Apply 1 second backoff if LIST failed (#1424)

It is mostly necessary to avoid flooding logs, but also help to prevent starvation of the main thread.

patroni/dcs/kubernetes.py

@@ -106,7 +106,11 @@ class ObjectCache(Thread):
         self.start()
 
     def _list(self):
-        return self._func(_request_timeout=(self._retry.deadline, Timeout.DEFAULT_TIMEOUT))
+        try:
+            return self._func(_request_timeout=(self._retry.deadline, Timeout.DEFAULT_TIMEOUT))
+        except Exception:
+            time.sleep(1)
+            raise
 
     def _watch(self, resource_version):
         return self._func(_request_timeout=(self._retry.deadline, Timeout.DEFAULT_TIMEOUT),

tests/test_kubernetes.py

@@ -174,3 +174,8 @@ class TestCacheBuilder(unittest.TestCase):
     @patch('patroni.dcs.kubernetes.ObjectCache._build_cache', Mock(side_effect=Exception))
     def test_run(self):
         self.assertRaises(SleepException, self.k._pods.run)
+
+    @patch('time.sleep', Mock())
+    def test__list(self):
+        self.k._pods._func = Mock(side_effect=Exception)
+        self.assertRaises(Exception, self.k._pods._list)