class Patroni(object):
PATRONI_CONFIG_VARIABLE = 'PATRONI_CONFIGURATION'
def __init__(self, config):
self.nap_time = config['loop_wait']
self.tags = {tag: value for tag, value in config.get('tags', {}).items()
if tag not in ('clonefrom', 'nofailover', 'noloadbalance') or value}
self.postgresql = Postgresql(config['postgresql'])
self.dcs = self.get_dcs(self.postgresql.name, config)
self.version = __version__
self.api = RestApiServer(self, config['restapi'])
self.ha = Ha(self)
self.next_run = time.time()
@property
def noloadbalance(self):
return self.tags.get('noloadbalance', False)
@property
def nofailover(self):
return self.tags.get('nofailover', False)
@property
def replicatefrom(self):
return self.tags.get('replicatefrom')
@staticmethod
def get_dcs(name, config):
if 'etcd' in config:
from patroni.etcd import Etcd
return Etcd(name, config['etcd'])
if 'zookeeper' in config:
from patroni.zookeeper import ZooKeeper
return ZooKeeper(name, config['zookeeper'])
if 'consul' in config:
from patroni.consul import Consul
return Consul(name, config['consul'])
raise PatroniException('Can not find suitable configuration of distributed configuration store')
def schedule_next_run(self):
self.next_run += self.nap_time
current_time = time.time()
nap_time = self.next_run - current_time
if nap_time <= 0:
self.next_run = current_time
elif self.dcs.watch(nap_time):
self.next_run = time.time()
def run(self):
self.api.start()
self.next_run = time.time()
while True:
logger.info(self.ha.run_cycle())
reap_children()
self.schedule_next_run()
class Patroni(object):
PATRONI_CONFIG_VARIABLE = 'PATRONI_CONFIGURATION'
def __init__(self, config):
self.nap_time = config['loop_wait']
self.tags = {
tag: value
for tag, value in config.get('tags', {}).items()
if tag not in ('clonefrom', 'nofailover', 'noloadbalance') or value
}
self.postgresql = Postgresql(config['postgresql'])
self.dcs = get_dcs(self.postgresql.name, config)
self.version = __version__
self.api = RestApiServer(self, config['restapi'])
self.ha = Ha(self)
self.next_run = time.time()
@property
def noloadbalance(self):
return self.tags.get('noloadbalance', False)
@property
def nofailover(self):
return self.tags.get('nofailover', False)
@property
def replicatefrom(self):
return self.tags.get('replicatefrom')
def schedule_next_run(self):
self.next_run += self.nap_time
current_time = time.time()
nap_time = self.next_run - current_time
if nap_time <= 0:
self.next_run = current_time
elif self.dcs.watch(nap_time):
self.next_run = time.time()
def run(self):
self.api.start()
self.next_run = time.time()
while True:
logger.info(self.ha.run_cycle())
reap_children()
self.schedule_next_run()
class Patroni(object):
PATRONI_CONFIG_VARIABLE = 'PATRONI_CONFIGURATION'
def __init__(self, config):
self.nap_time = config['loop_wait']
self.tags = {tag: value for tag, value in config.get('tags', {}).items()
if tag not in ('clonefrom', 'nofailover', 'noloadbalance') or value}
self.postgresql = Postgresql(config['postgresql'])
self.dcs = get_dcs(self.postgresql.name, config)
self.version = __version__
self.api = RestApiServer(self, config['restapi'])
self.ha = Ha(self)
self.next_run = time.time()
@property
def noloadbalance(self):
return self.tags.get('noloadbalance', False)
@property
def nofailover(self):
return self.tags.get('nofailover', False)
@property
def replicatefrom(self):
return self.tags.get('replicatefrom')
def schedule_next_run(self):
self.next_run += self.nap_time
current_time = time.time()
nap_time = self.next_run - current_time
if nap_time <= 0:
self.next_run = current_time
elif self.dcs.watch(nap_time):
self.next_run = time.time()
def run(self):
self.api.start()
