mirror of
https://github.com/outbackdingo/patroni.git
synced 2026-08-25 14:53:37 +00:00
Alexander KukushkinandGitHub
80fbe90056
It is safe to call pg_rewind on the replica only when pg_control on the primary contains information about the latest timeline. Postgres is usually doing immediate checkpoint right after promote and in most cases it works just fine. Unfortunately we regularly receive complaints that it takes to long (minutes) until the checkpoint is done and replicas can't perform rewind. At the same time doing the checkpoint manually immediately helped. So Patroni starts doing the same. When the promotion happened and postgres is not running in recovery, we explicitly issue the checkpoint. We are intentionally not using the AsyncExecutor here, because we want the HA loop continues doing its normal flow.
133 lines
6.4 KiB
Python
133 lines
6.4 KiB
Python
from mock import Mock, PropertyMock, patch
|
|
|
|
from patroni.postgresql import Postgresql
|
|
from patroni.postgresql.cancellable import CancellableSubprocess
|
|
from patroni.postgresql.rewind import Rewind
|
|
|
|
from . import BaseTestPostgresql, MockCursor, psycopg2_connect
|
|
|
|
|
|
class MockThread(object):
|
|
|
|
def __init__(self, target, args):
|
|
self._target = target
|
|
self._args = args
|
|
|
|
def start(self):
|
|
self._target(*self._args)
|
|
|
|
|
|
@patch('subprocess.call', Mock(return_value=0))
|
|
@patch('psycopg2.connect', psycopg2_connect)
|
|
class TestRewind(BaseTestPostgresql):
|
|
|
|
def setUp(self):
|
|
super(TestRewind, self).setUp()
|
|
self.r = Rewind(self.p)
|
|
|
|
def test_can_rewind(self):
|
|
with patch.object(Postgresql, 'controldata', Mock(return_value={'wal_log_hints setting': 'on'})):
|
|
self.assertTrue(self.r.can_rewind)
|
|
with patch('subprocess.call', Mock(return_value=1)):
|
|
self.assertFalse(self.r.can_rewind)
|
|
with patch('subprocess.call', side_effect=OSError):
|
|
self.assertFalse(self.r.can_rewind)
|
|
self.p.config._config['use_pg_rewind'] = False
|
|
self.assertFalse(self.r.can_rewind)
|
|
|
|
@patch.object(CancellableSubprocess, 'call')
|
|
def test_pg_rewind(self, mock_cancellable_subprocess_call):
|
|
r = {'user': '', 'host': '', 'port': '', 'database': '', 'password': ''}
|
|
mock_cancellable_subprocess_call.return_value = 0
|
|
self.assertTrue(self.r.pg_rewind(r))
|
|
mock_cancellable_subprocess_call.side_effect = OSError
|
|
self.assertFalse(self.r.pg_rewind(r))
|
|
|
|
@patch.object(Rewind, 'can_rewind', PropertyMock(return_value=True))
|
|
def test__get_local_timeline_lsn(self):
|
|
self.r.trigger_check_diverged_lsn()
|
|
with patch.object(Postgresql, 'controldata',
|
|
Mock(return_value={'Database cluster state': 'shut down in recovery',
|
|
'Minimum recovery ending location': '0/0',
|
|
"Min recovery ending loc's timeline": '0'})):
|
|
self.r.rewind_or_reinitialize_needed_and_possible(self.leader)
|
|
|
|
with patch.object(Postgresql, 'is_running', Mock(return_value=True)):
|
|
with patch.object(MockCursor, 'fetchone', Mock(side_effect=[(False, ), Exception])):
|
|
self.r.rewind_or_reinitialize_needed_and_possible(self.leader)
|
|
|
|
@patch.object(CancellableSubprocess, 'call', Mock(return_value=0))
|
|
@patch.object(Postgresql, 'checkpoint', side_effect=['', '1'],)
|
|
@patch.object(Postgresql, 'stop', Mock(return_value=False))
|
|
@patch.object(Postgresql, 'start', Mock())
|
|
def test_execute(self, mock_checkpoint):
|
|
self.r.execute(self.leader)
|
|
with patch.object(Rewind, 'pg_rewind', Mock(return_value=False)):
