merge-ort, diffcore-rename: employ cached renames when possible

When there are many renames between the old base of a series of commits
and the new base, the way sequencer.c, merge-recursive.c, and
diffcore-rename.c have traditionally split the work resulted in
redetecting the same renames with each and every commit being
transplanted.  To address this, the last several commits have been
creating a cache of rename detection results, determining when it was
safe to use such a cache in subsequent merge operations, adding helper
functions, and so on.  See the previous half dozen commit messages for
additional discussion of this optimization, particularly the message a
few commits ago entitled "add code to check for whether cached renames
can be reused".  This commit finally ties all of that work together,
modifying the merge algorithm to make use of these cached renames.

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:        5.553 s ±  0.078 s     5.624 s ±  0.077 s
    mega-renames:     11.308 s ±  0.062 s    10.213 s ±  0.032 s
    just-one-mega:   491.8  ms ±  7.6  ms   497.6  ms ±  5.3  ms

Note that this optimization competes with the previous optimizations
(namely full use of exact renames, basename-guided rename detection, and
detecting when we can skip detecting renames for certain paths and still
get the same result); if it were not for those previous optimizations,
this optimization would have sped up the mega-renames testcase by a
factor of nearly 35.  (The factor of 35 comes from the fact that the
mega-renames testcase involves rebasing 35 commits, and each one
essentially involves detecting the same renames.)  So, while the
improvement seen here is modest at best, keep in mind that this
optimization kicks in to help accelerate cases where the previous
optimizations do not apply, so there may be other testcases where this
optimization helps more.

The changes made in this optimization also lay some important groundwork
for a future optimization around having collect_merge_info() avoid
recursing into subtrees in more cases.

Signed-off-by: Elijah Newren <[email protected]>

Author: newren

diffcore-rename.c

@@ -562,7 +562,8 @@ static void update_dir_rename_counts(struct dir_rename_info *info,
 static void initialize_dir_rename_info(struct dir_rename_info *info,
 				       struct strintmap *relevant_sources,
 				       struct strintmap *dirs_removed,
-				       struct strmap *dir_rename_count)
+				       struct strmap *dir_rename_count,
+				       struct strmap *cached_pairs)
 {
 	struct hashmap_iter iter;
 	struct strmap_entry *entry;
@@ -626,6 +627,17 @@ static void initialize_dir_rename_info(struct dir_rename_info *info,
 					 rename_dst[i].p->two->path);
 	}
 
+	/* Add cached_pairs to counts */
+	strmap_for_each_entry(cached_pairs, &iter, entry) {
+		const char *old_name = entry->key;
+		const char *new_name = entry->value;
+		if (!new_name)
+			/* known delete; ignore it */
+			continue;
+
+		update_dir_rename_counts(info, dirs_removed, old_name, new_name);
+	}
+
 	/*
 	 * Now we collapse
 	 *    dir_rename_count: old_directory -> {new_directory -> count}
@@ -1194,7 +1206,8 @@ static void handle_early_known_dir_renames(struct dir_rename_info *info,
 void diffcore_rename_extended(struct diff_options *options,
 			      struct strintmap *relevant_sources,
 			      struct strintmap *dirs_removed,
-			      struct strmap *dir_rename_count)
+			      struct strmap *dir_rename_count,
+			      struct strmap *cached_pairs)
 {
 	int detect_rename = options->detect_rename;
 	int minimum_score = options->rename_score;
@@ -1310,7 +1323,8 @@ void diffcore_rename_extended(struct diff_options *options,
 		/* Preparation for basename-driven matching. */
 		trace2_region_enter("diff", "dir rename setup", options->repo);
 		initialize_dir_rename_info(&info, relevant_sources,
-					   dirs_removed, dir_rename_count);
+					   dirs_removed, dir_rename_count,
+					   cached_pairs);
 		trace2_region_leave("diff", "dir rename setup", options->repo);
 
 		/* Utilize file basenames to quickly find renames. */
@@ -1509,5 +1523,5 @@ void diffcore_rename_extended(struct diff_options *options,
 
 void diffcore_rename(struct diff_options *options)
 {
-	diffcore_rename_extended(options, NULL, NULL, NULL);
+	diffcore_rename_extended(options, NULL, NULL, NULL, NULL);
 }

diffcore.h

@@ -180,7 +180,8 @@ void diffcore_rename(struct diff_options *);
 void diffcore_rename_extended(struct diff_options *options,
 			      struct strintmap *relevant_sources,
 			      struct strintmap *dirs_removed,
-			      struct strmap *dir_rename_count);
+			      struct strmap *dir_rename_count,
+			      struct strmap *cached_pairs);
 void diffcore_merge_broken(void);
 void diffcore_pickaxe(struct diff_options *);
 void diffcore_order(const char *orderfile);

merge-ort.c

@@ -739,15 +739,48 @@ static void add_pair(struct merge_options *opt,
 	struct rename_info *renames = &opt->priv->renames;
 	int names_idx = is_add ? side : 0;
 