self.next_run = time.time()
while True:
logger.info(self.ha.run_cycle())
reap_children()
self.schedule_next_run()
class Patroni:
def __init__(self, config):
self.nap_time = config['loop_wait']
self.tags = config.get('tags', dict())
self.postgresql = Postgresql(config['postgresql'])
self.dcs = self.get_dcs(self.postgresql.name, config)
self.api = RestApiServer(self, config['restapi'])
self.ha = Ha(self)
self.next_run = time.time()
@property
def nofailover(self):
return self.tags.get('nofailover', False)
@staticmethod
def get_dcs(name, config):
if 'etcd' in config:
return Etcd(name, config['etcd'])
if 'zookeeper' in config:
return ZooKeeper(name, config['zookeeper'])
raise Exception(
'Can not find suitable configuration of distributed configuration store'
)
def schedule_next_run(self):
self.next_run += self.nap_time
current_time = time.time()
nap_time = self.next_run - current_time
if nap_time <= 0:
self.next_run = current_time
elif self.dcs.watch(nap_time):
self.next_run = time.time()
def run(self):
self.api.start()
self.next_run = time.time()
while True:
logger.info(self.ha.run_cycle())
reap_children()
self.schedule_next_run()
class Patroni:
def __init__(self, config):
self.nap_time = config["loop_wait"]
self.tags = config.get("tags", dict())
self.postgresql = Postgresql(config["postgresql"])
self.dcs = self.get_dcs(self.postgresql.name, config)
self.api = RestApiServer(self, config["restapi"])
self.ha = Ha(self)
self.next_run = time.time()
@property
def nofailover(self):
return self.tags.get("nofailover", False)
@staticmethod
def get_dcs(name, config):
if "etcd" in config:
return Etcd(name, config["etcd"])
if "zookeeper" in config:
return ZooKeeper(name, config["zookeeper"])
raise Exception("Can not find suitable configuration of distributed configuration store")
def schedule_next_run(self):
self.next_run += self.nap_time
current_time = time.time()
nap_time = self.next_run - current_time
if nap_time <= 0:
self.next_run = current_time
elif self.dcs.watch(nap_time):
self.next_run = time.time()
def run(self):
self.api.start()
self.next_run = time.time()
while True:
logger.info(self.ha.run_cycle())
reap_children()
self.schedule_next_run()
class Patroni:
def __init__(self, config):
self.nap_time = config['loop_wait']
self.postgresql = Postgresql(config['postgresql'])
self.dcs = self.get_dcs(self.postgresql.name, config)
host, port = config['restapi']['listen'].split(':')
self.api = RestApiServer(self, config['restapi'])
self.ha = Ha(self)
self.next_run = time.time()
@staticmethod
def get_dcs(name, config):
if 'etcd' in config:
return Etcd(name, config['etcd'])
if 'zookeeper' in config:
return ZooKeeper(name, config['zookeeper'])
raise Exception('Can not find sutable configuration of distributed configuration store')
def schedule_next_run(self):
self.next_run += self.nap_time
current_time = time.time()
nap_time = self.next_run - current_time
if nap_time <= 0:
self.next_run = current_time
elif self.dcs.watch(nap_time):
self.next_run = time.time()
def run(self):
self.api.start()
self.next_run = time.time()
while True:
logger.info(self.ha.run_cycle())
reap_children()
self.schedule_next_run()
class Patroni(object):
PATRONI_CONFIG_VARIABLE = 'PATRONI_CONFIGURATION'
def __init__(self, config):
self.nap_time = config['loop_wait']
self.tags = {
tag: value
for tag, value in config.get('tags', {}).items()
if tag not in ('clonefrom', 'nofailover', 'noloadbalance') or value
}
self.postgresql = Postgresql(config['postgresql'])
self.dcs = self.get_dcs(self.postgresql.name, config)
self.version = __version__
self.api = RestApiServer(self, config['restapi'])
self.ha = Ha(self)
self.next_run = time.time()
@property
