cruft packs to be at most `<n>` bytes. Overrides any
+	value specified via the `gc.maxCruftSize` configuration. See
+	the `--max-cruft-size` option of linkgit:git-repack[1] for
+	more.
+
 --prune=<date>::
 	Prune loose objects older than date (default is 2 weeks ago,
 	overridable by the config variable `gc.pruneExpire`).
diff --git a/Documentation/git-repack.txt b/Documentation/git-repack.txt
index 8545a32667..893b8a2fea 100644
--- a/Documentation/git-repack.txt
+++ b/Documentation/git-repack.txt
@@ -74,6 +74,17 @@ to the new separate pack will be written.
 	immediately instead of waiting for the next `git gc` invocation.
 	Only useful with `--cruft -d`.
 
+--max-cruft-size=<n>::
+	Repack cruft objects into packs as large as `<n>` bytes before
+	creating new packs. As long as there are enough cruft packs
+	smaller than `<n>`, repacking will cause a new cruft pack to
+	be created containing objects from any combined cruft packs,
+	along with any new unreachable objects. Cruft packs larger than
+	`<n>` will not be modified. When the new cruft pack is larger
+	than `<n>` bytes, it will be split into multiple packs, all of
+	which are guaranteed to be at most `<n>` bytes in size. Only
+	useful with `--cruft -d`.
+
 --expire-to=<dir>::
 	Write a cruft pack containing pruned objects (if any) to the
 	directory `<dir>`. This option is useful for keeping a copy of
diff --git a/builtin/gc.c b/builtin/gc.c
index 68ca8d45bf..7c11d5ebef 100644
--- a/builtin/gc.c
+++ b/builtin/gc.c
@@ -52,6 +52,7 @@ static const char * const builtin_gc_usage[] = {
 static int pack_refs = 1;
 static int prune_reflogs = 1;
 static int cruft_packs = 1;
+static unsigned long max_cruft_size;
 static int aggressive_depth = 50;
 static int aggressive_window = 250;
 static int gc_auto_threshold = 6700;
@@ -165,6 +166,7 @@ static void gc_config(void)
 	git_config_get_int("gc.autopacklimit", &gc_auto_pack_limit);
 	git_config_get_bool("gc.autodetach", &detach_auto);
 	git_config_get_bool("gc.cruftpacks", &cruft_packs);
+	git_config_get_ulong("gc.maxcruftsize", &max_cruft_size);
 	git_config_get_expiry("gc.pruneexpire", &prune_expire);
 	git_config_get_expiry("gc.worktreepruneexpire", &prune_worktrees_expire);
 	git_config_get_expiry("gc.logexpiry", &gc_log_expire);
@@ -352,6 +354,9 @@ static void add_repack_all_option(struct string_list *keep_pack)
 		strvec_push(&repack, "--cruft");
 		if (prune_expire)
 			strvec_pushf(&repack, "--cruft-expiration=%s", prune_expire);
+		if (max_cruft_size)
+			strvec_pushf(&repack, "--max-cruft-size=%lu",
+				     max_cruft_size);
 	} else {
 		strvec_push(&repack, "-A");
 		if (prune_expire)
@@ -585,6 +590,8 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
 			N_("prune unreferenced objects"),
 			PARSE_OPT_OPTARG, NULL, (intptr_t)prune_expire },
 		OPT_BOOL(0, "cruft", &cruft_packs, N_("pack unreferenced objects separately")),
+		OPT_MAGNITUDE(0, "max-cruft-size", &max_cruft_size,
+			      N_("with --cruft, limit the size of new cruft packs")),
 		OPT_BOOL(0, "aggressive", &aggressive, N_("be more thorough (increased runtime)")),
 		OPT_BOOL_F(0, "auto", &auto_gc, N_("enable auto-gc mode"),
 			   PARSE_OPT_NOCOMPLETE),
diff --git a/builtin/repack.c b/builtin/repack.c
index db9277081d..edaee4dbec 100644
--- a/builtin/repack.c
+++ b/builtin/repack.c
@@ -28,6 +28,7 @@
 #define PACK_CRUFT 4
 
 #define DELETE_PACK 1
+#define RETAIN_PACK 2
 
 static int pack_everything;
 static int delta_base_offset = 1;
@@ -52,7 +53,7 @@ struct pack_objects_args {
 	const char *window_memory;
 	const char *depth;
 	const char *threads;
-	const char *max_pack_size;
+	unsigned long max_pack_size;
 	int no_reuse_delta;
 	int no_reuse_object;
 	int quiet;
@@ -118,11 +119,26 @@ static void pack_mark_for_deletion(struct string_list_item *item)
 	item->util = (void*)((uintptr_t)item->util | DELETE_PACK);
 }
 
