mirror of
https://github.com/outbackdingo/patroni.git
synced 2026-08-25 14:53:37 +00:00
Ensure strict failover/switchover definition difference (#2784)
- Don't set leader in failover key from patronictl failover - Show warning and execute switchover if leader option is provided for patronictl failover command - Be more precise in the log messages - Allow to failover to an async candidate in sync mode - Check if candidate is the same as the leader specified in api - Fix and extend some tests - Add documentation
This commit is contained in:
Polina Bungina
+265
-98
@@ -435,6 +435,7 @@ class TestHa(PostgresInit):
|
||||
|
||||
def test_promote_without_watchdog(self):
|
||||
self.ha.has_lock = true
|
||||
self.p.is_primary = true
|
||||
with patch.object(Watchdog, 'activate', Mock(return_value=False)):
|
||||
self.assertEqual(self.ha.run_cycle(), 'Demoting self because watchdog could not be activated')
|
||||
self.p.is_primary = false
|
||||
@@ -614,6 +615,7 @@ class TestHa(PostgresInit):
|
||||
self.ha.cluster = get_cluster_not_initialized_without_leader()
|
||||
self.e.initialize = true
|
||||
self.ha.bootstrap()
|
||||
self.p.is_primary = true
|
||||
with patch.object(Watchdog, 'activate', Mock(return_value=False)), \
|
||||
patch('patroni.ha.logger.error') as mock_logger:
|
||||
self.assertEqual(self.ha.post_bootstrap(), 'running post_bootstrap')
|
||||
@@ -687,110 +689,289 @@ class TestHa(PostgresInit):
|
||||
|
||||
@patch('patroni.postgresql.citus.CitusHandler.is_coordinator', Mock(return_value=False))
|
||||
def test_manual_failover_from_leader(self):
|
||||
self.ha.has_lock = true # I am the leader
|
||||
|
||||
# to me
|
||||
with patch('patroni.ha.logger.warning') as mock_warning:
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, '', self.p.name, None))
|
||||
self.assertEqual(self.ha.run_cycle(), 'no action. I am (postgresql0), the leader with the lock')
|
||||
mock_warning.assert_called_with('%s: I am already the leader, no need to %s', 'manual failover', 'failover')
|
||||
|
||||
# to a non-existent candidate
|
||||
with patch('patroni.ha.logger.warning') as mock_warning:
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, '', 'blabla', None))
|
||||
self.assertEqual(self.ha.run_cycle(), 'no action. I am (postgresql0), the leader with the lock')
|
||||
mock_warning.assert_called_with(
|
||||
'%s: no healthy members found, %s is not possible', 'manual failover', 'failover')
|
||||
|
||||
# to an existent candidate
|
||||
self.ha.fetch_node_status = get_node_status()
|
||||
self.ha.has_lock = true
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, 'blabla', '', None))
|
||||
self.assertEqual(self.ha.run_cycle(), 'no action. I am (postgresql0), the leader with the lock')
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, '', self.p.name, None))
|
||||
self.assertEqual(self.ha.run_cycle(), 'no action. I am (postgresql0), the leader with the lock')
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, '', 'blabla', None))
|
||||
self.assertEqual(self.ha.run_cycle(), 'no action. I am (postgresql0), the leader with the lock')
|
||||
f = Failover(0, self.p.name, '', None)
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(f)
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, '', 'b', None))
|
||||
self.ha.cluster.members.append(Member(0, 'b', 28, {'api_url': 'http://127.0.0.1:8011/patroni'}))
|
||||
self.assertEqual(self.ha.run_cycle(), 'manual failover: demoting myself')
|
||||
|
||||
# to a candidate on an older timeline
|
||||
