[bradm] Added nagios checks
This commit is contained in:
Brad Marshall
parent
558a23d0a0
commit
cd7d5b1168
|
|
@ -7,3 +7,4 @@ include:
|
|||
- contrib.hahelpers
|
||||
- contrib.storage.linux
|
||||
- contrib.network.ip
|
||||
- contrib.charmsupport
|
||||
|
|
|
|||
10
config.yaml
10
config.yaml
|
|
@ -14,3 +14,13 @@ options:
|
|||
Note that updating this setting to a source that is known to
|
||||
provide a later version of OpenStack will trigger a software
|
||||
upgrade.
|
||||
nagios_context:
|
||||
default: "juju"
|
||||
type: string
|
||||
description: |
|
||||
Used by the nrpe-external-master subordinate charm.
|
||||
A string that will be prepended to instance name to set the host name
|
||||
in nagios. So for instance the hostname would be something like:
|
||||
juju-myservice-0
|
||||
If you're running multiple environments with the same services in them
|
||||
this allows you to differentiate between them.
|
||||
|
|
|
|||
|
|
@ -1,6 +1,7 @@
|
|||
#!/usr/bin/python
|
||||
|
||||
import sys
|
||||
import os
|
||||
import json
|
||||
from charmhelpers.fetch import (
|
||||
apt_install, filter_installed_packages,
|
||||
|
|
@ -10,7 +11,9 @@ from charmhelpers.core.hookenv import (
|
|||
config,
|
||||
Hooks, UnregisteredHookError,
|
||||
log,
|
||||
relation_set
|
||||
local_unit,
|
||||
relation_set,
|
||||
relations_of_type,
|
||||
)
|
||||
from charmhelpers.core.host import (
|
||||
restart_on_change,
|
||||
|
|
@ -22,12 +25,15 @@ from charmhelpers.contrib.openstack.utils import (
|
|||
)
|
||||
from ceilometer_utils import (
|
||||
restart_map,
|
||||
services,
|
||||
register_configs,
|
||||
CEILOMETER_AGENT_PACKAGES,
|
||||
NOVA_SETTINGS,
|
||||
do_openstack_upgrade
|
||||
)
|
||||
|
||||
from charmhelpers.contrib.charmsupport.nrpe import NRPE
|
||||
|
||||
hooks = Hooks()
|
||||
CONFIGS = register_configs()
|
||||
|
||||
|
|
@ -55,6 +61,7 @@ def nova_ceilometer_joined():
|
|||
@restart_on_change(restart_map())
|
||||
def ceilometer_changed():
|
||||
CONFIGS.write_all()
|
||||
update_nrpe_config()
|
||||
|
||||
|
||||
@hooks.hook('config-changed')
|
||||
|
|
@ -62,8 +69,59 @@ def ceilometer_changed():
|
|||
def config_changed():
|
||||
if openstack_upgrade_available('ceilometer-common'):
|
||||
do_openstack_upgrade(CONFIGS)
|
||||
update_nrpe_config()
|
||||
CONFIGS.write_all()
|
||||
|
||||
|
||||
@hooks.hook('nrpe-external-master-relation-joined',
|
||||
'nrpe-external-master-relation-changed')
|
||||
def update_nrpe_config():
|
||||
# Find out if nrpe set nagios_hostname
|
||||
hostname = None
|
||||
host_context = None
|
||||
for rel in relations_of_type('nrpe-external-master'):
|
||||
if 'nagios_hostname' in rel:
|
||||
hostname = rel['nagios_hostname']
|
||||
host_context = rel['nagios_host_context']
|
||||
break
|
||||
nrpe = NRPE(hostname=hostname)
|
||||
apt_install('python-dbus')
|
||||
|
||||
if host_context:
|
||||
current_unit = "%s:%s" % (host_context, local_unit())
|
||||
else:
|
||||
current_unit = local_unit()
|
||||
|
||||
services_to_monitor = services()
|
||||
|
||||
for service in services_to_monitor:
|
||||
upstart_init = '/etc/init/%s.conf' % service
|
||||
sysv_init = '/etc/init.d/%s' % service
|
||||
|
||||
if os.path.exists(upstart_init):
|
||||
nrpe.add_check(
|
||||
shortname=service,
|
||||
description='process check {%s}' % current_unit,
|
||||
check_cmd='check_upstart_job %s' % service,
|
||||
)
|
||||
elif os.path.exists(sysv_init):
|
||||
cronpath = '/etc/cron.d/nagios-service-check-%s' % service
|
||||
cron_template = '*/5 * * * * root \
|
||||
/usr/local/lib/nagios/plugins/check_exit_status.pl -s /etc/init.d/%s \
|
||||
status > /var/lib/nagios/service-check-%s.txt\n' % (service, service)
|
||||
f = open(cronpath, 'w')
|
||||
f.write(cron_template)
|
||||
f.close()
|
||||
nrpe.add_check(
|
||||
shortname=service,
|
||||
description='process check {%s}' % current_unit,
|
||||
check_cmd='check_status_file.py -f \
|
||||
/var/lib/nagios/service-check-%s.txt' % service,
|
||||
)
|
||||
|
||||
nrpe.write()
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
try:
|
||||
hooks.execute(sys.argv)
|
||||
|
|
|
|||
|
|
@ -94,6 +94,14 @@ def restart_map():
|
|||
return _map
|
||||
|
||||
|
||||
def services():
|
||||
''' Returns a list of services associate with this charm '''
|
||||
_services = []
|
||||
for v in restart_map().values():
|
||||
_services = _services + v
|
||||
return list(set(_services))
|
||||
|
||||
|
||||
def do_openstack_upgrade(configs):
|
||||
"""
|
||||
Perform an upgrade. Takes care of upgrading packages, rewriting
|
||||
|
|
|
|||
|
|
@ -0,0 +1,222 @@
|
|||
"""Compatibility with the nrpe-external-master charm"""
|
||||
# Copyright 2012 Canonical Ltd.
|
||||
#
|
||||
# Authors:
|
||||
# Matthew Wedgwood <matthew.wedgwood@canonical.com>
|
||||
|
||||
import subprocess
|
||||
import pwd
|
||||
import grp
|
||||
import os
|
||||
import re
|
||||
import shlex
|
||||
import yaml
|
||||
|
||||
from charmhelpers.core.hookenv import (
|
||||
config,
|
||||
local_unit,
|
||||
log,
|
||||
relation_ids,
|
||||
relation_set,
|
||||
)
