gc: add `--expire-to` option

This commit extends the functionality of `git gc`
by adding a new option, `--expire-to=<dir>`. Previously,
this feature was implemented in 91badeba32 (builtin/repack.c:
implement `--expire-to` for storing pruned objects, 2022-10-24),
which allowing users to specify a directory where unreachable
and expired cruft packs are stored during garbage collection.
However, users had to run `git repack --cruft --expire-to=<dir>`
followed by `git prune` to achieve similar results within `git gc`.

By introducing `--expire-to=<dir>` directly into `git gc`,
we simplify the process for users who wish to manage their
repository's cleanup more efficiently. This change involves
passing the `--expire-to=<dir>` parameter through to `git repack`,
making it easier for users to set up a backup location for cruft
packs that will be pruned.

Due to the original `git gc --prune=now` deleting all unreachable
objects by passing the `-a` parameter to git repack. With the
addition of the `--cruft` and `--expire-to` options, it is necessary
to modify this default behavior: instead of deleting these
unreachable objects, they should be merged into a cruft pack and
collected in a specified directory. Therefore, we do not pass `-a`
to the repack command but instead pass `--cruft`, `--expire-to`,
and `--cruft-expiration=now` to repack.

Signed-off-by: ZheNing Hu <adlternative@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

3 files changed, 47 insertions, 2 deletions

diff --git a/Documentation/git-gc.txt b/Documentation/git-gc.txt
index 370e22faae..0eac8e85f0 100644
--- a/Documentation/git-gc.txt
+++ b/Documentation/git-gc.txt
@@ -69,6 +69,13 @@ be performed as well.
 	the `--max-cruft-size` option of linkgit:git-repack[1] for
 	more.
 
+--expire-to=<dir>::
+	When packing unreachable objects into a cruft pack, write a cruft
+	pack containing pruned objects (if any) to the directory `<dir>`.
+	This option only has an effect when used together with `--cruft`.
+	See the `--expire-to` option of linkgit:git-repack[1] for
+	more information.
+
 --prune=<date>::
 	Prune loose objects older than date (default is 2 weeks ago,
 	overridable by the config variable `gc.pruneExpire`).
diff --git a/builtin/gc.c b/builtin/gc.c
index d52735354c..8656e1caff 100644
--- a/builtin/gc.c
+++ b/builtin/gc.c
@@ -136,6 +136,7 @@ struct gc_config {
 	char *prune_worktrees_expire;
 	char *repack_filter;
 	char *repack_filter_to;
+	char *repack_expire_to;
 	unsigned long big_pack_threshold;
 	unsigned long max_delta_cache_size;
 };
@@ -432,7 +433,8 @@ static int keep_one_pack(struct string_list_item *item, void *data UNUSED)
 static void add_repack_all_option(struct gc_config *cfg,
 				  struct string_list *keep_pack)
 {
-	if (cfg->prune_expire && !strcmp(cfg->prune_expire, "now"))
+	if (cfg->prune_expire && !strcmp(cfg->prune_expire, "now")
+		&& !(cfg->cruft_packs && cfg->repack_expire_to))
 		strvec_push(&repack, "-a");
 	else if (cfg->cruft_packs) {
 		strvec_push(&repack, "--cruft");
@@ -441,6 +443,8 @@ static void add_repack_all_option(struct gc_config *cfg,
 		if (cfg->max_cruft_size)
 			strvec_pushf(&repack, "--max-cruft-size=%lu",
 				     cfg->max_cruft_size);
+		if (cfg->repack_expire_to)
+			strvec_pushf(&repack, "--expire-to=%s", cfg->repack_expire_to);
 	} else {
 		strvec_push(&repack, "-A");
 		if (cfg->prune_expire)
@@ -675,7 +679,6 @@ struct repository *repo UNUSED)
 	const char *prune_expire_sentinel = "sentinel";
 	const char *prune_expire_arg = prune_expire_sentinel;
 	int ret;
-
 	struct option builtin_gc_options[] = {
 		OPT__QUIET(&quiet, N_("suppress progress reporting")),
 		{ OPTION_STRING, 0, "prune", &prune_expire_arg, N_("date"),
@@ -694,6 +697,8 @@ struct repository *repo UNUSED)
 			   PARSE_OPT_NOCOMPLETE),
 		OPT_BOOL(0, "keep-largest-pack", &keep_largest_pack,
 			 N_("repack all other packs except the largest pack")),
+		OPT_STRING(0, "expire-to", &cfg.repack_expire_to, N_("dir"),
+			   N_("pack prefix to store a pack containing pruned objects")),
 		OPT_END()
 	};
 
diff --git a/t/t6500-gc.sh b/t/t6500-gc.sh
index ee074b99b7..74f7bd0904 100755
--- a/t/t6500-gc.sh
+++ b/t/t6500-gc.sh
@@ -339,6 +339,39 @@ test_expect_success 'gc.maxCruftSize sets appropriate repack options' '
 	test_subcommand $cruft_max_size_opts --max-cruft-size=3145728 <trace2.txt
 '
 
+test_expect_success '--expire-to sets repack --expire-to' '
+	rm -rf expired &&
+	mkdir expired &&
+	expire_to="$(pwd)/expired/pack" &&
+	GIT_TRACE2_EVENT=$(pwd)/trace2.txt git -C cruft--max-size gc --cruft --expire-to="$expire_to" &&
+	test_subcommand $cruft_max_size_opts --expire-to="$expire_to" <trace2.txt
+'
+
+test_expect_success '--expire-to with --prune=now sets repack --expire-to' '
+	rm -rf expired &&
+	mkdir expired &&
+	expire_to="$(pwd)/expired/pack" &&
+	GIT_TRACE2_EVENT=$(pwd)/trace2.txt git -C cruft--max-size gc --cruft --prune=now --expire-to="$expire_to" &&
+	test_subcommand git repack -d -l --cruft --cruft-expiration=now --expire-to="$expire_to" <trace2.txt
+'
+
+
+test_expect_success '--expire-to with --no-cruft sets repack -A' '
+	rm -rf expired &&
+	mkdir expired &&
+	expire_to="$(pwd)/expired/pack" &&
+	GIT_TRACE2_EVENT=$(pwd)/trace2.txt git -C cruft--max-size gc --no-cruft --expire-to="$expire_to" &&
+	test_subcommand git repack -d -l -A --unpack-unreachable=2.weeks.ago <trace2.txt
+'
+
+test_expect_success '--expire-to with --no-cruft sets repack -a' '
+	rm -rf expired &&
+	mkdir expired &&
+	expire_to="$(pwd)/expired/pack" &&
+	GIT_TRACE2_EVENT=$(pwd)/trace2.txt git -C cruft--max-size gc --no-cruft --prune=now --expire-to="$expire_to" &&
+	test_subcommand git repack -d -l -a <trace2.txt
+'
+
 run_and_wait_for_gc () {
 	# We read stdout from gc for the side effect of waiting until the
 	# background gc process exits, closing its fd 9.  Furthermore, the