with patch('patroni.ha.logger.info') as mock_info:
|
||||
self.ha.fetch_node_status = get_node_status(timeline=1)
|
||||
self.assertEqual(self.ha.run_cycle(), 'no action. I am (postgresql0), the leader with the lock')
|
||||
self.assertEqual(mock_info.call_args_list[0][0],
|
||||
('Timeline %s of member %s is behind the cluster timeline %s', 1, 'b', 2))
|
||||
|
||||
# to a lagging candidate
|
||||
with patch('patroni.ha.logger.info') as mock_info:
|
||||
self.ha.fetch_node_status = get_node_status(wal_position=1)
|
||||
self.ha.cluster.config.data.update({'maximum_lag_on_failover': 5})
|
||||
self.assertEqual(self.ha.run_cycle(), 'no action. I am (postgresql0), the leader with the lock')
|
||||
self.assertEqual(mock_info.call_args_list[0][0],
|
||||
('Member %s exceeds maximum replication lag', 'b'))
|
||||
self.ha.cluster.members.pop()
|
||||
|
||||
@patch('patroni.postgresql.citus.CitusHandler.is_coordinator', Mock(return_value=False))
|
||||
def test_manual_switchover_from_leader(self):
|
||||
self.ha.has_lock = true # I am the leader
|
||||
|
||||
self.ha.fetch_node_status = get_node_status()
|
||||
|
||||
# different leader specified in failover key, no candidate
|
||||
with patch('patroni.ha.logger.warning') as mock_warning:
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, 'blabla', '', None))
|
||||
self.assertEqual(self.ha.run_cycle(), 'no action. I am (postgresql0), the leader with the lock')
|
||||
mock_warning.assert_called_with(
|
||||
'%s: leader name does not match: %s != %s', 'switchover', 'blabla', 'postgresql0')
|
||||
|
||||
# no candidate
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, self.p.name, '', None))
|
||||
self.assertEqual(self.ha.run_cycle(), 'switchover: demoting myself')
|
||||
|
||||
self.ha._rewind.rewind_or_reinitialize_needed_and_possible = true
|
||||
self.assertEqual(self.ha.run_cycle(), 'manual failover: demoting myself')
|
||||
self.ha.fetch_node_status = get_node_status(nofailover=True)
|
||||
self.assertEqual(self.ha.run_cycle(), 'no action. I am (postgresql0), the leader with the lock')
|
||||
self.ha.fetch_node_status = get_node_status(watchdog_failed=True)
|
||||
self.assertEqual(self.ha.run_cycle(), 'no action. I am (postgresql0), the leader with the lock')
|
||||
self.ha.fetch_node_status = get_node_status(timeline=1)
|
||||
self.assertEqual(self.ha.run_cycle(), 'no action. I am (postgresql0), the leader with the lock')
|
||||
self.ha.fetch_node_status = get_node_status(wal_position=1)
|
||||
self.ha.cluster.config.data.update({'maximum_lag_on_failover': 5})
|
||||
self.ha.global_config = self.ha.patroni.config.get_global_config(self.ha.cluster)
|
||||
self.assertEqual(self.ha.run_cycle(), 'no action. I am (postgresql0), the leader with the lock')
|
||||
# manual failover from the previous leader to us won't happen if we hold the nofailover flag
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, 'blabla', self.p.name, None))
|
||||
self.assertEqual(self.ha.run_cycle(), 'no action. I am (postgresql0), the leader with the lock')
|
||||
self.assertEqual(self.ha.run_cycle(), 'switchover: demoting myself')
|
||||
|
||||
# Failover scheduled time must include timezone
|
||||
scheduled = datetime.datetime.now()
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, 'blabla', self.p.name, scheduled))
|
||||
self.ha.run_cycle()
|
||||
# other members with failover_limitation_s
|
||||
with patch('patroni.ha.logger.info') as mock_info:
|
||||
self.ha.fetch_node_status = get_node_status(nofailover=True)
|
||||