|
||||
|
||||
from charmhelpers.core.host import service
|
||||
|
||||
# This module adds compatibility with the nrpe-external-master and plain nrpe
|
||||
# subordinate charms. To use it in your charm:
|
||||
#
|
||||
# 1. Update metadata.yaml
|
||||
#
|
||||
# provides:
|
||||
# (...)
|
||||
# nrpe-external-master:
|
||||
# interface: nrpe-external-master
|
||||
# scope: container
|
||||
#
|
||||
# and/or
|
||||
#
|
||||
# provides:
|
||||
# (...)
|
||||
# local-monitors:
|
||||
# interface: local-monitors
|
||||
# scope: container
|
||||
|
||||
#
|
||||
# 2. Add the following to config.yaml
|
||||
#
|
||||
# nagios_context:
|
||||
# default: "juju"
|
||||
# type: string
|
||||
# description: |
|
||||
# Used by the nrpe subordinate charms.
|
||||
# A string that will be prepended to instance name to set the host name
|
||||
# in nagios. So for instance the hostname would be something like:
|
||||
# juju-myservice-0
|
||||
# If you're running multiple environments with the same services in them
|
||||
# this allows you to differentiate between them.
|
||||
#
|
||||
# 3. Add custom checks (Nagios plugins) to files/nrpe-external-master
|
||||
#
|
||||
# 4. Update your hooks.py with something like this:
|
||||
#
|
||||
# from charmsupport.nrpe import NRPE
|
||||
# (...)
|
||||
# def update_nrpe_config():
|
||||
# nrpe_compat = NRPE()
|
||||
# nrpe_compat.add_check(
|
||||
# shortname = "myservice",
|
||||
# description = "Check MyService",
|
||||
# check_cmd = "check_http -w 2 -c 10 http://localhost"
|
||||
# )
|
||||
# nrpe_compat.add_check(
|
||||
# "myservice_other",
|
||||
# "Check for widget failures",
|
||||
# check_cmd = "/srv/myapp/scripts/widget_check"
|
||||
# )
|
||||
# nrpe_compat.write()
|
||||
#
|
||||
# def config_changed():
|
||||
# (...)
|
||||
# update_nrpe_config()
|
||||
#
|
||||
# def nrpe_external_master_relation_changed():
|
||||
# update_nrpe_config()
|
||||
#
|
||||
# def local_monitors_relation_changed():
|
||||
# update_nrpe_config()
|
||||
#
|
||||
# 5. ln -s hooks.py nrpe-external-master-relation-changed
|
||||
# ln -s hooks.py local-monitors-relation-changed
|
||||
|
||||
|
||||
class CheckException(Exception):
|
||||
pass
|
||||
|
||||
|
||||
class Check(object):
|
||||
shortname_re = '[A-Za-z0-9-_]+$'
|
||||
service_template = ("""
|
||||
#---------------------------------------------------
|
||||
# This file is Juju managed
|
||||
#---------------------------------------------------
|
||||
define service {{
|
||||
use active-service
|
||||
host_name {nagios_hostname}
|
||||
service_description {nagios_hostname}[{shortname}] """
|
||||
"""{description}
|
||||
check_command check_nrpe!{command}
|
||||
servicegroups {nagios_servicegroup}
|
||||
}}
|
||||
""")
|
||||
|
||||
def __init__(self, shortname, description, check_cmd):
|
||||
super(Check, self).__init__()
|
||||
# XXX: could be better to calculate this from the service name
|
||||
if not re.match(self.shortname_re, shortname):
|
||||
raise CheckException("shortname must match {}".format(
|
||||
Check.shortname_re))
|
||||
self.shortname = shortname
|
||||
self.command = "check_{}".format(shortname)
|
||||
# Note: a set of invalid characters is defined by the
|
||||
# Nagios server config
|
||||
