commit-reach: early exit paint_down_to_common for single merge-base

Commits not in the commit-graph get GENERATION_NUMBER_INFINITY and
sort to the top of the priority queue.  After those, commits with
finite generation numbers are popped in non-increasing order.
When MERGE_BASE_FIND_ALL is not set the first doubly-painted commit
with a finite generation is therefore a best merge-base: no commit
still in the queue can be a descendant of it.  Skip the expensive
STALE drain in this case.

Introduce enum merge_base_flags with MERGE_BASE_FIND_ALL and
MERGE_BASE_IGNORE_MISSING_COMMITS, replacing the two boolean
parameters in paint_down_to_common().  Thread the flags through
merge_bases_many(), get_merge_bases_many_0(), and the public
repo_get_merge_bases_many_dirty() API.  git merge-base (without
--all) passes 0, triggering the early exit.

On a 2.2M-commit merge-heavy monorepo with commit-graph:

  HEAD vs ~500:   5,229ms -> 24ms
  HEAD vs ~1000:  4,214ms -> 39ms
  HEAD vs ~5000:  3,799ms -> 46ms
  HEAD vs ~10000: 3,827ms -> 61ms

Signed-off-by: Kristofer Karlsson <krka@spotify.com>

Author: spkrka

builtin/merge-base.c

@@ -11,10 +11,12 @@
 
 static int show_merge_base(struct commit **rev, size_t rev_nr, int show_all)
 {
+	enum merge_base_flags flags = show_all ? MERGE_BASE_FIND_ALL : 0;
 	struct commit_list *result = NULL, *r;
 
 	if (repo_get_merge_bases_many_dirty(the_repository, rev[0],
-					    rev_nr - 1, rev + 1, &result) < 0) {
+					    rev_nr - 1, rev + 1,
+					    flags, &result) < 0) {
 		commit_list_free(result);
 		return -1;
 	}

commit-reach.c

@@ -54,7 +54,7 @@ static int paint_down_to_common(struct repository *r,
 				struct commit *one, int n,
 				struct commit **twos,
 				timestamp_t min_generation,
-				int ignore_missing_commits,
+				enum merge_base_flags mb_flags,
 				struct commit_list **result)
 {
 	struct prio_queue queue = { compare_commits_by_gen_then_commit_date };
@@ -97,6 +97,14 @@ static int paint_down_to_common(struct repository *r,
 			if (!(commit->object.flags & RESULT)) {
 				commit->object.flags |= RESULT;
 				tail = commit_list_append(commit, tail);
+				/*
+				 * The queue is generation-ordered; no
+				 * remaining common ancestor can be a
+				 * descendant of this one.
+				 */
+				if (!(mb_flags & MERGE_BASE_FIND_ALL) &&
+				    generation < GENERATION_NUMBER_INFINITY)
+					break;
 			}
 			/* Mark parents of a found merge stale */
 			flags |= STALE;
@@ -118,7 +126,7 @@ static int paint_down_to_common(struct repository *r,
 				 * corrupt commits would already have been
 				 * dispatched with a `die()`.
 				 */
-				if (ignore_missing_commits)
+				if (mb_flags & MERGE_BASE_IGNORE_MISSING_COMMITS)
 					return 0;
 				return error(_("could not parse commit %s"),
 					     oid_to_hex(&p->object.oid));
@@ -136,6 +144,7 @@ static int paint_down_to_common(struct repository *r,
 static int merge_bases_many(struct repository *r,
 			    struct commit *one, int n,
 			    struct commit **twos,
+			    enum merge_base_flags mb_flags,
 			    struct commit_list **result)
 {
 	struct commit_list *list = NULL, **tail = result;
@@ -165,7 +174,7 @@ static int merge_bases_many(struct repository *r,
 				     oid_to_hex(&twos[i]->object.oid));
 	}
 
-	if (paint_down_to_common(r, one, n, twos, 0, 0, &list)) {
+	if (paint_down_to_common(r, one, n, twos, 0, mb_flags, &list)) {
 		commit_list_free(list);
 		return -1;
 	}
@@ -246,7 +255,8 @@ static int remove_redundant_no_gen(struct repository *r,
 				min_generation = curr_generation;
 		}
 		if (paint_down_to_common(r, array[i], filled,
-					 work, min_generation, 0, &common)) {
+					 work, min_generation,
+					 MERGE_BASE_FIND_ALL, &common)) {
 			clear_commit_marks(array[i], all_flags);
 			clear_commit_marks_many(filled, work, all_flags);
 			commit_list_free(common);
@@ -425,14 +435,15 @@ static int get_merge_bases_many_0(struct repository *r,
 				  size_t n,
 				  struct commit **twos,
 				  int cleanup,
+				  enum merge_base_flags mb_flags,
 				  struct commit_list **result)
 {
 	struct commit_list *list, **tail = result;
 	struct commit **rslt;
 	size_t cnt, i;
 	int ret;
 
