[PATCH v3 12/28] clone: support remote shallow repository

["Nguyễn Thái Ngọc Duy" <pclouds@gmail.com>]

The gist of cloning a remote shallow repository is simple. The remote
gives you a pack and all its shallow roots. All you need to do is set
your .git/shallow correctly.

The rule to create this .git/shallow is simple and more importantly,
cheap: if a shallow root is found in the pack, it's probably used
(i.e. reachable from some refs), so we add it. Others are dropped.

One may notice this method seems flawed by the word "probably". A
shallow point may not be reachable from any refs at all if it's
attached to an object island (a group of objects that are not
reachable by any refs).

If that object island is not complete, a new fetch request may send
more objects to connect it to some ref. At that time, because we
incorrectly installed the shallow root in this island, the user will
not see anything after that root. This is not desired.

There is a stricter method to rule out unwanted shallow roots above:
mark_new_shallow_refs(). But it's expensive and even more so for a
clone because it's proportional to the (potentially huge) number of
commits.

Given that object islands are rare (C Git never sends such islands), a
tradeoff is made to surprise the user occasionally but work faster
everyday. --strict option could be added later to enforce
mark_new_shallow_refs().

Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 builtin/clone.c      |  1 +
 builtin/fetch-pack.c |  2 +-
 fetch-pack.c         | 50 +++++++++++++++++++++++++++++++++++++++++++++++---
 fetch-pack.h         |  4 ++++
 transport.c          | 11 ++++++++---
 transport.h          |  6 ++++++
 6 files changed, 67 insertions(+), 7 deletions(-)

diff --git a/builtin/clone.c b/builtin/clone.c
index 900f564..0b182ce 100644
--- a/builtin/clone.c
+++ b/builtin/clone.c
@@ -889,6 +889,7 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 
 	remote = remote_get(option_origin);
 	transport = transport_get(remote, remote->url[0]);
+	transport->cloning = 1;
 
 	if (!transport->get_refs_list || (!is_local && !transport->fetch))
 		die(_("Don't know how to clone %s"), transport->url);
diff --git a/builtin/fetch-pack.c b/builtin/fetch-pack.c
index c1d918f..927424b 100644
--- a/builtin/fetch-pack.c
+++ b/builtin/fetch-pack.c
@@ -153,7 +153,7 @@ int cmd_fetch_pack(int argc, const char **argv, const char *prefix)
 	get_remote_heads(fd[0], NULL, 0, &ref, 0, NULL, NULL);
 
 	ref = fetch_pack(&args, fd, conn, ref, dest,
-			 sought, nr_sought, pack_lockfile_ptr);
+			 sought, nr_sought, NULL, pack_lockfile_ptr);
 	if (pack_lockfile) {
 		printf("lock %s\n", pack_lockfile);
 		fflush(stdout);
diff --git a/fetch-pack.c b/fetch-pack.c
index 35d097e..b76581a 100644
--- a/fetch-pack.c
+++ b/fetch-pack.c
@@ -774,6 +774,7 @@ static struct ref *do_fetch_pack(struct fetch_pack_args *args,
 				 int fd[2],
 				 const struct ref *orig_ref,
 				 struct ref **sought, int nr_sought,
+				 struct extra_have_objects *shallow,
 				 char **pack_lockfile)
 {
 	struct ref *ref = copy_ref_list(orig_ref);
@@ -852,6 +853,8 @@ static struct ref *do_fetch_pack(struct fetch_pack_args *args,
 	if (args->depth > 0)
 		setup_alternate_shallow(&shallow_lock, &alternate_shallow_file,
 					NULL);
+	else if (args->cloning && shallow && shallow->nr)
+		alternate_shallow_file = setup_temporary_shallow(shallow);
 	else
 		alternate_shallow_file = NULL;
 	if (get_pack(args, fd, pack_lockfile))
@@ -925,8 +928,11 @@ static int remove_duplicates_in_refs(struct ref **ref, int nr)
 	return dst;
 }
 
-static void update_shallow(struct fetch_pack_args *args)
+static void update_shallow(struct fetch_pack_args *args,
+			   struct extra_have_objects *shallow)
 {
+	int i;
+
 	if (args->depth > 0 && alternate_shallow_file) {
 		if (*alternate_shallow_file == '\0') { /* --unshallow */
 			unlink_or_warn(git_path("shallow"));
@@ -935,6 +941,42 @@ static void update_shallow(struct fetch_pack_args *args)
 			commit_lock_file(&shallow_lock);
 		return;
 	}
+
+	if (!shallow || !shallow->nr)
+		return;
+
+	if (alternate_shallow_file) {
+		/*
+		 * The temporary shallow file is only useful for
+		 * index-pack and unpack-objects because it may
+		 * contain more roots than we want. Delete it.
+		 */
+		if (*alternate_shallow_file)
+			unlink(alternate_shallow_file);
+		free((char*)alternate_shallow_file);
+	}
+
+	if (args->cloning) {
+		/*
+		 * remote is shallow, but this is a clone, there are
+		 * no objects in repo to worry about. Accept any
+		 * shallow points that exist in the pack (iow in repo
+		 * after get_pack() and reprepare_packed_git())
+		 */
+		struct extra_have_objects extra;
+		memset(&extra, 0, sizeof(extra));
+		for (i = 0; i < shallow->nr; i++)
+			if (has_sha1_file(shallow->array[i]))
+				add_extra_have(&extra, shallow->array[i]);
+		if (extra.nr) {
+			setup_alternate_shallow(&shallow_lock,
+						&alternate_shallow_file,
+						&extra);
+			commit_lock_file(&shallow_lock);
+		}
+		free(extra.array);
+		return;
+	}
 }
 
