From 5bdbaaa4e9dd901dd2907b53bbecfdf3eac9276b Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@osdl.org>
Date: Thu, 15 Sep 2005 15:14:29 -0700
Subject: [PATCH] [PATCH] Re-organize "git-rev-list --objects" logic

The logic to calculate the full object list used to be very inter-twined
with the logic that looked up the commits.

For no good reason - it's actually a lot simpler to just do that logic
as a separate pass.

This improves performance a bit, and uses slightly less memory in my
tests, but more importantly it makes the code simpler to work with and
follow what it does.

The performance win is less than I had hoped for, but I get:

Before:

	[torvalds@g5 linux]$ /usr/bin/time git-rev-list --objects v2.6.12..HEAD | wc -l
	13.64user 0.42system 0:14.13elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k
	0inputs+0outputs (0major+47947minor)pagefaults 0swaps
	58945

After:

	[torvalds@g5 linux]$ /usr/bin/time git-rev-list --objects v2.6.12..HEAD | wc -l
	11.80user 0.36system 0:12.16elapsed 99%CPU (0avgtext+0avgdata 0maxresident)k
	0inputs+0outputs (0major+42684minor)pagefaults 0swaps
	58945

ie it improved by 2 seconds, and took a 5000+ fewer pages (hey, that's
20MB out of 174MB to go). And got the same number of objects (in theory,
the more expensive one might find some more shared objects to avoid. In
practice it obviously doesn't).

I know how to make it use _lots_ less memory, which will probably speed it
up. But that's for another time, and I'd prefer to see this go in first.

Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>
---
 rev-list.c | 40 +++++++++++++++-------------------------
 1 file changed, 15 insertions(+), 25 deletions(-)

diff --git a/rev-list.c b/rev-list.c
index 96aa34249e..c410bc33dc 100644
--- a/rev-list.c
+++ b/rev-list.c
@@ -231,8 +231,6 @@ static void mark_parents_uninteresting(struct commit *commit)
 {
 	struct commit_list *parents = commit->parents;
 
-	if (tree_objects)
-		mark_tree_uninteresting(commit->tree);
 	while (parents) {
 		struct commit *commit = parents->item;
 		commit->object.flags |= UNINTERESTING;
@@ -272,29 +270,6 @@ static int everybody_uninteresting(struct commit_list *orig)
 			continue;
 		return 0;
 	}
-
-	/*
-	 * Ok, go back and mark all the edge trees uninteresting,
-	 * since otherwise we can have situations where a parent
-	 * that was marked uninteresting (and we never even had
-	 * to look at) had lots of objects that we don't want to
-	 * include.
-	 *
-	 * NOTE! This still doesn't mean that the object list is
-	 * "correct", since we may end up listing objects that
-	 * even older commits (that we don't list) do actually
-	 * reference, but it gets us to a minimal list (or very
-	 * close) in practice.
-	 */
-	if (!tree_objects)
-		return 1;
-
-	while (orig) {
-		struct commit *commit = orig->item;
-		if (!parse_commit(commit) && commit->tree)
-			mark_tree_uninteresting(commit->tree);
-		orig = orig->next;
-	}
 	return 1;
 }
 
@@ -370,6 +345,19 @@ static struct commit_list *find_bisection(struct commit_list *list)
 	return best;
 }
 
+static void mark_edges_uninteresting(struct commit_list *list)
+{
+	for ( ; list; list = list->next) {
+		struct commit_list *parents = list->item->parents;
+
+		for ( ; parents; parents = parents->next) {
+			struct commit *commit = parents->item;
+			if (commit->object.flags & UNINTERESTING)
+				mark_tree_uninteresting(commit->tree);
+		}
+	}
+}
+
 static struct commit_list *limit_list(struct commit_list *list)
 {
 	struct commit_list *newlist = NULL;
@@ -388,6 +376,8 @@ static struct commit_list *limit_list(struct commit_list *list)
 		}
 		p = &commit_list_insert(commit, p)->next;
 	}
+	if (tree_objects)
+		mark_edges_uninteresting(newlist);
 	if (bisect_list)
 		newlist = find_bisection(newlist);
 	return newlist;
-- 
2.11.4.GIT