Push scan/join target list beneath Gather when possible.

This means that, for example, "SELECT expensive_func(a) FROM bigtab
WHERE something" can compute expensive_func(a) in the workers rather
than the leader if it happens to be parallel-safe, which figures to be
a big win in some practical cases.

Currently, we can only do this if the entire target list is
parallel-safe.  If we worked harder, we might be able to evaluate
parallel-safe targets in the worker and any parallel-restricted
targets in the leader, but that would be more complicated, and there
aren't that many parallel-restricted functions that people are likely
to use in queries anyway.  I think.  So just do the simple thing for
the moment.

Robert Haas, Amit Kapila, and Tom Lane

1 files changed, 30 insertions, 0 deletions

diff --git a/src/backend/optimizer/util/pathnode.c b/src/backend/optimizer/util/pathnode.c
index b8ea3168a84..541f7790ab0 100644
--- a/src/backend/optimizer/util/pathnode.c
+++ b/src/backend/optimizer/util/pathnode.c
@@ -2222,6 +2222,36 @@ apply_projection_to_path(PlannerInfo *root,
 	path->total_cost += target->cost.startup - oldcost.startup +
 		(target->cost.per_tuple - oldcost.per_tuple) * path->rows;
 
+	/*
+	 * If the path happens to be a Gather path, we'd like to arrange for the
+	 * subpath to return the required target list so that workers can help
+	 * project. But if there is something that is not parallel-safe in the
+	 * target expressions, then we can't.
+	 */
+	if (IsA(path, GatherPath) &&
+		!has_parallel_hazard((Node *) target->exprs, false))
+	{
+		GatherPath *gpath = (GatherPath *) path;
+
+		/*
+		 * We always use create_projection_path here, even if the subpath is
+		 * projection-capable, so as to avoid modifying the subpath in place.
+		 * It seems unlikely at present that there could be any other
+		 * references to the subpath anyway, but better safe than sorry.
+		 * (create_projection_plan will only insert a Result node if the
+		 * subpath is not projection-capable, so we only include the cost of
+		 * that node if it will actually be inserted.  This is a bit grotty
+		 * but we can improve it later if it seems important.)
+		 */
+		if (!is_projection_capable_path(gpath->subpath))
+			gpath->path.total_cost += cpu_tuple_cost * gpath->subpath->rows;
+		gpath->subpath = (Path *)
+			create_projection_path(root,
+								   gpath->subpath->parent,
+								   gpath->subpath,
+								   target);
+	}
+
 	return path;
 }