pack-objects: don't traverse objects unnecessarily

This brings back some of the performance lost in optimizing recency
order inside pack objects. We were doing extreme amounts of object
re-traversal: for the 2.14 million objects in the Linux kernel
repository, we were calling add_to_write_order() over 1.03 billion times
(a 0.2% hit rate, making 99.8% of of these calls extraneous).

Two optimizations take place here- we can start our objects array
iteration from a known point where we left off before we started trying
to find our tags, and we don't need to do the deep dives required by
add_family_to_write_order() if the object has already been marked as
filled.

These two optimizations bring some pretty spectacular results via `perf
stat`:

task-clock:   83373 ms        --> 43800 ms         (50% faster)
cycles:       221,633,461,676 --> 116,307,209,986  (47% fewer)
instructions: 149,299,179,939 --> 122,998,800,184  (18% fewer)

Helped-by: Ramsay Jones (format string fix in "die" message)
Signed-off-by: Dan McGee <dpmcgee@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 12 insertions, 6 deletions

diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index 5b544bf444..80ab6c39f9 100644
--- a/builtin/pack-objects.c
+++ b/builtin/pack-objects.c
@@ -520,7 +520,7 @@ static void add_family_to_write_order(struct object_entry **wo,
 
 static struct object_entry **compute_write_order(void)
 {
-	unsigned int i, wo_end;
+	unsigned int i, wo_end, last_untagged;
 
 	struct object_entry **wo = xmalloc(nr_objects * sizeof(*wo));
 
@@ -551,7 +551,7 @@ static struct object_entry **compute_write_order(void)
 	for_each_tag_ref(mark_tagged, NULL);
 
 	/*
-	 * Give the commits in the original recency order until
+	 * Give the objects in the original recency order until
 	 * we see a tagged tip.
 	 */
 	for (i = wo_end = 0; i < nr_objects; i++) {
@@ -559,6 +559,7 @@ static struct object_entry **compute_write_order(void)
 			break;
 		add_to_write_order(wo, &wo_end, &objects[i]);
 	}
+	last_untagged = i;
 
 	/*
 	 * Then fill all the tagged tips.
@@ -571,7 +572,7 @@ static struct object_entry **compute_write_order(void)
 	/*
 	 * And then all remaining commits and tags.
 	 */
-	for (i = 0; i < nr_objects; i++) {
+	for (i = last_untagged; i < nr_objects; i++) {
 		if (objects[i].type != OBJ_COMMIT &&
 		    objects[i].type != OBJ_TAG)
 			continue;
@@ -581,7 +582,7 @@ static struct object_entry **compute_write_order(void)
 	/*
 	 * And then all the trees.
 	 */
-	for (i = 0; i < nr_objects; i++) {
+	for (i = last_untagged; i < nr_objects; i++) {
 		if (objects[i].type != OBJ_TREE)
 			continue;
 		add_to_write_order(wo, &wo_end, &objects[i]);
@@ -590,8 +591,13 @@ static struct object_entry **compute_write_order(void)
 	/*
 	 * Finally all the rest in really tight order
 	 */
-	for (i = 0; i < nr_objects; i++)
-		add_family_to_write_order(wo, &wo_end, &objects[i]);
+	for (i = last_untagged; i < nr_objects; i++) {
+		if (!objects[i].filled)
+			add_family_to_write_order(wo, &wo_end, &objects[i]);
+	}
+
+	if (wo_end != nr_objects)
+		die("ordered %u objects, expected %"PRIu32, wo_end, nr_objects);
 
 	return wo;
 }