fsck: introduce partialclone extension

Currently, Git does not support repos with very large numbers of objects
or repos that wish to minimize manipulation of certain blobs (for
example, because they are very large) very well, even if the user
operates mostly on part of the repo, because Git is designed on the
assumption that every referenced object is available somewhere in the
repo storage. In such an arrangement, the full set of objects is usually
available in remote storage, ready to be lazily downloaded.

Teach fsck about the new state of affairs. In this commit, teach fsck
that missing promisor objects referenced from the reflog are not an
error case; in future commits, fsck will be taught about other cases.

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

1 files changed, 74 insertions, 3 deletions

diff --git a/packfile.c b/packfile.c
index 4a5fe7a..234797c 100644
--- a/packfile.c
+++ b/packfile.c
@@ -8,6 +8,11 @@
 #include "list.h"
 #include "streaming.h"
 #include "sha1-lookup.h"
+#include "commit.h"
+#include "object.h"
+#include "tag.h"
+#include "tree-walk.h"
+#include "tree.h"
 
 char *odb_pack_name(struct strbuf *buf,
 		    const unsigned char *sha1,
@@ -643,10 +648,10 @@ struct packed_git *add_packed_git(const char *path, size_t path_len, int local)
 		return NULL;
 
 	/*
-	 * ".pack" is long enough to hold any suffix we're adding (and
+	 * ".promisor" is long enough to hold any suffix we're adding (and
 	 * the use xsnprintf double-checks that)
 	 */
-	alloc = st_add3(path_len, strlen(".pack"), 1);
+	alloc = st_add3(path_len, strlen(".promisor"), 1);
 	p = alloc_packed_git(alloc);
 	memcpy(p->pack_name, path, path_len);
 
@@ -654,6 +659,10 @@ struct packed_git *add_packed_git(const char *path, size_t path_len, int local)
 	if (!access(p->pack_name, F_OK))
 		p->pack_keep = 1;
 
+	xsnprintf(p->pack_name + path_len, alloc - path_len, ".promisor");
+	if (!access(p->pack_name, F_OK))
+		p->pack_promisor = 1;
+
 	xsnprintf(p->pack_name + path_len, alloc - path_len, ".pack");
 	if (stat(p->pack_name, &st) || !S_ISREG(st.st_mode)) {
 		free(p);
@@ -781,7 +790,8 @@ static void prepare_packed_git_one(char *objdir, int local)
 		if (ends_with(de->d_name, ".idx") ||
 		    ends_with(de->d_name, ".pack") ||
 		    ends_with(de->d_name, ".bitmap") ||
-		    ends_with(de->d_name, ".keep"))
+		    ends_with(de->d_name, ".keep") ||
+		    ends_with(de->d_name, ".promisor"))
 			string_list_append(&garbage, path.buf);
 		else
 			report_garbage(PACKDIR_FILE_GARBAGE, path.buf);
@@ -1889,6 +1899,9 @@ int for_each_packed_object(each_packed_object_fn cb, void *data, unsigned flags)
 	for (p = packed_git; p; p = p->next) {
 		if ((flags & FOR_EACH_OBJECT_LOCAL_ONLY) && !p->pack_local)
 			continue;
+		if ((flags & FOR_EACH_OBJECT_PROMISOR_ONLY) &&
+		    !p->pack_promisor)
+			continue;
 		if (open_pack_index(p)) {
 			pack_errors = 1;
 			continue;
@@ -1899,3 +1912,61 @@ int for_each_packed_object(each_packed_object_fn cb, void *data, unsigned flags)
 	}
 	return r ? r : pack_errors;
 }
+
+static int add_promisor_object(const struct object_id *oid,
+			       struct packed_git *pack,
+			       uint32_t pos,
+			       void *set_)
+{
+	struct oidset *set = set_;
+	struct object *obj = parse_object(oid);
+	if (!obj)
+		return 1;
+
+	oidset_insert(set, oid);
+
+	/*
+	 * If this is a tree, commit, or tag, the objects it refers
+	 * to are also promisor objects. (Blobs refer to no objects.)
+	 */
+	if (obj->type == OBJ_TREE) {
+		struct tree *tree = (struct tree *)obj;
+		struct tree_desc desc;
+		struct name_entry entry;
+		if (init_tree_desc_gently(&desc, tree->buffer, tree->size))
+			/*
+			 * Error messages are given when packs are
+			 * verified, so do not print any here.
+			 */
+			return 0;
+		while (tree_entry_gently(&desc, &entry))
+			oidset_insert(set, entry.oid);
+	} else if (obj->type == OBJ_COMMIT) {
+		struct commit *commit = (struct commit *) obj;
+		struct commit_list *parents = commit->parents;
+
+		oidset_insert(set, &commit->tree->object.oid);
+		for (; parents; parents = parents->next)
+			oidset_insert(set, &parents->item->object.oid);
+	} else if (obj->type == OBJ_TAG) {
+		struct tag *tag = (struct tag *) obj;
+		oidset_insert(set, &tag->tagged->oid);
+	}
+	return 0;
+}
+
+int is_promisor_object(const struct object_id *oid)
+{
+	static struct oidset promisor_objects;
+	static int promisor_objects_prepared;
+
+	if (!promisor_objects_prepared) {
+		if (repository_format_partial_clone) {
+			for_each_packed_object(add_promisor_object,
+					       &promisor_objects,
+					       FOR_EACH_OBJECT_PROMISOR_ONLY);
+		}
+		promisor_objects_prepared = 1;
+	}
+	return oidset_contains(&promisor_objects, oid);
+}