pack-objects: match prune logic for discarding objects

A recent commit taught git-prune to keep non-recent objects
that are reachable from recent ones. However, pack-objects,
when loosening unreachable objects, tries to optimize out
the write in the case that the object will be immediately
pruned. It now gets this wrong, since its rule does not
reflect the new prune code (and this can be seen by running
t6501 with a strategically placed repack).

Let's teach pack-objects similar logic.

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

1 files changed, 39 insertions, 0 deletions

diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index 2fe2ab0..4df9499 100644
--- a/builtin/pack-objects.c
+++ b/builtin/pack-objects.c
@@ -20,6 +20,8 @@
 #include "streaming.h"
 #include "thread-utils.h"
 #include "pack-bitmap.h"
+#include "reachable.h"
+#include "sha1-array.h"
 
 static const char *pack_usage[] = {
 	N_("git pack-objects --stdout [options...] [< ref-list | < object-list]"),
@@ -2407,6 +2409,15 @@ static int has_sha1_pack_kept_or_nonlocal(const unsigned char *sha1)
 	return 0;
 }
 
+/*
+ * Store a list of sha1s that are should not be discarded
+ * because they are either written too recently, or are
+ * reachable from another object that was.
+ *
+ * This is filled by get_object_list.
+ */
+static struct sha1_array recent_objects;
+
 static int loosened_object_can_be_discarded(const unsigned char *sha1,
 					    unsigned long mtime)
 {
@@ -2414,6 +2425,8 @@ static int loosened_object_can_be_discarded(const unsigned char *sha1,
 		return 0;
 	if (mtime > unpack_unreachable_expiration)
 		return 0;
+	if (sha1_array_lookup(&recent_objects, sha1) >= 0)
+		return 0;
 	return 1;
 }
 
@@ -2470,6 +2483,19 @@ static int get_object_list_from_bitmap(struct rev_info *revs)
 	return 0;
 }
 
+static void record_recent_object(struct object *obj,
+				 const struct name_path *path,
+				 const char *last,
+				 void *data)
+{
+	sha1_array_append(&recent_objects, obj->sha1);
+}
+
+static void record_recent_commit(struct commit *commit, void *data)
+{
+	sha1_array_append(&recent_objects, commit->object.sha1);
+}
+
 static void get_object_list(int ac, const char **av)
 {
 	struct rev_info revs;
@@ -2517,10 +2543,23 @@ static void get_object_list(int ac, const char **av)
 	mark_edges_uninteresting(&revs, show_edge);
 	traverse_commit_list(&revs, show_commit, show_object, NULL);
 
+	if (unpack_unreachable_expiration) {
+		revs.ignore_missing_links = 1;
+		if (add_unseen_recent_objects_to_traversal(&revs,
+				unpack_unreachable_expiration))
+			die("unable to add recent objects");
+		if (prepare_revision_walk(&revs))
+			die("revision walk setup failed");
+		traverse_commit_list(&revs, record_recent_commit,
+				     record_recent_object, NULL);
+	}
+
 	if (keep_unreachable)
 		add_objects_in_unpacked_packs(&revs);
 	if (unpack_unreachable)
 		loosen_unused_packed_objects(&revs);
+
+	sha1_array_clear(&recent_objects);
 }
 
 static int option_parse_index_version(const struct option *opt,