# The default is: illegal_object_name_chars=`~!$%^&*"|'<>?,()=
|
||||
self.description = description
|
||||
self.check_cmd = self._locate_cmd(check_cmd)
|
||||
|
||||
def _locate_cmd(self, check_cmd):
|
||||
search_path = (
|
||||
'/',
|
||||
os.path.join(os.environ['CHARM_DIR'],
|
||||
'files/nrpe-external-master'),
|
||||
'/usr/lib/nagios/plugins',
|
||||
'/usr/local/lib/nagios/plugins',
|
||||
)
|
||||
parts = shlex.split(check_cmd)
|
||||
for path in search_path:
|
||||
if os.path.exists(os.path.join(path, parts[0])):
|
||||
command = os.path.join(path, parts[0])
|
||||
if len(parts) > 1:
|
||||
command += " " + " ".join(parts[1:])
|
||||
return command
|
||||
log('Check command not found: {}'.format(parts[0]))
|
||||
return ''
|
||||
|
||||
def write(self, nagios_context, hostname):
|
||||
nrpe_check_file = '/etc/nagios/nrpe.d/{}.cfg'.format(
|
||||
self.command)
|
||||
with open(nrpe_check_file, 'w') as nrpe_check_config:
|
||||
nrpe_check_config.write("# check {}\n".format(self.shortname))
|
||||
nrpe_check_config.write("command[{}]={}\n".format(
|
||||
self.command, self.check_cmd))
|
||||
|
||||
if not os.path.exists(NRPE.nagios_exportdir):
|
||||
log('Not writing service config as {} is not accessible'.format(
|
||||
NRPE.nagios_exportdir))
|
||||
else:
|
||||
self.write_service_config(nagios_context, hostname)
|
||||
|
||||
def write_service_config(self, nagios_context, hostname):
|
||||
for f in os.listdir(NRPE.nagios_exportdir):
|
||||
if re.search('.*{}.cfg'.format(self.command), f):
|
||||
os.remove(os.path.join(NRPE.nagios_exportdir, f))
|
||||
|
||||
templ_vars = {
|
||||
'nagios_hostname': hostname,
|
||||
'nagios_servicegroup': nagios_context,
|
||||
'description': self.description,
|
||||
'shortname': self.shortname,
|
||||
'command': self.command,
|
||||
}
|
||||
nrpe_service_text = Check.service_template.format(**templ_vars)
|
||||
nrpe_service_file = '{}/service__{}_{}.cfg'.format(
|
||||
NRPE.nagios_exportdir, hostname, self.command)
|
||||
with open(nrpe_service_file, 'w') as nrpe_service_config:
|
||||
nrpe_service_config.write(str(nrpe_service_text))
|
||||
|
||||
def run(self):
|
||||
subprocess.call(self.check_cmd)
|
||||
|
||||
|
||||
class NRPE(object):
|
||||
nagios_logdir = '/var/log/nagios'
|
||||
nagios_exportdir = '/var/lib/nagios/export'
|
||||
nrpe_confdir = '/etc/nagios/nrpe.d'
|
||||
|
||||
def __init__(self, hostname=None):
|
||||
super(NRPE, self).__init__()
|
||||
self.config = config()
|
||||
self.nagios_context = self.config['nagios_context']
|
||||
self.unit_name = local_unit().replace('/', '-')
|
||||
if hostname:
|
||||
self.hostname = hostname
|
||||
else:
|
||||
self.hostname = "{}-{}".format(self.nagios_context, self.unit_name)
|
||||
self.checks = []
|
||||
|
||||
def add_check(self, *args, **kwargs):
|
||||
self.checks.append(Check(*args, **kwargs))
|
||||
|
||||
def write(self):
|
||||
try:
|
||||
nagios_uid = pwd.getpwnam('nagios').pw_uid
|
||||
nagios_gid = grp.getgrnam('nagios').gr_gid
|
||||
except:
|
||||
log("Nagios user not set up, nrpe checks not updated")
|
||||
return
|
||||
|
||||
if not os.path.exists(NRPE.nagios_logdir):
|
||||
os.mkdir(NRPE.nagios_logdir)
|
||||
os.chown(NRPE.nagios_logdir, nagios_uid, nagios_gid)
|
||||
