[PATCH] Parallelize the pull algorithm

This processes objects in two simultaneous passes. Each object will
first be given to prefetch(), as soon as it is possible to tell that
it will be needed, and then will be given to fetch(), when it is the
next object that needs to be parsed. Unless an implementation does
something with prefetch(), this should have no effect.

Signed-off-by: Daniel Barkalow <barkalow@iabervon.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>

http-pull.c

@@ -67,6 +67,10 @@ static size_t fwrite_sha1_file(void *ptr, size_t eltsize, size_t nmemb,
 	return size;
 }
 
+void prefetch(unsigned char *sha1)
+{
+}
+
 static int got_indices = 0;
 
 static struct packed_git *packs = NULL;

local-pull.c

@@ -11,6 +11,10 @@ static int use_filecopy = 1;
 
 static char *path; /* "Remote" git repository */
 
+void prefetch(unsigned char *sha1)
+{
+}
+
 int fetch(unsigned char *sha1)
 {
 	static int object_name_start = -1;

pull.c

@@ -17,11 +17,8 @@ int get_all = 0;
 int get_verbosely = 0;
 static unsigned char current_commit_sha1[20];
 
-static const char commitS[] = "commit";
+void pull_say(const char *fmt, const char *hex) 
-static const char treeS[] = "tree";
+{
-static const char blobS[] = "blob";
-
-void pull_say(const char *fmt, const char *hex) {
 	if (get_verbosely)
 		fprintf(stderr, fmt, hex);
 }
@@ -48,93 +45,118 @@ static int make_sure_we_have_it(const char *what, unsigned char *sha1)
 	return status;
 }
 
-static int process_unknown(unsigned char *sha1);
+static int process(unsigned char *sha1, const char *type);
 
-static int process_tree(unsigned char *sha1)
+static int process_tree(struct tree *tree)
 {
-	struct tree *tree = lookup_tree(sha1);
 	struct tree_entry_list *entries;
 
 	if (parse_tree(tree))
 		return -1;
 
 	for (entries = tree->entries; entries; entries = entries->next) {
-		const char *what = entries->directory ? treeS : blobS;
+		if (process(entries->item.any->sha1,
-		if (make_sure_we_have_it(what, entries->item.tree->object.sha1))
+			    entries->directory ? tree_type : blob_type))
 			return -1;
-		if (entries->directory) {
-			if (process_tree(entries->item.tree->object.sha1))
-				return -1;
-		}
 	}
 	return 0;
 }
 
-static int process_commit(unsigned char *sha1)
+static int process_commit(struct commit *commit)
 {
-	struct commit *obj = lookup_commit(sha1);
+	if (parse_commit(commit))
-
-	if (make_sure_we_have_it(commitS, sha1))
 		return -1;
 
-	if (parse_commit(obj))
+	memcpy(current_commit_sha1, commit->object.sha1, 20);
-		return -1;
 
 	if (get_tree) {
-		if (make_sure_we_have_it(treeS, obj->tree->object.sha1))
+		if (process(commit->tree->object.sha1, tree_type))
-			return -1;
-		if (process_tree(obj->tree->object.sha1))
 			return -1;
 		if (!get_all)
 			get_tree = 0;
 	}
 	if (get_history) {
-		struct commit_list *parents = obj->parents;
+		struct commit_list *parents = commit->parents;
 		for (; parents; parents = parents->next) {
 			if (has_sha1_file(parents->item->object.sha1))
 				continue;
-			if (make_sure_we_have_it(NULL,
+			if (process(parents->item->object.sha1,
-						 parents->item->object.sha1)) {
+				    commit_type))
-				/* The server might not have it, and
-				 * we don't mind. 
-				 */
-				continue;
-			}
-			if (process_commit(parents->item->object.sha1))
 				return -1;
-			memcpy(current_commit_sha1, sha1, 20);
 		}
 	}
 	return 0;
 }
 
