Merge branch 'kk/streaming-walk-pqueue' into jch

Streaming revision walks have been optimized by using a priority queue
for date-sorting commits, speeding up walks repositories with many
merges.

* kk/streaming-walk-pqueue:
  revision: use priority queue for non-limited streaming walks
  revision: introduce rev_walk_mode to clarify get_revision_1()
  pack-objects: call release_revisions() after cruft traversal

builtin/pack-objects.c

@@ -4281,6 +4281,7 @@ static void enumerate_and_traverse_cruft_objects(struct string_list *fresh_packs
 	traverse_commit_list(&revs, show_cruft_commit, show_cruft_object, NULL);
 
 	stop_progress(&progress_state);
+	release_revisions(&revs);
 }
 
 static void read_cruft_objects(void)

commit.c

@@ -760,19 +760,6 @@ void commit_list_free(struct commit_list *list)
 		pop_commit(&list);
 }
 
-struct commit_list * commit_list_insert_by_date(struct commit *item, struct commit_list **list)
-{
-	struct commit_list **pp = list;
-	struct commit_list *p;
-	while ((p = *pp) != NULL) {
-		if (p->item->date < item->date) {
-			break;
-		}
-		pp = &p->next;
-	}
-	return commit_list_insert(item, pp);
-}
-
 static int commit_list_compare_by_date(const struct commit_list *a,
 				       const struct commit_list *b)
 {

commit.h

@@ -191,8 +191,6 @@ int commit_list_contains(struct commit *item,
 struct commit_list **commit_list_append(struct commit *commit,
 					struct commit_list **next);
 unsigned commit_list_count(const struct commit_list *l);
-struct commit_list *commit_list_insert_by_date(struct commit *item,
-				    struct commit_list **list);
 void commit_list_sort_by_date(struct commit_list **list);
 
 /* Shallow copy of the input list */

revision.c

@@ -1116,7 +1116,7 @@ static void try_to_simplify_commit(struct rev_info *revs, struct commit *commit)
 }
 
 static int process_parents(struct rev_info *revs, struct commit *commit,
-			   struct commit_list **list, struct prio_queue *queue)
+			   struct prio_queue *queue)
 {
 	struct commit_list *parent = commit->parents;
 	unsigned pass_flags;
@@ -1158,8 +1158,6 @@ static int process_parents(struct rev_info *revs, struct commit *commit,
 			if (p->object.flags & SEEN)
 				continue;
 			p->object.flags |= (SEEN | NOT_USER_GIVEN);
-			if (list)
-				commit_list_insert_by_date(p, list);
 			if (queue)
 				prio_queue_put(queue, p);
 			if (revs->exclude_first_parent_only)
@@ -1207,8 +1205,6 @@ static int process_parents(struct rev_info *revs, struct commit *commit,
 		p->object.flags |= pass_flags | CHILD_VISITED;
 		if (!(p->object.flags & SEEN)) {
 			p->object.flags |= (SEEN | NOT_USER_GIVEN);
-			if (list)
-				commit_list_insert_by_date(p, list);
 			if (queue)
 				prio_queue_put(queue, p);
 		}
@@ -1470,7 +1466,7 @@ static int limit_list(struct rev_info *revs)
 
 		if (revs->max_age != -1 && (commit->date < revs->max_age))
 			obj->flags |= UNINTERESTING;
-		if (process_parents(revs, commit, NULL, &queue) < 0) {
+		if (process_parents(revs, commit, &queue) < 0) {
 			clear_prio_queue(&queue);
 			return -1;
 		}
@@ -3286,6 +3282,7 @@ static void free_void_commit_list(void *list)
 void release_revisions(struct rev_info *revs)
 {
 	commit_list_free(revs->commits);
+	clear_prio_queue(&revs->commit_queue);
 	commit_list_free(revs->ancestry_path_bottoms);
 	release_display_notes(&revs->notes_opt);
 	object_array_clear(&revs->pending);
@@ -3755,7 +3752,7 @@ static void explore_walk_step(struct rev_info *revs)
 	if (revs->max_age != -1 && (c->date < revs->max_age))
 		c->object.flags |= UNINTERESTING;
 
