diffcore-rename: filter rename_src list when possible

newren · gitster · commit 829514c5151d · 2021-02-15T18:02:16.000-08:00
We have to look at each entry in rename_src a total of rename_dst_nr times. When we're not detecting copies, any exact renames or ignorable rename paths will just be skipped over. While checking that these can be skipped over is a relatively cheap check, it's still a waste of time to do that check more than once, let alone rename_dst_nr times. When rename_src_nr is a few thousand times bigger than the number of relevant sources (such as when cherry-picking a commit that only touched a handful of files, but from a side of history that has different names for some high level directories), this time can add up. First make an initial pass over the rename_src array and move all the relevant entries to the front, so that we can iterate over just those relevant entries. For the testcases mentioned in commit 557ac03 ("merge-ort: begin performance work; instrument with trace2_region_* calls", 2020-10-28), this change improves the performance as follows: Before After no-renames: 14.119 s ± 0.101 s 13.815 s ± 0.062 s mega-renames: 1802.044 s ± 0.828 s 1799.937 s ± 0.493 s just-one-mega: 51.391 s ± 0.028 s 51.289 s ± 0.019 s Signed-off-by: Elijah Newren <newren@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
diff --git a/diffcore-rename.c b/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;
@@ -529,14 +577,10 @@ 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;
-	if (!want_copies)
-		num_sources -= rename_count;
 
 	/* All done? */
 	if (!num_destinations || !num_sources)
@@ -578,8 +622,7 @@ void diffcore_rename(struct diff_options *options)
 			struct diff_filespec *one = rename_src[j].p->one;
 			struct diff_score this_src;
 
-			if (one->rename_used && !want_copies)
-				continue;
+			assert(!one->rename_used || want_copies || break_idx);
 
 			if (skip_unmodified &&
 			    diff_unmodified_pair(rename_src[j].p))