self.assertEqual(self.ha.run_cycle(), 'no action. I am (postgresql0), the leader with the lock')
|
||||
self.assertEqual(mock_info.call_args_list[0][0], ('Member %s is %s', 'leader', 'not allowed to promote'))
|
||||
with patch('patroni.ha.logger.info') as mock_info:
|
||||
self.ha.fetch_node_status = get_node_status(watchdog_failed=True)
|
||||
self.assertEqual(self.ha.run_cycle(), 'no action. I am (postgresql0), the leader with the lock')
|
||||
self.assertEqual(mock_info.call_args_list[0][0], ('Member %s is %s', 'leader', 'not watchdog capable'))
|
||||
with patch('patroni.ha.logger.info') as mock_info:
|
||||
self.ha.fetch_node_status = get_node_status(timeline=1)
|
||||
self.assertEqual(self.ha.run_cycle(), 'no action. I am (postgresql0), the leader with the lock')
|
||||
self.assertEqual(mock_info.call_args_list[0][0],
|
||||
('Timeline %s of member %s is behind the cluster timeline %s', 1, 'leader', 2))
|
||||
with patch('patroni.ha.logger.info') as mock_info:
|
||||
self.ha.fetch_node_status = get_node_status(wal_position=1)
|
||||
self.ha.cluster.config.data.update({'maximum_lag_on_failover': 5})
|
||||
self.ha.global_config = self.ha.patroni.config.get_global_config(self.ha.cluster)
|
||||
self.assertEqual(self.ha.run_cycle(), 'no action. I am (postgresql0), the leader with the lock')
|
||||
self.assertEqual(mock_info.call_args_list[0][0], ('Member %s exceeds maximum replication lag', 'leader'))
|
||||
|
||||
@patch('patroni.postgresql.citus.CitusHandler.is_coordinator', Mock(return_value=False))
|
||||
def test_scheduled_switchover_from_leader(self):
|
||||
self.ha.has_lock = true # I am the leader
|
||||
|
||||
self.ha.fetch_node_status = get_node_status()
|
||||
|
||||
# switchover scheduled time must include timezone
|
||||
with patch('patroni.ha.logger.warning') as mock_warning:
|
||||
scheduled = datetime.datetime.now()
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, self.p.name, 'blabla', scheduled))
|
||||
self.assertEqual(self.ha.run_cycle(), 'no action. I am (postgresql0), the leader with the lock')
|
||||
self.assertIn('Incorrect value of scheduled_at: %s', mock_warning.call_args_list[0][0])
|
||||
|
||||
# scheduled now
|
||||
scheduled = datetime.datetime.utcnow().replace(tzinfo=tzutc)
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, 'blabla', self.p.name, scheduled))
|
||||
self.assertEqual('no action. I am (postgresql0), the leader with the lock', self.ha.run_cycle())
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, self.p.name, 'b', scheduled))
|
||||
self.ha.cluster.members.append(Member(0, 'b', 28, {'api_url': 'http://127.0.0.1:8011/patroni'}))
|
||||
self.assertEqual('switchover: demoting myself', self.ha.run_cycle())
|
||||
|
||||
scheduled = scheduled + datetime.timedelta(seconds=30)
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, 'blabla', self.p.name, scheduled))
|
||||
self.assertEqual('no action. I am (postgresql0), the leader with the lock', self.ha.run_cycle())
|
||||
# scheduled in the future
|
||||
with patch('patroni.ha.logger.info') as mock_info:
|
||||
scheduled = scheduled + datetime.timedelta(seconds=30)
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, self.p.name, 'blabla', scheduled))
|
||||
self.assertEqual('no action. I am (postgresql0), the leader with the lock', self.ha.run_cycle())
|
||||
self.assertIn('Awaiting %s at %s (in %.0f seconds)', mock_info.call_args_list[0][0])
|
||||
|
||||
scheduled = scheduled + datetime.timedelta(seconds=-600)
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, 'blabla', self.p.name, scheduled))
