commit-reach: skip STALE drain in paint_down_to_common when only one merge-base needed

When find_all is false and generation numbers are available, the
priority queue pops in non-increasing generation order.  The first
doubly-painted commit is a valid best merge-base — no later commit
can dominate it.  Skip the expensive STALE drain in this case.

Add find_all parameter to repo_get_merge_bases_many_dirty() and
thread it through to paint_down_to_common().  git merge-base
(without --all) passes show_all=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

@@ -14,7 +14,8 @@ static int show_merge_base(struct commit **rev, size_t rev_nr, int show_all)
 	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,
+					    show_all, &result) < 0) {
 		commit_list_free(result);
 		return -1;
 	}

commit-reach.c

@@ -55,14 +55,16 @@ static int paint_down_to_common(struct repository *r,
 				struct commit **twos,
 				timestamp_t min_generation,
 				int ignore_missing_commits,
+				int find_all,
 				struct commit_list **result)
 {
 	struct prio_queue queue = { compare_commits_by_gen_then_commit_date };
 	int i;
+	int has_gens = min_generation || corrected_commit_dates_enabled(r);
 	timestamp_t last_gen = GENERATION_NUMBER_INFINITY;
 	struct commit_list **tail = result;
 
-	if (!min_generation && !corrected_commit_dates_enabled(r))
+	if (!has_gens)
 		queue.compare = compare_commits_by_commit_date;
 
 	one->object.flags |= PARENT1;
@@ -97,6 +99,10 @@ static int paint_down_to_common(struct repository *r,
 			if (!(commit->object.flags & RESULT)) {
 				commit->object.flags |= RESULT;
 				tail = commit_list_append(commit, tail);
+				/* Generation-ordered queue: no later
+				 * commit can dominate this one. */
+				if (!find_all && has_gens)
+					break;
 			}
 			/* Mark parents of a found merge stale */
 			flags |= STALE;
@@ -136,6 +142,7 @@ 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,
+			    int find_all,
 			    struct commit_list **result)
 {
 	struct commit_list *list = NULL, **tail = result;
@@ -165,7 +172,7 @@ 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, 0, find_all, &list)) {
 		commit_list_free(list);
 		return -1;
 	}
@@ -246,7 +253,7 @@ 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, 0, 1, &common)) {
 			clear_commit_marks(array[i], all_flags);
 			clear_commit_marks_many(filled, work, all_flags);
 			commit_list_free(common);
@@ -425,14 +432,15 @@ static int get_merge_bases_many_0(struct repository *r,
 				  size_t n,
 				  struct commit **twos,
 				  int cleanup,
+				  int find_all,
 				  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, find_all, result) < 0)
 		return -1;
 	for (i = 0; i < n; i++) {
 		if (one == twos[i])
@@ -475,24 +483,25 @@ 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, 1, result);
 }
 
 int repo_get_merge_bases_many_dirty(struct repository *r,
 				    struct commit *one,
 				    size_t n,
 				    struct commit **twos,
+				    int find_all,
 				    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, find_all, 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, 1, result);
 }
 
 /*
@@ -555,7 +564,7 @@ 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, ignore_missing_commits, 1, &bases))
 		ret = -1;
 	else if (commit->object.flags & PARENT2)
 		ret = 1;

commit-reach.h

@@ -17,10 +17,13 @@ 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 */
+/* To be used only when object flags after this call no longer matter.
+ * When find_all is false and generation numbers are 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,
+				    int find_all,
 				    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