reachable: only mark local objects as recentjk/reachable-recent-local-only

When pruning and repacking a repository that has an
alternate object store configured, we may traverse a large
number of objects in the alternate. This serves no purpose,
and may be expensive to do. A longer explanation is below.

Commits d3038d2 and abcb865 taught prune and pack-objects
(respectively) to treat "recent" objects as tips for
reachability, so that we keep whole chunks of history. They
built on the object traversal in 660c889 (sha1_file: add
for_each iterators for loose and packed objects,
2014-10-15), which covers both local and alternate objects.

In both cases, covering alternate objects is unnecessary, as
both commands can only drop objects from the local
repository. In the case of prune, we traverse only the local
object directory. And in the case of repacking, while we may
or may not include local objects in our pack, we will never
reach into the alternate with "repack -d". The "-l" option
is only a question of whether we are migrating objects from
the alternate into our repository, or leaving them
untouched.

It is possible that we may drop an object that is depended
upon by another object in the alternate. For example,
imagine two repositories, A and B, with A pointing to B as
an alternate. Now imagine a commit that is in B which
references a tree that is only in A. Traversing from recent
objects in B might prevent A from dropping that tree. But
this case isn't worth covering. Repo B should take
responsibility for its own objects. It would never have had
the commit in the first place if it did not also have the
tree, and assuming it is using the same "keep recent chunks
of history" scheme, then it would itself keep the tree, as
well.

So checking the alternate objects is not worth doing, and
come with a significant performance impact. In both cases,
we skip any recent objects that have already been marked
SEEN (i.e., that we know are already reachable for prune, or
included in the pack for a repack). So there is a slight
waste of time in opening the alternate packs at all, only to
notice that we have already considered each object. But much
worse, the alternate repository may have a large number of
objects that are not reachable from the local repository at
all, and we end up adding them to the traversal.

We can fix this by considering only local unseen objects.

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

3 files changed, 16 insertions, 7 deletions

diff --git a/cache.h b/cache.h
index 22b7b81290..fcfed2994b 100644
--- a/cache.h
+++ b/cache.h
@@ -1279,14 +1279,16 @@ int for_each_loose_file_in_objdir(const char *path,
 
 /*
  * Iterate over loose and packed objects in both the local
- * repository and any alternates repositories.
+ * repository and any alternates repositories (unless the
+ * LOCAL_ONLY flag is set).
  */
+#define FOR_EACH_OBJECT_LOCAL_ONLY 0x1
 typedef int each_packed_object_fn(const unsigned char *sha1,
 				  struct packed_git *pack,
 				  uint32_t pos,
 				  void *data);
-extern int for_each_loose_object(each_loose_object_fn, void *);
-extern int for_each_packed_object(each_packed_object_fn, void *);
+extern int for_each_loose_object(each_loose_object_fn, void *, unsigned flags);
+extern int for_each_packed_object(each_packed_object_fn, void *, unsigned flags);
 
 struct object_info {
 	/* Request */
diff --git a/reachable.c b/reachable.c
index a647267ae9..69fa6851da 100644
--- a/reachable.c
+++ b/reachable.c
@@ -142,10 +142,12 @@ int add_unseen_recent_objects_to_traversal(struct rev_info *revs,
 	data.revs = revs;
 	data.timestamp = timestamp;
 
-	r = for_each_loose_object(add_recent_loose, &data);
+	r = for_each_loose_object(add_recent_loose, &data,
+				  FOR_EACH_OBJECT_LOCAL_ONLY);
 	if (r)
 		return r;
-	return for_each_packed_object(add_recent_packed, &data);
+	return for_each_packed_object(add_recent_packed, &data,
+				      FOR_EACH_OBJECT_LOCAL_ONLY);
 }
 
 void mark_reachable_objects(struct rev_info *revs, int mark_reflog,
diff --git a/sha1_file.c b/sha1_file.c
index d7f1838c13..5d5e117249 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -3401,7 +3401,7 @@ static int loose_from_alt_odb(struct alternate_object_database *alt,
 					     data->data);
 }
 
-int for_each_loose_object(each_loose_object_fn cb, void *data)
+int for_each_loose_object(each_loose_object_fn cb, void *data, unsigned flags)
 {
 	struct loose_alt_odb_data alt;
 	int r;
@@ -3411,6 +3411,9 @@ int for_each_loose_object(each_loose_object_fn cb, void *data)
 	if (r)
 		return r;
 
+	if (flags & FOR_EACH_OBJECT_LOCAL_ONLY)
+		return 0;
+
 	alt.cb = cb;
 	alt.data = data;
 	return foreach_alt_odb(loose_from_alt_odb, &alt);
@@ -3435,13 +3438,15 @@ static int for_each_object_in_pack(struct packed_git *p, each_packed_object_fn c
 	return r;
 }
 
-int for_each_packed_object(each_packed_object_fn cb, void *data)
+int for_each_packed_object(each_packed_object_fn cb, void *data, unsigned flags)
 {
 	struct packed_git *p;
 	int r = 0;
 
 	prepare_packed_git();
 	for (p = packed_git; p; p = p->next) {
+		if ((flags & FOR_EACH_OBJECT_LOCAL_ONLY) && !p->pack_local)
+			continue;
 		r = for_each_object_in_pack(p, cb, data);
 		if (r)
 			break;