|
||||
self.assertEqual('no action. I am (postgresql0), the leader with the lock', self.ha.run_cycle())
|
||||
# stale value
|
||||
with patch('patroni.ha.logger.warning') as mock_warning:
|
||||
scheduled = scheduled + datetime.timedelta(seconds=-600)
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, self.p.name, 'b', scheduled))
|
||||
self.ha.cluster.members.append(Member(0, 'b', 28, {'api_url': 'http://127.0.0.1:8011/patroni'}))
|
||||
self.assertEqual('no action. I am (postgresql0), the leader with the lock', self.ha.run_cycle())
|
||||
self.assertIn('Found a stale %s value, cleaning up: %s', mock_warning.call_args_list[0][0])
|
||||
|
||||
scheduled = None
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, 'blabla', self.p.name, scheduled))
|
||||
self.assertEqual('no action. I am (postgresql0), the leader with the lock', self.ha.run_cycle())
|
||||
def test_manual_switchover_from_leader_in_pause(self):
|
||||
self.ha.has_lock = true # I am the leader
|
||||
self.ha.is_paused = true
|
||||
|
||||
# no candidate
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, self.p.name, '', None))
|
||||
with patch('patroni.ha.logger.warning') as mock_warning:
|
||||
self.assertEqual('PAUSE: no action. I am (postgresql0), the leader with the lock', self.ha.run_cycle())
|
||||
mock_warning.assert_called_with(
|
||||
'%s is possible only to a specific candidate in a paused state', 'Switchover')
|
||||
|
||||
def test_manual_failover_from_leader_in_pause(self):
|
||||
self.ha.has_lock = true
|
||||
self.ha.fetch_node_status = get_node_status()
|
||||
self.ha.is_paused = true
|
||||
scheduled = datetime.datetime.now()
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, 'blabla', self.p.name, scheduled))
|
||||
self.assertEqual('PAUSE: no action. I am (postgresql0), the leader with the lock', self.ha.run_cycle())
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, self.p.name, '', None))
|
||||
self.assertEqual('PAUSE: no action. I am (postgresql0), the leader with the lock', self.ha.run_cycle())
|
||||
|
||||
# failover from me, candidate is healthy
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, None, 'b', None))
|
||||
self.ha.cluster.members.append(Member(0, 'b', 28, {'api_url': 'http://127.0.0.1:8011/patroni'}))
|
||||
self.assertEqual('PAUSE: manual failover: demoting myself', self.ha.run_cycle())
|
||||
self.ha.cluster.members.pop()
|
||||
|
||||
def test_manual_failover_from_leader_in_synchronous_mode(self):
|
||||
self.ha.has_lock = true
|
||||
self.ha.is_synchronous_mode = true
|
||||
self.ha.process_sync_replication = Mock()
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, self.p.name, 'a', None), (self.p.name, None))
|
||||
self.assertEqual('no action. I am (postgresql0), the leader with the lock', self.ha.run_cycle())
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, self.p.name, 'a', None), (self.p.name, 'a'))
|
||||
self.ha.is_failover_possible = true
|
||||
self.ha.fetch_node_status = get_node_status()
|
||||
|
||||
# I am the leader
|
||||
self.p.is_primary = true
|
||||
self.ha.has_lock = true
|
||||
|
||||
# the candidate is not in sync members but we allow failover to an async candidate
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, None, 'b', None), sync=(self.p.name, 'a'))
|
||||
self.ha.cluster.members.append(Member(0, 'b', 28, {'api_url': 'http://127.0.0.1:8011/patroni'}))
|
||||
self.assertEqual('manual failover: demoting myself', self.ha.run_cycle())
|
||||
