connected: verify promisor-ness of partial clone

Commit dfa33a298d ("clone: do faster object check for partial clones",
2019-04-21) optimized the connectivity check done when cloning with
--filter to check only the existence of objects directly pointed to by
refs. But this is not sufficient: they also need to be promisor objects.
Make this check more robust by instead checking that these objects are
promisor objects, that is, they appear in a promisor pack.

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
Reviewed-by: Jonathan Nieder <jrnieder@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/builtin/clone.c b/builtin/clone.c
index 0fc89ae2b9c77d420153c8bef6680d3324cdf5ad..0516181052e5191737a167b6b27afcb4565e7327 100644 (file)
--- a/builtin/clone.c
+++ b/builtin/clone.c
@@ -673,7 +673,7 @@ static void update_remote_refs(const struct ref *refs,
                               const char *msg,
                               struct transport *transport,
                               int check_connectivity,
-                              int check_refs_only)
+                              int check_refs_are_promisor_objects_only)
 {
        const struct ref *rm = mapped_refs;
 
@@ -682,7 +682,8 @@ static void update_remote_refs(const struct ref *refs,
 
                opt.transport = transport;
                opt.progress = transport->progress;
-               opt.check_refs_only = !!check_refs_only;
+               opt.check_refs_are_promisor_objects_only =
+                       !!check_refs_are_promisor_objects_only;
 
                if (check_connected(iterate_ref_map, &rm, &opt))
                        die(_("remote did not send all necessary objects"));

diff --git a/connected.c b/connected.c
index c337f5f7f4dd0797a8dd3c4e54fb77fd1b4f6df4..7e9bd1bc622eefa3dad76c8e786767a0ffa3077f 100644 (file)
--- a/connected.c
+++ b/connected.c
@@ -52,19 +52,28 @@ int check_connected(oid_iterate_fn fn, void *cb_data,
                strbuf_release(&idx_file);
        }
 
-       if (opt->check_refs_only) {
+       if (opt->check_refs_are_promisor_objects_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.
+                * received, in a promisor packfile, the objects pointed to by
+                * each wanted ref.
                 */
                do {
-                       if (!repo_has_object_file_with_flags(the_repository, &oid,
-                                                            OBJECT_INFO_SKIP_FETCH_OBJECT))
-                               return 1;
+                       struct packed_git *p;
+
+                       for (p = get_all_packs(the_repository); p; p = p->next) {
+                               if (!p->pack_promisor)
+                                       continue;
+                               if (find_pack_entry_one(oid.hash, p))
+                                       goto promisor_pack_found;
+                       }
+                       return 1;
+promisor_pack_found:
+                       ;
                } while (!fn(cb_data, &oid));
                return 0;
        }

diff --git a/connected.h b/connected.h
index ce2e7d8f2e535aac72fb317448ad20fb2133429b..eba5c261bac1887289ac70425cee8c97e9006ece 100644 (file)
--- a/connected.h
+++ b/connected.h
@@ -48,12 +48,13 @@ struct check_connected_options {
        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.
+        * If non-zero, only check that the top-level objects referenced by the
+        * wanted refs (passed in as cb_data) are promisor objects. 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;
+       unsigned check_refs_are_promisor_objects_only : 1;
 };
 
 #define CHECK_CONNECTED_INIT { 0 }