Shrink "struct object" a bit

This shrinks "struct object" by a small amount, by getting rid of the
"struct type *" pointer and replacing it with a 3-bit bitfield instead.

In addition, we merge the bitfields and the "flags" field, which
incidentally should also remove a useless 4-byte padding from the object
when in 64-bit mode.

Now, our "struct object" is still too damn large, but it's now less
obviously bloated, and of the remaining fields, only the "util" (which is
not used by most things) is clearly something that should be eventually
discarded.

This shrinks the "git-rev-list --all" memory use by about 2.5% on the
kernel archive (and, perhaps more importantly, on the larger mozilla
archive). That may not sound like much, but I suspect it's more on a
64-bit platform.

There are other remaining inefficiencies (the parent lists, for example,
probably have horrible malloc overhead), but this was pretty obvious.

Most of the patch is just changing the comparison of the "type" pointer
from one of the constant string pointers to the appropriate new TYPE_xxx
small integer constant.

Signed-off-by: Linus Torvalds <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

blob.c

@@ -10,14 +10,14 @@ struct blob *lookup_blob(const unsigned char *sha1)
 	if (!obj) {
 		struct blob *ret = xcalloc(1, sizeof(struct blob));
 		created_object(sha1, &ret->object);
-		ret->object.type = blob_type;
+		ret->object.type = TYPE_BLOB;
 		return ret;
 	}
 	if (!obj->type)
-		obj->type = blob_type;
-	if (obj->type != blob_type) {
-		error("Object %s is a %s, not a blob", 
-		      sha1_to_hex(sha1), obj->type);
+		obj->type = TYPE_BLOB;
+	if (obj->type != TYPE_BLOB) {
+		error("Object %s is a %s, not a blob",
+		      sha1_to_hex(sha1), typename(obj->type));
 		return NULL;
 	}
 	return (struct blob *) obj;

builtin-diff.c

@@ -303,9 +303,9 @@ int cmd_diff(int argc, const char **argv, char **envp)
 		obj = deref_tag(obj, NULL, 0);
 		if (!obj)
 			die("invalid object '%s' given.", name);
-		if (!strcmp(obj->type, commit_type))
+		if (obj->type == TYPE_COMMIT)
 			obj = &((struct commit *)obj)->tree->object;
-		if (!strcmp(obj->type, tree_type)) {
+		if (obj->type == TYPE_TREE) {
 			if (ARRAY_SIZE(ent) <= ents)
 				die("more than %d trees given: '%s'",
 				    (int) ARRAY_SIZE(ent), name);
@@ -315,7 +315,7 @@ int cmd_diff(int argc, const char **argv, char **envp)
 			ents++;
 			continue;
 		}
-		if (!strcmp(obj->type, blob_type)) {
+		if (obj->type == TYPE_BLOB) {
 			if (2 <= blobs)
 				die("more than two blobs given: '%s'", name);
 			memcpy(blob[blobs].sha1, obj->sha1, 20);

builtin-grep.c

@@ -630,10 +630,9 @@ static int grep_tree(struct grep_opt *opt, const char **paths,
 static int grep_object(struct grep_opt *opt, const char **paths,
 		       struct object *obj, const char *name)
 {
-	if (!strcmp(obj->type, blob_type))
+	if (obj->type == TYPE_BLOB)
 		return grep_sha1(opt, obj->sha1, name);
-	if (!strcmp(obj->type, commit_type) ||
-	    !strcmp(obj->type, tree_type)) {
+	if (obj->type == TYPE_COMMIT || obj->type == TYPE_TREE) {
 		struct tree_desc tree;
 		void *data;
 		int hit;
@@ -646,7 +645,7 @@ static int grep_object(struct grep_opt *opt, const char **paths,
 		free(data);
 		return hit;
 	}
-	die("unable to grep from object of type %s", obj->type);
+	die("unable to grep from object of type %s", typename(obj->type));
 }
 
 static const char builtin_grep_usage[] =

builtin-rev-list.c

@@ -158,16 +158,16 @@ static void show_commit_list(struct rev_info *revs)
 		const char *name = pending->name;
 		if (obj->flags & (UNINTERESTING | SEEN))
 			continue;
-		if (obj->type == tag_type) {
+		if (obj->type == TYPE_TAG) {
 			obj->flags |= SEEN;
 			p = add_object(obj, p, NULL, name);
 			continue;
 		}
-		if (obj->type == tree_type) {
+		if (obj->type == TYPE_TREE) {
 			p = process_tree((struct tree *)obj, p, NULL, name);
 			continue;
 		}
-		if (obj->type == blob_type) {
+		if (obj->type == TYPE_BLOB) {
 			p = process_blob((struct blob *)obj, p, NULL, name);
 			continue;
 		}

builtin-show-branch.c

@@ -15,7 +15,7 @@ static const char **default_arg = NULL;
 #define UNINTERESTING	01
 
