Schedule update of machines cache when api_execute call has failed

Such situation could happen if we replaced all etcd nodes except one
which was used by patroni. After replacing the last node patroni will
try to execute request on all other nodes from machines_cache but non of
them are available. Michines cache would became empty and patroni will
stick to the latest node which was available in the machines_cache and
will never try to refresh machines_cache from dns for example.

Currently machines cache is refreshed only when one request to the etcd
cluster has failed, but probably it should be done periodically, for
example every minute...

patroni/etcd.py

@@ -52,7 +52,11 @@ class Client(etcd.Client):
     def api_execute(self, path, method, **kwargs):
         # Update machines_cache if previous attempt of update has failed
         self._update_machines_cache and self._load_machines_cache()
-        return super(Client, self).api_execute(path, method, **kwargs)
+        try:
+            return super(Client, self).api_execute(path, method, **kwargs)
+        except etcd.EtcdConnectionFailed:
+            self._update_machines_cache = True
+            raise
 
     @staticmethod
     def get_srv_record(host):

tests/test_etcd.py

@@ -106,13 +106,13 @@ def etcd_read(key, **kwargs):
                  "modifiedIndex": 20437, "createdIndex": 20437},
                 {"key": "/service/batman5/members", "dir": True, "nodes": [
                     {"key": "/service/batman5/members/postgresql1",
-                     "value": "postgres://replicator:[email protected]:5434/postgres"
-                        + "?application_name=http://127.0.0.1:8009/patroni",
+                     "value": "postgres://replicator:[email protected]:5434/postgres" +
+                        "?application_name=http://127.0.0.1:8009/patroni",
                      "expiration": "2015-05-15T09:10:59.949384522Z", "ttl": 21,
                      "modifiedIndex": 20727, "createdIndex": 20727},
                     {"key": "/service/batman5/members/postgresql0",
-                     "value": "postgres://replicator:[email protected]:5433/postgres"
-                        + "?application_name=http://127.0.0.1:8008/patroni",
+                     "value": "postgres://replicator:[email protected]:5433/postgres" +
+                        "?application_name=http://127.0.0.1:8008/patroni",
                      "expiration": "2015-05-15T09:11:09.611860899Z", "ttl": 30,
                      "modifiedIndex": 20730, "createdIndex": 20730}],
                  "modifiedIndex": 1581, "createdIndex": 1581}], "modifiedIndex": 1581, "createdIndex": 1581}}
@@ -143,6 +143,7 @@ def socket_getaddrinfo(*args):
 
 
 def http_request(method, url, **kwargs):
+    print('http_request', method, url, kwargs)
     if url == 'http://localhost:2379/':
         return MockResponse()
     raise socket.error
@@ -165,6 +166,11 @@ class TestClient(unittest.TestCase):
         self.client._base_uri = 'http://localhost:4001'
         self.client._machines_cache = ['http://localhost:2379']
         self.client.api_execute('/', 'GET')
+        self.client._update_machines_cache = False
+        self.client._base_uri = 'http://localhost:4001'
+        self.client._machines_cache = []
+        self.assertRaises(etcd.EtcdConnectionFailed, self.client.api_execute, '/', 'GET')
+        self.assertTrue(self.client._update_machines_cache)
 
     def test_get_srv_record(self):
         self.assertEquals(self.client.get_srv_record('blabla'), [])