last-modified: use Bloom filters when available

Our 'git last-modified' performs a revision walk, and computes a diff at
each point in the walk to figure out whether a given revision changed
any of the paths it considers interesting.

When changed-path Bloom filters are available, we can avoid computing
many such diffs. Before computing a diff, we first check if any of the
remaining paths of interest were possibly changed at a given commit by
consulting its Bloom filter. If any of them are, we are resigned to
compute the diff.

If none of those queries returned "maybe", we know that the given commit
doesn't contain any changed paths which are interesting to us. So, we
can avoid computing it in this case.

Comparing the perf test results on git.git:

    Test                                        HEAD~             HEAD
    ------------------------------------------------------------------------------------
    8020.1: top-level last-modified             4.49(4.34+0.11)   2.22(2.05+0.09) -50.6%
    8020.2: top-level recursive last-modified   5.64(5.45+0.11)   5.62(5.30+0.11) -0.4%
    8020.3: subdir last-modified                0.11(0.06+0.04)   0.07(0.03+0.04) -36.4%

Based-on-patch-by: Taylor Blau <[email protected]>
Signed-off-by: Toon Claes <[email protected]>

Author: To1ne

builtin/last-modified.c

@@ -1,5 +1,7 @@
 #include "git-compat-util.h"
+#include "bloom.h"
 #include "builtin.h"
+#include "commit-graph.h"
 #include "commit.h"
 #include "config.h"
 #include "diff.h"
@@ -17,6 +19,7 @@
 struct last_modified_entry {
 	struct hashmap_entry hashent;
 	struct object_id oid;
+	struct bloom_key key;
 	const char path[FLEX_ARRAY];
 };
 
@@ -41,6 +44,12 @@ struct last_modified {
 
 static void last_modified_release(struct last_modified *lm)
 {
+	struct hashmap_iter iter;
+	struct last_modified_entry *ent;
+
+	hashmap_for_each_entry(&lm->paths, &iter, ent, hashent)
+		bloom_key_clear(&ent->key);
+
 	hashmap_clear_and_free(&lm->paths, struct last_modified_entry, hashent);
 	release_revisions(&lm->rev);
 }
@@ -62,6 +71,9 @@ static void add_path_from_diff(struct diff_queue_struct *q,
 
 		FLEX_ALLOC_STR(ent, path, path);
 		oidcpy(&ent->oid, &p->two->oid);
+		if (lm->rev.bloom_filter_settings)
+			bloom_key_fill(&ent->key, path, strlen(path),
+				       lm->rev.bloom_filter_settings);
 		hashmap_entry_init(&ent->hashent, strhash(ent->path));
 		hashmap_add(&lm->paths, &ent->hashent);
 	}
@@ -138,6 +150,7 @@ static void mark_path(const char *path, const struct object_id *oid,
 	last_modified_emit(data->lm, path, data->commit);
 
 	hashmap_remove(&data->lm->paths, &ent->hashent, path);
+	bloom_key_clear(&ent->key);
 	free(ent);
 }
 
@@ -181,6 +194,27 @@ static void last_modified_diff(struct diff_queue_struct *q,
 	}
 }
 
+static bool maybe_changed_path(struct last_modified *lm, struct commit *origin)
+{
+	struct bloom_filter *filter;
+	struct last_modified_entry *ent;
+	struct hashmap_iter iter;
+
+	if (!lm->rev.bloom_filter_settings)
+		return true;
+
+	filter = get_bloom_filter(lm->rev.repo, origin);
+	if (!filter)
+		return true;
+
+	hashmap_for_each_entry(&lm->paths, &iter, ent, hashent) {
+		if (bloom_filter_contains(filter, &ent->key,
+					  lm->rev.bloom_filter_settings))
+			return true;
+	}
+	return false;
+}
+
 static int last_modified_run(struct last_modified *lm)
 {
 	struct last_modified_callback_data data = { .lm = lm };
@@ -196,14 +230,22 @@ static int last_modified_run(struct last_modified *lm)
 		if (!data.commit)
 			BUG("paths remaining beyond boundary in last-modified");
 
+		// TODO distinguish when boundary is the one touching paths and
+		// beyond it
+
 		if (data.commit->object.flags & BOUNDARY) {
 			diff_tree_oid(lm->rev.repo->hash_algo->empty_tree,
 				      &data.commit->object.oid, "",
 				      &lm->rev.diffopt);
 			diff_flush(&lm->rev.diffopt);
-		} else {
-			log_tree_commit(&lm->rev, data.commit);
+
+			//break;
 		}
+
+		if (!maybe_changed_path(lm, data.commit))
+			continue;
+
+		log_tree_commit(&lm->rev, data.commit);
 	}
 
 	return 0;
@@ -230,6 +272,8 @@ static int last_modified_init(struct last_modified *lm, struct repository *r,
 		return argc;
 	}
 
+	lm->rev.bloom_filter_settings = get_bloom_filter_settings(lm->rev.repo);
+
 	if (populate_paths_from_revs(lm) < 0)
 		return error(_("unable to setup last-modified"));
 

commit-graph.c

@@ -820,7 +820,12 @@ int corrected_commit_dates_enabled(struct repository *r)
 
 struct bloom_filter_settings *get_bloom_filter_settings(struct repository *r)
 {
-	struct commit_graph *g = r->objects->commit_graph;
+	struct commit_graph *g;
+
+	if (!prepare_commit_graph(r))
+	       return NULL;
+
+	g = r->objects->commit_graph;
 	while (g) {
 		if (g->bloom_filter_settings)
 			return g->bloom_filter_settings;

t/t8020-last-modified.sh

@@ -113,6 +113,8 @@ test_expect_success 'limit last-modified traversal by commit' '
 	EOF
 '
 
+# TODO test exact at boundary
+
 test_expect_success 'only last-modified files in the current tree' '
 	git rm -rf a &&
 	git commit -m "remove a" &&