 #define REV_SHIFT	 2
-#define MAX_REVS	29 /* should not exceed bits_per_int - REV_SHIFT */
+#define MAX_REVS	(FLAG_BITS - REV_SHIFT) /* should not exceed bits_per_int - REV_SHIFT */
 
 static struct commit *interesting(struct commit_list *list)
 {

commit.c

@@ -56,10 +56,10 @@ static struct commit *check_commit(struct object *obj,
 				   const unsigned char *sha1,
 				   int quiet)
 {
-	if (obj->type != commit_type) {
+	if (obj->type != TYPE_COMMIT) {
 		if (!quiet)
 			error("Object %s is a %s, not a commit",
-			      sha1_to_hex(sha1), obj->type);
+			      sha1_to_hex(sha1), typename(obj->type));
 		return NULL;
 	}
 	return (struct commit *) obj;
@@ -86,11 +86,11 @@ struct commit *lookup_commit(const unsigned char *sha1)
 	if (!obj) {
 		struct commit *ret = xcalloc(1, sizeof(struct commit));
 		created_object(sha1, &ret->object);
-		ret->object.type = commit_type;
+		ret->object.type = TYPE_COMMIT;
 		return ret;
 	}
 	if (!obj->type)
-		obj->type = commit_type;
+		obj->type = TYPE_COMMIT;
 	return check_commit(obj, sha1, 0);
 }
 

describe.c

@@ -67,7 +67,7 @@ static int get_name(const char *path, const unsigned char *sha1)
 	 * Otherwise only annotated tags are used.
 	 */
 	if (!strncmp(path, "refs/tags/", 10)) {
-		if (object->type == tag_type)
+		if (object->type == TYPE_TAG)
 			prio = 2;
 		else
 			prio = 1;

fetch-pack.c

@@ -46,7 +46,7 @@ static int rev_list_insert_ref(const char *path, const unsigned char *sha1)
 {
 	struct object *o = deref_tag(parse_object(sha1), path, 0);
 
-	if (o && o->type == commit_type)
+	if (o && o->type == TYPE_COMMIT)
 		rev_list_push((struct commit *)o, SEEN);
 
 	return 0;
@@ -251,14 +251,14 @@ static int mark_complete(const char *path, const unsigned char *sha1)
 {
 	struct object *o = parse_object(sha1);
 
-	while (o && o->type == tag_type) {
+	while (o && o->type == TYPE_TAG) {
 		struct tag *t = (struct tag *) o;
 		if (!t->tagged)
 			break; /* broken repository */
 		o->flags |= COMPLETE;
 		o = parse_object(t->tagged->sha1);
 	}
-	if (o && o->type == commit_type) {
+	if (o && o->type == TYPE_COMMIT) {
 		struct commit *commit = (struct commit *)o;
 		commit->object.flags |= COMPLETE;
 		insert_by_date(commit, &complete);
@@ -352,7 +352,7 @@ static int everything_local(struct ref **refs, int nr_match, char **match)
 		 * in sync with the other side at some time after
 		 * that (it is OK if we guess wrong here).
 		 */
-		if (o->type == commit_type) {
+		if (o->type == TYPE_COMMIT) {
 			struct commit *commit = (struct commit *)o;
 			if (!cutoff || cutoff < commit->date)
 				cutoff = commit->date;
@@ -371,7 +371,7 @@ static int everything_local(struct ref **refs, int nr_match, char **match)
 		struct object *o = deref_tag(lookup_object(ref->old_sha1),
 					     NULL, 0);
 
