openstack/neutron
Code Issues Proposed changes

Add 3 retry attempts to initialize ovs agent

Browse Source 
In case when TimeoutException will be raised by ovsdbapp during
initialization of neutron-ovs-agent, it will now try to create
object of agents class 3 times before agent will be terminated.

Such timeouts shouldn't happend usually but if for some reason
it happens e.g. once, e.g. in CI job, it should be better to just
retry and initialize this agent instead of left it dead on the
node.

Change-Id: I93e8d21d612e343479f26f8adc4477473579bab1
Closes-Bug: #1838563
This commit is contained in:
Slawek Kaplonski 2019-08-01 18:10:19 +02:00
parent 04b96b198e
commit 30a60d04f0
1 changed files with 21 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
neutron/plugins/ml2/drivers/openvswitch/agent/ovs_neutron_agent.py
View File

@ -45,6 +45,7 @@ from oslo_service import loopingcall
from oslo_service import systemd
from oslo_utils import netutils
from osprofiler import profiler
from ovsdbapp import exceptions as ovs_exceptions
import six
from neutron._i18n import _
@ -83,6 +84,8 @@ cfg.CONF.import_group('AGENT', 'neutron.plugins.ml2.drivers.openvswitch.'
cfg.CONF.import_group('OVS', 'neutron.plugins.ml2.drivers.openvswitch.agent.'
'common.config')
INIT_MAX_TRIES = 3
class _mac_mydialect(netaddr.mac_unix):
word_fmt = '%.2x'
@ -2568,10 +2571,22 @@ def main(bridge_classes):
validate_tunnel_config(cfg.CONF.AGENT.tunnel_types, cfg.CONF.OVS.local_ip)
try:
agent = OVSNeutronAgent(bridge_classes, ext_mgr, cfg.CONF)
capabilities.notify_init_event(n_const.AGENT_TYPE_OVS, agent)
except (RuntimeError, ValueError) as e:
LOG.error("%s Agent terminated!", e)
sys.exit(1)
init_try = 1
while True:
try:
agent = OVSNeutronAgent(bridge_classes, ext_mgr, cfg.CONF)
capabilities.notify_init_event(n_const.AGENT_TYPE_OVS, agent)
break
except ovs_exceptions.TimeoutException as e:
if init_try < INIT_MAX_TRIES:
LOG.warning("Ovsdb command timeout!")
init_try += 1
else:
LOG.error("%(err)s agent terminated after %(attempts)s "
"initialization attempts!",
{'err': e, 'attempts': init_try})
sys.exit(1)
except (RuntimeError, ValueError) as e:
LOG.error("%s agent terminated!", e)
sys.exit(1)
agent.daemon_loop()