[PATCH v4 3/7] gc: add --keep-largest-pack option

From

Nguyễn Thái Ngọc Duy <pclouds@gmail.com>

Date

Mar 24, 2018, 07:42 UTC

Message-ID

<20180324074308.18934-6-pclouds@gmail.com>

In-Reply-To

<20180324074308.18934-1-pclouds@gmail.com>

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 Documentation/git-gc.txt |  6 ++++-
 builtin/gc.c             | 47 ++++++++++++++++++++++++++++++++++++----
 t/t6500-gc.sh            | 25 +++++++++++++++++++++
 3 files changed, 73 insertions(+), 5 deletions(-)

diff --git a/Documentation/git-gc.txt b/Documentation/git-gc.txt
index 571b5a7e3c..bf81b8de30 100644
--- a/Documentation/git-gc.txt
+++ b/Documentation/git-gc.txt
@@ -9,7 +9,7 @@ git-gc - Cleanup unnecessary files and optimize the local repository
 SYNOPSIS
 --------
 [verse]
-'git gc' [--aggressive] [--auto] [--quiet] [--prune=<date> | --no-prune] [--force]
+'git gc' [--aggressive] [--auto] [--quiet] [--prune=<date> | --no-prune] [--force] [--keep-largest-pack]
 
 DESCRIPTION
 -----------
@@ -78,6 +78,10 @@ automatic consolidation of packs.
 	Force `git gc` to run even if there may be another `git gc`
 	instance running on this repository.
 
+--keep-largest-pack::
+	All packs except the largest pack and those marked with a
+	`.keep` files are consolidated into a single pack.
+
 Configuration
 -------------
 
diff --git a/builtin/gc.c b/builtin/gc.c
index 77fa720bd0..9a09cf53b0 100644
--- a/builtin/gc.c
+++ b/builtin/gc.c
@@ -164,6 +164,24 @@ static int too_many_loose_objects(void)
 	return needed;
 }
 
+static void find_base_packs(struct string_list *packs)
+{
+	struct packed_git *p, *base = NULL;
+
+	prepare_packed_git();
+
+	for (p = packed_git; p; p = p->next) {
+		if (!p->pack_local)
+			continue;
+		if (!base || base->pack_size < p->pack_size) {
+			base = p;
+		}
+	}
+
+	if (base)
+		string_list_append(packs, base->pack_name);
+}
+
 static int too_many_packs(void)
 {
 	struct packed_git *p;
@@ -187,7 +205,13 @@ static int too_many_packs(void)
 	return gc_auto_pack_limit < cnt;
 }
 
-static void add_repack_all_option(void)
+static int keep_one_pack(struct string_list_item *item, void *data)
+{
+	argv_array_pushf(&repack, "--keep-pack=%s", basename(item->string));
+	return 0;
+}
+
+static void add_repack_all_option(struct string_list *keep_pack)
 {
 	if (prune_expire && !strcmp(prune_expire, "now"))
 		argv_array_push(&repack, "-a");
@@ -196,6 +220,9 @@ static void add_repack_all_option(void)
 		if (prune_expire)
 			argv_array_pushf(&repack, "--unpack-unreachable=%s", prune_expire);
 	}
+
+	if (keep_pack)
+		for_each_string_list(keep_pack, keep_one_pack, NULL);
 }
 
 static void add_repack_incremental_option(void)
@@ -219,7 +246,7 @@ static int need_to_gc(void)
 	 * there is no need.
 	 */
 	if (too_many_packs())
-		add_repack_all_option();
+		add_repack_all_option(NULL);
 	else if (too_many_loose_objects())
 		add_repack_incremental_option();
 	else
@@ -353,6 +380,7 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
 	const char *name;
 	pid_t pid;
 	int daemonized = 0;
+	int keep_base_pack = -1;
 
 	struct option builtin_gc_options[] = {
 		OPT__QUIET(&quiet, N_("suppress progress reporting")),
@@ -362,6 +390,8 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
 		OPT_BOOL(0, "aggressive", &aggressive, N_("be more thorough (increased runtime)")),
 		OPT_BOOL(0, "auto", &auto_gc, N_("enable auto-gc mode")),
 		OPT_BOOL(0, "force", &force, N_("force running gc even if there may be another gc running")),
+		OPT_BOOL(0, "keep-largest-pack", &keep_base_pack,
+			 N_("repack all other packs except the largest pack")),
 		OPT_END()
 	};
 
@@ -427,8 +457,17 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
 			 */
 			daemonized = !daemonize();
 		}
-	} else
-		add_repack_all_option();
+	} else {
+		struct string_list keep_pack = STRING_LIST_INIT_NODUP;
+
+		if (keep_base_pack != -1) {
+			if (keep_base_pack)
+				find_base_packs(&keep_pack);
+		}
+
+		add_repack_all_option(&keep_pack);
+		string_list_clear(&keep_pack, 0);
+	}
 
 	name = lock_repo_for_gc(force, &pid);
 	if (name) {
diff --git a/t/t6500-gc.sh b/t/t6500-gc.sh
index 41b0be575d..a95969af2a 100755
--- a/t/t6500-gc.sh
+++ b/t/t6500-gc.sh
@@ -43,6 +43,31 @@ test_expect_success 'gc is not aborted due to a stale symref' '
 	)
 '
 
+test_expect_success 'gc --keep-largest-pack' '
+	test_create_repo keep-pack &&
+	(
+		cd keep-pack &&
+		test_commit one &&
+		test_commit two &&
+		test_commit three &&
+		git gc &&
+		( cd .git/objects/pack && ls *.pack ) >pack-list &&
+		test_line_count = 1 pack-list &&
+		BASE_PACK=.git/objects/pack/pack-*.pack &&
+		test_commit four &&
+		git repack -d &&
+		test_commit five &&
+		git repack -d &&
+		( cd .git/objects/pack && ls *.pack ) >pack-list &&
+		test_line_count = 3 pack-list &&
+		git gc --keep-largest-pack &&
+		( cd .git/objects/pack && ls *.pack ) >pack-list &&
+		test_line_count = 2 pack-list &&
+		test_path_is_file $BASE_PACK &&
+		git fsck
+	)
+'
+
 test_expect_success 'auto gc with too many loose objects does not attempt to create bitmaps' '
 	test_config gc.auto 3 &&
 	test_config gc.autodetach false &&

-- 
2.17.0.rc0.348.gd5a49e0b6f