-	if (process_parents(revs, c, NULL, NULL) < 0)
+	if (process_parents(revs, c, NULL) < 0)
 		return;
 
 	if (c->object.flags & UNINTERESTING)
@@ -3931,7 +3928,7 @@ static void expand_topo_walk(struct rev_info *revs, struct commit *commit)
 {
 	struct commit_list *p;
 	struct topo_walk_info *info = revs->topo_walk_info;
-	if (process_parents(revs, commit, NULL, NULL) < 0) {
+	if (process_parents(revs, commit, NULL) < 0) {
 		if (!revs->ignore_missing_links)
 			die("Failed to traverse parents of commit %s",
 			    oid_to_hex(&commit->object.oid));
@@ -3967,6 +3964,13 @@ static void expand_topo_walk(struct rev_info *revs, struct commit *commit)
 	}
 }
 
+void rev_info_commit_list_to_queue(struct rev_info *revs)
+{
+	while (revs->commits)
+		prio_queue_put(&revs->commit_queue, pop_commit(&revs->commits));
+}
+
+
 int prepare_revision_walk(struct rev_info *revs)
 {
 	int i;
@@ -4035,7 +4039,7 @@ static enum rewrite_result rewrite_one_1(struct rev_info *revs,
 	for (;;) {
 		struct commit *p = *pp;
 		if (!revs->limited)
-			if (process_parents(revs, p, NULL, queue) < 0)
+			if (process_parents(revs, p, queue) < 0)
 				return rewrite_one_error;
 		if (p->object.flags & UNINTERESTING)
 			return rewrite_one_ok;
@@ -4049,27 +4053,18 @@ static enum rewrite_result rewrite_one_1(struct rev_info *revs,
 	}
 }
 
-static void merge_queue_into_list(struct prio_queue *q, struct commit_list **list)
+static void merge_queue_into_prio_queue(struct prio_queue *from,
+					struct prio_queue *to)
 {
-	while (q->nr) {
-		struct commit *item = prio_queue_peek(q);
-		struct commit_list *p = *list;
-
-		if (p && p->item->date >= item->date)
-			list = &p->next;
-		else {
-			p = commit_list_insert(item, list);
-			list = &p->next; /* skip newly added item */
-			prio_queue_get(q); /* pop item */
-		}
-	}
+	while (from->nr)
+		prio_queue_put(to, prio_queue_get(from));
 }
 
 static enum rewrite_result rewrite_one(struct rev_info *revs, struct commit **pp)
 {
 	struct prio_queue queue = { compare_commits_by_commit_date };
 	enum rewrite_result ret = rewrite_one_1(revs, pp, &queue);
-	merge_queue_into_list(&queue, &revs->commits);
+	merge_queue_into_prio_queue(&queue, &revs->commit_queue);
 	clear_prio_queue(&queue);
 	return ret;
 }
@@ -4356,22 +4351,57 @@ static void track_linear(struct rev_info *revs, struct commit *commit)
 	revs->previous_parents = commit_list_copy(commit->parents);
 }
 
+enum rev_walk_mode {
+	REV_WALK_REFLOG,
+	REV_WALK_TOPO,
+	REV_WALK_LIMITED,
+	REV_WALK_NO_WALK,
+	REV_WALK_STREAMING,
+};
+
+static enum rev_walk_mode get_walk_mode(struct rev_info *revs)
+{
+	if (revs->reflog_info)
+		return REV_WALK_REFLOG;
+	if (revs->topo_walk_info)
+		return REV_WALK_TOPO;
+	if (revs->limited)
+		return REV_WALK_LIMITED;
+	if (revs->no_walk)
+		return REV_WALK_NO_WALK;
+	return REV_WALK_STREAMING;
+}
+
 static struct commit *get_revision_1(struct rev_info *revs)
 {
+	enum rev_walk_mode mode = get_walk_mode(revs);
+
+	if (mode == REV_WALK_STREAMING && revs->commits)
+		rev_info_commit_list_to_queue(revs);
+
 	while (1) {
 		struct commit *commit;
 
