Add config_dir option for configuration files location (#466)

On debian, the configuration files (postgresql.conf, pg_hba.conf, etc) are not stored in the data directory. It would be great to be able to configure the location of this separate directory. Patroni could override existing configuration files where they are used to be.

The default is to store configuration files in the data directory. This setting is targeting custom installations like debian and any others moving configuration files out of the data directory.

Fixes #465

docs/ENVIRONMENT.rst

@@ -46,6 +46,7 @@ PostgreSQL
 -  **PATRONI\_POSTGRESQL\_LISTEN**: IP address + port that Postgres listens to. Multiple comma-separated addresses are permitted, as long as the port component is appended after to the last one with a colon, i.e. ``listen: 127.0.0.1,127.0.0.2:5432``. Patroni will use the first address from this list to establish local connections to the PostgreSQL node.
 -  **PATRONI\_POSTGRESQL\_CONNECT\_ADDRESS**: IP address + port through which Postgres is accessible from other nodes and applications.
 -  **PATRONI\_POSTGRESQL\_DATA\_DIR**: The location of the Postgres data directory, either existing or to be initialized by Patroni.
+-  **PATRONI\_POSTGRESQL\_CONFIG\_DIR**: The location of the Postgres configuration directory, defaults to the data directory. Must be writable by Patroni.
 -  **PATRONI\_POSTGRESQL\_BIN_DIR**: Path to PostgreSQL binaries. (pg_ctl, pg_rewind, pg_basebackup, postgres) The  default value is an empty string meaning that PATH environment variable will be used to find the executables.
 -  **PATRONI\_POSTGRESQL\_PGPASS**: path to the `.pgpass <https://www.postgresql.org/docs/current/static/libpq-pgpass.html>`__ password file. Patroni creates this file before executing pg\_basebackup and under some other circumstances. The location must be writable by Patroni.
 -  **PATRONI\_REPLICATION\_USERNAME**: replication username; the user will be created during initialization. Replicas will use this user to access master via streaming replication

docs/SETTINGS.rst

@@ -82,6 +82,7 @@ PostgreSQL
 -  **connect\_address**: IP address + port through which Postgres is accessible from other nodes and applications.
 -  **create\_replica\_methods**: an ordered list of the create methods for turning a Patroni node into a new replica. "basebackup" is the default method; other methods are assumed to refer to scripts, each of which is configured as its own config item.
 -  **data\_dir**: The location of the Postgres data directory, either existing or to be initialized by Patroni.
+-  **config\_dir**: The location of the Postgres configuration directory, defaults to the data directory. Must be writable by Patroni.
 -  **bin\_dir**: Path to PostgreSQL binaries. (pg_ctl, pg_rewind, pg_basebackup, postgres) The  default value is an empty string meaning that PATH environment variable will be used to find the executables.
 -  **listen**: IP address + port that Postgres listens to; must be accessible from other nodes in the cluster, if you're using streaming replication. Multiple comma-separated addresses are permitted, as long as the port component is appended after to the last one with a colon, i.e. ``listen: 127.0.0.1,127.0.0.2:5432``. Patroni will use the first address from this list to establish local connections to the PostgreSQL node.
 -  **use\_unix\_socket**: specifies that Patroni should prefer to use unix sockets to connect to the cluster. Default value is ``false``. If ``unix_socket_directories`` is definded, Patroni will use first suitable value from it to connect to the cluster and fallback to tcp if nothing is suitable. If ``unix_socket_directories`` is not specified in ``postgresql.parameters``, Patroni will assume that default value should be used and omit ``host`` from connection parameters.

patroni/postgresql.py

@@ -99,6 +99,7 @@ class Postgresql(object):
         self._bin_dir = config.get('bin_dir') or ''
         self._database = config.get('database', 'postgres')
         self._data_dir = config['data_dir']
+        self._config_dir = config.get('config_dir') or self._data_dir
         self._pending_restart = False
         self.__thread_ident = current_thread().ident
 
