Merge pull request #61 from mistercrunch/backfill_dep_past

depends_on_past backfill fix

airflow/jobs.py

@@ -248,6 +248,7 @@ class BackfillJob(BaseJob):
             dag, start_date=None, end_date=None, mark_success=False,
             *args, **kwargs):
         self.dag = dag
+        dag.override_start_date(start_date)
         self.dag_id = dag.dag_id
         self.bf_start_date = start_date
         self.bf_end_date = end_date

airflow/models.py

@@ -392,15 +392,13 @@ class TaskInstance(Base):
                     self.execution_date-task.schedule_interval,
                 TI.state == State.SUCCESS,
             ).first()
-            if previous_ti:
-                previous_ti.task = task
-                if previous_ti.state != State.SUCCESS:
-                    return False
+            if not previous_ti:
+                return False
 
-                # Applying wait_for_downstream
-                if task.wait_for_downstream and not \
-                        previous_ti.are_dependents_done(session):
-                    return False
+            # Applying wait_for_downstream
+            if task.wait_for_downstream and not \
+                    previous_ti.are_dependents_done(session):
+                return False
 
         # Checking that all upstream dependencies have succeeded
         if task._upstream_list:
@@ -957,6 +955,15 @@ class DAG(Base):
     def pickle(self):
         return pickle.dumps(self)
 
+    def override_start_date(self, start_date):
+        """
+        Sets start_date of all tasks and of the DAG itself to a certain date.
+        This is used by BackfillJob.
+        """
+        for t in self.tasks:
+            t.start_date = start_date
+        self.start_date = start_date
+
     def set_dependency(self, upstream_task_id, downstream_task_id):
         """
         Simple utility method to set dependency between two tasks that

dags/examples/example2.py

@@ -5,6 +5,7 @@ from datetime import datetime
 default_args = {
     'owner': 'mistercrunch',
     'start_date': datetime(2014, 10, 1),
+    'depends_on_past': True,
 }
 
 dag = DAG(dag_id='example_2')
@@ -21,8 +22,8 @@ for i in range(10):
     i = str(i)
     task = BashOperator(
             task_id='runme_'+i,
-            bash_command='echo "'+str(i)+': {{ ti.execution_date }}"',
-            **default_args)
+            bash_command='sleep 10',
+            default_args=default_args)
     task.set_downstream(run_this)
     dag.add_task(task)