def noloadbalance(self):
return self.tags.get('noloadbalance', False)
@property
def nofailover(self):
return self.tags.get('nofailover', False)
@property
def replicatefrom(self):
return self.tags.get('replicatefrom')
@staticmethod
def get_dcs(name, config):
if 'etcd' in config:
from patroni.etcd import Etcd
return Etcd(name, config['etcd'])
if 'zookeeper' in config:
from patroni.zookeeper import ZooKeeper
return ZooKeeper(name, config['zookeeper'])
if 'consul' in config:
from patroni.consul import Consul
return Consul(name, config['consul'])
raise PatroniException(
'Can not find suitable configuration of distributed configuration store'
)
def schedule_next_run(self):
self.next_run += self.nap_time
current_time = time.time()
nap_time = self.next_run - current_time
if nap_time <= 0:
self.next_run = current_time
elif self.dcs.watch(nap_time):
self.next_run = time.time()
def run(self):
self.api.start()
self.next_run = time.time()
while True:
logger.info(self.ha.run_cycle())
reap_children()
self.schedule_next_run()
class Patroni(object):
def __init__(self):
from patroni.api import RestApiServer
from patroni.config import Config
from patroni.dcs import get_dcs
from patroni.ha import Ha
from patroni.postgresql import Postgresql
from patroni.version import __version__
from patroni.watchdog import Watchdog
self.setup_signal_handlers()
self.version = __version__
self.config = Config()
self.dcs = get_dcs(self.config)
self.watchdog = Watchdog(self.config)
self.load_dynamic_configuration()
self.postgresql = Postgresql(self.config['postgresql'])
self.api = RestApiServer(self, self.config['restapi'])
self.ha = Ha(self)
self.tags = self.get_tags()
self.next_run = time.time()
self.scheduled_restart = {}
def load_dynamic_configuration(self):
from patroni.exceptions import DCSError
while True:
try:
cluster = self.dcs.get_cluster()
if cluster and cluster.config and cluster.config.data:
if self.config.set_dynamic_configuration(cluster.config):
self.dcs.reload_config(self.config)
self.watchdog.reload_config(self.config)
elif not self.config.dynamic_configuration and 'bootstrap' in self.config:
if self.config.set_dynamic_configuration(
self.config['bootstrap']['dcs']):
self.dcs.reload_config(self.config)
break
except DCSError:
logger.warning('Can not get cluster from dcs')
def get_tags(self):
return {
tag: value
for tag, value in self.config.get('tags', {}).items()
if tag not in ('clonefrom', 'nofailover', 'noloadbalance',
'nosync') or value
}
@property
def nofailover(self):
return bool(self.tags.get('nofailover', False))
@property
def nosync(self):
return bool(self.tags.get('nosync', False))
def reload_config(self):
try:
self.tags = self.get_tags()
self.dcs.reload_config(self.config)
self.watchdog.reload_config(self.config)
self.api.reload_config(self.config['restapi'])
self.postgresql.reload_config(self.config['postgresql'])
except Exception:
logger.exception('Failed to reload config_file=%s',
self.config.config_file)
@property
def replicatefrom(self):
return self.tags.get('replicatefrom')
def sighup_handler(self, *args):
self._received_sighup = True
def sigterm_handler(self, *args):
if not self._received_sigterm:
self._received_sigterm = True
sys.exit()
@property
def noloadbalance(self):
return bool(self.tags.get('noloadbalance', False))
def schedule_next_run(self):
self.next_run += self.dcs.loop_wait
current_time = time.time()
nap_time = self.next_run - current_time
if nap_time <= 0:
self.next_run = current_time
# Release the GIL so we don't starve anyone waiting on async_executor lock
time.sleep(0.001)
# Warn user that Patroni is not keeping up
logger.warning("Loop time exceeded, rescheduling immediately.")
