Refactor acceptance tests to improve stability (#884)

Hope it will crash less often when executed on travis against k8s

features/environment.py

@@ -117,12 +117,24 @@ class PatroniController(AbstractController):
         except IOError:
             return None
 
-    def add_tag_to_config(self, tag, value):
+    @staticmethod
+    def recursive_update(dst, src):
+        for k, v in src.items():
+            if k in dst and isinstance(dst[k], dict):
+                PatroniController.recursive_update(dst[k], v)
+            else:
+                dst[k] = v
+
+    def update_config(self, custom_config):
         with open(self._config) as r:
             config = yaml.safe_load(r)
-            config['tags']['tag'] = value
+            self.recursive_update(config, custom_config)
             with open(self._config, 'w') as w:
                 yaml.safe_dump(config, w, default_flow_style=False)
+        self._scope = config.get('scope', 'batman')
+
+    def add_tag_to_config(self, tag, value):
+        self.update_config({'tags': {tag: value}})
 
     def _start(self):
         if self.watchdog:
@@ -174,13 +186,7 @@ class PatroniController(AbstractController):
                 config['bootstrap']['initdb'].extend([{'auth': 'md5'}, {'auth-host': 'md5'}])
 
         if custom_config is not None:
-            def recursive_update(dst, src):
-                for k, v in src.items():
-                    if k in dst and isinstance(dst[k], dict):
-                        recursive_update(dst[k], v)
-                    else:
-                        dst[k] = v
-            recursive_update(config, custom_config)
+            self.recursive_update(config, custom_config)
 
         if config['postgresql'].get('callbacks', {}).get('on_role_change'):
             config['postgresql']['callbacks']['on_role_change'] += ' ' + str(self.__PORT)

features/patroni_api.feature

@@ -43,7 +43,7 @@ Scenario: check dynamic configuration change via DCS
 	And I receive a response loop_wait 2
 	When I issue a GET request to http://127.0.0.1:8008/patroni
 	Then I receive a response code 200
-	And I receive a response tags {'tag': 'new_value'}
+	And I receive a response tags {'new_tag': 'new_value'}
 
 Scenario: check API requests for the primary-replica pair in the pause mode
 	Given I run patronictl.py pause batman

features/standby_cluster.feature

@@ -3,13 +3,15 @@ Feature: standby cluster
     Given I start postgres1
     Then postgres1 is a leader after 10 seconds
     And I sleep for 2 seconds
-    When I issue a PATCH request to http://127.0.0.1:8009/config with {"slots": {"pm_1": {"type": "physical"}}, "postgresql": {"parameters": {"wal_level": "logical"}}}
+    When I issue a PATCH request to http://127.0.0.1:8009/config with {"loop_wait": 2, "slots": {"pm_1": {"type": "physical"}}, "postgresql": {"parameters": {"wal_level": "logical"}}}
     Then I receive a response code 200
     And Response on GET http://127.0.0.1:8009/config contains slots after 10 seconds
+    And I sleep for 2 seconds
     When I issue a PATCH request to http://127.0.0.1:8009/config with {"slots": {"test_logical": {"type": "logical", "database": "postgres", "plugin": "test_decoding"}}}
     Then I receive a response code 200
     When I start postgres0 with callback configured
     Then "members/postgres0" key in DCS has state=running after 10 seconds
+    And replication works from postgres1 to postgres0 after 15 seconds
     When I shut down postgres1
     Then postgres0 is a leader after 10 seconds
     And I sleep for 2 seconds
@@ -20,8 +22,7 @@ Feature: standby cluster
   Scenario: check replication of a single table in a standby cluster
     Given I start postgres1 in a standby cluster batman1 as a clone of postgres0
     Then postgres1 is a leader of batman1 after 10 seconds
-    When I issue a PATCH request to http://127.0.0.1:8009/config with {"ttl": 20, "loop_wait": 2}
-    And I add the table foo to postgres0
+    When I add the table foo to postgres0
     Then table foo is present on postgres1 after 20 seconds
     When I start postgres2 in a cluster batman1
     Then postgres2 role is the replica after 24 seconds

features/steps/standby_cluster.py

@@ -30,12 +30,10 @@ def start_patroni(context, name, cluster_name):
 
 @step('I start {name:w} in a standby cluster {cluster_name:w} as a clone of {name2:w}')
 def start_patroni_stanby_cluster(context, name, cluster_name, name2):
-    ctl = context.pctl._processes.pop(name, None)
     # we need to remove patroni.dynamic.json in order to "bootstrap" standby cluster with existing PGDATA
-    if ctl:
-        os.unlink(os.path.join(ctl._data_dir, 'patroni.dynamic.json'))
+    os.unlink(os.path.join(context.pctl._processes[name]._data_dir, 'patroni.dynamic.json'))
     port = context.pctl._processes[name2]._connkwargs.get('port')
-    return context.pctl.start(name, custom_config={
+    context.pctl._processes[name].update_config({
         "scope": cluster_name,
         "bootstrap": {
             "dcs": {
@@ -47,6 +45,7 @@ def start_patroni_stanby_cluster(context, name, cluster_name, name2):
             }
         }
     })
+    return context.pctl.start(name)
 
 
 @step('{pg_name1:w} is replicating from {pg_name2:w} after {timeout:d} seconds')