put in the first run at new nagios configs

roles/nagios_client/files/scripts/check_datanommer_timesince.py

@@ -0,0 +1,72 @@
+#!/usr/bin/env python
+""" NRPE check for datanommer/fedmsg health.
+Given a category like 'bodhi', 'buildsys', or 'git', return an error if
+datanommer hasn't seen a message of that type in such and such time.
+You can alternatively provide a 'topic' which might look like
+org.fedoraproject.prod.bodhi.update.comment.
+
+Requires:  python-dateutil
+
+Usage:
+
+    $ check_datanommer_timesince CATEGORY WARNING_THRESH CRITICAL_THRESH
+
+:Author: Ralph Bean <rbean@redhat.com>
+
+"""
+
+import dateutil.relativedelta
+import subprocess
+import sys
+import json
+
+
+def query_timesince(identifier):
+    # If it has a '.', then assume it is a topic.
+    if '.' in identifier:
+        cmd = 'datanommer-latest --topic %s --timesince' % identifier
+    else:
+        cmd = 'datanommer-latest --category %s --timesince' % identifier
+    sys.stderr.write("Running %r\n" % cmd)
+    process = subprocess.Popen(cmd.split(), shell=False,
+                               stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+    stdout, stderr = process.communicate()
+    prefix, stdout = stdout.split("INFO] ", 1)
+    data = json.loads(stdout)
+    return float(data[0])
+
+
+def main():
+    identifier, warning_threshold, critical_threshold = sys.argv[-3:]
+    timesince = query_timesince(identifier)
+    warning_threshold = int(warning_threshold)
+    critical_threshold = int(critical_threshold)
+
+    time_strings = []
+    rd = dateutil.relativedelta.relativedelta(seconds=timesince)
+    for denomination in ['years', 'months', 'days', 'hours', 'minutes', 'seconds']:
+        value = getattr(rd, denomination, 0)
+        if value:
+            time_strings.append("%d %s" % (value, denomination))
+
+    string = ", ".join(time_strings)
+    reason = "datanommer has not seen a %r message in %s" % (identifier, string)
+
+    if timesince > critical_threshold:
+        print "CRIT: ", reason
+        sys.exit(2)
+
+    if timesince > warning_threshold:
+        print "WARN: ", reason
+        sys.exit(1)
+
+    print "OK: ", reason
+    sys.exit(0)
+
+
+if __name__ == '__main__':
+    try:
+        main()
+    except Exception as e:
+        print "UNKNOWN: ", str(e)
+        sys.exit(3)

roles/nagios_client/files/scripts/check_fcomm_queue

@@ -0,0 +1,23 @@
+#!/usr/bin/env python
+import sys
+
+try:
+    import retask.queue
+
+    queue = retask.queue.Queue('fedora-packages')
+    queue.connect()
+
+    items = queue.length
+    if items > 500:
+        print "CRITICAL:  %i tasks in fcomm queue" % items
+        sys.exit(2)
+    elif items > 250:
+        print "WARNING:  %i tasks in fcomm queue" % items
+        sys.exit(1)
+    else:
+        print "OK:  %i tasks in fcomm queue" % items
+        sys.exit(0)
+
+except Exception as e:
+    print "UNKNOWN:", str(e)
+    sys.exit(3)

