merge-ort: call diffcore_rename() directly

We want to pass additional information to diffcore_rename() (or some
variant thereof) without plumbing that extra information through
diff_tree_oid() and diffcore_std().  Further, since we will need to
gather additional special information related to diffs and are walking
the trees anyway in collect_merge_info(), it seems odd to have
diff_tree_oid()/diffcore_std() repeat those tree walks.  And there may
be times where we can avoid traversing into a subtree in
collect_merge_info() (based on additional information at our disposal),
that the basic diff logic would be unable to take advantage of.  For all
these reasons, just create the add and delete pairs ourself and then
call diffcore_rename() directly.

This change is primarily about enabling future optimizations; the
advantage of avoiding extra tree traversals is small compared to the
cost of rename detection, and the advantage of avoiding the extra tree
traversals is somewhat offset by the extra time spent in
collect_merge_info() collecting the additional data anyway.  However...

For the testcases mentioned in commit 557ac0350d ("merge-ort: begin
performance work; instrument with trace2_region_* calls", 2020-10-28),
this change improves the performance as follows:

                            Before                  After
    no-renames:       13.294 s ±  0.103 s    12.775 s ±  0.062 s
    mega-renames:    187.248 s ±  0.882 s   188.754 s ±  0.284 s
    just-one-mega:     5.557 s ±  0.017 s     5.599 s ±  0.019 s

Signed-off-by: Elijah Newren <newren@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 59 insertions, 7 deletions

diff --git a/merge-ort.c b/merge-ort.c
index 931b914..603d30c 100644
--- a/merge-ort.c
+++ b/merge-ort.c
@@ -535,6 +535,23 @@ static void setup_path_info(struct merge_options *opt,
 	result->util = mi;
 }
 
+static void add_pair(struct merge_options *opt,
+		     struct name_entry *names,
+		     const char *pathname,
+		     unsigned side,
+		     unsigned is_add /* if false, is_delete */)
+{
+	struct diff_filespec *one, *two;
+	struct rename_info *renames = &opt->priv->renames;
+	int names_idx = is_add ? side : 0;
+
+	one = alloc_filespec(pathname);
+	two = alloc_filespec(pathname);
+	fill_filespec(is_add ? two : one,
+		      &names[names_idx].oid, 1, names[names_idx].mode);
+	diff_queue(&renames->pairs[side], one, two);
+}
+
 static void collect_rename_info(struct merge_options *opt,
 				struct name_entry *names,
 				const char *dirname,
@@ -544,6 +561,7 @@ static void collect_rename_info(struct merge_options *opt,
 				unsigned match_mask)
 {
 	struct rename_info *renames = &opt->priv->renames;
+	unsigned side;
 
 	/* Update dirs_removed, as needed */
 	if (dirmask == 1 || dirmask == 3 || dirmask == 5) {
@@ -554,6 +572,21 @@ static void collect_rename_info(struct merge_options *opt,
 		if (sides & 2)
 			strset_add(&renames->dirs_removed[2], fullname);
 	}
+
+	if (filemask == 0 || filemask == 7)
+		return;
+
+	for (side = MERGE_SIDE1; side <= MERGE_SIDE2; ++side) {
+		unsigned side_mask = (1 << side);
+
+		/* Check for deletion on side */
+		if ((filemask & 1) && !(filemask & side_mask))
+			add_pair(opt, names, fullname, side, 0 /* delete */);
+
+		/* Check for addition on side */
+		if (!(filemask & 1) && (filemask & side_mask))
+			add_pair(opt, names, fullname, side, 1 /* add */);
+	}
 }
 
 static int collect_merge_info_callback(int n,
@@ -2079,6 +2112,27 @@ static int process_renames(struct merge_options *opt,
 	return clean_merge;
 }
 
+static void resolve_diffpair_statuses(struct diff_queue_struct *q)
+{
+	/*
+	 * A simplified version of diff_resolve_rename_copy(); would probably
+	 * just use that function but it's static...
+	 */
+	int i;
+	struct diff_filepair *p;
+
+	for (i = 0; i < q->nr; ++i) {
+		p = q->queue[i];
+		p->status = 0; /* undecided */
+		if (!DIFF_FILE_VALID(p->one))
+			p->status = DIFF_STATUS_ADDED;
+		else if (!DIFF_FILE_VALID(p->two))
+			p->status = DIFF_STATUS_DELETED;
+		else if (DIFF_PAIR_RENAME(p))
+			p->status = DIFF_STATUS_RENAMED;
+	}
+}
+
 static int compare_pairs(const void *a_, const void *b_)
 {
 	const struct diff_filepair *a = *((const struct diff_filepair **)a_);
@@ -2089,8 +2143,6 @@ static int compare_pairs(const void *a_, const void *b_)
 
 /* Call diffcore_rename() to compute which files have changed on given side */
 static void detect_regular_renames(struct merge_options *opt,
-				   struct tree *merge_base,
-				   struct tree *side,
 				   unsigned side_index)
 {
 	struct diff_options diff_opts;
@@ -2108,11 +2160,11 @@ static void detect_regular_renames(struct merge_options *opt,
 	diff_opts.output_format = DIFF_FORMAT_NO_OUTPUT;
 	diff_setup_done(&diff_opts);
 
+	diff_queued_diff = renames->pairs[side_index];
 	trace2_region_enter("diff", "diffcore_rename", opt->repo);
-	diff_tree_oid(&merge_base->object.oid, &side->object.oid, "",
-		      &diff_opts);
-	diffcore_std(&diff_opts);
+	diffcore_rename(&diff_opts);
 	trace2_region_leave("diff", "diffcore_rename", opt->repo);
+	resolve_diffpair_statuses(&diff_queued_diff);
 
 	if (diff_opts.needed_rename_limit > renames->needed_limit)
 		renames->needed_limit = diff_opts.needed_rename_limit;
@@ -2212,8 +2264,8 @@ static int detect_and_process_renames(struct merge_options *opt,
 	memset(&combined, 0, sizeof(combined));
 
 	trace2_region_enter("merge", "regular renames", opt->repo);
-	detect_regular_renames(opt, merge_base, side1, MERGE_SIDE1);
-	detect_regular_renames(opt, merge_base, side2, MERGE_SIDE2);
+	detect_regular_renames(opt, MERGE_SIDE1);
+	detect_regular_renames(opt, MERGE_SIDE2);
 	trace2_region_leave("merge", "regular renames", opt->repo);
 
 	trace2_region_enter("merge", "directory renames", opt->repo);