elif self.ha.watch(nap_time):
self.next_run = time.time()
def run(self):
self.api.start()
self.next_run = time.time()
while not self._received_sigterm:
if self._received_sighup:
self._received_sighup = False
if self.config.reload_local_configuration():
self.reload_config()
logger.info(self.ha.run_cycle())
if self.dcs.cluster and self.dcs.cluster.config and self.dcs.cluster.config.data \
and self.config.set_dynamic_configuration(self.dcs.cluster.config):
self.reload_config()
if self.postgresql.role != 'uninitialized':
self.config.save_cache()
self.schedule_next_run()
def setup_signal_handlers(self):
self._received_sighup = False
self._received_sigterm = False
signal.signal(signal.SIGHUP, self.sighup_handler)
signal.signal(signal.SIGTERM, self.sigterm_handler)
def shutdown(self):
self.api.shutdown()
self.ha.shutdown()
class Patroni:
def __init__(self, config):
self.nap_time = config['loop_wait']
self.postgresql = Postgresql(config['postgresql'])
self.ha = Ha(self.postgresql, self.get_dcs(self.postgresql.name, config))
host, port = config['restapi']['listen'].split(':')
self.api = RestApiServer(self, config['restapi'])
self.next_run = time.time()
self.shutdown_member_ttl = 300
@staticmethod
def get_dcs(name, config):
if 'etcd' in config:
return Etcd(name, config['etcd'])
if 'zookeeper' in config:
return ZooKeeper(name, config['zookeeper'])
raise Exception('Can not find sutable configuration of distributed configuration store')
def touch_member(self, ttl=None):
connection_string = self.postgresql.connection_string + '?application_name=' + self.api.connection_string
if self.ha.cluster:
for m in self.ha.cluster.members:
# Do not update member TTL when it is far from being expired
if m.name == self.postgresql.name and m.real_ttl() > self.shutdown_member_ttl:
return True
return self.ha.dcs.touch_member(connection_string, ttl)
def cleanup_on_failed_initialization(self):
""" cleanup the DCS if initialization was not successfull """
logger.info("removing initialize key after failed attempt to initialize the cluster")
self.ha.dcs.cancel_initialization()
self.touch_member(self.shutdown_member_ttl)
self.postgresql.stop()
self.postgresql.move_data_directory()
def initialize(self):
# wait for etcd to be available
while not self.touch_member():
logger.info('waiting on DCS')
sleep(5)
# is data directory empty?
if self.postgresql.data_directory_empty():
while True:
try:
cluster = self.ha.dcs.get_cluster()
if not cluster.is_unlocked(): # the leader already exists
if not cluster.initialize:
self.ha.dcs.initialize()
self.postgresql.bootstrap(cluster.leader)
break
# racing to initialize
elif not cluster.initialize and self.ha.dcs.initialize():
try:
self.postgresql.bootstrap()
except:
# bail out and clean the initialize flag.
self.cleanup_on_failed_initialization()
raise
self.ha.dcs.take_leader()
break
except DCSError:
logger.info('waiting on DCS')
sleep(5)
elif self.postgresql.is_running():
self.postgresql.load_replication_slots()
def schedule_next_run(self):
if self.postgresql.is_promoted:
self.next_run = time.time()
self.next_run += self.nap_time
current_time = time.time()
nap_time = self.next_run - current_time
if nap_time <= 0:
self.next_run = current_time
else:
self.ha.dcs.watch(nap_time)
def run(self):
self.api.start()
self.next_run = time.time()
while True:
self.touch_member()
logger.info(self.ha.run_cycle())
try:
if self.ha.state_handler.is_leader():
self.ha.cluster and self.ha.state_handler.create_replication_slots(self.ha.cluster)
else:
self.ha.state_handler.drop_replication_slots()
except:
logger.exception('Exception when changing replication slots')
reap_children()
self.schedule_next_run()
class Patroni(AbstractPatroniDaemon):
def __init__(self, config):
from patroni.api import RestApiServer
from patroni.dcs import get_dcs
from patroni.ha import Ha
from patroni.postgresql import Postgresql
from patroni.request import PatroniRequest
from patroni.watchdog import Watchdog
super(Patroni, self).__init__(config)
self.version = __version__
self.dcs = get_dcs(self.config)
self.watchdog = Watchdog(self.config)