roles/nagios_client/files/scripts/check_fedmsg_consumer_backlog.py

@@ -0,0 +1,62 @@
+#!/usr/bin/env python
+
+import json
+import os
+import socket
+import sys
+import zmq
+
+try:
+    service = sys.argv[1]
+    check_consumer = sys.argv[2]
+    backlog_warning = int(sys.argv[3])
+    backlog_critical = int(sys.argv[4])
+    fname = '/var/run/fedmsg/monitoring-%s.socket' % service
+
+    if not os.path.exists(fname):
+        print "UNKNOWN - %s does not exist" % fname
+        sys.exit(3)
+
+    if not os.access(fname, os.W_OK):
+        print "UNKNOWN - cannot write to %s" % fname
+        sys.exit(3)
+
+    connect_to = "ipc:///%s" % fname
+    ctx = zmq.Context()
+    s = ctx.socket(zmq.SUB)
+    s.connect(connect_to)
+    s.setsockopt(zmq.SUBSCRIBE, '')
+
+    poller = zmq.Poller()
+    poller.register(s, zmq.POLLIN)
+
+    timeout = 20000
+
+    events = dict(poller.poll(timeout))
+    if s in events and events[s] == zmq.POLLIN:
+        msg = s.recv()
+        msg = json.loads(msg)
+    else:
+       print 'UNKNOWN - ZMQ timeout.  No message received in %i ms' % timeout
+       sys.exit(3)
+
+    for consumer in msg['consumers']:
+        if consumer['name'] == check_consumer:
+            if consumer['backlog'] is None:
+                print 'ERROR: fedmsg consumer %s is not initialized' % consumer['name']
+                sys.exit(3)
+            elif consumer['backlog'] > backlog_critical:
+                print 'CRITICAL: fedmsg consumer %s backlog value is %i' % (consumer['name'],consumer['backlog'])
+                sys.exit(2)
+            elif consumer['backlog'] > backlog_warning:
+                print 'WARNING: fedmsg consumer %s backlog value is %i' % (consumer['name'],consumer['backlog'])
+                sys.exit(1)
+            else:
+                print 'OK: fedmsg consumer %s backlog value is %i' % (consumer['name'],consumer['backlog'])
+                sys.exit(0)
+
+    print "UNKNOWN: fedmsg consumer %s not found" % check_consumer
+    sys.exit(3)
+except Exception as err:
+    print "UNKNOWN:", str(err)
+    sys.exit(3)

roles/nagios_client/files/scripts/check_fedmsg_consumer_exceptions.py

@@ -0,0 +1,58 @@
+#!/usr/bin/env python
+
+import json
+import os
+import socket
+import sys
+import zmq
+
+try:
+    service = sys.argv[1]
+    check_consumer = sys.argv[2]
+    exceptions_warning = int(sys.argv[3])
+    exceptions_critical = int(sys.argv[4])
+    fname = '/var/run/fedmsg/monitoring-%s.socket' % service
+
+    if not os.path.exists(fname):
+        print "UNKNOWN - %s does not exist" % fname
+        sys.exit(3)
+
+    if not os.access(fname, os.W_OK):
+        print "UNKNOWN - cannot write to %s" % fname
+        sys.exit(3)
+
+    connect_to = "ipc:///%s" % fname
+    ctx = zmq.Context()
+    s = ctx.socket(zmq.SUB)
+    s.connect(connect_to)
+    s.setsockopt(zmq.SUBSCRIBE, '')
+    poller = zmq.Poller()
+    poller.register(s, zmq.POLLIN)
+
+    timeout = 20000
+
+    events = dict(poller.poll(timeout))
+    if s in events and events[s] == zmq.POLLIN:
+        msg = s.recv()
+        msg = json.loads(msg)
+    else:
+       print 'UNKNOWN - ZMQ timeout.  No message received in %i ms' % timeout
+       sys.exit(3)
+
+    for consumer in msg['consumers']:
+        if consumer['name'] == check_consumer:
+            if consumer['exceptions'] > exceptions_critical:
+                print 'CRITICAL: fedmsg consumer %s exceptions value is %i' % (consumer['name'],consumer['exceptions'])
+                sys.exit(2)
+            elif consumer['exceptions'] > exceptions_warning:
+                print 'WARNING: fedmsg consumer %s exceptions value is %i' % (consumer['name'],consumer['exceptions'])
+                sys.exit(1)
+            else:
+                print 'OK: fedmsg consumer %s exceptions value is %i' % (consumer['name'],consumer['exceptions'])
+                sys.exit(0)
+
+    print "UNKNOWN: fedmsg consumers %s not found" % check_consumer
+    sys.exit(3)
+except Exception as err:
+    print "UNKNOWN:", str(err)
+    sys.exit(3)

