Handle correctly health-checks for standby cluster (#1553)

Close https://github.com/zalando/patroni/issues/1388

features/patroni_api.feature

@@ -8,6 +8,8 @@ Scenario: check API requests on a stand-alone server
 	Then I receive a response code 200
 	And I receive a response state running
 	And I receive a response role master
+	When I issue a GET request to http://127.0.0.1:8008/standby_leader
+	Then I receive a response code 503
 	When I issue a GET request to http://127.0.0.1:8008/health
 	Then I receive a response code 200
 	When I issue a GET request to http://127.0.0.1:8008/replica

features/standby_cluster.feature

@@ -26,7 +26,7 @@ Feature: standby cluster
     When I add the table foo to postgres0
     Then table foo is present on postgres1 after 20 seconds
     When I issue a GET request to http://127.0.0.1:8009/master
-    Then I receive a response code 200
+    Then I receive a response code 503
     When I issue a GET request to http://127.0.0.1:8009/standby_leader
     Then I receive a response code 200
     And I receive a response role standby_leader
@@ -40,7 +40,7 @@ Feature: standby cluster
     And I kill postmaster on postgres1
     Then postgres2 is replicating from postgres0 after 32 seconds
     When I issue a GET request to http://127.0.0.1:8010/master
-    Then I receive a response code 200
+    Then I receive a response code 503
     When I issue a GET request to http://127.0.0.1:8010/standby_leader
     Then I receive a response code 200
     And I receive a response role standby_leader

patroni/api.py

@@ -89,23 +89,32 @@ class RestApiHandler(BaseHTTPRequestHandler):
         patroni = self.server.patroni
         cluster = patroni.dcs.cluster
 
-        if not cluster and patroni.ha.is_paused():
-            primary_status_code = 200 if response['role'] == 'master' else 503
-        else:
-            primary_status_code = 200 if patroni.ha.is_leader() else 503
-
         replica_status_code = 200 if not patroni.noloadbalance and \
             response.get('role') == 'replica' and response.get('state') == 'running' else 503
+
+        if not cluster and patroni.ha.is_paused():
+            primary_status_code = 200 if response.get('role') == 'master' else 503
+            standby_leader_status_code = 200 if response.get('role') == 'standby_leader' else 503
+        elif patroni.ha.is_leader():
+            if patroni.ha.is_standby_cluster():
+                primary_status_code = replica_status_code = 503
+                standby_leader_status_code = 200 if response.get('role') in ('replica', 'standby_leader') else 503
+            else:
+                primary_status_code = 200
+                standby_leader_status_code = 503
+        else:
+            primary_status_code = standby_leader_status_code = 503
+
         status_code = 503
 
-        if patroni.ha.is_standby_cluster() and ('standby_leader' in path or 'standby-leader' in path):
-            status_code = 200 if patroni.ha.is_leader() else 503
+        if 'standby_leader' in path or 'standby-leader' in path:
+            status_code = standby_leader_status_code
         elif 'master' in path or 'leader' in path or 'primary' in path or 'read-write' in path:
             status_code = primary_status_code
         elif 'replica' in path:
             status_code = replica_status_code
         elif 'read-only' in path:
-            status_code = 200 if primary_status_code == 200 else replica_status_code
+            status_code = 200 if 200 in (primary_status_code, standby_leader_status_code) else replica_status_code
         elif 'health' in path:
             status_code = 200 if response.get('state') == 'running' else 503
         elif cluster:  # dcs is available

patroni/ha.py

@@ -391,10 +391,13 @@ class Ha(object):
         if self.is_paused():
             if not (self._rewind.is_needed and self._rewind.can_rewind_or_reinitialize_allowed)\
                     or self.cluster.is_unlocked():
-                self.state_handler.set_role('master' if is_leader else 'replica')
                 if is_leader:
+                    self.state_handler.set_role('master')
                     return 'continue to run as master without lock'
-                elif not node_to_follow:
+                elif self.state_handler.role != 'standby_leader':
+                    self.state_handler.set_role('replica')
+
+                if not node_to_follow:
                     return 'no action'
         elif is_leader:
             self.demote('immediate-nolock')

tests/test_api.py

@@ -179,6 +179,8 @@ class TestRestApiHandler(unittest.TestCase):
             MockRestApiServer(RestApiHandler, 'GET /asynchronous')
         MockPatroni.ha.is_leader = Mock(return_value=True)
         MockRestApiServer(RestApiHandler, 'GET /replica')
+        with patch.object(MockHa, 'is_standby_cluster', Mock(return_value=True)):
+            MockRestApiServer(RestApiHandler, 'GET /standby_leader')
         MockPatroni.dcs.cluster = None
         with patch.object(RestApiHandler, 'get_postgresql_status', Mock(return_value={'role': 'master'})):
             MockRestApiServer(RestApiHandler, 'GET /master')