-	if (merge_bases_many(r, one, n, twos, result) < 0)
+	if (merge_bases_many(r, one, n, twos, mb_flags, result) < 0)
 		return -1;
 	for (i = 0; i < n; i++) {
 		if (one == twos[i])
@@ -475,24 +486,27 @@ int repo_get_merge_bases_many(struct repository *r,
 			      struct commit **twos,
 			      struct commit_list **result)
 {
-	return get_merge_bases_many_0(r, one, n, twos, 1, result);
+	return get_merge_bases_many_0(r, one, n, twos, 1,
+				     MERGE_BASE_FIND_ALL, result);
 }
 
 int repo_get_merge_bases_many_dirty(struct repository *r,
 				    struct commit *one,
 				    size_t n,
 				    struct commit **twos,
+				    enum merge_base_flags mb_flags,
 				    struct commit_list **result)
 {
-	return get_merge_bases_many_0(r, one, n, twos, 0, result);
+	return get_merge_bases_many_0(r, one, n, twos, 0, mb_flags, result);
 }
 
 int repo_get_merge_bases(struct repository *r,
 			 struct commit *one,
 			 struct commit *two,
 			 struct commit_list **result)
 {
-	return get_merge_bases_many_0(r, one, 1, &two, 1, result);
+	return get_merge_bases_many_0(r, one, 1, &two, 1,
+				     MERGE_BASE_FIND_ALL, result);
 }
 
 /*
@@ -537,6 +551,10 @@ int repo_in_merge_bases_many(struct repository *r, struct commit *commit,
 	struct commit_list *bases = NULL;
 	int ret = 0, i;
 	timestamp_t generation, max_generation = GENERATION_NUMBER_ZERO;
+	enum merge_base_flags mb_flags = MERGE_BASE_FIND_ALL;
+
+	if (ignore_missing_commits)
+		mb_flags |= MERGE_BASE_IGNORE_MISSING_COMMITS;
 
 	if (repo_parse_commit(r, commit))
 		return ignore_missing_commits ? 0 : -1;
@@ -555,7 +573,7 @@ int repo_in_merge_bases_many(struct repository *r, struct commit *commit,
 
 	if (paint_down_to_common(r, commit,
 				 nr_reference, reference,
-				 generation, ignore_missing_commits, &bases))
+				 generation, mb_flags, &bases))
 		ret = -1;
 	else if (commit->object.flags & PARENT2)
 		ret = 1;

commit-reach.h

@@ -17,10 +17,20 @@ int repo_get_merge_bases_many(struct repository *r,
 			      struct commit *one, size_t n,
 			      struct commit **twos,
 			      struct commit_list **result);
-/* To be used only when object flags after this call no longer matter */
+enum merge_base_flags {
+	MERGE_BASE_FIND_ALL               = (1 << 0),
+	MERGE_BASE_IGNORE_MISSING_COMMITS = (1 << 1),
+};
+
+/*
+ * To be used only when object flags after this call no longer matter.
+ * Without MERGE_BASE_FIND_ALL and with generation numbers available,
+ * returns after finding the first merge-base, skipping the STALE drain.
+ */
 int repo_get_merge_bases_many_dirty(struct repository *r,
 				    struct commit *one, size_t n,
 				    struct commit **twos,
+				    enum merge_base_flags mb_flags,
 				    struct commit_list **result);
 
 int get_octopus_merge_bases(struct commit_list *in, struct commit_list **result);

t/t6010-merge-base.sh

@@ -305,4 +305,123 @@ test_expect_success 'merge-base --octopus --all for complex tree' '
 	test_cmp expected actual
 '
 
