Web lists-archives.com

[PATCH v2] rev-list: exclude promisor objects at walk time




For large repositories, enumerating the list of all promisor objects (in
order to exclude them from a rev-list walk) can take a significant
amount of time).

When --exclude-promisor-objects is passed to rev-list, don't enumerate
the promisor objects. Instead, filter them (and any children objects)
during the actual graph walk.

Remove the mark_uninteresting() function as it's not used anywhere else.

Helped-By: Jonathan Tan <jonathantanmy@xxxxxxxxxx>
Helped-By: Jeff King <peff@xxxxxxxx>
Helped-By: Jonathan Nieder <jrnieder@xxxxxxxxx>

Signed-off-by: Josh Steadmon <steadmon@xxxxxxxxxx>
---

Re-implemented following Jonathan & Jeff's advice (and also previously
Jonathan Nieder's, although I didn't understand it at the time). Thanks
for the feedback all.


 list-objects.c | 26 ++++++++++++++++++++++++++
 revision.c     | 16 ----------------
 2 files changed, 26 insertions(+), 16 deletions(-)

diff --git a/list-objects.c b/list-objects.c
index dc77361e11..d1eaa0999e 100644
--- a/list-objects.c
+++ b/list-objects.c
@@ -30,6 +30,7 @@ static void process_blob(struct traversal_context *ctx,
 	struct object *obj = &blob->object;
 	size_t pathlen;
 	enum list_objects_filter_result r = LOFR_MARK_SEEN | LOFR_DO_SHOW;
+	struct object_info oi = OBJECT_INFO_INIT;
 
 	if (!ctx->revs->blob_objects)
 		return;
@@ -37,6 +38,11 @@ static void process_blob(struct traversal_context *ctx,
 		die("bad blob object");
 	if (obj->flags & (UNINTERESTING | SEEN))
 		return;
+	if (ctx->revs->exclude_promisor_objects &&
+	    !oid_object_info_extended(the_repository, &obj->oid, &oi, 0) &&
+	    oi.whence == OI_PACKED &&
+	    oi.u.packed.pack->pack_promisor)
+		return;
 
 	/*
 	 * Pre-filter known-missing objects when explicitly requested.
@@ -149,6 +155,7 @@ static void process_tree(struct traversal_context *ctx,
 	int baselen = base->len;
 	enum list_objects_filter_result r = LOFR_MARK_SEEN | LOFR_DO_SHOW;
 	int failed_parse;
+	struct object_info oi = OBJECT_INFO_INIT;
 
 	if (!revs->tree_objects)
 		return;
@@ -156,6 +163,11 @@ static void process_tree(struct traversal_context *ctx,
 		die("bad tree object");
 	if (obj->flags & (UNINTERESTING | SEEN))
 		return;
+	if (ctx->revs->exclude_promisor_objects &&
+	    !oid_object_info_extended(the_repository, &obj->oid, &oi, 0) &&
+	    oi.whence == OI_PACKED &&
+	    oi.u.packed.pack->pack_promisor)
+		return;
 
 	failed_parse = parse_tree_gently(tree, 1);
 	if (failed_parse) {
@@ -318,6 +330,7 @@ static void traverse_trees_and_blobs(struct traversal_context *ctx,
 				     struct strbuf *base)
 {
 	int i;
+	struct object_info oi = OBJECT_INFO_INIT;
 
 	assert(base->len == 0);
 
@@ -326,6 +339,12 @@ static void traverse_trees_and_blobs(struct traversal_context *ctx,
 		struct object *obj = pending->item;
 		const char *name = pending->name;
 		const char *path = pending->path;
+		if (ctx->revs->exclude_promisor_objects &&
+		    !oid_object_info_extended(the_repository, &obj->oid, &oi, 0) &&
+		    oi.whence == OI_PACKED &&
+		    oi.u.packed.pack->pack_promisor)
+			continue;
+
 		if (obj->flags & (UNINTERESTING | SEEN))
 			continue;
 		if (obj->type == OBJ_TAG) {
@@ -353,9 +372,16 @@ static void do_traverse(struct traversal_context *ctx)
 {
 	struct commit *commit;
 	struct strbuf csp; /* callee's scratch pad */
+	struct object_info oi = OBJECT_INFO_INIT;
 	strbuf_init(&csp, PATH_MAX);
 
 	while ((commit = get_revision(ctx->revs)) != NULL) {
+		if (ctx->revs->exclude_promisor_objects &&
+		    !oid_object_info_extended(the_repository, &commit->object.oid, &oi, 0) &&
+		    oi.whence == OI_PACKED &&
+		    oi.u.packed.pack->pack_promisor)
+			continue;
+
 		/*
 		 * an uninteresting boundary commit may not have its tree
 		 * parsed yet, but we are not going to show them anyway
diff --git a/revision.c b/revision.c
index eb8e51bc63..85974e941d 100644
--- a/revision.c
+++ b/revision.c
@@ -3067,17 +3067,6 @@ void reset_revision_walk(void)
 	clear_object_flags(SEEN | ADDED | SHOWN);
 }
 
-static int mark_uninteresting(const struct object_id *oid,
-			      struct packed_git *pack,
-			      uint32_t pos,
-			      void *cb)
-{
-	struct rev_info *revs = cb;
-	struct object *o = parse_object(revs->repo, oid);
-	o->flags |= UNINTERESTING | SEEN;
-	return 0;
-}
-
 define_commit_slab(indegree_slab, int);
 define_commit_slab(author_date_slab, timestamp_t);
 
@@ -3316,11 +3305,6 @@ int prepare_revision_walk(struct rev_info *revs)
 	    (revs->limited && limiting_can_increase_treesame(revs)))
 		revs->treesame.name = "treesame";
 
-	if (revs->exclude_promisor_objects) {
-		for_each_packed_object(mark_uninteresting, revs,
-				       FOR_EACH_OBJECT_PROMISOR_ONLY);
-	}
-
 	if (revs->no_walk != REVISION_WALK_NO_WALK_UNSORTED)
 		commit_list_sort_by_date(&revs->commits);
 	if (revs->no_walk)
-- 
2.21.0.392.gf8f6787159e-goog