self.load_dynamic_configuration()
self.postgresql = Postgresql(self.config['postgresql'])
self.api = RestApiServer(self, self.config['restapi'])
self.request = PatroniRequest(self.config, True)
self.ha = Ha(self)
self.tags = self.get_tags()
self.next_run = time.time()
self.scheduled_restart = {}
def load_dynamic_configuration(self):
from patroni.exceptions import DCSError
while True:
try:
cluster = self.dcs.get_cluster()
if cluster and cluster.config and cluster.config.data:
if self.config.set_dynamic_configuration(cluster.config):
self.dcs.reload_config(self.config)
self.watchdog.reload_config(self.config)
elif not self.config.dynamic_configuration and 'bootstrap' in self.config:
if self.config.set_dynamic_configuration(
self.config['bootstrap']['dcs']):
self.dcs.reload_config(self.config)
break
except DCSError:
logger.warning('Can not get cluster from dcs')
time.sleep(5)
def get_tags(self):
return {
tag: value
for tag, value in self.config.get('tags', {}).items()
if tag not in ('clonefrom', 'nofailover', 'noloadbalance',
'nosync') or value
}
@property
def nofailover(self):
return bool(self.tags.get('nofailover', False))
@property
def nosync(self):
return bool(self.tags.get('nosync', False))
def reload_config(self, sighup=False, local=False):
try:
super(Patroni, self).reload_config(sighup, local)
if local:
self.tags = self.get_tags()
self.request.reload_config(self.config)
self.api.reload_config(self.config['restapi'])
self.watchdog.reload_config(self.config)
self.postgresql.reload_config(self.config['postgresql'], sighup)
self.dcs.reload_config(self.config)
except Exception:
logger.exception('Failed to reload config_file=%s',
self.config.config_file)
@property
def replicatefrom(self):
return self.tags.get('replicatefrom')
@property
def noloadbalance(self):
return bool(self.tags.get('noloadbalance', False))
def schedule_next_run(self):
self.next_run += self.dcs.loop_wait
current_time = time.time()
nap_time = self.next_run - current_time
if nap_time <= 0:
self.next_run = current_time
# Release the GIL so we don't starve anyone waiting on async_executor lock
time.sleep(0.001)
# Warn user that Patroni is not keeping up
logger.warning("Loop time exceeded, rescheduling immediately.")
elif self.ha.watch(nap_time):
self.next_run = time.time()
def run(self):
self.api.start()
self.next_run = time.time()
super(Patroni, self).run()
def _run_cycle(self):
logger.info(self.ha.run_cycle())
if self.dcs.cluster and self.dcs.cluster.config and self.dcs.cluster.config.data \
and self.config.set_dynamic_configuration(self.dcs.cluster.config):
self.reload_config()
if self.postgresql.role != 'uninitialized':
self.config.save_cache()
self.schedule_next_run()
def _shutdown(self):
try:
self.api.shutdown()
except Exception:
logger.exception('Exception during RestApi.shutdown')
try:
self.ha.shutdown()
except Exception:
logger.exception('Exception during Ha.shutdown')
class Patroni(object):
def __init__(self):
self.version = __version__
self.config = Config()
self.dcs = get_dcs(self.config)
self.load_dynamic_configuration()
self.postgresql = Postgresql(self.config['postgresql'])
self.api = RestApiServer(self, self.config['restapi'])
self.ha = Ha(self)
self.tags = self.get_tags()
self.nap_time = self.config['loop_wait']
self.next_run = time.time()
self._reload_config_scheduled = False
self._received_sighup = False
self._received_sigterm = False
def load_dynamic_configuration(self):
while True:
try:
cluster = self.dcs.get_cluster()
if cluster and cluster.config:
self.config.set_dynamic_configuration(cluster.config)
elif not self.config.dynamic_configuration and 'bootstrap' in self.config:
self.config.set_dynamic_configuration(
self.config['bootstrap']['dcs'])
break
except DCSError:
logger.warning('Can not get cluster from dcs')
def get_tags(self):
return {
tag: value
for tag, value in self.config.get('tags', {}).items()
if tag not in ('clonefrom', 'nofailover', 'noloadbalance') or value
}
def reload_config(self):
try:
self.tags = self.get_tags()
self.nap_time = self.config['loop_wait']
