Merge branch 'jk/repack-keep-unreachable'

"git repack" learned the "--keep-unreachable" option, which sends
loose unreachable objects to a pack instead of leaving them loose.
This helps heuristics based on the number of loose objects
(e.g. "gc --auto").

* jk/repack-keep-unreachable:
  repack: extend --keep-unreachable to loose objects
  repack: add --keep-unreachable option
  repack: document --unpack-unreachable option

Documentation/git-repack.txt

@@ -128,6 +128,19 @@ other objects in that pack they already have locally.
 	with `-b` or `repack.writeBitmaps`, as it ensures that the
 	bitmapped packfile has the necessary objects.
 
+--unpack-unreachable=<when>::
+	When loosening unreachable objects, do not bother loosening any
+	objects older than `<when>`. This can be used to optimize out
+	the write of any objects that would be immediately pruned by
+	a follow-up `git prune`.
+
+-k::
+--keep-unreachable::
+	When used with `-ad`, any unreachable objects from existing
+	packs will be appended to the end of the packfile instead of
+	being removed. In addition, any unreachable loose objects will
+	be packed (and their loose counterparts removed).
+
 Configuration
 -------------
 

builtin/pack-objects.c

@@ -44,6 +44,7 @@ static int non_empty;
 static int reuse_delta = 1, reuse_object = 1;
 static int keep_unreachable, unpack_unreachable, include_tag;
 static unsigned long unpack_unreachable_expiration;
+static int pack_loose_unreachable;
 static int local;
 static int incremental;
 static int ignore_packed_keep;
@@ -2378,6 +2379,32 @@ static void add_objects_in_unpacked_packs(struct rev_info *revs)
 	free(in_pack.array);
 }
 
+static int add_loose_object(const unsigned char *sha1, const char *path,
+			    void *data)
+{
+	enum object_type type = sha1_object_info(sha1, NULL);
+
+	if (type < 0) {
+		warning("loose object at %s could not be examined", path);
+		return 0;
+	}
+
+	add_object_entry(sha1, type, "", 0);
+	return 0;
+}
+
+/*
+ * We actually don't even have to worry about reachability here.
+ * add_object_entry will weed out duplicates, so we just add every
+ * loose object we find.
+ */
+static void add_unreachable_loose_objects(void)
+{
+	for_each_loose_file_in_objdir(get_object_directory(),
+				      add_loose_object,
+				      NULL, NULL, NULL);
+}
+
 static int has_sha1_pack_kept_or_nonlocal(const unsigned char *sha1)
 {
 	static struct packed_git *last_found = (void *)1;
@@ -2547,6 +2574,8 @@ static void get_object_list(int ac, const char **av)
 
 	if (keep_unreachable)
 		add_objects_in_unpacked_packs(&revs);
+	if (pack_loose_unreachable)
+		add_unreachable_loose_objects();
 	if (unpack_unreachable)
 		loosen_unused_packed_objects(&revs);
 
@@ -2647,6 +2676,8 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 			 N_("include tag objects that refer to objects to be packed")),
 		OPT_BOOL(0, "keep-unreachable", &keep_unreachable,
 			 N_("keep unreachable objects")),
+		OPT_BOOL(0, "pack-loose-unreachable", &pack_loose_unreachable,
+			 N_("pack loose unreachable objects")),
 		{ OPTION_CALLBACK, 0, "unpack-unreachable", NULL, N_("time"),
 		  N_("unpack unreachable objects newer than <time>"),
 		  PARSE_OPT_OPTARG, option_parse_unpack_unreachable },

builtin/repack.c

@@ -146,6 +146,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	int pack_everything = 0;
 	int delete_redundant = 0;
 	const char *unpack_unreachable = NULL;
+	int keep_unreachable = 0;
 	const char *window = NULL, *window_memory = NULL;
 	const char *depth = NULL;
 	const char *max_pack_size = NULL;
@@ -175,6 +176,8 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 				N_("write bitmap index")),
 		OPT_STRING(0, "unpack-unreachable", &unpack_unreachable, N_("approxidate"),
 				N_("with -A, do not loosen objects older than this")),
+		OPT_BOOL('k', "keep-unreachable", &keep_unreachable,
+				N_("with -a, repack unreachable objects")),
 		OPT_STRING(0, "window", &window, N_("n"),
 				N_("size of the window used for delta compression")),
 		OPT_STRING(0, "window-memory", &window_memory, N_("bytes"),
@@ -196,6 +199,10 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	if (delete_redundant && repository_format_precious_objects)
 		die(_("cannot delete packs in a precious-objects repo"));
 
+	if (keep_unreachable &&
+	    (unpack_unreachable || (pack_everything & LOOSEN_UNREACHABLE)))
+		die(_("--keep-unreachable and -A are incompatible"));
+
 	if (pack_kept_objects < 0)
 		pack_kept_objects = write_bitmaps;
 
@@ -239,6 +246,9 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 			} else if (pack_everything & LOOSEN_UNREACHABLE) {
 				argv_array_push(&cmd.args,
 						"--unpack-unreachable");
+			} else if (keep_unreachable) {
+				argv_array_push(&cmd.args, "--keep-unreachable");
+				argv_array_push(&cmd.args, "--pack-loose-unreachable");
 			} else {
 				argv_array_push(&cmd.env_array, "GIT_REF_PARANOIA=1");
 			}

t/t7701-repack-unpack-unreachable.sh

@@ -122,4 +122,32 @@ test_expect_success 'keep packed objects found only in index' '
 	git cat-file blob :file
 '
 
+test_expect_success 'repack -k keeps unreachable packed objects' '
+	# create packed-but-unreachable object
+	sha1=$(echo unreachable-packed | git hash-object -w --stdin) &&
+	pack=$(echo $sha1 | git pack-objects .git/objects/pack/pack) &&
+	git prune-packed &&
+
+	# -k should keep it
+	git repack -adk &&
+	git cat-file -p $sha1 &&
+
+	# and double check that without -k it would have been removed
+	git repack -ad &&
+	test_must_fail git cat-file -p $sha1
+'
+
+test_expect_success 'repack -k packs unreachable loose objects' '
+	# create loose unreachable object
+	sha1=$(echo would-be-deleted-loose | git hash-object -w --stdin) &&
+	objpath=.git/objects/$(echo $sha1 | sed "s,..,&/,") &&
+	test_path_is_file $objpath &&
+
+	# and confirm that the loose object goes away, but we can
+	# still access it (ergo, it is packed)
+	git repack -adk &&
+	test_path_is_missing $objpath &&
+	git cat-file -p $sha1
+'
+
 test_done