-	if (!is_add) {
+	if (is_add) {
+		if (strset_contains(&renames->cached_target_names[side],
+				    pathname))
+			return;
+	} else {
 		unsigned content_relevant = (match_mask == 0);
 		unsigned location_relevant = (dir_rename_mask == 0x07);
 
+		/*
+		 * If pathname is found in cached_irrelevant[side] due to
+		 * previous pick but for this commit content is relevant,
+		 * then we need to remove it from cached_irrelevant.
+		 */
+		if (content_relevant)
+			/* strset_remove is no-op if strset doesn't have key */
+			strset_remove(&renames->cached_irrelevant[side],
+				      pathname);
+
+		/*
+		 * We do not need to re-detect renames for paths that we already
+		 * know the pairing, i.e. for cached_pairs (or
+		 * cached_irrelevant).  However, handle_deferred_entries() needs
+		 * to loop over the union of keys from relevant_sources[side] and
+		 * cached_pairs[side], so for simplicity we set relevant_sources
+		 * for all the cached_pairs too and then strip them back out in
+		 * prune_cached_from_relevant() at the beginning of
+		 * detect_regular_renames().
+		 */
 		if (content_relevant || location_relevant) {
 			/* content_relevant trumps location_relevant */
 			strintmap_set(&renames->relevant_sources[side], pathname,
 				      content_relevant ? RELEVANT_CONTENT : RELEVANT_LOCATION);
 		}
+
+		/*
+		 * Avoid creating pair if we've already cached rename results.
+		 * Note that we do this after setting relevant_sources[side]
+		 * as noted in the comment above.
+		 */
+		if (strmap_contains(&renames->cached_pairs[side], pathname) ||
+		    strset_contains(&renames->cached_irrelevant[side], pathname))
+			return;
 	}
 
 	one = alloc_filespec(pathname);
@@ -2274,7 +2307,9 @@ static inline int possible_side_renames(struct rename_info *renames,
 static inline int possible_renames(struct rename_info *renames)
 {
 	return possible_side_renames(renames, 1) ||
-	       possible_side_renames(renames, 2);
+	       possible_side_renames(renames, 2) ||
+	       !strmap_empty(&renames->cached_pairs[1]) ||
+	       !strmap_empty(&renames->cached_pairs[2]);
 }
 
 static void resolve_diffpair_statuses(struct diff_queue_struct *q)
@@ -2298,7 +2333,6 @@ static void resolve_diffpair_statuses(struct diff_queue_struct *q)
 	}
 }
 
-MAYBE_UNUSED
 static void prune_cached_from_relevant(struct rename_info *renames,
 				       unsigned side)
 {
@@ -2318,7 +2352,6 @@ static void prune_cached_from_relevant(struct rename_info *renames,
 	}
 }
 
-MAYBE_UNUSED
 static void use_cached_pairs(struct merge_options *opt,
 			     struct strmap *cached_pairs,
 			     struct diff_queue_struct *pairs)
@@ -2401,6 +2434,7 @@ static void detect_regular_renames(struct merge_options *opt,
 	struct diff_options diff_opts;
 	struct rename_info *renames = &opt->priv->renames;
 
+	prune_cached_from_relevant(renames, side_index);
 	if (!possible_side_renames(renames, side_index)) {
 		/*
 		 * No rename detection needed for this side, but we still need
@@ -2411,6 +2445,7 @@ static void detect_regular_renames(struct merge_options *opt,
 		return;
 	}
 
+	partial_clear_dir_rename_count(&renames->dir_rename_count[side_index]);
 	repo_diff_setup(opt->repo, &diff_opts);
 	diff_opts.flags.recursive = 1;
 	diff_opts.flags.rename_empty = 0;
@@ -2428,7 +2463,8 @@ static void detect_regular_renames(struct merge_options *opt,
 	diffcore_rename_extended(&diff_opts,
 				 &renames->relevant_sources[side_index],
 				 &renames->dirs_removed[side_index],
-				 &renames->dir_rename_count[side_index]);
+				 &renames->dir_rename_count[side_index],
+				 &renames->cached_pairs[side_index]);
 	trace2_region_leave("diff", "diffcore_rename", opt->repo);
 	resolve_diffpair_statuses(&diff_queued_diff);
 
@@ -2535,6 +2571,8 @@ static int detect_and_process_renames(struct merge_options *opt,
 	trace2_region_enter("merge", "regular renames", opt->repo);
 	detect_regular_renames(opt, MERGE_SIDE1);
 	detect_regular_renames(opt, MERGE_SIDE2);
+	use_cached_pairs(opt, &renames->cached_pairs[1], &renames->pairs[1]);
+	use_cached_pairs(opt, &renames->cached_pairs[2], &renames->pairs[2]);
 	trace2_region_leave("merge", "regular renames", opt->repo);
 
 	trace2_region_enter("merge", "directory renames", opt->repo);