self.dcs.set_ttl(self.config.get('ttl') or 30)
self.dcs.set_retry_timeout(
self.config.get('retry_timeout') or self.nap_time)
self.api.reload_config(self.config['restapi'])
self.postgresql.reload_config(self.config['postgresql'])
except Exception:
logger.exception('Failed to reload config_file=%s',
self.config.config_file)
def sighup_handler(self, *args):
self._received_sighup = True
def sigterm_handler(self, *args):
if not self._received_sigterm:
self._received_sigterm = True
sys.exit()
@property
def noloadbalance(self):
return self.tags.get('noloadbalance', False)
@property
def nofailover(self):
return self.tags.get('nofailover', False)
@property
def replicatefrom(self):
return self.tags.get('replicatefrom')
def schedule_next_run(self):
self.next_run += self.nap_time
current_time = time.time()
nap_time = self.next_run - current_time
if nap_time <= 0:
self.next_run = current_time
elif self.dcs.watch(nap_time):
self.next_run = time.time()
def run(self):
self.api.start()
self.next_run = time.time()
while not self._received_sigterm:
if self._received_sighup:
self._received_sighup = False
if self.config.reload_local_configuration():
self.reload_config()
logger.info(self.ha.run_cycle())
cluster = self.dcs.cluster
if cluster and cluster.config and self.config.set_dynamic_configuration(
cluster.config):
self.reload_config()
if not self.postgresql.data_directory_empty():
self.config.save_cache()
reap_children()
self.schedule_next_run()
def setup_signal_handlers(self):
signal.signal(signal.SIGHUP, self.sighup_handler)
signal.signal(signal.SIGTERM, self.sigterm_handler)
signal.signal(signal.SIGCHLD, sigchld_handler)
class Patroni(object):
def __init__(self):
from patroni.api import RestApiServer
from patroni.config import Config
from patroni.dcs import get_dcs
from patroni.ha import Ha
from patroni.postgresql import Postgresql
from patroni.version import __version__
self.setup_signal_handlers()
self.version = __version__
self.config = Config()
self.dcs = get_dcs(self.config)
self.load_dynamic_configuration()
self.postgresql = Postgresql(self.config['postgresql'])
self.api = RestApiServer(self, self.config['restapi'])
self.ha = Ha(self)
self.tags = self.get_tags()
self.next_run = time.time()
self.scheduled_restart = {}
def load_dynamic_configuration(self):
from patroni.exceptions import DCSError
while True:
try:
cluster = self.dcs.get_cluster()
if cluster and cluster.config:
if self.config.set_dynamic_configuration(cluster.config):
self.dcs.reload_config(self.config)
elif not self.config.dynamic_configuration and 'bootstrap' in self.config:
if self.config.set_dynamic_configuration(self.config['bootstrap']['dcs']):
self.dcs.reload_config(self.config)
break
except DCSError:
logger.warning('Can not get cluster from dcs')
def get_tags(self):
return {tag: value for tag, value in self.config.get('tags', {}).items()
if tag not in ('clonefrom', 'nofailover', 'noloadbalance', 'nosync') or value}
@property
def nofailover(self):
return bool(self.tags.get('nofailover', False))
@property
def nosync(self):
return bool(self.tags.get('nosync', False))
def reload_config(self):
try:
self.tags = self.get_tags()
self.dcs.reload_config(self.config)
self.api.reload_config(self.config['restapi'])
self.postgresql.reload_config(self.config['postgresql'])
except Exception:
logger.exception('Failed to reload config_file=%s', self.config.config_file)
@property
def replicatefrom(self):
return self.tags.get('replicatefrom')
def sighup_handler(self, *args):
self._received_sighup = True
def sigterm_handler(self, *args):
if not self._received_sigterm:
self._received_sigterm = True
sys.exit()
@property
def noloadbalance(self):
return bool(self.tags.get('noloadbalance', False))
def schedule_next_run(self):
self.next_run += self.dcs.loop_wait
current_time = time.time()
nap_time = self.next_run - current_time
if nap_time <= 0:
self.next_run = current_time
# Release the GIL so we don't starve anyone waiting on async_executor lock
time.sleep(0.001)
# Warn user that Patroni is not keeping up
logger.warning("Loop time exceeded, rescheduling immediately.")
