repack: extend --keep-unreachable to loose objects

If you use "repack -adk" currently, we will pack all objects
that are already packed into the new pack, and then drop the
old packs. However, loose unreachable objects will be left
as-is. In theory these are meant to expire eventually with
"git prune". But if you are using "repack -k", you probably
want to keep things forever and therefore do not run "git
prune" at all. Meaning those loose objects may build up over
time and end up fooling any object-count heuristics (such as
the one done by "gc --auto", though since git-gc does not
support "repack -k", this really applies to whatever custom
scripts people might have driving "repack -k").

With this patch, we instead stuff any loose unreachable
objects into the pack along with the already-packed
unreachable objects. This may seem wasteful, but it is
really no more so than using "repack -k" in the first place.
We are at a slight disadvantage, in that we have no useful
ordering for the result, or names to hand to the delta code.
However, this is again no worse than what "repack -k" is
already doing for the packed objects. The packing of these
objects doesn't matter much because they should not be
accessed frequently (unless they actually _do_ become
referenced, but then they would get moved to a different
part of the packfile during the next repack).

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 31 insertions, 0 deletions

diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index 8f5e358e22..a2f8cfdec0 100644
--- a/builtin/pack-objects.c
+++ b/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 },