--- /dev/null
+# Upstream contributions, bitergia will crawl this and extract the relevant information
+# system is one of Gerrit, Bugzilla, Launchpad (insert more)
+---
+-
+ url: https://blueprints.launchpad.net/ceilometer/+spec/event-alarm-evaluator
+ system: Launchpad
+-
+ url: https://blueprints.launchpad.net/nova/+spec/mark-host-down
+ system: Launchpad
+-
+ url: https://blueprints.launchpad.net/python-novaclient/+spec/support-force-down-service
+ system: Launchpad
+-
+ url: https://blueprints.launchpad.net/nova/+spec/get-valid-server-state
+ system: Launchpad
+-
+ url: https://blueprints.launchpad.net/nova/+spec/servers-by-host-status
+ system: Launchpad
+-
+ url: https://blueprints.launchpad.net/nova/+spec/maintenance-reason-to-server
+ system: Launchpad
+-
+ url: https://blueprints.launchpad.net/nova/+spec/service-status-notification
+ system: Launchpad
+-
+ url: https://blueprints.launchpad.net/congress/+spec/push-type-datasource-driver
+ system: Launchpad
+#-
+# url: https://review.openstack.org/#/c/314915/
+# system: Gerrit
+-
+ url: https://blueprints.launchpad.net/cinder/+spec/mark-services-down
+ system: Launchpad
+-
+ url: https://blueprints.launchpad.net/python-cinderclient/+spec/mark-service-down-cli
+ system: Launchpad
+#-
+# url: https://bugs.launchpad.net/neutron/+bug/1513144
+# system: Launchpad-bug
except in this case, the Consumer of a VM/VNF switches to STBY configuration
based on a predicted fault, rather than an occurred fault.
-NVFI Maintenance
+NFVI Maintenance
----------------
VM Retirement
High level northbound interface specification
---------------------------------------------
-Fault management
+Fault Management
^^^^^^^^^^^^^^^^
This interface allows the Consumer to subscribe to fault notification from the
shown in :numref:`figure5c`.
It consists of the following steps:
-5. The Consumer C3 switches to standby configuration (STDBY).
+5. The Consumer C3 switches to standby configuration (STBY).
6. Instructions from Consumers C2/C3 are shared to VIM requesting certain actions to be performed (steps 6a, 6b).
The VIM executes the requested actions and sends back a NACK to consumer C2 (step 6d) as the
migration of the virtual resource(s) is not completed by the given timeout.
from flask import Flask
from flask import request
import json
+import logger as doctor_log
import os
import time
+LOG = doctor_log.Logger('doctor_consumer').getLogger()
+
app = Flask(__name__)
@app.route('/failure', methods=['POST'])
def event_posted():
- app.logger.debug('doctor consumer notified at %s' % time.time())
- app.logger.debug('received data = %s' % request.data)
+ LOG.info('doctor consumer notified at %s' % time.time())
+ LOG.info('received data = %s' % request.data)
d = json.loads(request.data)
return "OK"
def main():
args = get_args()
- app.run(host="0.0.0.0", port=args.port, debug=True)
+ app.run(host="0.0.0.0", port=args.port)
if __name__ == '__main__':
from flask import Flask
from flask import request
import json
+import logger as doctor_log
import os
import time
import nova_force_down
+LOG = doctor_log.Logger('doctor_inspector').getLogger()
+
class DoctorInspectorSample(object):
try:
host=server.__dict__.get('OS-EXT-SRV-ATTR:host')
self.servers[host].append(server)
- app.logger.debug('get hostname=%s from server=%s' % (host, server))
+ LOG.debug('get hostname=%s from server=%s' % (host, server))
except Exception as e:
- app.logger.debug('can not get hostname from server=%s' % server)
+ LOG.error('can not get hostname from server=%s' % server)
def disable_compute_host(self, hostname):
for server in self.servers[hostname]:
app = Flask(__name__)
-app.debug = True
inspector = DoctorInspectorSample()
@app.route('/events', methods=['POST'])
def event_posted():
- app.logger.debug('event posted at %s' % time.time())
- app.logger.debug('inspector = %s' % inspector)
- app.logger.debug('received data = %s' % request.data)
+ LOG.info('event posted at %s' % time.time())
+ LOG.info('inspector = %s' % inspector)
+ LOG.info('received data = %s' % request.data)
d = json.loads(request.data)
hostname = d['hostname']
event_type = d['type']
args = get_args()
app.run(port=args.port)
+
if __name__ == '__main__':
main()
--- /dev/null
+##############################################################################
+# Copyright (c) 2016 ZTE Corporation and others.