roles/nagios_client/files/scripts/check_fedmsg_producer_last_ran.py

@@ -0,0 +1,69 @@
+#!/usr/bin/env python
+
+import arrow
+import json
+import os
+import socket
+import sys
+import time
+import zmq
+
+try:
+    service = sys.argv[1]
+    check_producer = sys.argv[2]
+    elapsed_warning = int(sys.argv[3])
+    elapsed_critical = int(sys.argv[4])
+    fname = '/var/run/fedmsg/monitoring-%s.socket' % service
+
+    if not os.path.exists(fname):
+        print "UNKNOWN - %s does not exist" % fname
+        sys.exit(3)
+
+    if not os.access(fname, os.W_OK):
+        print "UNKNOWN - cannot write to %s" % fname
+        sys.exit(3)
+
+    connect_to = "ipc:///%s" % fname
+    ctx = zmq.Context()
+    s = ctx.socket(zmq.SUB)
+    s.connect(connect_to)
+    s.setsockopt(zmq.SUBSCRIBE, '')
+
+    poller = zmq.Poller()
+    poller.register(s, zmq.POLLIN)
+
+    timeout = 20000
+
+    events = dict(poller.poll(timeout))
+    if s in events and events[s] == zmq.POLLIN:
+        msg = s.recv()
+        msg = json.loads(msg)
+    else:
+       print 'UNKNOWN - ZMQ timeout.  No message received in %i ms' % timeout
+       sys.exit(3)
+
+    now = time.time()
+
+    for prod in msg['producers']:
+        if prod['name'] != check_producer:
+            continue
+        diff = now - prod['last_ran']
+        then = arrow.get(prod['last_ran']).humanize()
+        if diff > elapsed_critical:
+            print "CRITICAL: %s last ran %s (%i seconds ago)" % (
+                check_producer, then, diff)
+            sys.exit(2)
+        elif diff > elapsed_warning:
+            print "WARNING: %s last ran %s (%i seconds ago)" % (
+                check_producer, then, diff)
+            sys.exit(1)
+        else:
+            print "OK: %s last ran %s (%i seconds ago)" % (
+                check_producer, then, diff)
+            sys.exit(0)
+
+    print "UNKNOWN: fedmsg producer %s not found" % check_producer
+    sys.exit(3)
+except Exception as err:
+    print "UNKNOWN:", str(err)
+    sys.exit(3)

roles/nagios_client/files/scripts/check_fedmsg_producers_consumers.py

@@ -0,0 +1,64 @@
+#!/usr/bin/env python
+
+import json
+import os
+import socket
+import sys
+import zmq
+
+try:
+    service = sys.argv[1]
+    check_list = frozenset(sys.argv[2:])
+    fname = '/var/run/fedmsg/monitoring-%s.socket' % service
+
+    if not check_list:
+        print "UNKNOWN - empty list of fedmsg consumers and producers to check"
+        sys.exit(3)
+
+    if not os.path.exists(fname):
+        print "UNKNOWN - %s does not exist" % fname
+        sys.exit(3)
+
+    if not os.access(fname, os.W_OK):
+        print "UNKNOWN - cannot write to %s" % fname
+        sys.exit(3)
+
+    connect_to = "ipc:///%s" % fname
+    ctx = zmq.Context()
+    s = ctx.socket(zmq.SUB)
+    s.connect(connect_to)
+    s.setsockopt(zmq.SUBSCRIBE, '')
+    poller = zmq.Poller()
+    poller.register(s, zmq.POLLIN)
+
+    timeout = 20000
+
+    events = dict(poller.poll(timeout))
+    if s in events and events[s] == zmq.POLLIN:
+        msg = s.recv()
+        msg = json.loads(msg)
+    else:
+       print 'UNKNOWN - ZMQ timeout.  No message received in %i ms' % timeout
+       sys.exit(3)
+
+    for consumer in msg['consumers']:
+        if consumer['name'] in check_list and not consumer['initialized']:
+            print 'ERROR: fedmsg consumer %s is not initialized' % consumer['name']
+            sys.exit(2)
+
+    for producer in msg['producers']:
+        if producer['name'] in check_list and not producer['initialized']:
+            print 'ERROR: fedmsg producer %s is not initialized' % producer['name']
+            sys.exit(2)
+
+    for item in check_list:
+        if item not in [p['name'] for p in msg['producers'] + msg['consumers']]:
+            print 'ERROR: %s not found among installed plugins' % item
+            sys.exit(2)
+
+    print "OK: fedmsg consumer(s) and producer(s) initialized"
+    sys.exit(0)
+
+except Exception as err:
+    print "UNKNOWN:", str(err)
+    sys.exit(3)