self.ha.cluster.members.pop()
|
||||
|
||||
def test_manual_switchover_from_leader_in_synchronous_mode(self):
|
||||
self.ha.is_synchronous_mode = true
|
||||
self.ha.process_sync_replication = Mock()
|
||||
|
||||
# I am the leader
|
||||
self.p.is_primary = true
|
||||
self.ha.has_lock = true
|
||||
|
||||
# candidate specified is not in sync members
|
||||
with patch('patroni.ha.logger.warning') as mock_warning:
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, self.p.name, 'a', None),
|
||||
sync=(self.p.name, 'blabla'))
|
||||
self.assertEqual('no action. I am (postgresql0), the leader with the lock', self.ha.run_cycle())
|
||||
self.assertEqual(mock_warning.call_args_list[0][0],
|
||||
('%s candidate=%s does not match with sync_standbys=%s', 'Switchover', 'a', 'blabla'))
|
||||
|
||||
# the candidate is in sync members and is healthy
|
||||
self.ha.fetch_node_status = get_node_status(wal_position=305419896)
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(Failover(0, self.p.name, 'a', None),
|
||||
sync=(self.p.name, 'a'))
|
||||
self.ha.cluster.members.append(Member(0, 'a', 28, {'api_url': 'http://127.0.0.1:8011/patroni'}))
|
||||
self.assertEqual('switchover: demoting myself', self.ha.run_cycle())
|
||||
|
||||
# the candidate is in sync members but is not healthy
|
||||
with patch('patroni.ha.logger.info') as mock_info:
|
||||
self.ha.fetch_node_status = get_node_status(nofailover=true)
|
||||
self.assertEqual('no action. I am (postgresql0), the leader with the lock', self.ha.run_cycle())
|
||||
self.assertEqual(mock_info.call_args_list[0][0], ('Member %s is %s', 'a', 'not allowed to promote'))
|
||||
|
||||
def test_manual_failover_process_no_leader(self):
|
||||
self.p.is_primary = false
|
||||
self.ha.cluster = get_cluster_initialized_without_leader(failover=Failover(0, '', self.p.name, None))
|
||||
self.ha.cluster = get_cluster_initialized_without_leader(failover=Failover(0, '', 'leader', None))
|
||||
self.p.set_role('replica')
|
||||
self.assertEqual(self.ha.run_cycle(), 'promoted self to leader by acquiring session lock')
|
||||
self.ha.fetch_node_status = get_node_status() # accessible, in_recovery
|
||||
self.assertEqual(self.ha.run_cycle(), 'following a different leader because i am not the healthiest node')
|
||||
self.ha.cluster = get_cluster_initialized_without_leader(failover=Failover(0, self.p.name, '', None))
|
||||
self.assertEqual(self.ha.run_cycle(), 'following a different leader because i am not the healthiest node')
|
||||
self.ha.fetch_node_status = get_node_status(reachable=False) # inaccessible, in_recovery
|
||||
|
||||
# failover to another member, fetch_node_status for candidate fails
|
||||
with patch('patroni.ha.logger.warning') as mock_warning:
|
||||
self.ha.cluster = get_cluster_initialized_without_leader(failover=Failover(0, '', 'leader', None))
|
||||
self.assertEqual(self.ha.run_cycle(), 'promoted self to leader by acquiring session lock')
|
||||
self.assertEqual(mock_warning.call_args_list[1][0],
|
||||
('%s: member %s is %s', 'manual failover', 'leader', 'not reachable'))
|
||||
|
||||
# failover to another member, candidate is accessible, in_recovery
|
||||
self.p.set_role('replica')
|
||||
self.assertEqual(self.ha.run_cycle(), 'promoted self to leader by acquiring session lock')
|
||||
# set failover flag to True for all members of the cluster
|
||||
self.ha.fetch_node_status = get_node_status()
|
||||
self.assertEqual(self.ha.run_cycle(), 'following a different leader because i am not the healthiest node')
