add a bunch of checks
[mirror/dsa-nagios.git] / config / nagios-master.cfg
index 84ffdde..230bf36 100644 (file)
@@ -131,6 +131,11 @@ servers:
     address: 82.94.249.153
     parents: gw-ubc
     hostgroups: routing-infrastructure
+  gw-telegraaf2:
+    address: 217.196.40.15
+    parents: gw-ubc
+    hostgroups: routing-infrastructure
+    contact_groups: +alioth-admins
   gw-helsinki:
     address: 128.214.173.25
     parents: gw-ubc
@@ -181,16 +186,32 @@ servers:
     address: 200.17.202.254
     parents: gw-ubc
     hostgroups: routing-infrastructure
+  gw-zivit:
+    address: 80.245.144.3
+    parents: gw-ubc
+    hostgroups: routing-infrastructure
 
   global:
     hostgroups: notacomputer
     pingable: false
     check_command: dsa_check_always_ok
 
+  vasks:
+    address: 217.196.43.132
+    parents: gw-telegraaf2
+    hostgroups: computers
+    contact_groups: alioth-admins
+
+  wagner:
+    address: 217.196.43.140
+    parents: gw-telegraaf2
+    hostgroups: computers, nfs-client, postgres84-hosts, inetd-hosts, apache2-hosts, acpid-hosts
+    contact_groups: alioth-admins
+
   samosa:
     address: 192.25.206.57
     parents: gw-HP-ftc
-    hostgroups: computers, service, dl380, hassrvfs, hasbootfs, acpid-hosts, nfs-client, postgres84-hosts, xinetd-hosts, apache2-hosts, squeeze
+    hostgroups: computers, service, dl380, hassrvfs, hasbootfs, acpid-hosts, nfs-client, postgres90-hosts, xinetd-hosts, apache2-hosts, squeeze
   raff:
     address: 192.25.206.59
     parents: gw-HP-ftc
@@ -206,7 +227,7 @@ servers:
   spohr:
     address: 192.25.206.33
     parents: gw-HP-ftc
-    hostgroups: computers, service, dl380, apache2-hosts, nfs-server, spamd, heavy-exim, squeeze, unbound-hosts
+    hostgroups: computers, service, dl380, apache2-hosts, nfs-server, spamd, heavy-exim, squeeze
   peri:
     address: 192.25.206.15
     parents: gw-HP-ftc
@@ -237,7 +258,7 @@ servers:
   sperger:
     address: 82.195.75.34
     parents: gw-man-da2
-    hostgroups: computers, porterbox, sw-raid, hasbootfs, hasorgfs, sparc, lenny
+    hostgroups: computers, porterbox, sw-raid, hasbootfs, hasorgfs, sparc, squeeze
     contacts: bzed
   agricola:
     address: 82.195.75.86
@@ -269,7 +290,7 @@ servers:
   handel:
     address: 82.195.75.104
     parents: unger
-    hostgroups: computers, service, hasbootfs, kvmdomains, apache2-hosts, lenny
+    hostgroups: computers, service, hasbootfs, kvmdomains, apache2-hosts, squeeze
   geo1:
     address: 82.195.75.105
     parents: unger
@@ -277,7 +298,7 @@ servers:
   draghi:
     address: 82.195.75.106
     parents: unger
-    hostgroups: computers, service, hasbootfs, hassrvfs, apache2-hosts, bind9-hosts, spamd, heavy-exim, kvmdomains, xinetd-hosts, apache-https, lenny
+    hostgroups: computers, service, hasbootfs, hassrvfs, apache2-hosts, bind9-hosts, spamd, heavy-exim, kvmdomains, xinetd-hosts, apache-https, squeeze
   kaufmann:
     address: 82.195.75.107
     parents: unger
@@ -293,7 +314,7 @@ servers:
   kokkonen:
     address: 82.195.75.97
     parents: gw-man-da
-    hostgroups: computers, service, acpid-hosts, heavy-exim, mail-relay, apache2-hosts, lenny
+    hostgroups: computers, service, acpid-hosts, heavy-exim, mail-relay, apache2-hosts, squeeze
   byrd:
     address: 82.195.75.92
     parents: unger
@@ -306,7 +327,7 @@ servers:
   master:
     address: 70.103.162.29
     parents: gw-brainfood
-    hostgroups: computers, general, apache2-hosts, spamd, heavy-exim, highload, xinetd-hosts, mptraid, unbound-hosts, lenny
+    hostgroups: computers, general, apache2-hosts, spamd, heavy-exim, highload, xinetd-hosts, mptraid, squeeze
   murphy:
     address: 70.103.162.31
     parents: gw-brainfood
@@ -402,7 +423,7 @@ servers:
   widor:
     address: 93.94.130.161
     parents: gw-dg-i.net
-    hostgroups: computers, apache2-hosts, sw-raid, acpid-hosts, hasorgfs, service, apache-https, unbound-hosts, squeeze
+    hostgroups: computers, apache2-hosts, sw-raid, acpid-hosts, hasorgfs, service, apache-https, squeeze
     contacts: bzed
 
