Merge branch 'kk/merge-base-exhaustion' into seen

The merge-base computation has been optimized by stopping the walk
early when one side's exclusive commits in the queue are exhausted,
yielding significant speedups for queries with one-sided histories.

* kk/merge-base-exhaustion:
  commit-reach: remove commit-date ordering fallback
  commit-reach: move min_generation check into paint_queue_get()
  commit-reach: terminate merge-base walk when one paint side is exhausted
  commit-reach: introduce struct paint_state with per-side counters
  t6600: add clock-skew topologies and step counts for edge cases
  commit-reach: add trace2 instrumentation to paint_down_to_common()
  t6099, t6600: add side-exhaustion regression tests
  t6600: add test cases for side-exhaustion edge cases
  test-lib-functions: improve diagnostic output for trace2 data assertions
  Documentation/technical: add paint-down-to-common doc

commit-reach.c

@@ -11,6 +11,7 @@
 #include "tag.h"
 #include "commit-reach.h"
 #include "ewah/ewok.h"
+#include "trace2.h"
 
 /* Remember to update object flag allocation in object.h */
 #define PARENT1		(1u<<16)
@@ -78,25 +79,106 @@ static void clear_nonstale_queue(struct nonstale_queue *queue)
 	queue->max_nonstale = NULL;
 }
 
-static void nonstale_queue_put_dedup(struct nonstale_queue *queue,
-				     struct commit *c)
+/*
+ * Priority queue with per-side commit counters for paint_down_to_common().
+ * Each non-stale queued commit occupies exactly one bucket: PARENT1-only,
+ * PARENT2-only, or both (a pending merge-base candidate).
+ */
+struct paint_state {
+	struct prio_queue queue;
+	size_t parent1_count;
+	size_t parent2_count;
+	size_t mb_candidate_count;
+	timestamp_t min_generation;
+	timestamp_t last_gen;
+	timestamp_t topo_ceiling;
+};
+
+static void paint_count_update(struct paint_state *state,
+			       unsigned flags, int delta)
 {
-	if (c->object.flags & ENQUEUED)
-		return;
-	c->object.flags |= ENQUEUED;
-	nonstale_queue_put(queue, c);
+	switch (flags & (PARENT1 | PARENT2 | STALE)) {
+	case PARENT1:
+		state->parent1_count += delta;
+		break;
+
+	case PARENT2:
+		state->parent2_count += delta;
+		break;
+
+	case PARENT1 | PARENT2:
+		state->mb_candidate_count += delta;
+		break;
+
+	case PARENT1 | PARENT2 | STALE:
+		break;
+
+	default:
+		BUG("unexpected paint state");
+	}
 }
 
-static struct commit *nonstale_queue_get_dedup(struct nonstale_queue *queue)
+static void paint_queue_put(struct paint_state *state,
+			    struct commit *c, unsigned add_flags)
 {
-	struct commit *commit = nonstale_queue_get(queue);
+	unsigned old_flags = c->object.flags;
+	c->object.flags |= add_flags;
 
-	if (commit)
-		commit->object.flags &= ~ENQUEUED;
+	if (old_flags & ENQUEUED) {
+		paint_count_update(state, old_flags, -1);
+		paint_count_update(state, c->object.flags, 1);
+	} else {
+		c->object.flags |= ENQUEUED;
+		prio_queue_put(&state->queue, c);
+		paint_count_update(state, c->object.flags, 1);
+	}
+}
+
+/*
+ * Dequeue the next commit for the paint walk, or return NULL when
+ * no more merge bases can be discovered.
+ */
+static struct commit *paint_queue_get(struct paint_state *state)
+{
+	struct commit *commit = prio_queue_get(&state->queue);
+	timestamp_t generation;
+
+	if (!commit)
+		return NULL;
+
+	commit->object.flags &= ~ENQUEUED;
+	generation = commit_graph_generation(commit);
+
+	if (state->min_generation && generation > state->last_gen)
+		BUG("bad generation skip %"PRItime" > %"PRItime" at %s",
+		    generation, state->last_gen,
+		    oid_to_hex(&commit->object.oid));
+	state->last_gen = generation;
+
+	/* generation cutoff */
+	if (generation < state->min_generation)
+		return NULL;
+
+	if (!state->mb_candidate_count) {
+		/* only stale entries remain */
+		if (!state->parent1_count && !state->parent2_count)
+			return NULL;
+
+		/* one side is exhausted */
+		if ((!state->parent1_count || !state->parent2_count) &&
+		    generation < state->topo_ceiling)
+			return NULL;
+	}
+
+	paint_count_update(state, commit->object.flags, -1);
 	return commit;
 }
 
