gc: add gc.bigPackThreshold config

The --keep-largest-pack option is not very convenient to use because
you need to tell gc to do this explicitly (and probably on just a few
large repos).

Add a config key that enables this mode when packs larger than a limit
are found. Note that there's a slight behavior difference compared to
--keep-largest-pack: all packs larger than the threshold are kept, not
just the largest one.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Documentation/config.txt

@@ -1558,6 +1558,13 @@ gc.autoDetach::
 	Make `git gc --auto` return immediately and run in background
 	if the system supports it. Default is true.
 
+gc.bigPackThreshold::
+	If non-zero, all packs larger than this limit are kept when
+	`git gc` is run. This is very similar to `--keep-base-pack`
+	except that all packs that meet the threshold are kept, not
+	just the base pack. Defaults to zero. Common unit suffixes of
+	'k', 'm', or 'g' are supported.
+
 gc.logExpiry::
 	If the file gc.log exists, then `git gc --auto` won't run
 	unless that file is more than 'gc.logExpiry' old.  Default is

Documentation/git-gc.txt

@@ -56,7 +56,8 @@ single pack using `git repack -d -l`.  Setting the value of `gc.auto`
 to 0 disables automatic packing of loose objects.
 +
 If the number of packs exceeds the value of `gc.autoPackLimit`,
-then existing packs (except those marked with a `.keep` file)
+then existing packs (except those marked with a `.keep` file
+or over `gc.bigPackThreshold` limit)
 are consolidated into a single pack by using the `-A` option of
 'git repack'. Setting `gc.autoPackLimit` to 0 disables
 automatic consolidation of packs.
@@ -86,7 +87,8 @@ be performed as well.
 
 --keep-largest-pack::
 	All packs except the largest pack and those marked with a
-	`.keep` files are consolidated into a single pack.
+	`.keep` files are consolidated into a single pack. When this
+	option is used, `gc.bigPackThreshold` is ignored.
 
 Configuration
 -------------

builtin/gc.c

@@ -41,6 +41,7 @@ static timestamp_t gc_log_expire_time;
 static const char *gc_log_expire = "1.day.ago";
 static const char *prune_expire = "2.weeks.ago";
 static const char *prune_worktrees_expire = "3.months.ago";
+static unsigned long big_pack_threshold;
 
 static struct argv_array pack_refs_cmd = ARGV_ARRAY_INIT;
 static struct argv_array reflog = ARGV_ARRAY_INIT;
@@ -128,6 +129,8 @@ static void gc_config(void)
 	git_config_get_expiry("gc.worktreepruneexpire", &prune_worktrees_expire);
 	git_config_get_expiry("gc.logexpiry", &gc_log_expire);
 
+	git_config_get_ulong("gc.bigpackthreshold", &big_pack_threshold);
+
 	git_config(git_default_config, NULL);
 }
 
@@ -166,14 +169,17 @@ static int too_many_loose_objects(void)
 	return needed;
 }
 
-static void find_base_packs(struct string_list *packs)
+static void find_base_packs(struct string_list *packs, unsigned long limit)
 {
 	struct packed_git *p, *base = NULL;
 
 	for (p = get_packed_git(the_repository); p; p = p->next) {
 		if (!p->pack_local)
 			continue;
-		if (!base || base->pack_size < p->pack_size) {
+		if (limit) {
+			if (p->pack_size >= limit)
+				string_list_append(packs, p->pack_name);
+		} else if (!base || base->pack_size < p->pack_size) {
 			base = p;
 		}
 	}
@@ -244,9 +250,15 @@ static int need_to_gc(void)
 	 * we run "repack -A -d -l".  Otherwise we tell the caller
 	 * there is no need.
 	 */
-	if (too_many_packs())
-		add_repack_all_option(NULL);
-	else if (too_many_loose_objects())
+	if (too_many_packs()) {
+		struct string_list keep_pack = STRING_LIST_INIT_NODUP;
+
+		if (big_pack_threshold)
+			find_base_packs(&keep_pack, big_pack_threshold);
+
+		add_repack_all_option(&keep_pack);
+		string_list_clear(&keep_pack, 0);
+	} else if (too_many_loose_objects())
 		add_repack_incremental_option();
 	else
 		return 0;
@@ -464,7 +476,9 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
 
 		if (keep_base_pack != -1) {
 			if (keep_base_pack)
-				find_base_packs(&keep_pack);
+				find_base_packs(&keep_pack, 0);
+		} else if (big_pack_threshold) {
+			find_base_packs(&keep_pack, big_pack_threshold);
 		}
 
 		add_repack_all_option(&keep_pack);