Optimization batch 6: make full use of exact renames

diffcore-rename.c

@@ -454,6 +454,54 @@ static int find_renames(struct diff_score *mx, int dst_cnt, int minimum_score, i
 	return count;
 }
 
+static void remove_unneeded_paths_from_src(int detecting_copies)
+{
+	int i, new_num_src;
+
+	if (detecting_copies)
+		return; /* nothing to remove */
+	if (break_idx)
+		return; /* culling incompatible with break detection */
+
+	/*
+	 * Note on reasons why we cull unneeded sources but not destinations:
+	 *   1) Pairings are stored in rename_dst (not rename_src), which we
+	 *      need to keep around.  So, we just can't cull rename_dst even
+	 *      if we wanted to.  But doing so wouldn't help because...
+	 *
+	 *   2) There is a matrix pairwise comparison that follows the
+	 *      "Performing inexact rename detection" progress message.
+	 *      Iterating over the destinations is done in the outer loop,
+	 *      hence we only iterate over each of those once and we can
+	 *      easily skip the outer loop early if the destination isn't
+	 *      relevant.  That's only one check per destination path to
+	 *      skip.
+	 *
+	 *      By contrast, the sources are iterated in the inner loop; if
+	 *      we check whether a source can be skipped, then we'll be
+	 *      checking it N separate times, once for each destination.
+	 *      We don't want to have to iterate over known-not-needed
+	 *      sources N times each, so avoid that by removing the sources
+	 *      from rename_src here.
+	 */
+	for (i = 0, new_num_src = 0; i < rename_src_nr; i++) {
+		/*
+		 * renames are stored in rename_dst, so if a rename has
+		 * already been detected using this source, we can just
+		 * remove the source knowing rename_dst has its info.
+		 */
+		if (rename_src[i].p->one->rename_used)
+			continue;
+
+		if (new_num_src < i)
+			memcpy(&rename_src[new_num_src], &rename_src[i],
+			       sizeof(struct diff_rename_src));
+		new_num_src++;
+	}
+
+	rename_src_nr = new_num_src;
+}
+
 void diffcore_rename(struct diff_options *options)
 {
 	int detect_rename = options->detect_rename;
@@ -463,9 +511,11 @@ void diffcore_rename(struct diff_options *options)
 	struct diff_score *mx;
 	int i, j, rename_count, skip_unmodified = 0;
 	int num_destinations, dst_cnt;
+	int num_sources, want_copies;
 	struct progress *progress = NULL;
 
 	trace2_region_enter("diff", "setup", options->repo);
+	want_copies = (detect_rename == DIFF_DETECT_COPY);
 	if (!minimum_score)
 		minimum_score = DEFAULT_RENAME_SCORE;
 
@@ -502,7 +552,7 @@ void diffcore_rename(struct diff_options *options)
 				p->one->rename_used++;
 			register_rename_src(p);
 		}
-		else if (detect_rename == DIFF_DETECT_COPY) {
+		else if (want_copies) {
 			/*
 			 * Increment the "rename_used" score by
 			 * one, to indicate ourselves as a user.
@@ -527,17 +577,16 @@ void diffcore_rename(struct diff_options *options)
 	if (minimum_score == MAX_SCORE)
 		goto cleanup;
 
-	/*
-	 * Calculate how many renames are left (but all the source
-	 * files still remain as options for rename/copies!)
-	 */
+	/* Calculate how many renames are left */
 	num_destinations = (rename_dst_nr - rename_count);
+	remove_unneeded_paths_from_src(want_copies);
+	num_sources = rename_src_nr;
 
 	/* All done? */
-	if (!num_destinations)
+	if (!num_destinations || !num_sources)
 		goto cleanup;
 
-	switch (too_many_rename_candidates(num_destinations, rename_src_nr,
+	switch (too_many_rename_candidates(num_destinations, num_sources,
 					   options)) {
 	case 1:
 		goto cleanup;
@@ -553,7 +602,7 @@ void diffcore_rename(struct diff_options *options)
 	if (options->show_rename_progress) {
 		progress = start_delayed_progress(
 				_("Performing inexact rename detection"),
-				(uint64_t)num_destinations * (uint64_t)rename_src_nr);
+				(uint64_t)num_destinations * (uint64_t)num_sources);
 	}
 
 	mx = xcalloc(st_mult(NUM_CANDIDATE_PER_DST, num_destinations),
@@ -573,6 +622,8 @@ void diffcore_rename(struct diff_options *options)
 			struct diff_filespec *one = rename_src[j].p->one;
 			struct diff_score this_src;
 
+			assert(!one->rename_used || want_copies || break_idx);
+
 			if (skip_unmodified &&
 			    diff_unmodified_pair(rename_src[j].p))
 				continue;
@@ -594,15 +645,15 @@ void diffcore_rename(struct diff_options *options)
 		}
 		dst_cnt++;
 		display_progress(progress,
-				 (uint64_t)dst_cnt * (uint64_t)rename_src_nr);
+				 (uint64_t)dst_cnt * (uint64_t)num_sources);
 	}
 	stop_progress(&progress);
 
 	/* cost matrix sorted by most to least similar pair */
 	STABLE_QSORT(mx, dst_cnt * NUM_CANDIDATE_PER_DST, score_compare);
 
 	rename_count += find_renames(mx, dst_cnt, minimum_score, 0);
-	if (detect_rename == DIFF_DETECT_COPY)
+	if (want_copies)
 		rename_count += find_renames(mx, dst_cnt, minimum_score, 1);
 	free(mx);
 	trace2_region_leave("diff", "inexact renames", options->repo);