-		if (!o || o->type != commit_type || !(o->flags & COMPLETE))
+		if (!o || o->type != TYPE_COMMIT || !(o->flags & COMPLETE))
 			continue;
 
 		if (!(o->flags & SEEN)) {

fetch.c

@@ -118,27 +118,27 @@ static struct object_list **process_queue_end = &process_queue;
 
 static int process_object(struct object *obj)
 {
-	if (obj->type == commit_type) {
+	if (obj->type == TYPE_COMMIT) {
 		if (process_commit((struct commit *)obj))
 			return -1;
 		return 0;
 	}
-	if (obj->type == tree_type) {
+	if (obj->type == TYPE_TREE) {
 		if (process_tree((struct tree *)obj))
 			return -1;
 		return 0;
 	}
-	if (obj->type == blob_type) {
+	if (obj->type == TYPE_BLOB) {
 		return 0;
 	}
-	if (obj->type == tag_type) {
+	if (obj->type == TYPE_TAG) {
 		if (process_tag((struct tag *)obj))
 			return -1;
 		return 0;
 	}
 	return error("Unable to determine requirements "
 		     "of type %s for %s",
-		     obj->type, sha1_to_hex(obj->sha1));
+		     typename(obj->type), sha1_to_hex(obj->sha1));
 }
 
 static int process(struct object *obj)
@@ -179,9 +179,7 @@ static int loop(void)
 		 */
 		if (! (obj->flags & TO_SCAN)) {
 			if (fetch(obj->sha1)) {
-				report_missing(obj->type
-					       ? obj->type
-					       : "object", obj->sha1);
+				report_missing(typename(obj->type), obj->sha1);
 				return -1;
 			}
 		}

fsck-objects.c

@@ -34,7 +34,7 @@ static void objreport(struct object *obj, const char *severity,
                       const char *err, va_list params)
 {
 	fprintf(stderr, "%s in %s %s: ",
-	        severity, obj->type, sha1_to_hex(obj->sha1));
+	        severity, typename(obj->type), sha1_to_hex(obj->sha1));
 	vfprintf(stderr, err, params);
 	fputs("\n", stderr);
 }
@@ -74,7 +74,7 @@ static void check_connectivity(void)
 				; /* it is in pack */
 			else
 				printf("missing %s %s\n",
-				       obj->type, sha1_to_hex(obj->sha1));
+				       typename(obj->type), sha1_to_hex(obj->sha1));
 			continue;
 		}
 
@@ -87,20 +87,20 @@ static void check_connectivity(void)
 				    (has_sha1_file(ref->sha1)))
 					continue;
 				printf("broken link from %7s %s\n",
-				       obj->type, sha1_to_hex(obj->sha1));
+				       typename(obj->type), sha1_to_hex(obj->sha1));
 				printf("              to %7s %s\n",
-				       ref->type, sha1_to_hex(ref->sha1));
+				       typename(ref->type), sha1_to_hex(ref->sha1));
 			}
 		}
 
 		if (show_unreachable && !(obj->flags & REACHABLE)) {
 			printf("unreachable %s %s\n",
-			       obj->type, sha1_to_hex(obj->sha1));
+			       typename(obj->type), sha1_to_hex(obj->sha1));
 			continue;
 		}
 
 		if (!obj->used) {
-			printf("dangling %s %s\n", obj->type, 
+			printf("dangling %s %s\n", typename(obj->type),
 			       sha1_to_hex(obj->sha1));
 		}
 	}
@@ -282,7 +282,7 @@ static int fsck_tag(struct tag *tag)
 	if (!show_tags)
 		return 0;
 
-	printf("tagged %s %s", tagged->type, sha1_to_hex(tagged->sha1));
+	printf("tagged %s %s", typename(tagged->type), sha1_to_hex(tagged->sha1));
 	printf(" (%s) in %s\n", tag->tag, sha1_to_hex(tag->object.sha1));
 	return 0;
 }
@@ -295,16 +295,16 @@ static int fsck_sha1(unsigned char *sha1)
 	if (obj->flags & SEEN)
 		return 0;
 	obj->flags |= SEEN;
-	if (obj->type == blob_type)
+	if (obj->type == TYPE_BLOB)
 		return 0;
-	if (obj->type == tree_type)
+	if (obj->type == TYPE_TREE)
 		return fsck_tree((struct tree *) obj);
-	if (obj->type == commit_type)
+	if (obj->type == TYPE_COMMIT)
 		return fsck_commit((struct commit *) obj);
-	if (obj->type == tag_type)
+	if (obj->type == TYPE_TAG)
 		return fsck_tag((struct tag *) obj);
 	/* By now, parse_object() would've returned NULL instead. */
-	return objerror(obj, "unknown type '%s' (internal fsck error)", obj->type);
+	return objerror(obj, "unknown type '%d' (internal fsck error)", obj->type);
 }
 