|
|
mock_checkpoint.side_effect = ['1', '', '', '']
|
|
self.r.execute(self.leader)
|
|
self.r.execute(self.leader)
|
|
with patch.object(Rewind, 'check_leader_is_not_in_recovery', Mock(return_value=False)):
|
|
self.r.execute(self.leader)
|
|
self.p.config._config['remove_data_directory_on_rewind_failure'] = False
|
|
self.r.trigger_check_diverged_lsn()
|
|
self.r.execute(self.leader)
|
|
|
|
self.leader.member.data.update(version='1.5.7', checkpoint_after_promote=False, role='master')
|
|
self.assertIsNone(self.r.execute(self.leader))
|
|
|
|
del self.leader.member.data['checkpoint_after_promote']
|
|
with patch.object(Rewind, 'check_leader_is_not_in_recovery', Mock(return_value=False)):
|
|
self.assertIsNone(self.r.execute(self.leader))
|
|
|
|
with patch.object(Postgresql, 'is_running', Mock(return_value=True)):
|
|
self.r.execute(self.leader)
|
|
|
|
@patch.object(Postgresql, 'start', Mock())
|
|
@patch.object(Rewind, 'can_rewind', PropertyMock(return_value=True))
|
|
@patch.object(Rewind, '_get_local_timeline_lsn', Mock(return_value=(2, '40159C1')))
|
|
@patch.object(Rewind, 'check_leader_is_not_in_recovery')
|
|
def test__check_timeline_and_lsn(self, mock_check_leader_is_not_in_recovery):
|
|
mock_check_leader_is_not_in_recovery.return_value = False
|
|
self.r.trigger_check_diverged_lsn()
|
|
self.assertFalse(self.r.rewind_or_reinitialize_needed_and_possible(self.leader))
|
|
self.leader = self.leader.member
|
|
self.assertFalse(self.r.rewind_or_reinitialize_needed_and_possible(self.leader))
|
|
mock_check_leader_is_not_in_recovery.return_value = True
|
|
self.assertFalse(self.r.rewind_or_reinitialize_needed_and_possible(self.leader))
|
|
self.r.trigger_check_diverged_lsn()
|
|
with patch('psycopg2.connect', Mock(side_effect=Exception)):
|
|
self.assertFalse(self.r.rewind_or_reinitialize_needed_and_possible(self.leader))
|
|
self.r.trigger_check_diverged_lsn()
|
|
with patch.object(MockCursor, 'fetchone', Mock(side_effect=[('', 2, '0/0'), ('', b'3\t0/40159C0\tn\n')])):
|
|
self.assertFalse(self.r.rewind_or_reinitialize_needed_and_possible(self.leader))
|
|
self.r.trigger_check_diverged_lsn()
|
|
with patch.object(MockCursor, 'fetchone', Mock(return_value=('', 1, '0/0'))):
|
|
with patch.object(Rewind, '_get_local_timeline_lsn', Mock(return_value=(1, '0/0'))):
|
|
self.assertFalse(self.r.rewind_or_reinitialize_needed_and_possible(self.leader))
|
|
self.r.trigger_check_diverged_lsn()
|
|
self.assertTrue(self.r.rewind_or_reinitialize_needed_and_possible(self.leader))
|
|
|
|
@patch.object(MockCursor, 'fetchone', Mock(side_effect=[(True,), Exception]))
|
|
def test_check_leader_is_not_in_recovery(self):
|
|
self.r.check_leader_is_not_in_recovery()
|
|
self.r.check_leader_is_not_in_recovery()
|
|
|
|
@patch('patroni.postgresql.rewind.Thread', MockThread)
|
|
@patch.object(Postgresql, 'controldata')
|
|
@patch.object(Postgresql, 'checkpoint')
|
|
def test_ensure_checkpoint_after_promote(self, mock_checkpoint, mock_controldata):
|
|
mock_checkpoint.return_value = None
|
|
self.r.ensure_checkpoint_after_promote()
|
|
self.r.ensure_checkpoint_after_promote()
|
|
|
|
self.r.reset_state()
|
|
mock_controldata.return_value = {"Latest checkpoint's TimeLineID": 1}
|
|
mock_checkpoint.side_effect = Exception
|
|
self.r.ensure_checkpoint_after_promote()
|
|
self.r.ensure_checkpoint_after_promote()
|
|
|
|
self.r.reset_state()
|
|
mock_controldata.side_effect = TypeError
|
|
self.r.ensure_checkpoint_after_promote()
|
|
self.r.ensure_checkpoint_after_promote()
|