fsck: introduce `git fsck --connectivity-only`

This option avoids unpacking each and all blob objects, and just
verifies the connectivity. In particular with large repositories, this
speeds up the operation, at the expense of missing corrupt blobs,
ignoring unreachable objects and other fsck issues, if any.

Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Documentation/git-fsck.txt

@@ -11,7 +11,7 @@ SYNOPSIS
 [verse]
 'git fsck' [--tags] [--root] [--unreachable] [--cache] [--no-reflogs]
 	 [--[no-]full] [--strict] [--verbose] [--lost-found]
-	 [--[no-]dangling] [--[no-]progress] [<object>*]
+	 [--[no-]dangling] [--[no-]progress] [--connectivity-only] [<object>*]
 
 DESCRIPTION
 -----------
@@ -60,6 +60,11 @@ index file, all SHA-1 references in `refs` namespace, and all reflogs
 	object pools.  This is now default; you can turn it off
 	with --no-full.
 
+--connectivity-only::
+	Check only the connectivity of tags, commits and tree objects. By
+	avoiding to unpack blobs, this speeds up the operation, at the
+	expense of missing corrupt objects or other problematic issues.
+
 --strict::
 	Enable more strict checking, namely to catch a file mode
 	recorded with g+w bit set, which was created by older

builtin/fsck.c

@@ -23,6 +23,7 @@ static int show_tags;
 static int show_unreachable;
 static int include_reflogs = 1;
 static int check_full = 1;
+static int connectivity_only;
 static int check_strict;
 static int keep_cache_objects;
 static struct fsck_options fsck_walk_options = FSCK_OPTIONS_DEFAULT;
@@ -181,6 +182,8 @@ static void check_reachable_object(struct object *obj)
 	if (!(obj->flags & HAS_OBJ)) {
 		if (has_sha1_pack(obj->sha1))
 			return; /* it is in pack - forget about it */
+		if (connectivity_only && has_sha1_file(obj->sha1))
+			return;
 		printf("missing %s %s\n", typename(obj->type), sha1_to_hex(obj->sha1));
 		errors_found |= ERROR_REACHABLE;
 		return;
@@ -617,6 +620,7 @@ static struct option fsck_opts[] = {
 	OPT_BOOL(0, "cache", &keep_cache_objects, N_("make index objects head nodes")),
 	OPT_BOOL(0, "reflogs", &include_reflogs, N_("make reflogs head nodes (default)")),
 	OPT_BOOL(0, "full", &check_full, N_("also consider packs and alternate objects")),
+	OPT_BOOL(0, "connectivity-only", &connectivity_only, N_("check only connectivity")),
 	OPT_BOOL(0, "strict", &check_strict, N_("enable more strict checking")),
 	OPT_BOOL(0, "lost-found", &write_lost_and_found,
 				N_("write dangling objects in .git/lost-found")),
@@ -653,7 +657,8 @@ int cmd_fsck(int argc, const char **argv, const char *prefix)
 	git_config(fsck_config, NULL);
 
 	fsck_head_link();
-	fsck_object_dir(get_object_directory());
+	if (!connectivity_only)
+		fsck_object_dir(get_object_directory());
 
 	prepare_alt_odb();
 	for (alt = alt_odb_list; alt; alt = alt->next) {

t/t1450-fsck.sh

@@ -431,4 +431,26 @@ test_expect_success 'fsck notices ref pointing to missing tag' '
 	test_must_fail git -C missing fsck
 '
 
+test_expect_success 'fsck --connectivity-only' '
+	rm -rf connectivity-only &&
+	git init connectivity-only &&
+	(
+		cd connectivity-only &&
+		touch empty &&
+		git add empty &&
+		test_commit empty &&
+		empty=.git/objects/e6/9de29bb2d1d6434b8b29ae775ad8c2e48c5391 &&
+		rm -f $empty &&
+		echo invalid >$empty &&
+		test_must_fail git fsck --strict &&
+		git fsck --strict --connectivity-only &&
+		tree=$(git rev-parse HEAD:) &&
+		suffix=${tree#??} &&
+		tree=.git/objects/${tree%$suffix}/$suffix &&
+		rm -f $tree &&
+		echo invalid >$tree &&
+		test_must_fail git fsck --strict --connectivity-only
+	)
+'
+
 test_done