|
||||
|
||||
# set nofailover flag to True for all members of the cluster
|
||||
# this should elect the current member, as we are not going to call the API for it.
|
||||
self.ha.cluster = get_cluster_initialized_without_leader(failover=Failover(0, '', 'other', None))
|
||||
self.ha.fetch_node_status = get_node_status(nofailover=True) # accessible, in_recovery
|
||||
self.p.set_role('replica')
|
||||
self.ha.fetch_node_status = get_node_status(nofailover=True)
|
||||
self.assertEqual(self.ha.run_cycle(), 'promoted self to leader by acquiring session lock')
|
||||
# same as previous, but set the current member to nofailover. In no case it should be elected as a leader
|
||||
|
||||
# failover to me but I am set to nofailover. In no case I should be elected as a leader
|
||||
self.p.set_role('replica')
|
||||
self.ha.cluster = get_cluster_initialized_without_leader(failover=Failover(0, '', 'postgresql0', None))
|
||||
self.ha.patroni.nofailover = True
|
||||
self.assertEqual(self.ha.run_cycle(), 'following a different leader because I am not allowed to promote')
|
||||
|
||||
self.ha.patroni.nofailover = False
|
||||
|
||||
# failover to another member that is on an older timeline (only failover_limitation() is checked)
|
||||
with patch('patroni.ha.logger.info') as mock_info:
|
||||
self.ha.cluster = get_cluster_initialized_without_leader(failover=Failover(0, '', 'b', None))
|
||||
self.ha.cluster.members.append(Member(0, 'b', 28, {'api_url': 'http://127.0.0.1:8011/patroni'}))
|
||||
self.ha.fetch_node_status = get_node_status(timeline=1)
|
||||
self.assertEqual(self.ha.run_cycle(), 'following a different leader because i am not the healthiest node')
|
||||
mock_info.assert_called_with('%s: to %s, i am %s', 'manual failover', 'b', 'postgresql0')
|
||||
|
||||
# failover to another member lagging behind the cluster_lsn (only failover_limitation() is checked)
|
||||
with patch('patroni.ha.logger.info') as mock_info:
|
||||
self.ha.cluster.config.data.update({'maximum_lag_on_failover': 5})
|
||||
self.ha.fetch_node_status = get_node_status(wal_position=1)
|
||||
self.assertEqual(self.ha.run_cycle(), 'following a different leader because i am not the healthiest node')
|
||||
mock_info.assert_called_with('%s: to %s, i am %s', 'manual failover', 'b', 'postgresql0')
|
||||
|
||||
def test_manual_switchover_process_no_leader(self):
|
||||
self.p.is_primary = false
|
||||
self.p.set_role('replica')
|
||||
|
||||
# I was the leader, other members are healthy
|
||||
self.ha.fetch_node_status = get_node_status()
|
||||
self.ha.cluster = get_cluster_initialized_without_leader(failover=Failover(0, self.p.name, '', None))
|
||||
self.assertEqual(self.ha.run_cycle(), 'following a different leader because i am not the healthiest node')
|
||||
|
||||
# I was the leader, I am the only healthy member
|
||||
with patch('patroni.ha.logger.info') as mock_info:
|
||||
self.ha.fetch_node_status = get_node_status(reachable=False) # inaccessible, in_recovery
|
||||
self.assertEqual(self.ha.run_cycle(), 'promoted self to leader by acquiring session lock')
|
||||
self.assertEqual(mock_info.call_args_list[0][0], ('Member %s is %s', 'leader', 'not reachable'))
|
||||
self.assertEqual(mock_info.call_args_list[1][0], ('Member %s is %s', 'other', 'not reachable'))
|
||||
|
||||
def test_manual_failover_process_no_leader_in_synchronous_mode(self):
|
||||
self.ha.is_synchronous_mode = true
|
||||
self.p.is_primary = false
|
||||
self.ha.fetch_node_status = get_node_status(nofailover=True) # other nodes are not healthy
|
||||
|
||||
# switchover to a specific node, which name doesn't match our name (postgresql0)
|
||||
# manual failover when our name (postgresql0) isn't in the /sync key and the candidate node is not available
|
||||
self.ha.cluster = get_cluster_initialized_without_leader(failover=Failover(0, '', 'other', None),
|
||||