+static void pack_unmark_for_deletion(struct string_list_item *item)
+{
+	item->util = (void*)((uintptr_t)item->util & ~DELETE_PACK);
+}
+
 static int pack_is_marked_for_deletion(struct string_list_item *item)
 {
 	return (uintptr_t)item->util & DELETE_PACK;
 }
 
+static void pack_mark_retained(struct string_list_item *item)
+{
+	item->util = (void*)((uintptr_t)item->util | RETAIN_PACK);
+}
+
+static int pack_is_retained(struct string_list_item *item)
+{
+	return (uintptr_t)item->util & RETAIN_PACK;
+}
+
 static void mark_packs_for_deletion_1(struct string_list *names,
 				      struct string_list *list)
 {
@@ -135,17 +151,39 @@ static void mark_packs_for_deletion_1(struct string_list *names,
 		if (len < hexsz)
 			continue;
 		sha1 = item->string + len - hexsz;
-		/*
-		 * Mark this pack for deletion, which ensures that this
-		 * pack won't be included in a MIDX (if `--write-midx`
-		 * was given) and that we will actually delete this pack
-		 * (if `-d` was given).
-		 */
-		if (!string_list_has_string(names, sha1))
+
+		if (pack_is_retained(item)) {
+			pack_unmark_for_deletion(item);
+		} else if (!string_list_has_string(names, sha1)) {
+			/*
+			 * Mark this pack for deletion, which ensures
+			 * that this pack won't be included in a MIDX
+			 * (if `--write-midx` was given) and that we
+			 * will actually delete this pack (if `-d` was
+			 * given).
+			 */
 			pack_mark_for_deletion(item);
+		}
 	}
 }
 
+static void retain_cruft_pack(struct existing_packs *existing,
+			      struct packed_git *cruft)
+{
+	struct strbuf buf = STRBUF_INIT;
+	struct string_list_item *item;
+
+	strbuf_addstr(&buf, pack_basename(cruft));
+	strbuf_strip_suffix(&buf, ".pack");
+
+	item = string_list_lookup(&existing->cruft_packs, buf.buf);
+	if (!item)
+		BUG("could not find cruft pack '%s'", pack_basename(cruft));
+
+	pack_mark_retained(item);
+	strbuf_release(&buf);
+}
+
 static void mark_packs_for_deletion(struct existing_packs *existing,
 				    struct string_list *names)
 
@@ -227,6 +265,8 @@ static void collect_pack_filenames(struct existing_packs *existing,
 	}
 
 	string_list_sort(&existing->kept_packs);
+	string_list_sort(&existing->non_kept_packs);
+	string_list_sort(&existing->cruft_packs);
 	strbuf_release(&buf);
 }
 
@@ -244,7 +284,7 @@ static void prepare_pack_objects(struct child_process *cmd,
 	if (args->threads)
 		strvec_pushf(&cmd->args, "--threads=%s", args->threads);
 	if (args->max_pack_size)
-		strvec_pushf(&cmd->args, "--max-pack-size=%s", args->max_pack_size);
+		strvec_pushf(&cmd->args, "--max-pack-size=%lu", args->max_pack_size);
 	if (args->no_reuse_delta)
 		strvec_pushf(&cmd->args, "--no-reuse-delta");
 	if (args->no_reuse_object)
@@ -317,6 +357,18 @@ static struct generated_pack_data *populate_pack_exts(const char *name)
 	return data;
 }
 
+static int has_pack_ext(const struct generated_pack_data *data,
+			const char *ext)
+{
+	int i;
+	for (i = 0; i < ARRAY_SIZE(exts); i++) {
+		if (strcmp(exts[i].name, ext))
+			continue;
+		return !!data->tempfiles[i];
+	}
+	BUG("unknown pack extension: '%s'", ext);
+}
+
 static void repack_promisor_objects(const struct pack_objects_args *args,
 				    struct string_list *names)
 {
@@ -734,6 +786,7 @@ static void midx_included_packs(struct string_list *include,
 
 static int write_midx_included_packs(struct string_list *include,
 				     struct pack_geometry *geometry,
+				     struct string_list *names,
 				     const char *refs_snapshot,
 				     int show_progress, int write_bitmaps)
 {
@@ -763,6 +816,38 @@ static int write_midx_included_packs(struct string_list *include,
 	if (preferred)
 		strvec_pushf(&cmd.args, "--preferred-pack=%s",
 			     pack_basename(preferred));
+	else if (names->nr) {
+		/* The largest pack was repacked, meaning that either
+		 * one or two packs exist depending on whether the
+		 * repository has a cruft pack or not.
+		 *
+		 * Select the non-cruft one as preferred to encourage
+		 * pack-reuse among packs containing reachable objects
+		 * over unreachable ones.
+		 *
+		 * (Note we could write multiple packs here if
+		 * `--max-pack-size` was given, but any one of them
+		 * will suffice, so pick the first one.)
+		 */
+		for_each_string_list_item(item, names) {
+			struct generated_pack_data *data = item->util;
+			if (has_pack_ext(data, ".mtimes"))
+				continue;
+
+			strvec_pushf(&cmd.args, "--preferred-pack=pack-%s.pack",
+				     item->string);
+			break;
+		}
+	} else {
+		/*
+		 * No packs were kept, and no packs were written. The
+		 * only thing remaining are .keep packs (unless
+		 * --pack-kept-objects was given).
+		 *
+		 * Set the `--preferred-pack` arbitrarily here.
+		 */
+		;
+	}
 