 /*
@@ -470,7 +470,7 @@ static int fsck_cache_tree(struct cache_tree *it)
 		}
 		mark_reachable(obj, REACHABLE);
 		obj->used = 1;
-		if (obj->type != tree_type)
+		if (obj->type != TYPE_TREE)
 			err |= objerror(obj, "non-tree in cache-tree");
 	}
 	for (i = 0; i < it->subtree_nr; i++)

http-push.c

@@ -1773,16 +1773,16 @@ static int get_delta(struct rev_info *revs, struct remote_lock *lock)
 
 		if (obj->flags & (UNINTERESTING | SEEN))
 			continue;
-		if (obj->type == tag_type) {
+		if (obj->type == TYPE_TAG) {
 			obj->flags |= SEEN;
 			p = add_object(obj, p, NULL, name);
 			continue;
 		}
-		if (obj->type == tree_type) {
+		if (obj->type == TYPE_TREE) {
 			p = process_tree((struct tree *)obj, p, NULL, name);
 			continue;
 		}
-		if (obj->type == blob_type) {
+		if (obj->type == TYPE_BLOB) {
 			p = process_blob((struct blob *)obj, p, NULL, name);
 			continue;
 		}
@@ -1949,12 +1949,12 @@ static int ref_newer(const unsigned char *new_sha1,
 	 * old.  Otherwise we require --force.
 	 */
 	o = deref_tag(parse_object(old_sha1), NULL, 0);
-	if (!o || o->type != commit_type)
+	if (!o || o->type != TYPE_COMMIT)
 		return 0;
 	old = (struct commit *) o;
 
 	o = deref_tag(parse_object(new_sha1), NULL, 0);
-	if (!o || o->type != commit_type)
+	if (!o || o->type != TYPE_COMMIT)
 		return 0;
 	new = (struct commit *) o;
 
@@ -2033,7 +2033,7 @@ static void add_remote_info_ref(struct remote_ls_ctx *ls)
 	fwrite_buffer(ref_info, 1, len, buf);
 	free(ref_info);
 
-	if (o->type == tag_type) {
+	if (o->type == TYPE_TAG) {
 		o = deref_tag(o, ls->dentry_name, 0);
 		if (o) {
 			len = strlen(ls->dentry_name) + 45;

name-rev.c

@@ -84,14 +84,14 @@ static int name_ref(const char *path, const unsigned char *sha1)
 	if (tags_only && strncmp(path, "refs/tags/", 10))
 		return 0;
 
-	while (o && o->type == tag_type) {
+	while (o && o->type == TYPE_TAG) {
 		struct tag *t = (struct tag *) o;
 		if (!t->tagged)
 			break; /* broken repository */
 		o = parse_object(t->tagged->sha1);
 		deref = 1;
 	}
-	if (o && o->type == commit_type) {
+	if (o && o->type == TYPE_COMMIT) {
 		struct commit *commit = (struct commit *)o;
 
 		if (!strncmp(path, "refs/heads/", 11))
@@ -167,7 +167,7 @@ int main(int argc, char **argv)
 		}
 
 		o = deref_tag(parse_object(sha1), *argv, 0);
-		if (!o || o->type != commit_type) {
+		if (!o || o->type != TYPE_COMMIT) {
 			fprintf(stderr, "Could not get commit for %s. Skipping.\n",
 					*argv);
 			continue;

object.c

@@ -9,6 +9,10 @@ struct object **objs;
 static int nr_objs;
 int obj_allocs;
 
+const char *type_names[] = {
+	"none", "blob", "tree", "commit", "bad"
+};
+
 int track_object_refs = 0;
 
 static int hashtable_index(const unsigned char *sha1)
@@ -50,7 +54,7 @@ void created_object(const unsigned char *sha1, struct object *obj)
 
 	obj->parsed = 0;
 	memcpy(obj->sha1, sha1, 20);
-	obj->type = NULL;
+	obj->type = TYPE_NONE;
 	obj->refs = NULL;
 	obj->used = 0;
 
@@ -179,7 +183,7 @@ struct object *lookup_unknown_object(const unsigned char *sha1)
 	if (!obj) {
 		union any_object *ret = xcalloc(1, sizeof(*ret));
 		created_object(sha1, &ret->object);
-		ret->object.type = NULL;
+		ret->object.type = TYPE_NONE;
 		return &ret->object;
 	}
 	return obj;