[bradm] initial nrpe checks

config.yaml

@@ -153,3 +153,14 @@ options:
       The CPU core multiplier to use when configuring worker processes for
       Glance.  By default, the number of workers for each daemon is set to
       twice the number of CPU cores a service unit has.
+  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.
+

files/nrpe-external-master/check_upstart_job

@@ -0,0 +1,72 @@
+#!/usr/bin/python
+
+#
+# Copyright 2012, 2013 Canonical Ltd.
+#
+# Author: Paul Collins <paul.collins@canonical.com>
+#
+# Based on http://www.eurion.net/python-snippets/snippet/Upstart%20service%20status.html
+#
+
+import sys
+
+import dbus
+
+
+class Upstart(object):
+    def __init__(self):
+        self._bus = dbus.SystemBus()
+        self._upstart = self._bus.get_object('com.ubuntu.Upstart',
+                                             '/com/ubuntu/Upstart')
+    def get_job(self, job_name):
+        path = self._upstart.GetJobByName(job_name,
+                                          dbus_interface='com.ubuntu.Upstart0_6')
+        return self._bus.get_object('com.ubuntu.Upstart', path)
+
+    def get_properties(self, job):
+        path = job.GetInstance([], dbus_interface='com.ubuntu.Upstart0_6.Job')
+        instance = self._bus.get_object('com.ubuntu.Upstart', path)
+        return instance.GetAll('com.ubuntu.Upstart0_6.Instance',
+                               dbus_interface=dbus.PROPERTIES_IFACE)
+
+    def get_job_instances(self, job_name):
+        job = self.get_job(job_name)
+        paths = job.GetAllInstances([], dbus_interface='com.ubuntu.Upstart0_6.Job')
+        return [self._bus.get_object('com.ubuntu.Upstart', path) for path in paths]
+
+    def get_job_instance_properties(self, job):
+        return job.GetAll('com.ubuntu.Upstart0_6.Instance',
+                          dbus_interface=dbus.PROPERTIES_IFACE)
+
+try:
+    upstart = Upstart()
+    try:
+        job = upstart.get_job(sys.argv[1])        
+        props = upstart.get_properties(job)
+
+        if props['state'] == 'running':
+            print 'OK: %s is running' % sys.argv[1]
+            sys.exit(0)
+        else:
+            print 'CRITICAL: %s is not running' % sys.argv[1]
+            sys.exit(2)
+
+    except dbus.DBusException as e:
+        instances = upstart.get_job_instances(sys.argv[1])
+        propses = [upstart.get_job_instance_properties(instance) for instance in instances]
+        states = dict([(props['name'], props['state']) for props in propses])
+        if len(states) != states.values().count('running'):
+            not_running = []
+            for name in states.keys():
+                if states[name] != 'running':
+                    not_running.append(name)
+            print 'CRITICAL: %d instances of %s not running: %s' % \
+                (len(not_running), sys.argv[1], not_running.join(', '))
+            sys.exit(2)
+        else:
+            print 'OK: %d instances of %s running' % (len(states), sys.argv[1])
+
+except dbus.DBusException as e:
+    print 'CRITICAL: failed to get properties of \'%s\' from upstart' % sys.argv[1]
+    sys.exit(2)
+

hooks/charmhelpers/contrib/charmsupport/nrpe.py

@@ -0,0 +1,218 @@
+"""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',
+        )
+        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):
+        super(NRPE, self).__init__()
+        self.config = config()
+        self.nagios_context = self.config['nagios_context']
+        self.unit_name = local_unit().replace('/', '-')
+        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))

hooks/charmhelpers/contrib/charmsupport/volumes.py

@@ -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']

hooks/glance_relations.py

@@ -73,6 +73,8 @@ from charmhelpers.contrib.openstack.ip import (
 
 from charmhelpers.contrib.openstack.context import ADDRESS_TYPES
 
+from charmhelpers.contrib.charmsupport.nrpe import NRPE
+
 from subprocess import (
     check_call,
     call, )
@@ -297,6 +299,8 @@ def config_changed():
     open_port(9292)
     configure_https()
 
+    update_nrpe_config()
+
     # Pickup and changes due to network reference architecture
     # configuration
     [keystone_joined(rid) for rid in relation_ids('identity-service')]
@@ -334,6 +338,7 @@ def cluster_changed():
 def upgrade_charm():
     apt_install(filter_installed_packages(PACKAGES), fatal=True)
     configure_https()
+    update_nrpe_config()
     CONFIGS.write_all()
 
 
@@ -446,6 +451,25 @@ def amqp_changed():
         return
     CONFIGS.write(GLANCE_API_CONF)
 
+@hooks.hook('nrpe-external-master-relation-joined', 'nrpe-external-master-relation-changed')
+def update_nrpe_config():
+    nrpe = NRPE()
+    apt_install('python-dbus')
+    
+    nrpe.add_check(
+        shortname='glance-api',
+        description='glance-api process',
+        check_cmd = 'check_upstart_job glance-api',
+        )
+    nrpe.add_check(
+        shortname='glance-registry',
+        description='glance-registry process',
+        check_cmd = 'check_upstart_job glance-registry',
+        )
+
+    nrpe.write()
+
+
 if __name__ == '__main__':
     try:
         hooks.execute(sys.argv)

hooks/nrpe-external-master-relation-changed

@@ -0,0 +1 @@
+glance_relations.py

hooks/nrpe-external-master-relation-joined

@@ -0,0 +1 @@
+glance_relations.py

metadata.yaml

@@ -9,6 +9,9 @@ description: |
 categories:
   - miscellaneous
 provides:
+  nrpe-external-master:
+    interface: nrpe-external-master
+    scope: container
   image-service:
     interface: glance
 requires: