[PATCH v2 2/3] commit-reach: deduplicate queue entries in paint_down_to_common

["Kristofer Karlsson via GitGitGadget" <gitgitgadget@gmail.com>]

From: Kristofer Karlsson <krka@spotify.com>

paint_down_to_common() can enqueue the same commit multiple times
when it is reached through different parents with different flag
combinations. Add an ENQUEUED flag to track whether a commit is
currently in the priority queue, and skip it if already present.

Introduce prio_queue_put_dedup() and prio_queue_get_dedup()
wrappers that manage the ENQUEUED flag on enqueue and dequeue.

This change is performance-neutral on its own: the O(n)
queue_has_nonstale() scan still dominates the per-iteration cost.
However, the deduplication guarantee (each commit appears in the
queue at most once) is a prerequisite for the next commit, which
replaces that scan with O(1) tracking.

Signed-off-by: Kristofer Karlsson <krka@spotify.com>
---
 commit-reach.c | 27 ++++++++++++++++++++++-----
 object.h       |  2 +-
 2 files changed, 23 insertions(+), 6 deletions(-)

diff --git a/commit-reach.c b/commit-reach.c
index 5a52be90a6..85583ae359 100644
--- a/commit-reach.c
+++ b/commit-reach.c
@@ -17,8 +17,9 @@
 #define PARENT2		(1u<<17)
 #define STALE		(1u<<18)
 #define RESULT		(1u<<19)
+#define ENQUEUED	(1u<<20)
 
-static const unsigned all_flags = (PARENT1 | PARENT2 | STALE | RESULT);
+static const unsigned all_flags = (PARENT1 | PARENT2 | STALE | RESULT | ENQUEUED);
 
 static int compare_commits_by_gen(const void *_a, const void *_b)
 {
@@ -39,6 +40,22 @@ static int compare_commits_by_gen(const void *_a, const void *_b)
 	return 0;
 }
 
+static void prio_queue_put_dedup(struct prio_queue *queue, struct commit *c)
+{
+	if (c->object.flags & ENQUEUED)
+		return;
+	c->object.flags |= ENQUEUED;
+	prio_queue_put(queue, c);
+}
+
+static struct commit *prio_queue_get_dedup(struct prio_queue *queue)
+{
+	struct commit *commit = prio_queue_get(queue);
+	if (commit)
+		commit->object.flags &= ~ENQUEUED;
+	return commit;
+}
+
 static int queue_has_nonstale(struct prio_queue *queue)
 {
 	for (size_t i = 0; i < queue->nr; i++) {
@@ -70,15 +87,15 @@ static int paint_down_to_common(struct repository *r,
 		commit_list_append(one, result);
 		return 0;
 	}
-	prio_queue_put(&queue, one);
+	prio_queue_put_dedup(&queue, one);
 
 	for (i = 0; i < n; i++) {
 		twos[i]->object.flags |= PARENT2;
-		prio_queue_put(&queue, twos[i]);
+		prio_queue_put_dedup(&queue, twos[i]);
 	}
 
 	while (queue_has_nonstale(&queue)) {
-		struct commit *commit = prio_queue_get(&queue);
+		struct commit *commit = prio_queue_get_dedup(&queue);
 		struct commit_list *parents;
 		int flags;
 		timestamp_t generation = commit_graph_generation(commit);
@@ -132,7 +149,7 @@ static int paint_down_to_common(struct repository *r,
 					     oid_to_hex(&p->object.oid));
 			}
 			p->object.flags |= flags;
-			prio_queue_put(&queue, p);
+			prio_queue_put_dedup(&queue, p);
 		}
 	}
 
diff --git a/object.h b/object.h
index 2b26de3044..8fb03ff90a 100644
--- a/object.h
+++ b/object.h
@@ -75,7 +75,7 @@ void object_array_init(struct object_array *array);
  * bundle.c:                                        16
  * http-push.c:                          11-----14
  * commit-graph.c:                                15
- * commit-reach.c:                                  16-----19
+ * commit-reach.c:                                  16-------20
  * builtin/last-modified.c:                         1617
  * object-name.c:                                            20
  * list-objects-filter.c:                                      21
-- 
gitgitgadget