@@ -120,9 +121,9 @@ class Postgresql(object):
         self.__cb_called = False
         self.__cb_pending = None
         config_base_name = config.get('config_base_name', 'postgresql')
-        self._postgresql_conf = os.path.join(self._data_dir, config_base_name + '.conf')
+        self._postgresql_conf = os.path.join(self._config_dir, config_base_name + '.conf')
         self._postgresql_base_conf_name = config_base_name + '.base.conf'
-        self._postgresql_base_conf = os.path.join(self._data_dir, self._postgresql_base_conf_name)
+        self._postgresql_base_conf = os.path.join(self._config_dir, self._postgresql_base_conf_name)
         self._recovery_conf = os.path.join(self._data_dir, 'recovery.conf')
         self._postmaster_pid = os.path.join(self._data_dir, 'postmaster.pid')
         self._trigger_file = config.get('recovery_conf', {}).get('trigger_file') or 'promote'
@@ -162,11 +163,11 @@ class Postgresql(object):
 
     @property
     def _configuration_to_save(self):
-        configuration = [self._postgresql_conf]
+        configuration = [os.path.basename(self._postgresql_conf)]
         if 'custom_conf' not in self.config:
-            configuration.append(self._postgresql_base_conf)
+            configuration.append(os.path.basename(self._postgresql_base_conf))
         if not self.config['parameters'].get('hba_file'):
-            configuration.append(os.path.join(self._data_dir, 'pg_hba.conf'))
+            configuration.append('pg_hba.conf')
         return configuration
 
     @property
@@ -826,8 +827,9 @@ class Postgresql(object):
                 return False
 
             start_initiated = time.time()
-            proc = call_self(['pg_ctl_start', self._pgcommand('postgres'), '-D', self._data_dir] + options,
+            proc = call_self(['pg_ctl_start', self._pgcommand('postgres'), '-D', self._data_dir,
-                             close_fds=True, preexec_fn=os.setsid, stdout=subprocess.PIPE,
+                             '--config-file={}'.format(self._postgresql_conf)] + options, close_fds=True,
+                             preexec_fn=os.setsid, stdout=subprocess.PIPE,
                              env={p: os.environ[p] for p in ('PATH', 'LC_ALL', 'LANG') if p in os.environ})
             pid = int(proc.stdout.readline().strip())
             proc.wait()
@@ -1060,6 +1062,9 @@ class Postgresql(object):
         with open(self._postgresql_conf, 'w') as f:
             f.write('# Do not edit this file manually!\n# It will be overwritten by Patroni!\n')
             f.write("include '{0}'\n\n".format(self.config.get('custom_conf') or self._postgresql_base_conf_name))
+            f.write("data_directory = '{}'\n".format(self._data_dir))
+            f.write("hba_file = '{}'\n".format(os.path.join(self._config_dir, 'pg_hba.conf')))
+            f.write("ident_file = '{}'\n".format(os.path.join(self._config_dir, 'pg_ident.conf')))
             for name, value in sorted(self._server_parameters.items()):
                 f.write("{0} = '{1}'\n".format(name, value))
 
@@ -1070,7 +1075,7 @@ class Postgresql(object):
         return True
 
     def write_pg_hba(self, config):
-        with open(os.path.join(self._data_dir, 'pg_hba.conf'), 'a') as f:
+        with open(os.path.join(self._config_dir, 'pg_hba.conf'), 'a') as f:
             f.write('\n{}\n'.format('\n'.join(config)))
 
     def _replace_pg_hba(self):
@@ -1081,7 +1086,7 @@ class Postgresql(object):
         :returns: True if pg_hba.conf was rewritten.
         """
         if not self.config['parameters'].get('hba_file') and self.config.get('pg_hba'):
-            with open(os.path.join(self._data_dir, 'pg_hba.conf'), 'w') as f:
+            with open(os.path.join(self._config_dir, 'pg_hba.conf'), 'w') as f:
                 f.write('# Do not edit this file manually!\n# It will be overwritten by Patroni!\n')
                 for line in self.config['pg_hba']:
                     f.write('{0}\n'.format(line))
@@ -1366,8 +1371,10 @@ class Postgresql(object):
         """
         try:
             for f in self._configuration_to_save:
-                if os.path.isfile(f):
+                config_file = os.path.join(self._config_dir, f)
-                    shutil.copy(f, f + '.backup')
+                backup_file = os.path.join(self._data_dir, f + '.backup')
+                if os.path.isfile(config_file):
+                    shutil.copy(config_file, backup_file)
         except IOError:
             logger.exception('unable to create backup copies of configuration files')
 