-static int process_tag(unsigned char *sha1)
+static int process_tag(struct tag *tag)
 {
-	struct tag *obj = lookup_tag(sha1);
+	if (parse_tag(tag))
-
-	if (parse_tag(obj))
 		return -1;
-	return process_unknown(obj->tagged->sha1);
+	return process(tag->tagged->sha1, NULL);
 }
 
-static int process_unknown(unsigned char *sha1)
+static struct object_list *process_queue = NULL;
+static struct object_list **process_queue_end = &process_queue;
+
+static int process(unsigned char *sha1, const char *type)
 {
 	struct object *obj;
-	if (make_sure_we_have_it("object", sha1))
+	if (has_sha1_file(sha1))
-		return -1;
-	obj = parse_object(sha1);
-	if (!obj)
-		return error("Unable to parse object %s", sha1_to_hex(sha1));
-	if (obj->type == commit_type)
-		return process_commit(sha1);
-	if (obj->type == tree_type)
-		return process_tree(sha1);
-	if (obj->type == blob_type)
 		return 0;
-	if (obj->type == tag_type)
+	obj = lookup_object_type(sha1, type);
-		return process_tag(sha1);
+	if (object_list_contains(process_queue, obj))
-	return error("Unable to determine requirement of type %s for %s",
+		return 0;
-		     obj->type, sha1_to_hex(sha1));
+	object_list_insert(obj, process_queue_end);
+	process_queue_end = &(*process_queue_end)->next;
+
+	//fprintf(stderr, "prefetch %s\n", sha1_to_hex(sha1));
+	prefetch(sha1);
+		
+	return 0;
+}
+
+static int loop(void)
+{
+	while (process_queue) {
+		struct object *obj = process_queue->item;
+		/*
+		fprintf(stderr, "%d objects to pull\n", 
+			object_list_length(process_queue));
+		*/
+		process_queue = process_queue->next;
+		if (!process_queue)
+			process_queue_end = &process_queue;
+
+		//fprintf(stderr, "fetch %s\n", sha1_to_hex(obj->sha1));
+		
+		if (make_sure_we_have_it(obj->type ?: "object", 
+					 obj->sha1))
+			return -1;
+		if (!obj->type)
+			parse_object(obj->sha1);
+		if (obj->type == commit_type) {
+			if (process_commit((struct commit *)obj))
+				return -1;
+			continue;
+		}
+		if (obj->type == tree_type) {
+			if (process_tree((struct tree *)obj))
+				return -1;
+			continue;
+		}
+		if (obj->type == blob_type) {
+			continue;
+		}
+		if (obj->type == tag_type) {
+			if (process_tag((struct tag *)obj))
+				return -1;
+			continue;
+		}
+		return error("Unable to determine requirements "
+			     "of type %s for %s",
+			     obj->type, sha1_to_hex(obj->sha1));
+	}
+	return 0;
 }
 
 static int interpret_target(char *target, unsigned char *sha1)
@@ -164,7 +186,9 @@ int pull(char *target)
 	if (interpret_target(target, sha1))
 		return error("Could not interpret %s as something to pull",
 			     target);
-	if (process_unknown(sha1))
+	if (process(sha1, NULL))
+		return -1;
+	if (loop())
 		return -1;
 	
 	if (write_ref) {

pull.h

@@ -8,6 +8,13 @@
  */
 extern int fetch(unsigned char *sha1);
 
+/*
+ * Fetch the specified object and store it locally; fetch() will be
+ * called later to determine success. To be provided by the particular
+ * implementation.
+ */
+extern void prefetch(unsigned char *sha1);
+
 /*
  * Fetch ref (relative to $GIT_DIR/refs) from the remote, and store
  * the 20-byte SHA1 in sha1.  Return 0 on success, -1 on failure.  To

ssh-pull.c

@@ -10,6 +10,10 @@ static int fd_out;
 static unsigned char remote_version = 0;
 static unsigned char local_version = 1;
 
+void prefetch(unsigned char *sha1)
+{
+}
+
 int fetch(unsigned char *sha1)
 {
 	int ret;