roles/nagios_client/files/scripts/check_haproxy_conns.py

@@ -0,0 +1,76 @@
+#!/usr/bin/env python
+""" Nagios check for haproxy over-subscription.
+
+fedmsg-gateway is the primary concern as it can eat up a ton of simultaneous
+connections.
+
+:Author:  Ralph Bean <rbean@redhat.com>
+"""
+
+import socket
+import sys
+
+
+def _numeric(value):
+    """ Type casting utility """
+    try:
+        return int(value)
+    except ValueError:
+        try:
+            return float(value)
+        except ValueError:
+            return value
+
+
+def query(sockname="/var/run/haproxy-stat"):
+    """ Read stats from the haproxy socket and return a dict """
+    s = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM)
+    s.connect("/var/run/haproxy-stat")
+    s.send('show info\n')
+    try:
+        response = s.recv(1024).strip()
+        lines = response.split('\n')
+        data = dict([map(str.strip, line.split(':')) for line in lines])
+        data = dict([(k, _numeric(v)) for k, v in data.items()])
+        return data
+    except Exception, e:
+        print str(e)
+    finally:
+        s.close()
+
+    return None
+
+
+def nagios_check(data):
+    """ Print warnings and return nagios exit codes. """
+
+    current = data['CurrConns']
+    maxconn = data['Maxconn']
+    percent = 100 * float(current) / float(maxconn)
+    details = "%.2f%% subscribed.  %i current of %i maxconn." % (
+        percent, current, maxconn,
+    )
+
+    if percent < 50:
+        print "HAPROXY SUBS OK: " + details
+        return 0
+
+    if percent < 75:
+        print "HAPROXY SUBS WARN: " + details
+        return 1
+
+    if percent <= 100:
+        print "HAPROXY SUBS CRIT: " + details
+        return 2
+
+    print "HAPROXY SUBS UNKNOWN: " + details
+    return 3
+
+
+if __name__ == '__main__':
+    try:
+        data = query(sockname="/var/run/haproxy-stat")
+    except Exception as e:
+        print "HAPROXY SUBS UNKNOWN: " + str(e)
+        sys.exit(3)
+    sys.exit(nagios_check(data))

roles/nagios_client/files/scripts/check_haproxy_mirrorlist.py

@@ -0,0 +1,59 @@
+#!/usr/bin/env python
+
+import socket
+import sys
+
+
+try:
+
+    unixsocket="/var/run/haproxy-stat"
+    s = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM)
+    s.connect(unixsocket)
+    s.send('show stat\n')
+
+    try:
+
+        output = s.recv(16384).strip().split('\n')
+	fields = output.pop(0).split(',')
+	fields[0]=fields[0].replace('# ','')
+	proxies = list()
+	for line in output:
+	  proxies.append(dict(zip(fields,line.split(','))))
+
+    except Exception, e:
+      print str(e)
+    finally:
+      s.close()
+
+except Exception as e:
+  print "MIRRORLIST STATE UNKNOWN: " + str(e)
+  sys.exit(3)
+
+total=0
+downcount=0
+downlist=""
+for proxy in proxies:
+ if proxy['svname'] == "FRONTEND" or proxy['svname'] == "BACKEND":
+   continue
+ if proxy['pxname'] == "mirror-lists":
+   total+=1
+   if proxy['status'] == "DOWN":
+     downlist+=proxy["svname"]+" "
+     downcount+=1
+
+unavailability = 100 * float(downcount) / float(total)
+
+if unavailability == 0:
+  print "MIRRORLIST STATE OK: " + downlist
+  sys.exit(0)
+
+if unavailability < 50:
+  print "MIRRORLIST STATE WARN: " + downlist
+  sys.exit(1)
+
+if unavailability >= 50:
+  print "MIRRORLIST STATE CRIT: " + downlist
+  sys.exit(2)
+
+print "MIRRORLIST STATE UNKNOWN: " + downlist
+sys.exit(3)

roles/nagios_client/files/scripts/check_ipa_replication

@@ -0,0 +1,74 @@
+#!/usr/bin/python 
+# Source: https://github.com/opinkerfi/nagios-plugins/blob/master/check_ipa/check_ipa_replication
+# Copyright 2013, Tomas Edwardsson 
+# Copyright 2016, Patrick Uiterwijk
+#
+# This script is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This script is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+import ldap
+from pynag.Plugins import PluginHelper, critical, warning, ok
+
+plugin = PluginHelper()
+
+plugin.parser.add_option('-u', help="ldap uri", dest="uri")
+plugin.parser.add_option('-D', help="bind DN", dest="binddn")
+plugin.parser.add_option('-w', help="bind password", dest="bindpw")
+plugin.parse_arguments()
+
+if not plugin.options.uri:
+    plugin.parser.error('-u (uri) argument is required')
+
+try:
+    l = ldap.initialize(plugin.options.uri)
+
+    if plugin.options.binddn:
+        l.bind_s(plugin.options.binddn, plugin.options.bindpw)
+
+    replication = l.search_s('cn=config', 
+        ldap.SCOPE_SUBTREE, 
+        '(objectclass=nsds5replicationagreement)',
+        ['nsDS5ReplicaHost', 'nsds5replicaLastUpdateStatus'])
+except Exception, e:
+    plugin.status(critical)
+    plugin.add_summary("Unable to initialize ldap connection: %s" % (e))
+    plugin.exit()
+
+
+# Loop through replication agreements
+for rhost in replication:
+    plugin.add_summary("Replica %s Status: %s" % (rhost[1]['nsDS5ReplicaHost'][0], rhost[1]['nsds5replicaLastUpdateStatus'][0]))
+
+    status = rhost[1]['nsds5replicaLastUpdateStatus'][0]
+    code = status[:2]
+    if status.startswith('Error ('):
+        # IPA >=4.4.0
+        code = status[status.find('(')+1:status.find(')')]
+    else:
+        # IPA <4.4.0
+        code = status[:status.find(' ')]
+
+    if code == '0':
+        plugin.status(ok)
+    elif code == '1':
+        # Busy Replica is not an error, its "unknown" (but its "ok" for now)
+        plugin.status(ok)
+    else:
+        plugin.status(critical)
+
+if not len(replication):
+    plugin.add_summary("Warning: No replicas found")
+    plugin.status(warning)
+
+plugin.exit()
+