sync=('leader1', 'blabla'))
|
||||
self.assertEqual(self.ha.run_cycle(), 'following a different leader because i am not the healthiest node')
|
||||
|
||||
# manual failover when the candidate node isn't available but our name is in the /sync key
|
||||
# while other sync node is nofailover
|
||||
with patch('patroni.ha.logger.warning') as mock_warning:
|
||||
self.ha.cluster = get_cluster_initialized_without_leader(failover=Failover(0, '', 'other', None),
|
||||
sync=('leader1', 'postgresql0'))
|
||||
self.p.sync_handler.current_state = Mock(return_value=(CaseInsensitiveSet(), CaseInsensitiveSet()))
|
||||
self.ha.dcs.write_sync_state = Mock(return_value=SyncState.empty())
|
||||
self.assertEqual(self.ha.run_cycle(), 'promoted self to leader by acquiring session lock')
|
||||
self.assertEqual(mock_warning.call_args_list[0][0],
|
||||
('%s: member %s is %s', 'manual failover', 'other', 'not allowed to promote'))
|
||||
|
||||
# manual failover to our node (postgresql0),
|
||||
# which name is not in sync nodes list (some sync nodes are available)
|
||||
self.p.set_role('replica')
|
||||
self.ha.cluster = get_cluster_initialized_without_leader(failover=Failover(0, '', 'postgresql0', None),
|
||||
sync=('leader1', 'other'))
|
||||
self.p.sync_handler.current_state = Mock(return_value=(CaseInsensitiveSet(['leader1']),
|
||||
CaseInsensitiveSet(['leader1'])))
|
||||
self.assertEqual(self.ha.run_cycle(), 'promoted self to leader by acquiring session lock')
|
||||
|
||||
def test_manual_switchover_process_no_leader_in_synchronous_mode(self):
|
||||
self.ha.is_synchronous_mode = true
|
||||
self.p.is_primary = false
|
||||
|
||||
# to a specific node, which name doesn't match our name (postgresql0)
|
||||
self.ha.cluster = get_cluster_initialized_without_leader(failover=Failover(0, 'leader', 'other', None))
|
||||
self.assertEqual(self.ha.run_cycle(), 'following a different leader because i am not the healthiest node')
|
||||
|
||||
# switchover to our node (postgresql0), which name is not in sync nodes list
|
||||
# to our node (postgresql0), which name is not in sync nodes list
|
||||
self.ha.cluster = get_cluster_initialized_without_leader(failover=Failover(0, 'leader', 'postgresql0', None),
|
||||
sync=('leader1', 'blabla'))
|
||||
self.assertEqual(self.ha.run_cycle(), 'following a different leader because i am not the healthiest node')
|
||||
|
||||
# switchover from a specific leader, but our name (postgresql0) is not in the sync nodes list
|
||||
# without candidate, our name (postgresql0) is not in the sync nodes list
|
||||
self.ha.cluster = get_cluster_initialized_without_leader(failover=Failover(0, 'leader', '', None),
|
||||
sync=('leader', 'blabla'))
|
||||
self.assertEqual(self.ha.run_cycle(), 'following a different leader because i am not the healthiest node')
|
||||
@@ -800,45 +981,31 @@ class TestHa(PostgresInit):
|
||||
sync=('postgresql0'))
|
||||
self.ha.patroni.nofailover = True
|
||||
self.assertEqual(self.ha.run_cycle(), 'following a different leader because I am not allowed to promote')
|
||||
self.ha.patroni.nofailover = False
|
||||
|
||||
# manual failover when our name (postgresql0) isn't in the /sync key and the `other` node is not available
|
||||
self.ha.fetch_node_status = get_node_status(nofailover=True) # accessible, in_recovery
|
||||
self.ha.cluster = get_cluster_initialized_without_leader(failover=Failover(0, '', 'other', None),
|
||||
sync=('leader1', 'blabla'))
|
||||
self.assertEqual(self.ha.run_cycle(), 'following a different leader because i am not the healthiest node')
|
||||
|
||||
# manual failover when the `other` node isn't available but our name is in the /sync key
|
||||
self.ha.cluster = get_cluster_initialized_without_leader(failover=Failover(0, '', 'other', None),
|
||||
sync=('leader1', 'postgresql0'))
|
||||
self.p.sync_handler.current_state = Mock(return_value=(CaseInsensitiveSet(), CaseInsensitiveSet()))