|
||||
nrpe_monitors = {}
|
||||
monitors = {"monitors": {"remote": {"nrpe": nrpe_monitors}}}
|
||||
for nrpecheck in self.checks:
|
||||
nrpecheck.write(self.nagios_context, self.hostname)
|
||||
nrpe_monitors[nrpecheck.shortname] = {
|
||||
"command": nrpecheck.command,
|
||||
}
|
||||
|
||||
service('restart', 'nagios-nrpe-server')
|
||||
|
||||
for rid in relation_ids("local-monitors"):
|
||||
relation_set(relation_id=rid, monitors=yaml.dump(monitors))
|
||||
|
|
@ -0,0 +1,156 @@
|
|||
'''
|
||||
Functions for managing volumes in juju units. One volume is supported per unit.
|
||||
Subordinates may have their own storage, provided it is on its own partition.
|
||||
|
||||
Configuration stanzas:
|
||||
volume-ephemeral:
|
||||
type: boolean
|
||||
default: true
|
||||
description: >
|
||||
If false, a volume is mounted as sepecified in "volume-map"
|
||||
If true, ephemeral storage will be used, meaning that log data
|
||||
will only exist as long as the machine. YOU HAVE BEEN WARNED.
|
||||
volume-map:
|
||||
type: string
|
||||
default: {}
|
||||
description: >
|
||||
YAML map of units to device names, e.g:
|
||||
"{ rsyslog/0: /dev/vdb, rsyslog/1: /dev/vdb }"
|
||||
Service units will raise a configure-error if volume-ephemeral
|
||||
is 'true' and no volume-map value is set. Use 'juju set' to set a
|
||||
value and 'juju resolved' to complete configuration.
|
||||
|
||||
Usage:
|
||||
from charmsupport.volumes import configure_volume, VolumeConfigurationError
|
||||
from charmsupport.hookenv import log, ERROR
|
||||
def post_mount_hook():
|
||||
stop_service('myservice')
|
||||
def post_mount_hook():
|
||||
start_service('myservice')
|
||||
|
||||
if __name__ == '__main__':
|
||||
try:
|
||||
configure_volume(before_change=pre_mount_hook,
|
||||
after_change=post_mount_hook)
|
||||
except VolumeConfigurationError:
|
||||
log('Storage could not be configured', ERROR)
|
||||
'''
|
||||
|
||||
# XXX: Known limitations
|
||||
# - fstab is neither consulted nor updated
|
||||
|
||||
import os
|
||||
from charmhelpers.core import hookenv
|
||||
from charmhelpers.core import host
|
||||
import yaml
|
||||
|
||||
|
||||
MOUNT_BASE = '/srv/juju/volumes'
|
||||
|
||||
|
||||
class VolumeConfigurationError(Exception):
|
||||
'''Volume configuration data is missing or invalid'''
|
||||
pass
|
||||
|
||||
|
||||
def get_config():
|
||||
'''Gather and sanity-check volume configuration data'''
|
||||
volume_config = {}
|
||||
config = hookenv.config()
|
||||
|
||||
errors = False
|
||||
|
||||
if config.get('volume-ephemeral') in (True, 'True', 'true', 'Yes', 'yes'):
|
||||
volume_config['ephemeral'] = True
|
||||
else:
|
||||
volume_config['ephemeral'] = False
|
||||
|
||||
try:
|
||||
volume_map = yaml.safe_load(config.get('volume-map', '{}'))
|
||||
except yaml.YAMLError as e:
|
||||
hookenv.log("Error parsing YAML volume-map: {}".format(e),
|
||||
hookenv.ERROR)
|
||||
errors = True
|
||||
if volume_map is None:
|
||||
# probably an empty string
|
||||
volume_map = {}
|
||||
elif not isinstance(volume_map, dict):
|
||||
hookenv.log("Volume-map should be a dictionary, not {}".format(
|
||||
type(volume_map)))
|
||||
errors = True
|
||||
|
||||
volume_config['device'] = volume_map.get(os.environ['JUJU_UNIT_NAME'])