 	if (refs_snapshot)
 		strvec_pushf(&cmd.args, "--refs-snapshot=%s", refs_snapshot);
@@ -888,6 +973,73 @@ static int write_filtered_pack(const struct pack_objects_args *args,
 	return finish_pack_objects_cmd(&cmd, names, local);
 }
 
+static int existing_cruft_pack_cmp(const void *va, const void *vb)
+{
+	struct packed_git *a = *(struct packed_git **)va;
+	struct packed_git *b = *(struct packed_git **)vb;
+
+	if (a->pack_size < b->pack_size)
+		return -1;
+	if (a->pack_size > b->pack_size)
+		return 1;
+	return 0;
+}
+
+static void collapse_small_cruft_packs(FILE *in, size_t max_size,
+				       struct existing_packs *existing)
+{
+	struct packed_git **existing_cruft, *p;
+	struct strbuf buf = STRBUF_INIT;
+	size_t total_size = 0;
+	size_t existing_cruft_nr = 0;
+	size_t i;
+
+	ALLOC_ARRAY(existing_cruft, existing->cruft_packs.nr);
+
+	for (p = get_all_packs(the_repository); p; p = p->next) {
+		if (!(p->is_cruft && p->pack_local))
+			continue;
+
+		strbuf_reset(&buf);
+		strbuf_addstr(&buf, pack_basename(p));
+		strbuf_strip_suffix(&buf, ".pack");
+
+		if (!string_list_has_string(&existing->cruft_packs, buf.buf))
+			continue;
+
+		if (existing_cruft_nr >= existing->cruft_packs.nr)
+			BUG("too many cruft packs (found %"PRIuMAX", but knew "
+			    "of %"PRIuMAX")",
+			    (uintmax_t)existing_cruft_nr + 1,
+			    (uintmax_t)existing->cruft_packs.nr);
+		existing_cruft[existing_cruft_nr++] = p;
+	}
+
+	QSORT(existing_cruft, existing_cruft_nr, existing_cruft_pack_cmp);
+
+	for (i = 0; i < existing_cruft_nr; i++) {
+		size_t proposed;
+
+		p = existing_cruft[i];
+		proposed = st_add(total_size, p->pack_size);
+
+		if (proposed <= max_size) {
+			total_size = proposed;
+			fprintf(in, "-%s\n", pack_basename(p));
+		} else {
+			retain_cruft_pack(existing, p);
+			fprintf(in, "%s\n", pack_basename(p));
+		}
+	}
+
+	for (i = 0; i < existing->non_kept_packs.nr; i++)
+		fprintf(in, "-%s.pack\n",
+			existing->non_kept_packs.items[i].string);
+
+	strbuf_release(&buf);
+	free(existing_cruft);
+}
+
 static int write_cruft_pack(const struct pack_objects_args *args,
 			    const char *destination,
 			    const char *pack_prefix,
@@ -934,10 +1086,14 @@ static int write_cruft_pack(const struct pack_objects_args *args,
 	in = xfdopen(cmd.in, "w");
 	for_each_string_list_item(item, names)
 		fprintf(in, "%s-%s.pack\n", pack_prefix, item->string);
-	for_each_string_list_item(item, &existing->non_kept_packs)
-		fprintf(in, "-%s.pack\n", item->string);
-	for_each_string_list_item(item, &existing->cruft_packs)
-		fprintf(in, "-%s.pack\n", item->string);
+	if (args->max_pack_size && !cruft_expiration) {
+		collapse_small_cruft_packs(in, args->max_pack_size, existing);
+	} else {
+		for_each_string_list_item(item, &existing->non_kept_packs)
+			fprintf(in, "-%s.pack\n", item->string);
+		for_each_string_list_item(item, &existing->cruft_packs)
+			fprintf(in, "-%s.pack\n", item->string);
+	}
 	for_each_string_list_item(item, &existing->kept_packs)
 		fprintf(in, "%s.pack\n", item->string);
 	fclose(in);
@@ -990,6 +1146,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 				   PACK_CRUFT),
 		OPT_STRING(0, "cruft-expiration", &cruft_expiration, N_("approxidate"),
 				N_("with --cruft, expire objects older than this")),
+		OPT_MAGNITUDE(0, "max-cruft-size", &cruft_po_args.max_pack_size,
+				N_("with --cruft, limit the size of new cruft packs")),
 		OPT_BOOL('d', NULL, &delete_redundant,
 				N_("remove redundant packs, and run git-prune-packed")),
 		OPT_BOOL('f', NULL, &po_args.no_reuse_delta,
@@ -1017,7 +1175,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 				N_("limits the maximum delta depth")),
 		OPT_STRING(0, "threads", &po_args.threads, N_("n"),
 				N_("limits the maximum number of threads")),
-		OPT_STRING(0, "max-pack-size", &po_args.max_pack_size, N_("bytes"),
+		OPT_MAGNITUDE(0, "max-pack-size", &po_args.max_pack_size,
 				N_("maximum size of each packfile")),
 		OPT_PARSE_LIST_OBJECTS_FILTER(&po_args.filter_options),
 		OPT_BOOL(0, "pack-kept-objects", &pack_kept_objects,
@@ -1327,7 +1485,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 		struct string_list include = STRING_LIST_INIT_NODUP;
 		midx_included_packs(&include, &existing, &names, &geometry);
 
