gitops/patroni
1
0
Fork 0
mirror of https://github.com/outbackdingo/patroni.git synced 2026-08-25 14:53:37 +00:00
Code Issues Packages Projects Releases Wiki Activity

Use config file as a fallback when all current etcd nodes failed (#2599)

Browse Source 
If communication with etcd nodes failed it is logical to start from scratch, from nodes that are listed in the config. But, it could happen that config is in fact outdated and all nodes in the real cluster were replaced.

Previously we used to track whether config file was changed, which turned out not to work in all possible cases.
The new strategy is a bit more different - if communication with all nodes failed we will continue keeping the last know topology and at the same time will try to figure out the new one by merging two lists together, the cached list and the list from the config file.
This commit is contained in:
Alexander Kukushkin
2023-03-14 15:54:17 +01:00
committed by GitHub
parent 36c17e944b
commit ddac8683e6
5 changed files with 94 additions and 79 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test_ha.py
+12 -13
View File
@@ -199,21 +199,20 @@ class TestHa(PostgresInit):
@patch('socket.getaddrinfo', socket_getaddrinfo)
@patch('patroni.dcs.dcs_modules', Mock(return_value=['patroni.dcs.etcd']))
@patch.object(etcd.Client, 'read', etcd_read)
@patch.object(AbstractEtcdClientWithFailover, '_get_machines_list', Mock(return_value=['http://remotehost:2379']))
def setUp(self):
super(TestHa, self).setUp()
with patch.object(AbstractEtcdClientWithFailover, 'machines') as mock_machines:
mock_machines.__get__ = Mock(return_value=['http://remotehost:2379'])
self.p.set_state('running')
self.p.set_role('replica')
self.p.postmaster_start_time = MagicMock(return_value=str(postmaster_start_time))
self.p.can_create_replica_without_replication_connection = MagicMock(return_value=False)
self.e = get_dcs({'etcd': {'ttl': 30, 'host': 'ok:2379', 'scope': 'test',
'name': 'foo', 'retry_timeout': 10},
'citus': {'database': 'citus', 'group': None}})
self.ha = Ha(MockPatroni(self.p, self.e))
self.ha.old_cluster = self.e.get_cluster()
self.ha.cluster = get_cluster_initialized_without_leader()
self.ha.load_cluster_from_dcs = Mock()
self.p.set_state('running')
self.p.set_role('replica')
self.p.postmaster_start_time = MagicMock(return_value=str(postmaster_start_time))
self.p.can_create_replica_without_replication_connection = MagicMock(return_value=False)
self.e = get_dcs({'etcd': {'ttl': 30, 'host': 'ok:2379', 'scope': 'test',
'name': 'foo', 'retry_timeout': 10},
'citus': {'database': 'citus', 'group': None}})
self.ha = Ha(MockPatroni(self.p, self.e))
self.ha.old_cluster = self.e.get_cluster()
self.ha.cluster = get_cluster_initialized_without_leader()
self.ha.load_cluster_from_dcs = Mock()
def test_update_lock(self):
self.ha.is_failsafe_mode = true