[PATCH v3] gc: add `--expire-to` option

["ZheNing Hu via GitGitGadget" <gitgitgadget@gmail.com>]

From: ZheNing Hu <adlternative@gmail.com>

This commit extends the functionality of `git gc`
by adding a new option, `--expire-to=<dir>`. Previously,
this feature was implemented in `git repack` (see 91badeb),
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.

Note: When git-gc is used with both `--cruft` and `--expire-to`,
it does not pass `-a` to git-repack to delete all unreachable
objects as `git gc --prune=now` originally did. Instead, it
generates a cruft pack in the directory specified by expire-to.

Signed-off-by: ZheNing Hu <adlternative@gmail.com>
---
    gc: add --expire-to option
    
    I want to perform a "safe" garbage collection for the Git repository on
    the server, which avoids data corruption issues caused by concurrent
    pushes during git GC. To achieve this, I currently need to use git
    repack --cruft --expire-to=<dir> and git prune in combination. However,
    it would be simpler if we could directly use --expire-to=<dir> with the
    git-gc command.
    
    v1: add --expire-to option to gc v1 -> v2: fix git gc --prune=now with
    --expire-to v2 -> v3: squash two patch into one patch

Published-As: https://github.com/gitgitgadget/git/releases/tag/pr-1843%2Fadlternative%2Fzh%2Fgc-expire-to-v3
Fetch-It-Via: git fetch https://github.com/gitgitgadget/git pr-1843/adlternative/zh/gc-expire-to-v3
Pull-Request: https://github.com/gitgitgadget/git/pull/1843

Range-diff vs v2:

 1:  14e94bf04e5 ! 1:  0842ec34948 gc: add `--expire-to` option
     @@ Commit message
          making it easier for users to set up a backup location for cruft
          packs that will be pruned.
      
     +    Note: When git-gc is used with both `--cruft` and `--expire-to`,
     +    it does not pass `-a` to git-repack to delete all unreachable
     +    objects as `git gc --prune=now` originally did. Instead, it
     +    generates a cruft pack in the directory specified by expire-to.
     +
          Signed-off-by: ZheNing Hu <adlternative@gmail.com>
      
       ## Documentation/git-gc.txt ##
     @@ builtin/gc.c: struct gc_config {
       	unsigned long big_pack_threshold;
       	unsigned long max_delta_cache_size;
       };
     +@@ builtin/gc.c: 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");
      @@ builtin/gc.c: static void add_repack_all_option(struct gc_config *cfg,
       		if (cfg->max_cruft_size)
       			strvec_pushf(&repack, "--max-cruft-size=%lu",
 2:  579757957d2 < -:  ----------- fix(gc): make --prune=now compatible with --expire-to


 Documentation/git-gc.txt | 6 ++++++
 builtin/gc.c             | 9 +++++++--
 t/t6500-gc.sh            | 6 ++++++
 3 files changed, 19 insertions(+), 2 deletions(-)

diff --git a/Documentation/git-gc.txt b/Documentation/git-gc.txt
index 370e22faaeb..b4c0cf02972 100644
--- a/Documentation/git-gc.txt
+++ b/Documentation/git-gc.txt
@@ -69,6 +69,12 @@ 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>`.
+	See the `--expire-to` 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/builtin/gc.c b/builtin/gc.c
index d52735354c9..8656e1caff0 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 ee074b99b70..d4b0653a9b7 100755
--- a/t/t6500-gc.sh
+++ b/t/t6500-gc.sh
@@ -339,6 +339,12 @@ 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 appropriate repack options' '
+	mkdir expired &&
+	GIT_TRACE2_EVENT=$(pwd)/trace2.txt git -C cruft--max-size gc --cruft --expire-to=./expired/pack &&
+	test_subcommand $cruft_max_size_opts --expire-to=./expired/pack <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

base-commit: 92999a42db1c5f43f330e4f2bca4026b5b81576f
-- 
gitgitgadget