-/* all input commits in one and twos[] must have been parsed! */
+/*
+ * See Documentation/technical/paint-down-to-common.adoc
+ *
+ * All input commits in one and twos[] must have been parsed!
+ */
 static int paint_down_to_common(struct repository *r,
 				struct commit *one, int n,
 				struct commit **twos,
@@ -104,45 +186,40 @@ static int paint_down_to_common(struct repository *r,
 				enum merge_base_flags mb_flags,
 				struct commit_list **result)
 {
-	struct nonstale_queue queue = {
-		{ compare_commits_by_gen_then_commit_date }
+	/*
+	 * Generation ordering is required for the side-exhaustion and
+	 * single-result early exits, which rely on topological traversal
+	 * order (children visited before parents) in the finite region.
+	 */
+	struct paint_state state = {
+		.queue = { compare_commits_by_gen_then_commit_date }
 	};
+	struct commit *commit;
 	int i;
-	int gen_ordered = 1;
-	timestamp_t last_gen = GENERATION_NUMBER_INFINITY;
+	int steps = 0;
 	struct commit_list **tail = result;
 
-	if (!min_generation && !corrected_commit_dates_enabled(r)) {
-		queue.pq.compare = compare_commits_by_commit_date;
-		gen_ordered = 0;
-	}
+	state.min_generation = min_generation;
+	state.last_gen = GENERATION_NUMBER_INFINITY;
+	state.topo_ceiling = corrected_commit_dates_enabled(r)
+		? GENERATION_NUMBER_INFINITY
+		: GENERATION_NUMBER_V1_MAX;
+
 
 	one->object.flags |= PARENT1;
 	if (!n) {
 		commit_list_append(one, result);
 		return 0;
 	}
-	nonstale_queue_put_dedup(&queue, one);
+	paint_queue_put(&state, one, 0);
 
-	for (i = 0; i < n; i++) {
-		twos[i]->object.flags |= PARENT2;
-		nonstale_queue_put_dedup(&queue, twos[i]);
-	}
+	for (i = 0; i < n; i++)
+		paint_queue_put(&state, twos[i], PARENT2);
 
-	while (queue.max_nonstale) {
-		struct commit *commit = nonstale_queue_get_dedup(&queue);
+	while ((commit = paint_queue_get(&state))) {
 		struct commit_list *parents;
 		int flags;
-		timestamp_t generation = commit_graph_generation(commit);
-
-		if (min_generation && generation > last_gen)
-			BUG("bad generation skip %"PRItime" > %"PRItime" at %s",
-			    generation, last_gen,
-			    oid_to_hex(&commit->object.oid));
-		last_gen = generation;
-
-		if (generation < min_generation)
-			break;
+		steps++;
 
 		flags = commit->object.flags & (PARENT1 | PARENT2 | STALE);
 		if (flags == (PARENT1 | PARENT2)) {
@@ -155,8 +232,7 @@ static int paint_down_to_common(struct repository *r,
 				 * descendant of this one.
 				 */
 				if (!(mb_flags & MERGE_BASE_FIND_ALL) &&
-				    gen_ordered &&
-				    generation < GENERATION_NUMBER_INFINITY)
+				    state.last_gen < state.topo_ceiling)
 					break;
 			}
 			/* Mark parents of a found merge stale */
@@ -169,7 +245,7 @@ static int paint_down_to_common(struct repository *r,
 			if ((p->object.flags & flags) == flags)
 				continue;
 			if (repo_parse_commit(r, p)) {
-				clear_nonstale_queue(&queue);
+				clear_prio_queue(&state.queue);
 				commit_list_free(*result);
 				*result = NULL;
 				/*
@@ -184,12 +260,13 @@ static int paint_down_to_common(struct repository *r,
 				return error(_("could not parse commit %s"),
 					     oid_to_hex(&p->object.oid));
 			}
-			p->object.flags |= flags;
-			nonstale_queue_put_dedup(&queue, p);
+			paint_queue_put(&state, p, flags);
 		}
 	}
 
-	clear_nonstale_queue(&queue);
+	clear_prio_queue(&state.queue);
+	trace2_data_intmax("paint_down_to_common", r,
+			   "steps", steps);
 	commit_list_sort_by_date(result);
 	return 0;
 }