clone: do faster object check for partial clones

For partial clones, doing a full connectivity check is wasteful; we skip
promisor objects (which, for a partial clone, is all known objects), and
enumerating them all to exclude them from the connectivity check can
take a significant amount of time on large repos.

At most, we want to make sure that we get the objects referred to by any
wanted refs. For partial clones, just check that these objects were
transferred.

Signed-off-by: Josh Steadmon <steadmon@google.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

3 files changed, 29 insertions, 2 deletions

diff --git a/builtin/clone.c b/builtin/clone.c
index 50bde99618..fdbbd8942a 100644
--- a/builtin/clone.c
+++ b/builtin/clone.c
@@ -657,7 +657,8 @@ static void update_remote_refs(const struct ref *refs,
 			       const char *branch_top,
 			       const char *msg,
 			       struct transport *transport,
-			       int check_connectivity)
+			       int check_connectivity,
+			       int check_refs_only)
 {
 	const struct ref *rm = mapped_refs;
 
@@ -666,6 +667,7 @@ static void update_remote_refs(const struct ref *refs,
 
 		opt.transport = transport;
 		opt.progress = transport->progress;
+		opt.check_refs_only = !!check_refs_only;
 
 		if (check_connected(iterate_ref_map, &rm, &opt))
 			die(_("remote did not send all necessary objects"));
@@ -1224,7 +1226,7 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 
 	update_remote_refs(refs, mapped_refs, remote_head_points_at,
 			   branch_top.buf, reflog_msg.buf, transport,
-			   !is_local);
+			   !is_local, filter_options.choice);
 
 	update_head(our_head_points_at, remote_head, reflog_msg.buf);
 
diff --git a/connected.c b/connected.c
index 1bba888eff..1ab481fed6 100644
--- a/connected.c
+++ b/connected.c
@@ -1,4 +1,5 @@
 #include "cache.h"
+#include "object-store.h"
 #include "run-command.h"
 #include "sigchain.h"
 #include "connected.h"
@@ -49,6 +50,22 @@ int check_connected(oid_iterate_fn fn, void *cb_data,
 		strbuf_release(&idx_file);
 	}
 
+	if (opt->check_refs_only) {
+		/*
+		 * For partial clones, we don't want to have to do a regular
+		 * connectivity check because we have to enumerate and exclude
+		 * all promisor objects (slow), and then the connectivity check
+		 * itself becomes a no-op because in a partial clone every
+		 * object is a promisor object. Instead, just make sure we
+		 * received the objects pointed to by each wanted ref.
+		 */
+		do {
+			if (!repo_has_object_file(the_repository, &oid))
+				return 1;
+		} while (!fn(cb_data, &oid));
+		return 0;
+	}
+
 	if (opt->shallow_file) {
 		argv_array_push(&rev_list.args, "--shallow-file");
 		argv_array_push(&rev_list.args, opt->shallow_file);
diff --git a/connected.h b/connected.h
index 8d5a6b3ad6..ce2e7d8f2e 100644
--- a/connected.h
+++ b/connected.h
@@ -46,6 +46,14 @@ struct check_connected_options {
 	 * during a fetch.
 	 */
 	unsigned is_deepening_fetch : 1;
+
+	/*
+	 * If non-zero, only check the top-level objects referenced by the
+	 * wanted refs (passed in as cb_data). This is useful for partial
+	 * clones, where enumerating and excluding all promisor objects is very
+	 * slow and the commit-walk itself becomes a no-op.
+	 */
+	unsigned check_refs_only : 1;
 };
 
 #define CHECK_CONNECTED_INIT { 0 }