roles/nagios_client/files/scripts/check_lock

@@ -0,0 +1,17 @@
+#!/usr/bin/python
+
+import fcntl
+import sys
+
+try:
+    f = open('/mnt/koji/.nagios_test', 'r')
+    f.close()
+    f = open('/mnt/koji/.nagios_test', 'w')
+except IOError:
+    print "Could not create file"
+    sys.exit(2)
+    
+fcntl.flock(f, fcntl.LOCK_EX)
+f.close()
+print "File Locked Successfully"
+sys.exit(0)

roles/nagios_client/files/scripts/check_lock_file_age

@@ -0,0 +1,123 @@
+#! /usr/bin/perl -w
+
+# check_lock_file_age.pl Copyright (C) 2010 Ricky Elrod <codeblock@fedoraproject.org>
+#
+# Fork of check_file_age.pl
+#
+# Checks a lock file's size and modification time to make sure it's not empty
+# and that it's sufficiently recent.
+#
+#
+# This program is free software; you can redistribute it and/or
+# modify it under the terms of the GNU General Public License
+# as published by the Free Software Foundation; either version 2
+# of the License, or (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty
+# of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# you should have received a copy of the GNU General Public License
+# along with this program (or with Nagios);  if not, write to the
+# Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+# Boston, MA 02111-1307, USA
+
+use strict;
+use English;
+use Getopt::Long;
+use File::stat;
+use vars qw($PROGNAME);
+use lib "/usr/lib64/nagios/plugins";
+use utils qw (%ERRORS &print_revision &support);
+
+sub print_help ();
+sub print_usage ();
+
+my ($opt_c, $opt_f, $opt_w, $opt_h, $opt_V);
+my ($result, $message, $age, $size, $st);
+
+$PROGNAME="check_lock_file_age";
+
+$opt_w = 1;
+$opt_c = 5;
+$opt_f = "";
+
+Getopt::Long::Configure('bundling');
+GetOptions(
+	"V"   => \$opt_V, "version"	=> \$opt_V,
+	"h"   => \$opt_h, "help"	=> \$opt_h,
+	"f=s" => \$opt_f, "file"	=> \$opt_f,
+	"w=f" => \$opt_w, "warning-age=f" => \$opt_w,
+	"c=f" => \$opt_c, "critical-age=f" => \$opt_c);
+
+if ($opt_V) {
+	print_revision($PROGNAME, '1.4.14');
+	exit $ERRORS{'OK'};
+}
+
+if ($opt_h) {
+	print_help();
+	exit $ERRORS{'OK'};
+}
+
+if (($opt_c and $opt_w) and ($opt_c < $opt_w)) {
+        print "Warning time must be less than Critical time.\n";
+        exit $ERRORS{'UNKNOWN'};
+}
+
+$opt_f = shift unless ($opt_f);
+
+if (! $opt_f) {
+	print "LOCK_FILE_AGE UNKNOWN: No file specified\n";
+	exit $ERRORS{'UNKNOWN'};
+}
+
+# Check that file exists (can be directory or link)
+unless (-e $opt_f) {
+	print "LOCK_FILE_AGE OK: File not found (Lock file removed) - $opt_f\n";
+	exit $ERRORS{'OK'};
+}
+
+$st = File::stat::stat($opt_f);
+$age = time - $st->mtime;
+
+$result = 'OK';
+
+# Convert minutes to seconds
+if($opt_c) { $opt_c *= 60; }
+if($opt_w) { $opt_w *= 60; }
+
+if ($opt_c and $age > $opt_c) {
+	$result = 'CRITICAL';
+}
+elsif ($opt_w and $age > $opt_w) {
+	$result = 'WARNING';
+}
+
+# If the age is higher than 2 minutes, convert seconds -> minutes
+# If it's higher than a day, use days.
+# Just a nicety, to make people not have to do math ;)
+if($age > 86400) { $age = int(($age/86400))." days"; }
+elsif($age > 120) { $age = int(($age/60))." minutes"; }
+else { $age = "$age seconds"; }
+
+print "LOCK_FILE_AGE $result: $opt_f is $age old.\n";
+exit $ERRORS{$result};
+
+sub print_usage () {
+	print "Usage:\n";
+	print "  $PROGNAME [-w <secs>] [-c <secs>] -f <file>\n";
+	print "  $PROGNAME [-h | --help]\n";
+	print "  $PROGNAME [-V | --version]\n";
+}
+
+sub print_help () {
+	print_revision($PROGNAME, '1.4.14');
+	print "Copyright (c) 2010 Ricky Elrod\n\n";
+	print_usage();
+	print "\n";
+	print "  <mins>  File must be no more than this many minutes old (default: warn 1m, crit 5m)\n";
+	print "\n";
+	support();
+}