 struct ref *fetch_pack(struct fetch_pack_args *args,
@@ -942,6 +984,7 @@ struct ref *fetch_pack(struct fetch_pack_args *args,
 		       const struct ref *ref,
 		       const char *dest,
 		       struct ref **sought, int nr_sought,
+		       struct extra_have_objects *shallow,
 		       char **pack_lockfile)
 {
 	struct ref *ref_cpy;
@@ -954,8 +997,9 @@ struct ref *fetch_pack(struct fetch_pack_args *args,
 		packet_flush(fd[1]);
 		die("no matching remote head");
 	}
-	ref_cpy = do_fetch_pack(args, fd, ref, sought, nr_sought, pack_lockfile);
-	update_shallow(args);
+	ref_cpy = do_fetch_pack(args, fd, ref, sought, nr_sought,
+				shallow, pack_lockfile);
 	reprepare_packed_git();
+	update_shallow(args, shallow);
 	return ref_cpy;
 }
diff --git a/fetch-pack.h b/fetch-pack.h
index 9b08388..cabfb60 100644
--- a/fetch-pack.h
+++ b/fetch-pack.h
@@ -4,6 +4,8 @@
 #include "string-list.h"
 #include "run-command.h"
 
+struct extra_have_objects;
+
 struct fetch_pack_args {
 	const char *uploadpack;
 	int unpacklimit;
@@ -20,6 +22,7 @@ struct fetch_pack_args {
 	unsigned stateless_rpc:1;
 	unsigned check_self_contained_and_connected:1;
 	unsigned self_contained_and_connected:1;
+	unsigned cloning:1;
 };
 
 /*
@@ -33,6 +36,7 @@ struct ref *fetch_pack(struct fetch_pack_args *args,
 		       const char *dest,
 		       struct ref **sought,
 		       int nr_sought,
+		       struct extra_have_objects *shallow,
 		       char **pack_lockfile);
 
 #endif
diff --git a/transport.c b/transport.c
index 9c51767..fa3dc16 100644
--- a/transport.c
+++ b/transport.c
@@ -455,6 +455,7 @@ struct git_transport_data {
 	int fd[2];
 	unsigned got_remote_heads : 1;
 	struct extra_have_objects extra_have;
+	struct extra_have_objects shallow;
 };
 
 static int set_git_option(struct git_transport_options *opts,
@@ -511,7 +512,9 @@ static struct ref *get_refs_via_connect(struct transport *transport, int for_pus
 
 	connect_setup(transport, for_push, 0);
 	get_remote_heads(data->fd[0], NULL, 0, &refs,
-			 for_push ? REF_NORMAL : 0, &data->extra_have, NULL);
+			 for_push ? REF_NORMAL : 0,
+			 &data->extra_have,
+			 transport->cloning ? &data->shallow : NULL);
 	data->got_remote_heads = 1;
 
 	return refs;
@@ -538,17 +541,19 @@ static int fetch_refs_via_pack(struct transport *transport,
 	args.depth = data->options.depth;
 	args.check_self_contained_and_connected =
 		data->options.check_self_contained_and_connected;
+	args.cloning = transport->cloning;
 
 	if (!data->got_remote_heads) {
 		connect_setup(transport, 0, 0);
 		get_remote_heads(data->fd[0], NULL, 0, &refs_tmp, 0,
-				 NULL, NULL);
+				 NULL,
+				 transport->cloning ? &data->shallow : NULL);
 		data->got_remote_heads = 1;
 	}
 
 	refs = fetch_pack(&args, data->fd, data->conn,
 			  refs_tmp ? refs_tmp : transport->remote_refs,
-			  dest, to_fetch, nr_heads,
+			  dest, to_fetch, nr_heads, &data->shallow,
 			  &transport->pack_lockfile);
 	close(data->fd[0]);
 	close(data->fd[1]);
diff --git a/transport.h b/transport.h
index b3679bb..59842d4 100644
--- a/transport.h
+++ b/transport.h
@@ -35,6 +35,12 @@ struct transport {
 	 */
 	unsigned cannot_reuse : 1;
 
+	/*
+	 * A hint from caller that it will be performing a clone, not
+	 * normal fetch. IOW the repository is guaranteed empty.
+	 */
+	unsigned cloning : 1;
+
 	/**
 	 * Returns 0 if successful, positive if the option is not
 	 * recognized or is inapplicable, and negative if the option
-- 
1.8.2.83.gc99314b