elif self.ha.watch(nap_time):
self.next_run = time.time()
def run(self):
self.api.start()
self.next_run = time.time()
while not self._received_sigterm:
if self._received_sighup:
self._received_sighup = False
if self.config.reload_local_configuration():
self.reload_config()
logger.info(self.ha.run_cycle())
cluster = self.dcs.cluster
if cluster and cluster.config and self.config.set_dynamic_configuration(cluster.config):
self.reload_config()
if not self.postgresql.data_directory_empty():
self.config.save_cache()
self.schedule_next_run()
def setup_signal_handlers(self):
self._received_sighup = False
self._received_sigterm = False
signal.signal(signal.SIGHUP, self.sighup_handler)
signal.signal(signal.SIGTERM, self.sigterm_handler)
class Patroni(object):
def __init__(self):
self.setup_signal_handlers()
self.version = __version__
self.config = Config()
self.dcs = get_dcs(self.config)
self.load_dynamic_configuration()
self.postgresql = Postgresql(self.config['postgresql'])
self.api = RestApiServer(self, self.config['restapi'])
self.ha = Ha(self)
self.tags = self.get_tags()
self.next_run = time.time()
self.scheduled_restart = {}
def load_dynamic_configuration(self):
while True:
try:
cluster = self.dcs.get_cluster()
if cluster and cluster.config:
self.config.set_dynamic_configuration(cluster.config)
elif not self.config.dynamic_configuration and 'bootstrap' in self.config:
self.config.set_dynamic_configuration(self.config['bootstrap']['dcs'])
break
except DCSError:
logger.warning('Can not get cluster from dcs')
def get_tags(self):
return {tag: value for tag, value in self.config.get('tags', {}).items()
if tag not in ('clonefrom', 'nofailover', 'noloadbalance') or value}
@property
def nofailover(self):
return self.tags.get('nofailover', False)
def reload_config(self):
try:
self.tags = self.get_tags()
self.dcs.reload_config(self.config)
self.api.reload_config(self.config['restapi'])
self.postgresql.reload_config(self.config['postgresql'])
except Exception:
logger.exception('Failed to reload config_file=%s', self.config.config_file)
@property
def replicatefrom(self):
return self.tags.get('replicatefrom')
def sighup_handler(self, *args):
self._received_sighup = True
def sigterm_handler(self, *args):
if not self._received_sigterm:
self._received_sigterm = True
sys.exit()
@property
def noloadbalance(self):
return self.tags.get('noloadbalance', False)
def schedule_next_run(self):
self.next_run += self.dcs.loop_wait
current_time = time.time()
nap_time = self.next_run - current_time
if nap_time <= 0:
self.next_run = current_time
elif self.dcs.watch(nap_time):
self.next_run = time.time()
def run(self):
self.api.start()
self.next_run = time.time()
while not self._received_sigterm:
if self._received_sighup:
self._received_sighup = False
if self.config.reload_local_configuration():
self.reload_config()
logger.info(self.ha.run_cycle())
cluster = self.dcs.cluster
if cluster and cluster.config and self.config.set_dynamic_configuration(cluster.config):
self.reload_config()
if not self.postgresql.data_directory_empty():
self.config.save_cache()
reap_children()
self.schedule_next_run()
def setup_signal_handlers(self):
self._received_sighup = False
self._received_sigterm = False
signal.signal(signal.SIGHUP, self.sighup_handler)
signal.signal(signal.SIGTERM, self.sigterm_handler)
signal.signal(signal.SIGCHLD, sigchld_handler)
class Patroni(object):
def __init__(self, conf):
from patroni.api import RestApiServer
from patroni.dcs import get_dcs
from patroni.ha import Ha
from patroni.log import PatroniLogger
from patroni.postgresql import Postgresql
from patroni.request import PatroniRequest
from patroni.watchdog import Watchdog
self.setup_signal_handlers()
self.version = __version__
self.logger = PatroniLogger()
self.config = conf
self.logger.reload_config(self.config.get('log', {}))
self.dcs = get_dcs(self.config)
self.watchdog = Watchdog(self.config)