|
||||
if volume_config['device'] and volume_config['ephemeral']:
|
||||
# asked for ephemeral storage but also defined a volume ID
|
||||
hookenv.log('A volume is defined for this unit, but ephemeral '
|
||||
'storage was requested', hookenv.ERROR)
|
||||
errors = True
|
||||
elif not volume_config['device'] and not volume_config['ephemeral']:
|
||||
# asked for permanent storage but did not define volume ID
|
||||
hookenv.log('Ephemeral storage was requested, but there is no volume '
|
||||
'defined for this unit.', hookenv.ERROR)
|
||||
errors = True
|
||||
|
||||
unit_mount_name = hookenv.local_unit().replace('/', '-')
|
||||
volume_config['mountpoint'] = os.path.join(MOUNT_BASE, unit_mount_name)
|
||||
|
||||
if errors:
|
||||
return None
|
||||
return volume_config
|
||||
|
||||
|
||||
def mount_volume(config):
|
||||
if os.path.exists(config['mountpoint']):
|
||||
if not os.path.isdir(config['mountpoint']):
|
||||
hookenv.log('Not a directory: {}'.format(config['mountpoint']))
|
||||
raise VolumeConfigurationError()
|
||||
else:
|
||||
host.mkdir(config['mountpoint'])
|
||||
if os.path.ismount(config['mountpoint']):
|
||||
unmount_volume(config)
|
||||
if not host.mount(config['device'], config['mountpoint'], persist=True):
|
||||
raise VolumeConfigurationError()
|
||||
|
||||
|
||||
def unmount_volume(config):
|
||||
if os.path.ismount(config['mountpoint']):
|
||||
if not host.umount(config['mountpoint'], persist=True):
|
||||
raise VolumeConfigurationError()
|
||||
|
||||
|
||||
def managed_mounts():
|
||||
'''List of all mounted managed volumes'''
|
||||
return filter(lambda mount: mount[0].startswith(MOUNT_BASE), host.mounts())
|
||||
|
||||
|
||||
def configure_volume(before_change=lambda: None, after_change=lambda: None):
|
||||
'''Set up storage (or don't) according to the charm's volume configuration.
|
||||
Returns the mount point or "ephemeral". before_change and after_change
|
||||
are optional functions to be called if the volume configuration changes.
|
||||
'''
|
||||
|
||||
config = get_config()
|
||||
if not config:
|
||||
hookenv.log('Failed to read volume configuration', hookenv.CRITICAL)
|
||||
raise VolumeConfigurationError()
|
||||
|
||||
if config['ephemeral']:
|
||||
if os.path.ismount(config['mountpoint']):
|
||||
before_change()
|
||||
unmount_volume(config)
|
||||
after_change()
|
||||
return 'ephemeral'
|
||||
else:
|
||||
# persistent storage
|
||||
if os.path.ismount(config['mountpoint']):
|
||||
mounts = dict(managed_mounts())
|
||||
if mounts.get(config['mountpoint']) != config['device']:
|
||||
before_change()
|
||||
unmount_volume(config)
|
||||
mount_volume(config)
|
||||
after_change()
|
||||
else:
|
||||
before_change()
|
||||
mount_volume(config)
|
||||
after_change()
|
||||
return config['mountpoint']
|
||||
|
|
@ -0,0 +1 @@
|
|||
ceilometer_hooks.py
|
||||
|
|
@ -0,0 +1 @@
|
|||
ceilometer_hooks.py
|
||||
|
|
@ -15,6 +15,9 @@ categories:
|
|||
- miscellaneous
|
||||
- openstack
|
||||
provides:
|
||||
nrpe-external-master:
|
||||
interface: nrpe-external-master
|
||||
scope: container
|
||||
nova-ceilometer:
|
||||
interface: nova-ceilometer
|
||||
scope: container
|
||||
|
|
|
|||
Loading…
Reference in New Issue