mirror of
https://github.com/outbackdingo/patroni.git
synced 2026-01-28 10:20:05 +00:00
1290b30b84
Previously pg_ctl waited for a timeout and then happily trodded on considering PostgreSQL to be running. This caused PostgreSQL to show up in listings as running when it was actually not and caused a race condition that resulted in either a failover or a crash recovery or a crash recovery interrupted by failover and a missed rewind. This change adds a master_start_timeout parameter and introduces a new state for the main run_cycle loop: starting. When master_start_timeout is zero we will fail over as soon as there is a failover candidate. Otherwise PostgreSQL will be started, but once master_start_timeout expires we will stop and release leader lock if failover is possible. Once failover succeeds or fails (no leader and no one to take the role) we continue with normal processing. While we are waiting for the master timeout we handle manual failover requests. * Introduce timeout parameter to restart. When restart timeout is set master becomes eligible for failover after that timeout expires regardless of master_start_time. Immediate restart calls will wait for this timeout to pass, even when node is a standby.
59 lines
1.7 KiB
Python
59 lines
1.7 KiB
Python
import unittest
|
|
|
|
from mock import Mock, patch
|
|
from patroni.exceptions import PatroniException
|
|
from patroni.utils import Retry, RetryFailedError, polling_loop
|
|
|
|
|
|
class TestUtils(unittest.TestCase):
|
|
|
|
def test_polling_loop(self):
|
|
self.assertEquals(list(polling_loop(0.001, interval=0.001)), [0])
|
|
|
|
|
|
@patch('time.sleep', Mock())
|
|
class TestRetrySleeper(unittest.TestCase):
|
|
|
|
@staticmethod
|
|
def _fail(times=1):
|
|
scope = dict(times=0)
|
|
|
|
def inner():
|
|
if scope['times'] >= times:
|
|
pass
|
|
else:
|
|
scope['times'] += 1
|
|
raise PatroniException('Failed!')
|
|
return inner
|
|
|
|
def test_reset(self):
|
|
retry = Retry(delay=0, max_tries=2)
|
|
retry(self._fail())
|
|
self.assertEquals(retry._attempts, 1)
|
|
retry.reset()
|
|
self.assertEquals(retry._attempts, 0)
|
|
|
|
def test_too_many_tries(self):
|
|
retry = Retry(delay=0)
|
|
self.assertRaises(RetryFailedError, retry, self._fail(times=999))
|
|
self.assertEquals(retry._attempts, 1)
|
|
|
|
def test_maximum_delay(self):
|
|
retry = Retry(delay=10, max_tries=100)
|
|
retry(self._fail(times=10))
|
|
self.assertTrue(retry._cur_delay < 4000, retry._cur_delay)
|
|
# gevent's sleep function is picky about the type
|
|
self.assertEquals(type(retry._cur_delay), float)
|
|
|
|
def test_deadline(self):
|
|
retry = Retry(deadline=0.0001)
|
|
self.assertRaises(RetryFailedError, retry, self._fail(times=100))
|
|
|
|
def test_copy(self):
|
|
def _sleep(t):
|
|
pass
|
|
|
|
retry = Retry(sleep_func=_sleep)
|
|
rcopy = retry.copy()
|
|
self.assertTrue(rcopy.sleep_func is _sleep)
|