-		ret = write_midx_included_packs(&include, &geometry,
+		ret = write_midx_included_packs(&include, &geometry, &names,
 						refs_snapshot ? get_tempfile_path(refs_snapshot) : NULL,
 						show_progress, write_bitmaps > 0);
 
diff --git a/t/t6500-gc.sh b/t/t6500-gc.sh
index e412cf8daf..04acf22d93 100755
--- a/t/t6500-gc.sh
+++ b/t/t6500-gc.sh
@@ -327,6 +327,33 @@ test_expect_success 'gc.bigPackThreshold ignores cruft packs' '
 	)
 '
 
+cruft_max_size_opts="git repack -d -l --cruft --cruft-expiration=2.weeks.ago"
+
+test_expect_success 'setup for --max-cruft-size tests' '
+	git init cruft--max-size &&
+	(
+		cd cruft--max-size &&
+		prepare_cruft_history
+	)
+'
+
+test_expect_success '--max-cruft-size sets appropriate repack options' '
+	GIT_TRACE2_EVENT=$(pwd)/trace2.txt git -C cruft--max-size \
+		gc --cruft --max-cruft-size=1M &&
+	test_subcommand $cruft_max_size_opts --max-cruft-size=1048576 <trace2.txt
+'
+
+test_expect_success 'gc.maxCruftSize sets appropriate repack options' '
+	GIT_TRACE2_EVENT=$(pwd)/trace2.txt \
+		git -C cruft--max-size -c gc.maxCruftSize=2M gc --cruft &&
+	test_subcommand $cruft_max_size_opts --max-cruft-size=2097152 <trace2.txt &&
+
+	GIT_TRACE2_EVENT=$(pwd)/trace2.txt \
+		git -C cruft--max-size -c gc.maxCruftSize=2M gc --cruft \
+		--max-cruft-size=3M &&
+	test_subcommand $cruft_max_size_opts --max-cruft-size=3145728 <trace2.txt
+'
+
 run_and_wait_for_auto_gc () {
 	# We read stdout from gc for the side effect of waiting until the
 	# background gc process exits, closing its fd 9.  Furthermore, the
diff --git a/t/t7700-repack.sh b/t/t7700-repack.sh
index 48e92aa6f7..d2975e6c93 100755
--- a/t/t7700-repack.sh
+++ b/t/t7700-repack.sh
@@ -830,125 +830,4 @@ test_expect_success '-n overrides repack.updateServerInfo=true' '
 	test_server_info_missing
 '
 