@@ -1375,8 +1382,10 @@ class Postgresql(object):
         """ restore a previously saved postgresql.conf """
         try:
             for f in self._configuration_to_save:
-                if not os.path.isfile(f) and os.path.isfile(f + '.backup'):
+                config_file = os.path.join(self._config_dir, f)
-                    shutil.copy(f + '.backup', 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)
         except IOError:
             logger.exception('unable to restore configuration files from backup')
 

postgres0.yml

@@ -66,6 +66,7 @@ postgresql:
   connect_address: 127.0.0.1:5432
   data_dir: data/postgresql0
 #  bin_dir:
+#  config_dir:
   pgpass: /tmp/pgpass0
   authentication:
     replication:

postgres1.yml

@@ -64,6 +64,7 @@ postgresql:
   connect_address: 127.0.0.1:5433
   data_dir: data/postgresql1
 #  bin_dir:
+#  config_dir:
   pgpass: /tmp/pgpass1
   authentication:
     replication:

postgres2.yml

@@ -61,6 +61,7 @@ postgresql:
   connect_address: 127.0.0.1:5434
   data_dir: data/postgresql2
 #  bin_dir:
+#  config_dir:
   pgpass: /tmp/pgpass2
   authentication:
     replication:

tests/test_config.py

@@ -39,6 +39,7 @@ class TestConfig(unittest.TestCase):
             'PATRONI_POSTGRESQL_LISTEN': '0.0.0.0:5432',
             'PATRONI_POSTGRESQL_CONNECT_ADDRESS': '127.0.0.1:5432',
             'PATRONI_POSTGRESQL_DATA_DIR': 'data/postgres0',
+            'PATRONI_POSTGRESQL_CONFIG_DIR': 'data/postgres0',
             'PATRONI_POSTGRESQL_PGPASS': '/tmp/pgpass0',
             'PATRONI_ETCD_HOST': '127.0.0.1:2379',
             'PATRONI_ETCD_URL': 'https://127.0.0.1:2379',

tests/test_postgresql.py

@@ -168,9 +168,11 @@ class TestPostgresql(unittest.TestCase):
     @patch.object(Postgresql, 'is_running', Mock(return_value=True))
     def setUp(self):
         self.data_dir = 'data/test0'
+        self.config_dir = self.data_dir
         if not os.path.exists(self.data_dir):
             os.makedirs(self.data_dir)
-        self.p = Postgresql({'name': 'test0', 'scope': 'batman', 'data_dir': self.data_dir, 'retry_timeout': 10,
+        self.p = Postgresql({'name': 'test0', 'scope': 'batman', 'data_dir': self.data_dir,
+                             'config_dir': self.config_dir, 'retry_timeout': 10,
                              'listen': '127.0.0.2, 127.0.0.3:5432', 'connect_address': '127.0.0.2:5432',
                              'authentication': {'superuser': {'username': 'test', 'password': 'test'},
                                                 'replication': {'username': 'replicator', 'password': 'rep-pass'}},
@@ -502,7 +504,7 @@ class TestPostgresql(unittest.TestCase):
         config = {'users': {'replicator': {'password': 'rep-pass', 'options': ['replication']}}}
 
         self.p.bootstrap(config)
-        with open(os.path.join(self.data_dir, 'pg_hba.conf')) as f:
+        with open(os.path.join(self.config_dir, 'pg_hba.conf')) as f:
             lines = f.readlines()
             self.assertTrue('host all all 0.0.0.0/0 md5\n' in lines)