builtin/gc.c: conditionally avoid pruning objects via loose

Expose the new `git repack --cruft` mode from `git gc` via a new opt-in
flag. When invoked like `git gc --cruft`, `git gc` will avoid exploding
unreachable objects as loose ones, and instead create a cruft pack and
`.mtimes` file.

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

Author: ttaylorr

Documentation/config/gc.txt

@@ -81,14 +81,21 @@ gc.packRefs::
 	to enable it within all non-bare repos or it can be set to a
 	boolean value.  The default is `true`.
 
+gc.cruftPacks::
+	Store unreachable objects in a cruft pack (see
+	linkgit:git-repack[1]) instead of as loose objects. The default
+	is `false`.
+
 gc.pruneExpire::
-	When 'git gc' is run, it will call 'prune --expire 2.weeks.ago'.
-	Override the grace period with this config variable.  The value
-	"now" may be used to disable this grace period and always prune
-	unreachable objects immediately, or "never" may be used to
-	suppress pruning.  This feature helps prevent corruption when
-	'git gc' runs concurrently with another process writing to the
-	repository; see the "NOTES" section of linkgit:git-gc[1].
+	When 'git gc' is run, it will call 'prune --expire 2.weeks.ago'
+	(and 'repack --cruft --cruft-expiration 2.weeks.ago' if using
+	cruft packs via `gc.cruftPacks` or `--cruft`).  Override the
+	grace period with this config variable.  The value "now" may be
+	used to disable this grace period and always prune unreachable
+	objects immediately, or "never" may be used to suppress pruning.
+	This feature helps prevent corruption when 'git gc' runs
+	concurrently with another process writing to the repository; see
+	the "NOTES" section of linkgit:git-gc[1].
 
 gc.worktreePruneExpire::
 	When 'git gc' is run, it calls

Documentation/git-gc.txt

@@ -54,6 +54,11 @@ other housekeeping tasks (e.g. rerere, working trees, reflog...) will
 be performed as well.
 
 
+--cruft::
+	When expiring unreachable objects, pack them separately into a
+	cruft pack instead of storing the loose objects as loose
+	objects.
+
 --prune=<date>::
 	Prune loose objects older than date (default is 2 weeks ago,
 	overridable by the config variable `gc.pruneExpire`).

builtin/gc.c

@@ -42,6 +42,7 @@ static const char * const builtin_gc_usage[] = {
 
 static int pack_refs = 1;
 static int prune_reflogs = 1;
+static int cruft_packs = 0;
 static int aggressive_depth = 50;
 static int aggressive_window = 250;
 static int gc_auto_threshold = 6700;
@@ -152,6 +153,7 @@ static void gc_config(void)
 	git_config_get_int("gc.auto", &gc_auto_threshold);
 	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_expiry("gc.pruneexpire", &prune_expire);
 	git_config_get_expiry("gc.worktreepruneexpire", &prune_worktrees_expire);
 	git_config_get_expiry("gc.logexpiry", &gc_log_expire);
@@ -331,7 +333,11 @@ static void add_repack_all_option(struct string_list *keep_pack)
 {
 	if (prune_expire && !strcmp(prune_expire, "now"))
 		strvec_push(&repack, "-a");
-	else {
+	else if (cruft_packs) {
+		strvec_push(&repack, "--cruft");
+		if (prune_expire)
+			strvec_pushf(&repack, "--cruft-expiration=%s", prune_expire);
+	} else {
 		strvec_push(&repack, "-A");
 		if (prune_expire)
 			strvec_pushf(&repack, "--unpack-unreachable=%s", prune_expire);
@@ -551,6 +557,7 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
 		{ OPTION_STRING, 0, "prune", &prune_expire, N_("date"),
 			N_("prune unreferenced objects"),
 			PARSE_OPT_OPTARG, NULL, (intptr_t)prune_expire },
+		OPT_BOOL(0, "cruft", &cruft_packs, N_("pack unreferenced objects separately")),
 		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),
@@ -670,6 +677,7 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
 			die(FAILED_RUN, repack.v[0]);
 
 		if (prune_expire) {
+			/* run `git prune` even if using cruft packs */
 			strvec_push(&prune, prune_expire);
 			if (quiet)
 				strvec_push(&prune, "--no-progress");

t/t5329-pack-objects-cruft.sh

@@ -429,6 +429,43 @@ test_expect_success 'loose objects mtimes upsert others' '
 	)
 '
 
+test_expect_success 'expiring cruft objects with git gc' '
+	git init repo &&
+	test_when_finished "rm -fr repo" &&
+	(
+		cd repo &&
+
+		test_commit reachable &&
+		git branch -M main &&
+		git checkout --orphan other &&
+		test_commit unreachable &&
+
+		git checkout main &&
+		git branch -D other &&
+		git tag -d unreachable &&
+		# objects are not cruft if they are contained in the reflogs
+		git reflog expire --all --expire=all &&
+
+		git rev-list --objects --all --no-object-names >reachable.raw &&
+		git cat-file --batch-all-objects --batch-check="%(objectname)" >objects &&
+		sort <reachable.raw >reachable &&
+		comm -13 reachable objects >unreachable &&
+
+		git repack --cruft -d &&
+
+		mtimes=$(ls .git/objects/pack/pack-*.mtimes) &&
+		test_path_is_file $mtimes &&
+
+		git gc --cruft --prune=now &&
+
+		git cat-file --batch-all-objects --batch-check="%(objectname)" >objects &&
+
+		comm -23 unreachable objects >removed &&
+		test_cmp unreachable removed &&
+		test_path_is_missing $mtimes
+	)
+'
+
 test_expect_success 'cruft packs are not included in geometric repack' '
 	git init repo &&
 	test_when_finished "rm -fr repo" &&