-test_expect_success '--expire-to stores pruned objects (now)' '
-	git init expire-to-now &&
-	(
-		cd expire-to-now &&
-
-		git branch -M main &&
-
-		test_commit base &&
-
-		git checkout -b cruft &&
-		test_commit --no-tag cruft &&
-
-		git rev-list --objects --no-object-names main..cruft >moved.raw &&
-		sort moved.raw >moved.want &&
-
-		git rev-list --all --objects --no-object-names >expect.raw &&
-		sort expect.raw >expect &&
-
-		git checkout main &&
-		git branch -D cruft &&
-		git reflog expire --all --expire=all &&
-
-		git init --bare expired.git &&
-		git repack -d \
-			--cruft --cruft-expiration="now" \
-			--expire-to="expired.git/objects/pack/pack" &&
-
-		expired="$(ls expired.git/objects/pack/pack-*.idx)" &&
-		test_path_is_file "${expired%.idx}.mtimes" &&
-
-		# Since the `--cruft-expiration` is "now", the effective
-		# behavior is to move _all_ unreachable objects out to
-		# the location in `--expire-to`.
-		git show-index <$expired >expired.raw &&
-		cut -d" " -f2 expired.raw | sort >expired.objects &&
-		git rev-list --all --objects --no-object-names \
-			>remaining.objects &&
-
-		# ...in other words, the combined contents of this
-		# repository and expired.git should be the same as the
-		# set of objects we started with.
-		cat expired.objects remaining.objects | sort >actual &&
-		test_cmp expect actual &&
-
-		# The "moved" objects (i.e., those in expired.git)
-		# should be the same as the cruft objects which were
-		# expired in the previous step.
-		test_cmp moved.want expired.objects
-	)
-'
-
-test_expect_success '--expire-to stores pruned objects (5.minutes.ago)' '
-	git init expire-to-5.minutes.ago &&
-	(
-		cd expire-to-5.minutes.ago &&
-
-		git branch -M main &&
-
-		test_commit base &&
-
-		# Create two classes of unreachable objects, one which
-		# is older than 5 minutes (stale), and another which is
-		# newer (recent).
-		for kind in stale recent
-		do
-			git checkout -b $kind main &&
-			test_commit --no-tag $kind || return 1
-		done &&
-
-		git rev-list --objects --no-object-names main..stale >in &&
-		stale="$(git pack-objects $objdir/pack/pack <in)" &&
-		mtime="$(test-tool chmtime --get =-600 $objdir/pack/pack-$stale.pack)" &&
-
-		# expect holds the set of objects we expect to find in
-		# this repository after repacking
-		git rev-list --objects --no-object-names recent >expect.raw &&
-		sort expect.raw >expect &&
-
-		# moved.want holds the set of objects we expect to find
-		# in expired.git
-		git rev-list --objects --no-object-names main..stale >out &&
-		sort out >moved.want &&
-
-		git checkout main &&
-		git branch -D stale recent &&
-		git reflog expire --all --expire=all &&
-		git prune-packed &&
-
-		git init --bare expired.git &&
-		git repack -d \
-			--cruft --cruft-expiration=5.minutes.ago \
-			--expire-to="expired.git/objects/pack/pack" &&
-
-		# Some of the remaining objects in this repository are
-		# unreachable, so use `cat-file --batch-all-objects`
-		# instead of `rev-list` to get their names
-		git cat-file --batch-all-objects --batch-check="%(objectname)" \
-			>remaining.objects &&
-		sort remaining.objects >actual &&
-		test_cmp expect actual &&
-
-		(
-			cd expired.git &&
-
-			expired="$(ls objects/pack/pack-*.mtimes)" &&
-			test-tool pack-mtimes $(basename $expired) >out &&
-			cut -d" " -f1 out | sort >../moved.got &&
-
-			# Ensure that there are as many objects with the
-			# expected mtime as were moved to expired.git.
-			#
-			# In other words, ensure that the recorded
-			# mtimes of any moved objects was written
-			# correctly.
-			grep " $mtime$" out >matching &&
-			test_line_count = $(wc -l <../moved.want) matching
-		) &&
-		test_cmp moved.want moved.got
-	)
-'
-
 test_done
diff --git a/t/t7704-repack-cruft.sh b/t/t7704-repack-cruft.sh
new file mode 100755
index 0000000000..be3735dff0
--- /dev/null
+++ b/t/t7704-repack-cruft.sh
@@ -0,0 +1,414 @@
+#!/bin/sh
+
+test_description='git repack works correctly'
+
+. ./test-lib.sh
+
+objdir=.git/objects
+packdir=$objdir/pack
+
+test_expect_success '--expire-to stores pruned objects (now)' '
