commit-reach: terminate merge-base walk when one side is exhausted

Documentation/Makefile

@@ -129,6 +129,7 @@ TECH_DOCS += technical/long-running-process-protocol
 TECH_DOCS += technical/multi-pack-index
 TECH_DOCS += technical/packfile-uri
 TECH_DOCS += technical/pack-heuristics
+TECH_DOCS += technical/paint-down-to-common
 TECH_DOCS += technical/parallel-checkout
 TECH_DOCS += technical/partial-clone
 TECH_DOCS += technical/platform-support

Documentation/technical/meson.build

@@ -18,6 +18,7 @@ articles = [
   'multi-pack-index.adoc',
   'packfile-uri.adoc',
   'pack-heuristics.adoc',
+  'paint-down-to-common.adoc',
   'parallel-checkout.adoc',
   'partial-clone.adoc',
   'platform-support.adoc',

Documentation/technical/paint-down-to-common.adoc

@@ -0,0 +1,149 @@
+Merge-Base Computation and paint_down_to_common()
+==================================================
+
+The function `paint_down_to_common()` in `commit-reach.c` computes merge
+bases by walking the commit graph backwards from two sets of tips and
+finding where their ancestry meets.
+
+Use cases
+---------
+
+Computing merge bases is used in two different ways:
+
+ 1. *Finding all merge bases* (`merge-base --all`, `merge-tree`,
+    `merge`, `rebase`). A merge base is a common ancestor that is
+    not itself an ancestor of another common ancestor.
+
+ 2. *Ancestry checks* (`in_merge_bases`, used by `merge-base
+    --is-ancestor`, `branch -d`, `fetch`). These ask: "is commit A
+    an ancestor of commit B?" If a common ancestor equals one of the
+    inputs, that input is necessarily the only merge base -- no other
+    common ancestor can be both as recent and not an ancestor of it.
+
+Both use cases share the same algorithm and implementation.
+
+Algorithm
+---------
+
+Given a commit `one` and a set of commits `twos[]`, the walk paints
+commits with two colors:
+
+  - PARENT1: reachable from `one`
+  - PARENT2: reachable from any commit in `twos[]`
+
+The walk uses a priority queue ordered by generation number (falling
+back to commit date when generation numbers are unavailable). Each
+step dequeues the highest-priority commit (this is when we say a
+commit is "visited") and propagates its paint flags to its parents,
+enqueuing them if they gained new flags. When a commit receives
+both PARENT1 and PARENT2, it is a merge-base candidate. A candidate
+gains the STALE flag so its ancestors propagate staleness -- any
+deeper common ancestor is necessarily redundant.
+
+INFINITY and finite generation regions
+--------------------------------------
+
+The commit-graph stores a generation number for each commit. Commits
+not in the commit-graph have generation `GENERATION_NUMBER_INFINITY`. The
+graph is closed under reachability: if a commit is in the graph, all
+its ancestors are too. This partitions the commit graph into two regions:
+
+....
+    +---------------------------------------+
+    |          INFINITY region              |
+    |  generation = INFINITY                |
+    |  queue order: heuristic (commit date) |
+    +---------------------------------------+
+                    |
+                    v
+    +---------------------------------------+
+    |          Finite region                |
+    |  generation = finite                  |
+    |  queue order: topological             |
+    +---------------------------------------+
+....
+
+When the commit-graph is enabled, the INFINITY region is typically
+very small -- it only contains commits added since the last
+commit-graph refresh.
+
+All reachable INFINITY-generation commits are visited before any
+finite-generation commit, because INFINITY is larger than any finite
+value. Once the walk crosses into the finite region, it stays there.
+
+In the finite region, generation ordering guarantees topological
+traversal: children are always visited before their parents. This
+means that paint on already-visited commits is final -- no future
+traversal step can add paint to them.
+
+In the INFINITY region, commit-date ordering can violate this: a
+parent with a later date can be visited before a child with an earlier
+date. Paint flags are therefore NOT final at visit time, and a
+commit visited with only one side's paint may later gain the other.
+
+Paint flags are only added, never removed. Since each flag can be set
+at most once per commit, the number of times a commit can be
+re-enqueued is bounded by the number of flag transitions.
+
+Termination
+-----------
+
+The walk tracks the number of commits of each type in the queue
+(PARENT1-only, PARENT2-only, pending merge-base). The main loop
+ends when one of the following conditions holds:
+
+  1. The queue is empty.
+  2. The queue contains only stale entries.
+  3. Generation cutoff: the dequeued commit's generation is below
+     a caller-supplied `min_generation` threshold.
+  4. Single result: the caller only needs one merge base, one has
+     been found, and the walk has entered the finite-generation
+     region.
+  5. Side exhaustion: no pure PARENT1 or pure PARENT2 commits
+     remain in the queue, no pending merge-base candidates exist,
+     and the walk has entered the finite-generation region.
+
+Stale entry condition
+~~~~~~~~~~~~~~~~~~~~~
+Once all queued entries are stale, no new merge-base candidates can
+be discovered -- that requires at least one non-stale commit from
+each side meeting. Continuing the walk could still invalidate
+existing candidates by proving one is an ancestor of another, but
+`remove_redundant()` handles that as a post-processing step, so it
+is safe to exit early.
+
+Side-exhaustion condition
+~~~~~~~~~~~~~~~~~~~~~~~~~
+A new merge-base requires commits from both sides to meet. When one
+side's exclusive counter reaches zero and there are no pending
+merge-base candidates, no future traversal step can produce a new
+candidate.
+
+This optimization only activates in the finite-generation region
+where topological ordering holds. In that region, children are
+always visited before parents, so paint flags are final at visit
+time and an exhausted side cannot reappear. In the INFINITY region,
+commit-date ordering can violate this guarantee, so the check is
+skipped.
+
+Generation cutoff
+~~~~~~~~~~~~~~~~~
+Some callers (notably `remove_redundant()`) supply a `min_generation`
+threshold -- the minimum generation of the input commits. No merge
+base can have a generation below this threshold, so the walk
+terminates as soon as it dequeues such a commit.
+
+Single result
+~~~~~~~~~~~~~
+When only one merge base is needed and the walk is in the
+finite-generation region, the first candidate found is necessarily
+the highest-generation common ancestor. No remaining commit in the
+queue can be a descendant of this candidate (generation ordering
+guarantees children are visited first), so it cannot be redundant
+and the walk can stop immediately.
+
+Related documentation
+---------------------
+
+  - `Documentation/technical/commit-graph.adoc` -- generation numbers
+    and the reachability closure property.