roles/nagios_client/files/scripts/check_memcache_connect

@@ -0,0 +1,24 @@
+#!/bin/bash
+#
+# 2014-11-19
+# Author: Ralph Bean <rbean@redhat.com>
+
+# exit codes
+ok=0
+warn=1
+crit=2
+unkn=3
+
+# Right now we just check to see if we can even run this command without
+# hanging and timing out.  In the future, we could parse stdout for more
+# fine-grained information.
+echo stats | nc 127.0.0.1 11211 > /dev/null
+status=$?
+
+if [ $status -ne 0 ]; then
+    echo "CRIT:  stats command got status code $status"
+    exit $crit
+else
+    echo "OK:  stats command got status code $status"
+    exit $ok
+fi

roles/nagios_client/files/scripts/check_osbs_api.py

@@ -0,0 +1,14 @@
+#!/usr/bin/python
+
+import requests
+import sys
+
+r =  requests.get("https://localhost:8443/", verify=False)
+
+if 'paths' in r.json().keys():
+    print "OK: OSBS API endpoint is responding with path data"
+    sys.exit(0)
+else:
+    print "CRITICAL: OSBS API not responding properly"
+    sys.exit(2)
+

roles/nagios_client/files/scripts/check_osbs_builds.py

@@ -0,0 +1,23 @@
+#!/usr/bin/python
+
+import subprocess
+import sys
+
+sp = subprocess.Popen(
+    ["osbs", "list-builds"],
+    stdout=subprocess.PIPE,
+    stderr=subprocess.PIPE,
+    stdin=subprocess.PIPE
+)
+sp_out, sp_err = sp.communicate()
+sp_err = sp_err.split('\n')
+
+if 'not attached to terminal' in sp_err[0]:
+    sp_err = sp_err[1:]
+
+if sp_err[0].split()[0] == 'BUILD':
+    print "OK: OSBS is responsive to 'osbs list-builds'"
+    sys.exit(0)
+else:
+    print "CRITICAL: OSBS UNRESPONSIVE"
+    sys.exit(2)

roles/nagios_client/files/scripts/check_postfix_queue

@@ -0,0 +1,49 @@
+#!/bin/bash
+#
+# 19-07-2010
+# Author: Cherwin Nooitmeer <cherwin@gmail.com>
+#
+
+# exit codes
+e_ok=0
+e_warning=1
+e_critical=2
+e_unknown=3
+
+# regular expression that matches queue IDs (e.g. D71EF7AC80F8)
+queue_id='^[A-F0-9][A-F0-9][A-F0-9][A-F0-9][A-F0-9][A-F0-9][A-F0-9][A-F0-9][A-F0-9][A-F0-9]'
+
+usage="Invalid command line usage"
+
+if [ -z $1 ]; then
+    echo $usage
+    exit $e_unknown
+fi
+
+while getopts ":w:c:" options
+do
+    case $options in
+        w ) warning=$OPTARG ;;
+        c ) critical=$OPTARG ;;
+        * ) echo $usage
+            exit $e_unknown ;;
+    esac
+done
+
+# determine queue size
+qsize=$(mailq | egrep -c $queue_id)
+if [ -z $qsize ]
+then
+    exit $e_unknown
+fi
+
+if [ $qsize -ge $critical ]; then
+    retval=$e_critical
+elif [ $qsize -ge $warning ]; then
+    retval=$e_warning
+elif [ $qsize -lt $warning ]; then
+    retval=$e_ok
+fi
+
+echo "$qsize mail(s) in queue | mail_queue=$qsize"
+exit $retval