+	git init expire-to-now &&
+	(
+		cd expire-to-now &&
+
+		git branch -M main &&
+
+		test_commit base &&
+
+		git checkout -b cruft &&
+		test_commit --no-tag cruft &&
+
+		git rev-list --objects --no-object-names main..cruft >moved.raw &&
+		sort moved.raw >moved.want &&
+
+		git rev-list --all --objects --no-object-names >expect.raw &&
+		sort expect.raw >expect &&
+
+		git checkout main &&
+		git branch -D cruft &&
+		git reflog expire --all --expire=all &&
+
+		git init --bare expired.git &&
+		git repack -d \
+			--cruft --cruft-expiration="now" \
+			--expire-to="expired.git/objects/pack/pack" &&
+
+		expired="$(ls expired.git/objects/pack/pack-*.idx)" &&
+		test_path_is_file "${expired%.idx}.mtimes" &&
+
+		# Since the `--cruft-expiration` is "now", the effective
+		# behavior is to move _all_ unreachable objects out to
+		# the location in `--expire-to`.
+		git show-index <$expired >expired.raw &&
+		cut -d" " -f2 expired.raw | sort >expired.objects &&
+		git rev-list --all --objects --no-object-names \
+			>remaining.objects &&
+
+		# ...in other words, the combined contents of this
+		# repository and expired.git should be the same as the
+		# set of objects we started with.
+		cat expired.objects remaining.objects | sort >actual &&
+		test_cmp expect actual &&
+
+		# The "moved" objects (i.e., those in expired.git)
+		# should be the same as the cruft objects which were
+		# expired in the previous step.
+		test_cmp moved.want expired.objects
+	)
+'
+
+test_expect_success '--expire-to stores pruned objects (5.minutes.ago)' '
+	git init expire-to-5.minutes.ago &&
+	(
+		cd expire-to-5.minutes.ago &&
+
+		git branch -M main &&
+
+		test_commit base &&
+
+		# Create two classes of unreachable objects, one which
+		# is older than 5 minutes (stale), and another which is
+		# newer (recent).
+		for kind in stale recent
+		do
+			git checkout -b $kind main &&
+			test_commit --no-tag $kind || return 1
+		done &&
+
+		git rev-list --objects --no-object-names main..stale >in &&
+		stale="$(git pack-objects $objdir/pack/pack <in)" &&
+		mtime="$(test-tool chmtime --get =-600 $objdir/pack/pack-$stale.pack)" &&
+
+		# expect holds the set of objects we expect to find in
+		# this repository after repacking
+		git rev-list --objects --no-object-names recent >expect.raw &&
+		sort expect.raw >expect &&
+
+		# moved.want holds the set of objects we expect to find
+		# in expired.git
+		git rev-list --objects --no-object-names main..stale >out &&
+		sort out >moved.want &&
+
+		git checkout main &&
+		git branch -D stale recent &&
+		git reflog expire --all --expire=all &&
+		git prune-packed &&
+
+		git init --bare expired.git &&
+		git repack -d \
+			--cruft --cruft-expiration=5.minutes.ago \
+			--expire-to="expired.git/objects/pack/pack" &&
+
+		# Some of the remaining objects in this repository are
+		# unreachable, so use `cat-file --batch-all-objects`
+		# instead of `rev-list` to get their names
+		git cat-file --batch-all-objects --batch-check="%(objectname)" \
+			>remaining.objects &&
+		sort remaining.objects >actual &&
+		test_cmp expect actual &&
+
+		(
+			cd expired.git &&
+
+			expired="$(ls objects/pack/pack-*.mtimes)" &&
+			test-tool pack-mtimes $(basename $expired) >out &&
+			cut -d" " -f1 out | sort >../moved.got &&
+
+			# Ensure that there are as many objects with the
+			# expected mtime as were moved to expired.git.
+			#
+			# In other words, ensure that the recorded
+			# mtimes of any moved objects was written
+			# correctly.
+			grep " $mtime$" out >matching &&
+			test_line_count = $(wc -l <../moved.want) matching
+		) &&
+		test_cmp moved.want moved.got
+	)
+'
+
+generate_random_blob() {
+	test-tool genrandom "$@" >blob &&
+	git hash-object -w -t blob blob &&
+	rm blob
+}
+
+pack_random_blob () {
+	generate_random_blob "$@" &&
+	git repack -d -q >/dev/null
+}
+
+generate_cruft_pack () {
+	pack_random_blob "$@" >/dev/null &&
+
+	ls $packdir/pack-*.pack | xargs -n 1 basename >in &&
+	pack="$(git pack-objects --cruft $packdir/pack <in)" &&
+	git prune-packed &&
+
+	echo "$packdir/pack-$pack.mtimes"
+}