+# The following tests verify that "git merge-base" (without --all)
+# returns the same result with and without a commit-graph.
+# This exercises the early-exit optimisation in paint_down_to_common
+# that skips the STALE drain when generation numbers are available.
+
+test_expect_success 'setup for commit-graph tests' '
+	git init graph-repo &&
+	(
+		cd graph-repo &&
+
+		# Build a forked DAG:
+		#
+		#     L1---L2  (left)
+		#    /
+		#   S
+		#    \
+		#     R1---R2  (right)
+		#
+		test_commit GS &&
+		git checkout -b left &&
+		test_commit L1 &&
+		test_commit L2 &&
+		git checkout GS &&
+		git checkout -b right &&
+		test_commit GR1 &&
+		test_commit GR2
+	)
+'
+
+test_expect_success 'merge-base without commit-graph' '
+	(
+		cd graph-repo &&
+		rm -f .git/objects/info/commit-graph &&
+		git merge-base left right >actual &&
+		git rev-parse GS >expected &&
+		test_cmp expected actual
+	)
+'
+
+test_expect_success 'merge-base with commit-graph' '
+	(
+		cd graph-repo &&
+		git commit-graph write --reachable &&
+		git merge-base left right >actual &&
+		git rev-parse GS >expected &&
+		test_cmp expected actual
+	)
+'
+
+test_expect_success 'merge-base --all with commit-graph' '
+	(
+		cd graph-repo &&
+		git merge-base --all left right >actual &&
+		git rev-parse GS >expected &&
+		test_cmp expected actual
+	)
+'
+
+test_expect_success 'merge-base agrees with --all for single result' '
+	(
+		cd graph-repo &&
+		git commit-graph write --reachable &&
+		git merge-base left right >actual.single &&
+		git merge-base --all left right >actual.all &&
+		test_cmp actual.all actual.single
+	)
+'
+
+test_expect_success 'setup for deep chain commit-graph test' '
+	git init deep-repo &&
+	(
+		cd deep-repo &&
+
+		# Build a deep forked DAG:
+		#
+		#   L1--L2--...--L20  (left)
+		#  /
+		# S
+		#  \
+		#   R1--R2--...--R20  (right)
+		#
+		test_commit DS &&
+		git checkout -b left &&
+		for i in $(test_seq 1 20)
+		do
+			test_commit DL$i || return 1
+		done &&
+		git checkout DS &&
+		git checkout -b right &&
+		for i in $(test_seq 1 20)
+		do
+			test_commit DR$i || return 1
+		done
+	)
+'
+
+test_expect_success 'deep chain: merge-base matches with and without commit-graph' '
+	(
+		cd deep-repo &&
+		rm -f .git/objects/info/commit-graph &&
+		git merge-base left right >actual.no-graph &&
+		git rev-parse DS >expected &&
+		test_cmp expected actual.no-graph &&
+		git commit-graph write --reachable &&
+		git merge-base left right >actual.graph &&
+		test_cmp expected actual.graph
+	)
+'
+
+test_expect_success 'deep chain: --all and non---all agree with commit-graph' '
+	(
+		cd deep-repo &&
+		git commit-graph write --reachable &&
+		git merge-base left right >actual.single &&
+		git merge-base --all left right >actual.all &&
+		test_cmp actual.all actual.single
+	)
+'
+
 test_done

t/t6600-test-reach.sh

@@ -882,4 +882,44 @@ test_expect_success 'rev-list --maximal-only matches merge-base --independent' '
 	test_cmp expect.sorted actual.sorted
 '
 
+# The following tests verify the early-exit optimisation in
+# paint_down_to_common when merge-base is invoked without --all.
+# Each test checks all four commit-graph configurations.
+
+merge_base_all_modes () {
+	test_when_finished rm -rf .git/objects/info/commit-graph &&
+	git merge-base "$@" >actual &&
+	test_cmp expect actual &&
+	cp commit-graph-full .git/objects/info/commit-graph &&
+	git merge-base "$@" >actual &&
+	test_cmp expect actual &&
+	cp commit-graph-half .git/objects/info/commit-graph &&
+	git merge-base "$@" >actual &&
+	test_cmp expect actual &&
+	cp commit-graph-no-gdat .git/objects/info/commit-graph &&
+	git merge-base "$@" >actual &&
+	test_cmp expect actual
+}
+
+test_expect_success 'merge-base without --all (unique base)' '
+	git rev-parse commit-5-3 >expect &&
+	merge_base_all_modes commit-5-7 commit-8-3
+'
+
+test_expect_success 'merge-base without --all is one of --all results' '
+	test_when_finished rm -rf .git/objects/info/commit-graph &&
+
+	cp commit-graph-full .git/objects/info/commit-graph &&
+	git merge-base --all commit-5-7 commit-4-8 commit-6-6 commit-8-3 >all &&
+	git merge-base commit-5-7 commit-4-8 commit-6-6 commit-8-3 >single &&
+	test_line_count = 1 single &&
+	grep -F -f single all &&
+
+	cp commit-graph-half .git/objects/info/commit-graph &&
+	git merge-base --all commit-5-7 commit-4-8 commit-6-6 commit-8-3 >all &&
+	git merge-base commit-5-7 commit-4-8 commit-6-6 commit-8-3 >single &&
+	test_line_count = 1 single &&
+	grep -F -f single all
+'
+
 test_done