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)
@@ -78,68 +79,139 @@ 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;
+};
+
+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 (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 (commit)
-		commit->object.flags &= ~ENQUEUED;
+	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 < GENERATION_NUMBER_INFINITY)
+			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,
 				timestamp_t min_generation,
 				enum merge_base_flags mb_flags,
 				struct commit_list **result)
 {
-	struct nonstale_queue queue = {
-		{ compare_commits_by_gen_then_commit_date }
+	struct paint_state state = {
+		.queue = { compare_commits_by_gen_then_commit_date }
 	};
+	struct commit *commit;
 	int i;
-	timestamp_t last_gen = GENERATION_NUMBER_INFINITY;
+	int steps = 0;
 	struct commit_list **tail = result;
 
+	state.min_generation = min_generation;
+	state.last_gen = GENERATION_NUMBER_INFINITY;
 	if (!min_generation && !corrected_commit_dates_enabled(r))
-		queue.pq.compare = compare_commits_by_commit_date;
+		state.queue.compare = compare_commits_by_commit_date;
 
 	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)) {
@@ -152,7 +224,7 @@ static int paint_down_to_common(struct repository *r,
 				 * descendant of this one.
 				 */
 				if (!(mb_flags & MERGE_BASE_FIND_ALL) &&
-				    generation < GENERATION_NUMBER_INFINITY)
+				    state.last_gen < GENERATION_NUMBER_INFINITY)
 					break;
 			}
 			/* Mark parents of a found merge stale */
@@ -165,7 +237,7 @@ 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;
 				/*
@@ -180,12 +252,13 @@ 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;
 }

t/meson.build

@@ -786,6 +786,7 @@ integration_tests = [
   't6041-bisect-submodule.sh',
   't6050-replace.sh',
   't6060-merge-index.sh',
+  't6099-merge-base-side-exhaustion.sh',
   't6100-rev-list-in-order.sh',
   't6101-rev-parse-parents.sh',
   't6102-rev-list-unexpected-objects.sh',