roles/nagios_client/files/scripts/check_rabbitmq_size

@@ -0,0 +1,26 @@
+#!/bin/python
+import sys
+import requests
+
+url = 'http://localhost:15672/api/queues/%%2f/%s' % (sys.argv[1])
+
+r = requests.get(url, auth=('guest', 'guest')).json()
+consumers = r['consumers']
+messages = r['messages']
+
+msg = 'Messages in queue: %i (%i consumers)' % (messages, consumers)
+
+if consumers < 1:
+    print 'CRITICAL: No consumers: %s' % msg
+    sys.exit(2)
+
+if messages > sys.argv[2]:
+    print 'CRITICAL: %s' % msg
+    sys.exit(2)
+
+if messages > sys.argv[3]:
+    print 'WARNING: %s' % msg
+    sys.exit(1)
+
+print 'OK: %s' % msg
+sys.exit(0)

roles/nagios_client/files/scripts/check_raid.py

@@ -0,0 +1,45 @@
+#!/usr/bin/env python
+#
+# very simple python script to parse out /proc/mdstat
+# and give results for nagios to monitor
+#
+
+import sys
+import string
+
+devices = []
+
+try:
+    mdstat = string.split(open('/proc/mdstat').read(), '\n')
+except IOError:
+    # seems we have no software raid on this machines
+    sys.exit(0)
+
+error = ""
+i = 0
+for line in mdstat:
+    if line[0:2] == 'md':
+        device = string.split(line)[0]
+        devices.append(device)
+        status = string.split(mdstat[i+1])[3]
+        if string.count(status, "_"):
+            # see if we can figure out what's going on
+            err = string.split(mdstat[i+2])
+            msg = "device=%s status=%s" % (device, status)
+            if len(err) > 0:
+                msg = msg + " rebuild=%s" % err[0]
+
+            if not error:
+                error = msg
+            else:
+                error = error + ", " + msg
+    i = i + 1
+
+if not error:
+    print "DEVICES %s OK" % " ".join(devices)
+    sys.exit(0)
+
+else:
+    print error
+    sys.exit(2)
+

roles/nagios_client/files/scripts/check_readonly_fs

@@ -0,0 +1,84 @@
+#!/bin/bash
+
+# check_readonlyfs: Check for readonly filesystems
+# Copyright (C) 2010 Davide Madrisan <davide.madrisan@gmail.com>
+
+PROGNAME=`/bin/basename $0`
+PROGPATH=`echo $0 | sed -e 's,[\\/][^\\/][^\\/]*$,,'`
+REVISION=`echo '$Revision: 1 $' | sed -e 's/[^0-9.]//g'`
+
+. $PROGPATH/utils.sh
+
+print_usage() {
+    echo "Usage: $PROGNAME --no-network-fs"
+    echo "Usage: $PROGNAME --help"
+    echo "Usage: $PROGNAME --version"
+}
+
+print_help() {
+    print_revision $PROGNAME $REVISION
+    echo ""
+    print_usage
+    echo ""
+    echo "readonly filesystem checker plugin for Nagios"
+    echo ""
+    support
+}
+
+NETFS=1
+
+# Grab the command line arguments
+
+exitstatus=$STATE_WARNING #default
+
+while test -n "$1"; do
+    case "$1" in
+        --help|-h)
+            print_help
+            exit $STATE_OK
+            ;;
+        --version|-V)
+            print_revision $PROGNAME $REVISION
+            exit $STATE_OK
+            ;;
+        --no-network-fs|-n)
+            NETFS="0"
+            ;;
+        *)
+            echo "Unknown argument: $1"
+            print_usage
+            exit $STATE_UNKNOWN
+            ;;
+    esac
+    shift
+done
+
+[ -r /proc/mounts ] || { echo "cannot read /proc/mounts!"; exit $STATE_UNKNOWN; }
+
+nerr=0
+IFS_SAVE="$IFS"
+
+rofs_list=""
+while read dev mp fs mopt ignore; do
+   [ "$dev" = none ] && continue
+   case $fs in binfmt_misc|devpts|iso9660|proc|selinuxfs|rpc_pipefs|sysfs|tmpfs|usbfs)
+      continue ;;
+   esac
+   case $fs in autofs|nfs|nfs4|smbfs)
+      # skip the network filesystems
+      [ "$NETFS" = 0 ] && continue ;;
+   esac
+
+   IFS=","; set -- $mopt; IFS="$IFS_SAVE"
+   while :; do
+   case "$1" in
+      ro) rofs_list="$rofs_list $mp"; nerr=$(( $nerr + 1 )) ;;
+      "") shift; break ;;
+   esac
+   shift
+   done
+done < <(LC_ALL=C /bin/cat /proc/mounts 2>/dev/null)
+
+[ $nerr -eq 0 ] && { echo OK; exit $STATE_OK; } || echo "$rofs_list: read only fs"
+
+exit $exitstatus

