From 6523078b96cd39f681e6fa11135049808591fb95 Mon Sep 17 00:00:00 2001
From: Nicolas Pitre <nico@cam.org>
Date: Thu, 3 Sep 2009 19:08:33 -0400
Subject: make shallow repository deepening more network efficient

First of all, I can't find any reason why thin pack generation is
explicitly disabled when dealing with a shallow repository.  The
possible delta base objects are collected from the edge commits which
are always obtained through history walking with the same shallow refs
as the client, Therefore the client is always going to have those base
objects available. So let's remove that restriction.

Then we can make shallow repository deepening much more efficient by
using the remote's unshallowed commits as edge commits to get preferred
base objects for thin pack generation.  On git.git, this makes the data
transfer for the deepening of a shallow repository from depth 1 to depth 2
around 134 KB instead of 3.68 MB.

Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/upload-pack.c b/upload-pack.c
index edc7861..7428ff7 100644
--- a/upload-pack.c
+++ b/upload-pack.c
@@ -31,6 +31,7 @@ static int use_thin_pack, use_ofs_delta, use_include_tag;
 static int no_progress;
 static struct object_array have_obj;
 static struct object_array want_obj;
+static struct object_array extra_edge_obj;
 static unsigned int timeout;
 /* 0 for no sideband,
  * otherwise maximum packet size (up to 65520 bytes).
@@ -136,6 +137,10 @@ static int do_rev_list(int fd, void *create_full_pack)
 	if (prepare_revision_walk(&revs))
 		die("revision walk setup failed");
 	mark_edges_uninteresting(revs.commits, &revs, show_edge);
+	if (use_thin_pack)
+		for (i = 0; i < extra_edge_obj.nr; i++)
+			fprintf(pack_pipe, "-%s\n", sha1_to_hex(
+					extra_edge_obj.objects[i].item->sha1));
 	traverse_commit_list(&revs, show_commit, show_object, NULL);
 	fflush(pack_pipe);
 	fclose(pack_pipe);
@@ -466,7 +471,6 @@ static void receive_needs(void)
 		if (!prefixcmp(line, "shallow ")) {
 			unsigned char sha1[20];
 			struct object *object;
-			use_thin_pack = 0;
 			if (get_sha1(line + 8, sha1))
 				die("invalid shallow line: %s", line);
 			object = parse_object(sha1);
@@ -478,7 +482,6 @@ static void receive_needs(void)
 		}
 		if (!prefixcmp(line, "deepen ")) {
 			char *end;
-			use_thin_pack = 0;
 			depth = strtol(line + 7, &end, 0);
 			if (end == line + 7 || depth <= 0)
 				die("Invalid deepen: %s", line);
@@ -556,6 +559,7 @@ static void receive_needs(void)
 							NULL, &want_obj);
 					parents = parents->next;
 				}
+				add_object_array(object, NULL, &extra_edge_obj);
 			}
 			/* make sure commit traversal conforms to client */
 			register_shallow(object->sha1);
-- 
cgit v0.10.2-6-g49f6


From 0ef95f72f878184fbce8d7c855ab4346c081abed Mon Sep 17 00:00:00 2001
From: Nicolas Pitre <nico@cam.org>
Date: Thu, 3 Sep 2009 21:54:03 -0400
Subject: pack-objects: free preferred base memory after usage

When adding objects for preferred delta base, the content from tree
objects leading to given paths is kept in a cache. This has the
potential to grow significantly, especially with large directories as
the whole tree object content is loaded in memory, even if in practice
the number of those objects is limited to the 256 cache entries plus the
$window root tree objects.  Still, that can't hurt freeing that up after
object enumeration is done, and before more memory is needed for delta
search.

Signed-off-by: Nicolas Pitre <nico@cam.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/builtin-pack-objects.c b/builtin-pack-objects.c
index 941cc2d..b44fa0e 100644
--- a/builtin-pack-objects.c
+++ b/builtin-pack-objects.c
@@ -1012,6 +1012,33 @@ static void add_preferred_base(unsigned char *sha1)
 	it->pcache.tree_size = size;
 }
 
+static void cleanup_preferred_base(void)
+{
+	struct pbase_tree *it;
+	unsigned i;
+
+	it = pbase_tree;
+	pbase_tree = NULL;
+	while (it) {
+		struct pbase_tree *this = it;
+		it = this->next;
+		free(this->pcache.tree_data);
+		free(this);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(pbase_tree_cache); i++) {
+		if (!pbase_tree_cache[i])
+			continue;
+		free(pbase_tree_cache[i]->tree_data);
+		free(pbase_tree_cache[i]);
+		pbase_tree_cache[i] = NULL;
+	}
+
+	free(done_pbase_paths);
+	done_pbase_paths = NULL;
+	done_pbase_paths_num = done_pbase_paths_alloc = 0;
+}
+
 static void check_object(struct object_entry *entry)
 {
 	if (entry->in_pack) {
@@ -2308,6 +2335,7 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 		rp_av[rp_ac] = NULL;
 		get_object_list(rp_ac, rp_av);
 	}
+	cleanup_preferred_base();
 	if (include_tag && nr_result)
 		for_each_ref(add_ref_tag, NULL);
 	stop_progress(&progress_state);
-- 
cgit v0.10.2-6-g49f6