def start(self):
"""Start the connection."""
with self.lock:
if self.thread is not None:
return False
if not self.idl.has_ever_connected():
idlutils.wait_for_change(self.idl, self.timeout)
try:
self.idl.post_connect()
except AttributeError:
# An ovs.db.Idl class has no post_connect
pass
self.poller = poller.Poller()
self._is_running = True
self.thread = threading.Thread(target=self.run)
self.thread.setDaemon(True)
self.thread.start()
def run(self):
errors = 0
while self.is_running:
# If we fail in an Idl call, we could have missed an update
# from the server, leaving us out of sync with ovsdb-server.
# It is not safe to continue without restarting the connection.
# Though it is likely that the error is unrecoverable, keep trying
# indefinitely just in case.
try:
self.idl.wait(self.poller)
self.poller.fd_wait(self.txns.alert_fileno, poller.POLLIN)
self.poller.block()
with self.lock:
self.idl.run()
except Exception as e:
# This shouldn't happen, but is possible if there is a bug
# in python-ovs
errors += 1
LOG.exception(e)
with self.lock:
self.idl.force_reconnect()
try:
idlutils.wait_for_change(self.idl, self.timeout)
except Exception as e:
# This could throw the same exception as idl.run()
# or Exception("timeout"), either way continue
LOG.exception(e)
sleep = min(2**errors, 60)
LOG.info("Trying to recover, sleeping %s seconds", sleep)
time.sleep(sleep)
continue
errors = 0
txn = self.txns.get_nowait()
if txn is not None:
try:
with self.lock:
txn.results.put(txn.do_commit())
except Exception as ex:
er = idlutils.ExceptionResult(ex=ex,
tb=traceback.format_exc())
txn.results.put(er)
self.txns.task_done()
self.idl.close()
def run(self):
errors = 0
while self._is_running:
# If we fail in an Idl call, we could have missed an update
# from the server, leaving us out of sync with ovsdb-server.
# It is not safe to continue without restarting the connection,
# though it is likely that the error is unrecoverable, so only try
# a few times before bailing completely.
try:
self.idl.wait(self.poller)
self.poller.fd_wait(self.txns.alert_fileno, poller.POLLIN)
# TODO(jlibosva): Remove next line once losing connection to
# ovsdb is solved.
self.poller.timer_wait(self.timeout * 1000)
self.poller.block()
self.idl.run()
except Exception as e:
# This shouldn't happen, but is possible if there is a bug
# in python-ovs
errors += 1
LOG.exception(e)
if errors <= 3:
self.idl.force_reconnect()
idlutils.wait_for_change(self.idl, self.timeout)
continue
self._is_running = False
break
errors = 0
txn = self.txns.get_nowait()
if txn is not None:
try:
txn.results.put(txn.do_commit())
except Exception as ex:
er = idlutils.ExceptionResult(ex=ex,
tb=traceback.format_exc())
txn.results.put(er)
self.txns.task_done()