roles/nagios_client/files/scripts/check_supybot_plugin

@@ -0,0 +1,108 @@
+#!/usr/bin/env python
+""" check_supybot_plugin -- ensure that a plugin is loaded by supybot.
+
+Run like:
+
+    check_supybot_plugin --target fedmsg
+    check_supybot_plugin --target koji --debug
+
+"""
+
+import argparse
+import sys
+import socket
+import string
+import uuid
+
+
+def process_args():
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        '-t', '--target', default=None, dest='target',
+        help="Required.  The plugin we're looking for."
+    )
+    parser.add_argument(
+        '-n', '--nick', default=None, dest='nick',
+        help="NICK to use when connecting to freenode.",
+    )
+    parser.add_argument(
+        '-d', '--debug', default=False, action='store_true',
+        help='Print out debug information.', dest='debug',
+    )
+    parser.add_argument(
+        '-H', '--host', default='irc.freenode.net',
+        help='Host to connect to.', dest='host',
+    )
+    parser.add_argument(
+        '-p', '--port', default=6667, type=int,
+        help='Host to connect to.', dest='port',
+    )
+    return parser.parse_args()
+
+args = process_args()
+
+# Use a random nick so people can't mess with us
+if not args.nick:
+    args.nick = 'nrpe-' + str(uuid.uuid4()).split('-')[0]
+
+name = "NRPE Bot"
+readbuffer = ""
+
+if not args.target:
+    print "UNKNOWN:  No 'target' specified."
+    sys.exit(3)
+
+args.target = args.target.lower()
+
+if args.debug:
+    print "connecting to %s/%i" % (args.host, args.port)
+
+try:
+    s = socket.socket()
+    s.connect((args.host, args.port))
+
+    if args.debug:
+        print "as %s/%s (%s)" % (args.nick, args.nick, name)
+
+    s.send("nick %s\r\n" % args.nick)
+    s.send("USER %s %s bla :%s\r\n" % (args.nick, args.host, name))
+
+    while 1:
+        readbuffer = readbuffer+s.recv(1024)
+        temp = string.split(readbuffer, "\n")
+        readbuffer = temp.pop()
+
+        for line in temp:
+            line = string.rstrip(line)
+
+            if args.debug:
+                print " * ", line
+
+            line = string.split(line)
+
+            if line[1] == 'MODE':
+                msg = "privmsg zodbot :list\r\n"
+                if args.debug:
+                    print "sending:"
+                    print " ->", msg
+                s.send(msg)
+
+            if line[1] == 'PRIVMSG':
+                if args.debug:
+                    print "Got our response.."
+
+                plugins = map(str.lower, ' '.join(line[3:][1:]).split(', '))
+
+                if args.target in plugins:
+                    print "OK"
+                    s.send("QUIT")
+                    sys.exit(0)
+                else:
+                    print "CRITICAL: %r not loaded by supybot" % args.target
+                    s.send("QUIT")
+                    sys.exit(2)
+except Exception as e:
+    print "UNKNOWN: ", str(e)
+    if args.debug:
+        raise
+    sys.exit(3)

roles/nagios_client/files/scripts/check_testcloud

@@ -0,0 +1,19 @@
+#!/bin/bash
+
+RUNNING_VMS=`testcloud instance list | grep -i 'running' | wc -l`
+CRITICAL=20
+WARNING=15
+
+
+if [ $RUNNING_VMS -gt $CRITICAL ]
+then
+    echo "Testcloud: CRITICAL Number of VMs running: $RUNNING_VMS"
+    exit 2
+elif [ $RUNNING_VMS -gt $WARNING ]
+then
+    echo "Testcloud: WARNING Number of VMs running: $RUNNING_VMS"
+    exit 1
+else
+    echo "Testcloud: OK Number of VMs running: $RUNNING_VMS"
+    exit 0
+fi