+#
+# All rights reserved. This program and the accompanying materials
+# are made available under the terms of the Apache License, Version 2.0
+# which accompanies this distribution, and is available at
+# http://www.apache.org/licenses/LICENSE-2.0
+##############################################################################
+# Usage:
+# import doctor_logger
+# logger = doctor_logger.Logger("script_name").getLogger()
+# logger.info("message to be shown with - INFO - ")
+# logger.debug("message to be shown with - DEBUG -")
+
+import logging
+import os
+
+
+class Logger:
+ def __init__(self, logger_name):
+
+ CI_DEBUG = os.getenv('CI_DEBUG')
+
+ self.logger = logging.getLogger(logger_name)
+ self.logger.propagate = 0
+ self.logger.setLevel(logging.DEBUG)
+
+ formatter = logging.Formatter('%(asctime)s %(filename)s %(lineno)d '
+ '%(levelname)-6s %(message)s')
+
+ ch = logging.StreamHandler()
+ ch.setFormatter(formatter)
+ if CI_DEBUG is not None and CI_DEBUG.lower() == "true":
+ ch.setLevel(logging.DEBUG)
+ else:
+ ch.setLevel(logging.INFO)
+ self.logger.addHandler(ch)
+
+ file_handler = logging.FileHandler('%s.log' % logger_name)
+ file_handler.setFormatter(formatter)
+ file_handler.setLevel(logging.DEBUG)
+ self.logger.addHandler(file_handler)
+
+
+ def getLogger(self):
+ return self.logger
+
import argparse
from datetime import datetime
import json
+import logger as doctor_log
import os
import requests
import socket
SUPPORTED_INSPECTOR_TYPES = ['sample', 'congress']
+LOG = doctor_log.Logger('doctor_monitor').getLogger()
+
class DoctorMonitorSample(object):
interval = 0.1 # second
(congress_endpoint, doctor_ds['id']))
def start_loop(self):
- print "start ping to host %(h)s (ip=%(i)s)" % {'h': self.hostname,
- 'i': self.ip_addr}
+ LOG.debug("start ping to host %(h)s (ip=%(i)s)" % {'h': self.hostname,
+ 'i': self.ip_addr})
sock = socket.socket(socket.AF_INET, socket.SOCK_RAW,
socket.IPPROTO_ICMP)
sock.settimeout(self.timeout)
sock.sendto(ICMP_ECHO_MESSAGE, (self.ip_addr, 0))
data = sock.recv(4096)
except socket.timeout:
- print "doctor monitor detected at %s" % time.time()
+ LOG.info("doctor monitor detected at %s" % time.time())
self.report_error()
- print "ping timeout, quit monitoring..."
+ LOG.info("ping timeout, quit monitoring...")
return
time.sleep(self.interval)
}
calculate_notification_time() {
- detected=$(grep "doctor monitor detected at" monitor.log | awk '{print $5}')
- notified=$(grep "doctor consumer notified at" consumer.log | awk '{print $5}')
+ detected=$(grep "doctor monitor detected at" monitor.log | awk '{print $10}')
+ notified=$(grep "doctor consumer notified at" consumer.log | awk '{print $10}')
if ! grep -q "doctor consumer notified at" consumer.log ; then
die $LINENO "Consumer hasn't received fault notification."
fi
Code Review / doctor.git / commitdiff