|
||||
self.ha.dcs.write_sync_state = Mock(return_value=SyncState.empty())
|
||||
self.assertEqual(self.ha.run_cycle(), 'promoted self to leader by acquiring session lock')
|
||||
|
||||
# manual failover to our node (postgresql0),
|
||||
# which name is not in sync nodes list (the leader and all sync nodes are not available)
|
||||
self.p.set_role('replica')
|
||||
self.ha.cluster = get_cluster_initialized_without_leader(failover=Failover(0, '', 'postgresql0', None),
|
||||
sync=('leader1', 'other'))
|
||||
self.assertEqual(self.ha.run_cycle(), 'promoted self to leader by acquiring session lock')
|
||||
|
||||
# manual failover to our node (postgresql0),
|
||||
# which name is not in sync nodes list (some sync nodes are available)
|
||||
self.ha.cluster = get_cluster_initialized_without_leader(failover=Failover(0, '', 'postgresql0', None),
|
||||
sync=('leader1', 'other'))
|
||||
self.p.set_role('replica')
|
||||
self.p.sync_handler.current_state = Mock(return_value=(CaseInsensitiveSet(['leader1']),
|
||||
CaseInsensitiveSet(['leader1'])))
|
||||
self.assertEqual(self.ha.run_cycle(), 'promoted self to leader by acquiring session lock')
|
||||
|
||||
def test_manual_failover_process_no_leader_in_pause(self):
|
||||
self.ha.is_paused = true
|
||||
|
||||
# I am running as primary, cluster is unlocked, the candidate is allowed to promote
|
||||
# but we are in pause
|
||||
self.ha.cluster = get_cluster_initialized_without_leader(failover=Failover(0, '', 'other', None))
|
||||
self.assertEqual(self.ha.run_cycle(), 'PAUSE: continue to run as primary without lock')
|
||||
|
||||
def test_manual_switchover_process_no_leader_in_pause(self):
|
||||
self.ha.is_paused = true
|
||||
|
||||
# I am running as primary, cluster is unlocked, no candidate specified
|
||||
self.ha.cluster = get_cluster_initialized_without_leader(failover=Failover(0, 'leader', '', None))
|
||||
self.assertEqual(self.ha.run_cycle(), 'PAUSE: continue to run as primary without lock')
|
||||
self.ha.cluster = get_cluster_initialized_without_leader(failover=Failover(0, 'leader', 'blabla', None))
|
||||
self.assertEqual('PAUSE: acquired session lock as a leader', self.ha.run_cycle())
|
||||
|
||||
# the candidate is not running
|
||||
with patch('patroni.ha.logger.warning') as mock_warning:
|
||||
self.ha.cluster = get_cluster_initialized_without_leader(failover=Failover(0, 'leader', 'blabla', None))
|
||||
self.assertEqual('PAUSE: acquired session lock as a leader', self.ha.run_cycle())
|
||||
self.assertEqual(
|
||||
mock_warning.call_args_list[0][0],
|
||||
('%s: removing failover key because failover candidate is not running', 'switchover'))
|
||||
|
||||
# switchover to me, I am not leader
|
||||
self.p.is_primary = false
|
||||
self.p.set_role('replica')
|
||||
self.ha.cluster = get_cluster_initialized_without_leader(failover=Failover(0, 'leader', self.p.name, None))
|
||||
@@ -846,7 +1013,7 @@ class TestHa(PostgresInit):
|
||||
|
||||
def test_is_healthiest_node(self):
|
||||
self.ha.is_failsafe_mode = true
|
||||
self.p.is_primary = false
|
||||
self.ha.state_handler.is_primary = false
|
||||
self.ha.patroni.nofailover = False
|
||||
self.ha.fetch_node_status = get_node_status()
|
||||
self.ha.dcs._last_failsafe = {'foo': ''}
|
||||
@@ -1088,7 +1255,7 @@ class TestHa(PostgresInit):
|
||||
f = Failover(0, self.p.name, '', None)
|
||||
self.ha.cluster = get_cluster_initialized_with_leader(f)
|
||||
self.ha.fetch_node_status = get_node_status() # accessible, in_recovery
|
||||
self.assertEqual(self.ha.run_cycle(), 'manual failover: demoting myself')
|
||||
self.assertEqual(self.ha.run_cycle(), 'switchover: demoting myself')
|
||||
|
||||
@patch('patroni.ha.Ha.demote')
|
||||
def test_failover_immediately_on_zero_primary_start_timeout(self, demote):
|
||||
|
||||
Reference in New Issue
Block a user