+
+test_expect_success '--max-cruft-size creates new packs when above threshold' '
+	git init max-cruft-size-large &&
+	(
+		cd max-cruft-size-large &&
+		test_commit base &&
+
+		foo="$(pack_random_blob foo $((1*1024*1024)))" &&
+		git repack --cruft -d &&
+		cruft_foo="$(ls $packdir/pack-*.mtimes)" &&
+
+		bar="$(pack_random_blob bar $((1*1024*1024)))" &&
+		git repack --cruft -d --max-cruft-size=1M &&
+		cruft_bar="$(ls $packdir/pack-*.mtimes | grep -v $cruft_foo)" &&
+
+		test-tool pack-mtimes $(basename "$cruft_foo") >foo.objects &&
+		test-tool pack-mtimes $(basename "$cruft_bar") >bar.objects &&
+
+		grep "^$foo" foo.objects &&
+		test_line_count = 1 foo.objects &&
+		grep "^$bar" bar.objects &&
+		test_line_count = 1 bar.objects
+	)
+'
+
+test_expect_success '--max-cruft-size combines existing packs when below threshold' '
+	git init max-cruft-size-small &&
+	(
+		cd max-cruft-size-small &&
+		test_commit base &&
+
+		foo="$(pack_random_blob foo $((1*1024*1024)))" &&
+		git repack --cruft -d &&
+
+		bar="$(pack_random_blob bar $((1*1024*1024)))" &&
+		git repack --cruft -d --max-cruft-size=10M &&
+
+		cruft=$(ls $packdir/pack-*.mtimes) &&
+		test-tool pack-mtimes $(basename "$cruft") >cruft.objects &&
+
+		grep "^$foo" cruft.objects &&
+		grep "^$bar" cruft.objects &&
+		test_line_count = 2 cruft.objects
+	)
+'
+
+test_expect_success '--max-cruft-size combines smaller packs first' '
+	git init max-cruft-size-consume-small &&
+	(
+		cd max-cruft-size-consume-small &&
+
+		test_commit base &&
+		git repack -ad &&
+
+		cruft_foo="$(generate_cruft_pack foo 524288)" &&    # 0.5 MiB
+		cruft_bar="$(generate_cruft_pack bar 524288)" &&    # 0.5 MiB
+		cruft_baz="$(generate_cruft_pack baz 1048576)" &&   # 1.0 MiB
+		cruft_quux="$(generate_cruft_pack quux 1572864)" && # 1.5 MiB
+
+		test-tool pack-mtimes "$(basename $cruft_foo)" >expect.raw &&
+		test-tool pack-mtimes "$(basename $cruft_bar)" >>expect.raw &&
+		sort expect.raw >expect.objects &&
+
+		# repacking with `--max-cruft-size=2M` should combine
+		# both 0.5 MiB packs together, instead of, say, one of
+		# the 0.5 MiB packs with the 1.0 MiB pack
+		ls $packdir/pack-*.mtimes | sort >cruft.before &&
+		git repack -d --cruft --max-cruft-size=2M &&
+		ls $packdir/pack-*.mtimes | sort >cruft.after &&
+
+		comm -13 cruft.before cruft.after >cruft.new &&
+		comm -23 cruft.before cruft.after >cruft.removed &&
+
+		test_line_count = 1 cruft.new &&
+		test_line_count = 2 cruft.removed &&
+
+		# the two smaller packs should be rolled up first
+		printf "%s\n" $cruft_foo $cruft_bar | sort >expect.removed &&
+		test_cmp expect.removed cruft.removed &&
+
+		# ...and contain the set of objects rolled up
+		test-tool pack-mtimes "$(basename $(cat cruft.new))" >actual.raw &&
+		sort actual.raw >actual.objects &&
+
+		test_cmp expect.objects actual.objects
+	)
+'
+
+test_expect_success 'setup --max-cruft-size with freshened objects' '
+	git init max-cruft-size-freshen &&
+	(
+		cd max-cruft-size-freshen &&
+
+		test_commit base &&
+		git repack -ad &&
+
+		foo="$(generate_random_blob foo 64)" &&
+		test-tool chmtime --get -10000 \
+			"$objdir/$(test_oid_to_path "$foo")" >foo.mtime &&
+
+		git repack --cruft -d &&
+
+		cruft="$(ls $packdir/pack-*.mtimes)" &&
+		test-tool pack-mtimes "$(basename $cruft)" >actual &&
+		echo "$foo $(cat foo.mtime)" >expect &&
+		test_cmp expect actual
+	)
+'
+
+test_expect_success '--max-cruft-size with freshened objects (loose)' '
+	(
+		cd max-cruft-size-freshen &&
+
+		# regenerate the object, setting its mtime to be more recent
+		foo="$(generate_random_blob foo 64)" &&
+		test-tool chmtime --get -100 \
+			"$objdir/$(test_oid_to_path "$foo")" >foo.mtime &&
+
+		git repack --cruft -d &&
+
+		cruft="$(ls $packdir/pack-*.mtimes)" &&
+		test-tool pack-mtimes "$(basename $cruft)" >actual &&
+		echo "$foo $(cat foo.mtime)" >expect &&
+		test_cmp expect actual
+	)
+'
+
+test_expect_success '--max-cruft-size with freshened objects (packed)' '
+	(
+		cd max-cruft-size-freshen &&
+
+		# regenerate the object and store it in a packfile,
+		# setting its mtime to be more recent
