loop over dnr nodes by topological sort

* Perform topological sort on graph nodes before looping over them to
mark do not run. This guarantees that parent nodes will be processed
before calling dependent child nodes. The complexity of the sorting is
N. The complexity of marking the the nodes is N*V

awx/main/scheduler/dag_simple.py

@@ -1,3 +1,5 @@
+from collections import deque
+
 
 class SimpleDAG(object):
     ''' A simple implementation of a directed acyclic graph '''
@@ -198,3 +200,26 @@ class SimpleDAG(object):
                 node_objs_visited.add(node_obj)
                 path.discard(node_obj)
         return res
+
+    def sort_nodes_topological(self):
+        nodes_sorted = deque()
+        obj_ids_processed = set([])
+
+        def visit(node):
+            obj = node['node_object']
+            if obj.id in obj_ids_processed:
+                return
+
+            for child in self.get_dependencies(obj):
+                visit(child)
+            obj_ids_processed.add(obj.id)
+            nodes_sorted.appendleft(node)
+
+        for node in self.nodes:
+            obj = node['node_object']
+            if obj.id in obj_ids_processed:
+                continue
+
+            visit(node)
+
+        return nodes_sorted

awx/main/scheduler/dag_workflow.py

@@ -1,6 +1,5 @@
 
 # Python
-import copy
 from awx.main.models import (
     WorkflowJobTemplateNode,
     WorkflowJobNode,
@@ -201,10 +200,9 @@ class WorkflowDAG(SimpleDAG):
 
     def mark_dnr_nodes(self):
         root_nodes = self.get_root_nodes()
-        nodes = copy.copy(root_nodes)
         nodes_marked_do_not_run = []
 
-        for index, node in enumerate(nodes):
+        for node in self.sort_nodes_topological():
             obj = node['node_object']
 
             if obj.do_not_run is False and not obj.job:
@@ -217,7 +215,4 @@ class WorkflowDAG(SimpleDAG):
                         obj.do_not_run = True
                         nodes_marked_do_not_run.append(node)
 
-            nodes.extend(self.get_dependencies(obj, 'success_nodes') +
-                         self.get_dependencies(obj, 'failure_nodes') +
-                         self.get_dependencies(obj, 'always_nodes'))
         return [n['node_object'] for n in nodes_marked_do_not_run]