Small bugfixes (#499)

* Short after promote synchronous replication was disabled even is synchronous_mode_strict is set
* Create empty pg_ident.conf if it is missing after restoring from backup
* Bump version

features/patroni_api.feature

@@ -34,9 +34,9 @@ Scenario: check local configuration reload
 	Then I receive a response code 202
 
 Scenario: check dynamic configuration change via DCS
-	Given I issue a PATCH request to http://127.0.0.1:8008/config with {"ttl": 10, "loop_wait": 2, "postgresql": {"parameters": {"max_connections": 101}}}
-	Then I receive a response code 200
-	And I receive a response loop_wait 2
+	Given I run patronictl.py edit-config -s 'ttl=10' -s 'loop_wait=2' -p 'max_connections=101' --force batman
+	Then I receive a response returncode 0
+	And I receive a response output "+loop_wait: 2"
 	And Response on GET http://127.0.0.1:8008/patroni contains pending_restart after 11 seconds
 	When I issue a GET request to http://127.0.0.1:8008/config
 	Then I receive a response code 200
@@ -65,8 +65,8 @@ Scenario: check API requests for the primary-replica pair in the pause mode
 	Then postgres1 role is the secondary after 15 seconds
 
 Scenario: check the failover via the API in the pause mode
-	Given I run patronictl.py failover batman --master postgres0 --candidate postgres1 --force
-	Then I receive a response returncode 0
+	Given I issue a POST request to http://127.0.0.1:8008/failover with {"leader": "postgres0", "candidate": "postgres1"}
+	Then I receive a response code 200
 	And postgres1 is a leader after 5 seconds
 	And postgres1 role is the primary after 10 seconds
 	And postgres0 role is the secondary after 10 seconds

patroni/api.py

@@ -300,8 +300,8 @@ class RestApiHandler(BaseHTTPRequestHandler):
             members = [m for m in cluster.members if m.name != cluster.leader.name and m.api_url]
             if not members:
                 return 'failover is not possible: cluster does not have members except leader'
-        for _, reachable, _, _, tags in self.server.patroni.ha.fetch_nodes_statuses(members):
-            if reachable and not tags.get('nofailover', False):
+        for st in self.server.patroni.ha.fetch_nodes_statuses(members):
+            if st.failover_limitation() is None:
                 return None
         return 'failover is not possible: no good candidates have been found'
 

patroni/ctl.py

@@ -903,14 +903,14 @@ def apply_config_changes(before_editing, data, kvpairs):
         if prefix == ('postgresql', 'parameters'):
             path = ['.'.join(path)]
 
+        key = path[0]
         if len(path) == 1:
             if value is None:
-                config.pop(path[0], None)
+                config.pop(key, None)
             else:
-                config[path[0]] = value
+                config[key] = value
         else:
-            key = path[0]
-            if key not in config:
+            if not isinstance(config.get(key), dict):
                 config[key] = {}
             set_path_value(config[key], path[1:], value, prefix + (key,))
             if config[key] == {}:
@@ -1017,7 +1017,7 @@ def edit_config(obj, cluster_name, force, quiet, kvpairs, pgkvpairs, apply_filen
         return
 
     if force or click.confirm('Apply these changes?'):
-        if not dcs.set_config_value(json.dumps(changed_data), cluster.config.modify_index):
+        if not dcs.set_config_value(json.dumps(changed_data), cluster.config.index):
             raise PatroniCtlException("Config modification aborted due to concurrent changes")
         click.echo("Configuration changed")
 

patroni/ha.py

@@ -26,6 +26,7 @@ class _MemberStatus(namedtuple('_MemberStatus', 'member,reachable,in_recovery,wa
         in_recovery - `!True` if pg_is_in_recovery() == true
         wal_position - value of `replayed_location` or `location` from JSON, dependin on its role.
         tags - dictionary with values of different tags (i.e. nofailover)
+        watchdog_failed - indicates that watchdog is required by configuration but not available or failed
     """
     @classmethod
     def from_api_response(cls, member, json):
@@ -363,7 +364,7 @@ class Ha(object):
                     # Somebody else updated sync state, it may be due to us losing the lock. To be safe, postpone
                     # promotion until next cycle. TODO: trigger immediate retry of run_cycle
                     return 'Postponing promotion because synchronous replication state was updated by somebody else'
-                self.state_handler.set_synchronous_standby(None)
+                self.state_handler.set_synchronous_standby('*' if self.is_synchronous_mode_strict() else None)
             self.state_handler.promote()
             return promote_message
 

patroni/postgresql.py

@@ -1137,7 +1137,7 @@ class Postgresql(object):
             with open(self._pg_hba_conf, 'w') as f:
                 f.write(self._CONFIG_WARNING_HEADER)
                 for address, t in addresses.items():
-                    f.write('{0}\t{1}\t{2}\t{3}\ttrust\n'.format(t, self._database,
+                    f.write('{0}\t{1}\t{2}\t{3}\ttrust\n'.format(t, 'all',
                                                                  self._superuser.get('username') or 'all', address))
         elif not self._server_parameters.get('hba_file') and self.config.get('pg_hba'):
             with open(self._pg_hba_conf, 'w') as f:
@@ -1396,8 +1396,12 @@ class Postgresql(object):
             for f in self._configuration_to_save:
                 config_file = os.path.join(self._config_dir, f)
                 backup_file = os.path.join(self._data_dir, f + '.backup')
-                if not os.path.isfile(config_file) and os.path.isfile(backup_file):
-                    shutil.copy(backup_file, config_file)
+                if not os.path.isfile(config_file):
+                    if os.path.isfile(backup_file):
+                        shutil.copy(backup_file, config_file)
+                    # Previously we didn't backup pg_ident.conf, if file is missing just create empty
+                    elif f == 'pg_ident.conf':
+                        open(config_file, 'w').close()
         except IOError:
             logger.exception('unable to restore configuration files from backup')
 

patroni/version.py

@@ -1 +1 @@
-__version__ = '1.3'
+__version__ = '1.3.3'

tests/test_api.py

@@ -6,6 +6,7 @@ import unittest
 from mock import Mock, patch
 from patroni.api import RestApiHandler, RestApiServer
 from patroni.dcs import ClusterConfig, Member
+from patroni.ha import _MemberStatus
 from patroni.utils import tzutc
 from six import BytesIO as IO
 from six.moves import BaseHTTPServer
@@ -38,7 +39,7 @@ class MockPostgresql(object):
 
 
 class MockWatchdog(object):
-    is_healthy = True
+    is_healthy = False
 
 
 class MockHa(object):
@@ -64,7 +65,7 @@ class MockHa(object):
 
     @staticmethod
     def fetch_nodes_statuses(members):
-        return [[None, True, None, None, {}]]
+        return [_MemberStatus(None, True, None, None, {}, False)]
 
     @staticmethod
     def schedule_future_restart(data):

tests/test_watchdog.py

@@ -135,6 +135,7 @@ class TestWatchdog(unittest.TestCase):
         self.assertIsNone(wd.disable())
         self.assertIsNone(wd.keepalive())
 
+    @patch('platform.system', Mock(return_value='Linux'))
     def test_config_reload(self):
         watchdog = Watchdog({'ttl': 30, 'loop_wait': 15, 'watchdog': {'mode': 'required'}})
         self.assertTrue(watchdog.activate())