+		#
+		# store it alongside another cruft object so that we
+		# do not create an identical copy of the existing
+		# cruft pack (which contains $foo).
+		foo="$(generate_random_blob foo 64)" &&
+		bar="$(generate_random_blob bar 64)" &&
+		foo_pack="$(printf "%s\n" $foo $bar | git pack-objects $packdir/pack)" &&
+		git prune-packed &&
+
+		test-tool chmtime --get -10 \
+			"$packdir/pack-$foo_pack.pack" >foo.mtime &&
+
+		git repack --cruft -d &&
+
+		cruft="$(ls $packdir/pack-*.mtimes)" &&
+		test-tool pack-mtimes "$(basename $cruft)" >actual &&
+		echo "$foo $(cat foo.mtime)" >expect.raw &&
+		echo "$bar $(cat foo.mtime)" >>expect.raw &&
+		sort expect.raw >expect &&
+		test_cmp expect actual
+	)
+'
+
+test_expect_success '--max-cruft-size with pruning' '
+	git init max-cruft-size-prune &&
+	(
+		cd max-cruft-size-prune &&
+
+		test_commit base &&
+		foo="$(generate_random_blob foo $((1024*1024)))" &&
+		bar="$(generate_random_blob bar $((1024*1024)))" &&
+		baz="$(generate_random_blob baz $((1024*1024)))" &&
+
+		test-tool chmtime -10000 "$objdir/$(test_oid_to_path "$foo")" &&
+
+		git repack -d --cruft --max-cruft-size=1M &&
+
+		# backdate the mtimes of all cruft packs to validate
+		# that they were rewritten as a result of pruning
+		ls $packdir/pack-*.mtimes | sort >cruft.before &&
+		for cruft in $(cat cruft.before)
+		do
+			mtime="$(test-tool chmtime --get -10000 "$cruft")" &&
+			echo $cruft $mtime >>mtimes || return 1
+		done &&
+
+		# repack (and prune) with a --max-cruft-size to ensure
+		# that we appropriately split the resulting set of packs
+		git repack -d --cruft --max-cruft-size=1M \
+			--cruft-expiration=10.seconds.ago &&
+		ls $packdir/pack-*.mtimes | sort >cruft.after &&
+
+		for cruft in $(cat cruft.after)
+		do
+			old_mtime="$(grep $cruft mtimes | cut -d" " -f2)" &&
+			new_mtime="$(test-tool chmtime --get $cruft)" &&
+			test $old_mtime -lt $new_mtime || return 1
+		done &&
+
+		test_line_count = 3 cruft.before &&
+		test_line_count = 2 cruft.after &&
+		test_must_fail git cat-file -e $foo &&
+		git cat-file -e $bar &&
+		git cat-file -e $baz
+	)
+'
+
+test_expect_success '--max-cruft-size ignores non-local packs' '
+	repo="max-cruft-size-non-local" &&
+	git init $repo &&
+	(
+		cd $repo &&
+		test_commit base &&
+		generate_random_blob foo 64 &&
+		git repack --cruft -d
+	) &&
+
+	git clone --reference=$repo $repo $repo-alt &&
+	(
+		cd $repo-alt &&
+
+		test_commit other &&
+		generate_random_blob bar 64 &&
+
+		# ensure that we do not attempt to pick up packs from
+		# the non-alternated repository, which would result in a
+		# crash
+		git repack --cruft --max-cruft-size=1M -d
+	)
+'
+
+test_expect_success 'reachable packs are preferred over cruft ones' '
+	repo="cruft-preferred-packs" &&
+	git init "$repo" &&
+	(
+		cd "$repo" &&
+
+		# This test needs to exercise careful control over when a MIDX
+		# is and is not written. Unset the corresponding TEST variable
+		# accordingly.
+		sane_unset GIT_TEST_MULTI_PACK_INDEX &&
+
+		test_commit base &&
+		test_commit --no-tag cruft &&
+
+		non_cruft="$(echo base | git pack-objects --revs $packdir/pack)" &&
+		# Write a cruft pack which both (a) sorts ahead of the non-cruft
+		# pack in lexical order, and (b) has an older mtime to appease
+		# the MIDX preferred pack selection routine.
+		cruft="$(echo pack-$non_cruft.pack | git pack-objects --cruft $packdir/pack-A)" &&
+		test-tool chmtime -1000 $packdir/pack-A-$cruft.pack &&
+
+		test_commit other &&
+		git repack -d &&
+
+		git repack --geometric 2 -d --write-midx --write-bitmap-index &&
+
+		# After repacking, there are two packs left: one reachable one
+		# (which is the result of combining both of the existing two
+		# non-cruft packs), and one cruft pack.
+		find .git/objects/pack -type f -name "*.pack" >packs &&
+		test_line_count = 2 packs &&
+
+		# Make sure that the pack we just wrote is marked as preferred,
+		# not the cruft one.
+		pack="$(test-tool read-midx --preferred-pack $objdir)" &&
+		test_path_is_missing "$packdir/$(basename "$pack" ".idx").mtimes"
+	)
+'
+
+test_done