self.load_dynamic_configuration()
self.postgresql = Postgresql(self.config['postgresql'])
self.api = RestApiServer(self, self.config['restapi'])
self.request = PatroniRequest(self.config, True)
self.ha = Ha(self)
self.tags = self.get_tags()
self.next_run = time.time()
self.scheduled_restart = {}
def load_dynamic_configuration(self):
from patroni.exceptions import DCSError
while True:
try:
cluster = self.dcs.get_cluster()
#TODO: 动态参数 cluster.config 有哪些？如何设置？
if cluster and cluster.config and cluster.config.data:
if self.config.set_dynamic_configuration(cluster.config):
self.dcs.reload_config(self.config)
self.watchdog.reload_config(self.config)
elif not self.config.dynamic_configuration and 'bootstrap' in self.config:
if self.config.set_dynamic_configuration(
self.config['bootstrap']['dcs']):
self.dcs.reload_config(self.config)
break
except DCSError:
logger.warning('Can not get cluster from dcs')
time.sleep(5)
def get_tags(self):
return {
tag: value
for tag, value in self.config.get('tags', {}).items()
if tag not in ('clonefrom', 'nofailover', 'noloadbalance',
'nosync') or value
}
@property
def nofailover(self):
return bool(self.tags.get('nofailover', False))
@property
def nosync(self):
return bool(self.tags.get('nosync', False))
def reload_config(self, sighup=False):
try:
self.tags = self.get_tags()
self.logger.reload_config(self.config.get('log', {}))
self.watchdog.reload_config(self.config)
if sighup:
self.request.reload_config(self.config)
self.api.reload_config(self.config['restapi'])
self.postgresql.reload_config(self.config['postgresql'], sighup)
self.dcs.reload_config(self.config)
except Exception:
logger.exception('Failed to reload config_file=%s',
self.config.config_file)
@property
def replicatefrom(self):
return self.tags.get('replicatefrom')
def sighup_handler(self, *args):
self._received_sighup = True
def sigterm_handler(self, *args):
with self._sigterm_lock:
if not self._received_sigterm:
self._received_sigterm = True
sys.exit()
@property
def noloadbalance(self):
return bool(self.tags.get('noloadbalance', False))
def schedule_next_run(self):
self.next_run += self.dcs.loop_wait
current_time = time.time()
nap_time = self.next_run - current_time
if nap_time <= 0:
self.next_run = current_time
# Release the GIL so we don't starve anyone waiting on async_executor lock
time.sleep(0.001)
# Warn user that Patroni is not keeping up
logger.warning("Loop time exceeded, rescheduling immediately.")
elif self.ha.watch(nap_time):
self.next_run = time.time()
@property
def received_sigterm(self):
with self._sigterm_lock:
return self._received_sigterm
def run(self):
# SGS: 启动API
self.api.start()
# SGS: 启动日志记录
self.logger.start()
self.next_run = time.time()
while not self.received_sigterm:
# SGS: 是否收到SIGHUP信号 如何触发这个信息，直接用kill命令下发？
if self._received_sighup:
self._received_sighup = False
if self.config.reload_local_configuration():
self.reload_config(True)
else:
self.postgresql.config.reload_config(
self.config['postgresql'], True)
# SGS: 定时检查本patroni关联的member的状态并做响应处理，具体见 run_cycle 函数里的注释
logger.info(self.ha.run_cycle())
if self.dcs.cluster and self.dcs.cluster.config and self.dcs.cluster.config.data \
and self.config.set_dynamic_configuration(self.dcs.cluster.config):
self.reload_config()
if self.postgresql.role != 'uninitialized':
self.config.save_cache()
self.schedule_next_run()
def setup_signal_handlers(self):
from threading import Lock
self._received_sighup = False
self._sigterm_lock = Lock()
self._received_sigterm = False
if os.name != 'nt':
signal.signal(signal.SIGHUP, self.sighup_handler)
signal.signal(signal.SIGTERM, self.sigterm_handler)
def shutdown(self):
with self._sigterm_lock:
self._received_sigterm = True
try:
self.api.shutdown()
except Exception:
logger.exception('Exception during RestApi.shutdown')
try:
self.ha.shutdown()
except Exception:
logger.exception('Exception during Ha.shutdown')
self.logger.shutdown()