-		if (revs->reflog_info)
+		switch (mode) {
+		case REV_WALK_REFLOG:
 			commit = next_reflog_entry(revs->reflog_info);
-		else if (revs->topo_walk_info)
+			break;
+		case REV_WALK_TOPO:
 			commit = next_topo_commit(revs);
-		else
+			break;
+		case REV_WALK_LIMITED:
+		case REV_WALK_NO_WALK:
 			commit = pop_commit(&revs->commits);
+			break;
+		case REV_WALK_STREAMING:
+			commit = prio_queue_get(&revs->commit_queue);
+			break;
+		}
 
 		if (!commit)
 			return NULL;
 
-		if (revs->reflog_info)
+		if (mode == REV_WALK_REFLOG)
 			commit->object.flags &= ~(ADDED | SEEN | SHOWN);
 
 		/*
@@ -4379,20 +4409,29 @@ static struct commit *get_revision_1(struct rev_info *revs)
 		 * the parents here. We also need to do the date-based limiting
 		 * that we'd otherwise have done in limit_list().
 		 */
-		if (!revs->limited) {
-			if (revs->max_age != -1 &&
-			    comparison_date(revs, commit) < revs->max_age)
-				continue;
+		if (mode != REV_WALK_LIMITED &&
+		    revs->max_age != -1 &&
+		    comparison_date(revs, commit) < revs->max_age)
+			continue;
 
-			if (revs->reflog_info)
-				try_to_simplify_commit(revs, commit);
-			else if (revs->topo_walk_info)
-				expand_topo_walk(revs, commit);
-			else if (process_parents(revs, commit, &revs->commits, NULL) < 0) {
+		switch (mode) {
+		case REV_WALK_REFLOG:
+			try_to_simplify_commit(revs, commit);
+			break;
+		case REV_WALK_TOPO:
+			expand_topo_walk(revs, commit);
+			break;
+		case REV_WALK_STREAMING:
+			if (process_parents(revs, commit,
+					    &revs->commit_queue) < 0) {
 				if (!revs->ignore_missing_links)
 					die("Failed to traverse parents of commit %s",
-						oid_to_hex(&commit->object.oid));
+					    oid_to_hex(&commit->object.oid));
 			}
+			break;
+		case REV_WALK_NO_WALK:
+		case REV_WALK_LIMITED:
+			break;
 		}
 
 		switch (simplify_commit(revs, commit)) {

revision.h

@@ -12,6 +12,7 @@
 #include "decorate.h"
 #include "ident.h"
 #include "list-objects-filter-options.h"
+#include "prio-queue.h"
 #include "strvec.h"
 
 /**
@@ -122,8 +123,14 @@ struct oidset;
 struct topo_walk_info;
 
 struct rev_info {
-	/* Starting list */
+	/*
+	 * Work queue of commits, stored as either a linked list or a
+	 * priority queue, but never both at the same time.
+	 * rev_info_commit_list_to_queue() converts list to queue.
+	 */
 	struct commit_list *commits;
+	struct prio_queue commit_queue;
+
 	struct object_array pending;
 	struct repository *repo;
 
@@ -403,6 +410,7 @@ struct rev_info {
  * uninitialized.
  */
 #define REV_INFO_INIT { \
+	.commit_queue = { .compare = compare_commits_by_commit_date }, \
 	.abbrev = DEFAULT_ABBREV, \
 	.simplify_history = 1, \
 	.pruning.flags.recursive = 1, \
@@ -481,6 +489,8 @@ void reset_revision_walk(void);
  */
 int prepare_revision_walk(struct rev_info *revs);
 
+/* Drain the commits linked list into the priority queue. */
+void rev_info_commit_list_to_queue(struct rev_info *revs);
 /**
  * Takes a pointer to a `rev_info` structure and iterates over it, returning a
  * `struct commit *` each time you call it. The end of the revision list is