   pergolesi:
@@ -507,12 +528,12 @@ servers:
   spontini:
     address: 206.12.19.14
     parents: gw-ubc
-    hostgroups: computers, buildd, hasbootfs, hassrvfs, sparc, lenny, squeeze
+    hostgroups: computers, buildd, hasbootfs, hassrvfs, sparc, squeeze
     contacts: lfilipoz
   ravel:
     address: 206.12.19.5
     parents: tchaikovsky
-    hostgroups: computers, general, dl385, apache2-hosts, acpid-hosts, hasbootfs, nfs-server, rsyncd-hosts, bind9-hosts, uploadqueue, hasorgfs, heavy-exim, xinetd-hosts, lenny
+    hostgroups: computers, general, dl385, apache2-hosts, acpid-hosts, hasbootfs, nfs-server, rsyncd-hosts, bind9-hosts, uploadqueue, hasorgfs, heavy-exim, xinetd-hosts, squeeze
   dijkstra:
     address: 206.12.19.218
     parents: tchaikovsky
@@ -547,7 +568,7 @@ servers:
   bellini:
     address: 206.12.19.7
     parents: gw-ubc
-    hostgroups: computers, hasbootfs, nfs-client, hassrvfs, aacraid, heavy-exim, service, apache2-hosts, lenny
+    hostgroups: computers, hasbootfs, nfs-client, hassrvfs, aacraid, heavy-exim, service, apache2-hosts, squeeze, autofs
   morricone:
     address: 206.12.19.9
     parents: tchaikovsky
@@ -559,7 +580,7 @@ servers:
   paganini:
     address: 206.12.19.10
     parents: tchaikovsky
-    hostgroups: computers, hasbootfs, aacraid, hassrvfs, xinetd-hosts, nfs-client, service, apache2-hosts, lenny
+    hostgroups: computers, hasbootfs, aacraid, hassrvfs, xinetd-hosts, nfs-client, service, apache2-hosts, squeeze, autofs
   respighi:
     address: 206.12.19.11
     parents: gw-ubc
@@ -567,7 +588,7 @@ servers:
   vivaldi:
     address: 206.12.19.12
     parents: tchaikovsky
-    hostgroups: computers, hasbootfs, aacraid, hassrvfs, apache2-hosts, postgres84-hosts, service, apache-https, lenny
+    hostgroups: computers, hasbootfs, aacraid, hassrvfs, apache2-hosts, postgres84-hosts, service, apache-https, lenny, autofs
   # MSA 2000 (2012i)
   giustini:
     address: 192.168.2.6
@@ -623,7 +644,7 @@ servers:
   quantz:
     address: 206.12.19.122
     parents: salieri
-    hostgroups: computers, service, hasbootfs, kvmdomains, squeeze, hassrvfs, nfs-client, xinetd-hosts, heavy-exim, postgres84-hosts, apache2-hosts
+    hostgroups: computers, service, hasbootfs, kvmdomains, squeeze, hassrvfs, nfs-client, xinetd-hosts, heavy-exim, postgres84-hosts, apache2-hosts, autofs
   nono:
     address: 206.12.19.123
     parents: salieri
@@ -639,16 +660,24 @@ servers:
   glinka:
     address: 206.12.19.126
     parents: traetta
-    hostgroups: computers, service, hasbootfs, kvmdomains, squeeze, apache2-hosts, nfs-client, xinetd-hosts
+    hostgroups: computers, service, hasbootfs, kvmdomains, squeeze, apache2-hosts, nfs-client, xinetd-hosts, autofs
+  dukas:
+    address: 206.12.19.128
+    parents: traetta
+    hostgroups: computers, service, hasbootfs, kvmdomains, squeeze, apache2-hosts, hassrvfs
+  tye:
+    address: 206.12.19.129
+    parents: traetta
+    hostgroups: computers, service, hasbootfs, kvmdomains, squeeze, apache2-hosts, nfs-client, autofs, hassrvfs
 
   lebrun:
     address: 193.198.184.10
     parents: gw-carnet
-    hostgroups: computers, buildd, sw-raid, hasorgfs, sparc, lenny
+    hostgroups: computers, buildd, sw-raid, hasorgfs, sparc, squeeze
   schroeder:
     address: 193.198.184.11
     parents: gw-carnet
-    hostgroups: computers, buildd, sw-raid, hassrvfs, sparc, lenny
+    hostgroups: computers, buildd, sw-raid, hassrvfs, sparc, squeeze
 
   tartini:
     address: 82.94.249.158
@@ -668,12 +697,12 @@ servers:
 
   zelenka:
     address: 80.245.147.40
-    parents: gw-HP-ftc
-    hostgroups: computers, porterbox, hassrvfs, xinetd-hosts, lenny
+    parents: gw-zivit
+    hostgroups: computers, porterbox, hassrvfs, squeeze
   zandonai:
     address: 80.245.147.46
-    parents: gw-HP-ftc
-    hostgroups: computers, buildd, hassrvfs, lenny
+    parents: gw-zivit
+    hostgroups: computers, buildd, hassrvfs, squeeze
 
   goedel:
     address: 213.188.99.214
@@ -688,11 +717,11 @@ servers:
   praetorius:
     address: 130.239.18.121
     parents: gw-aca
-    hostgroups: computers, buildd, hassrvfs, lenny
+    hostgroups: computers, buildd, hassrvfs, squeeze
   pettersson:
     address: 130.239.18.123
     parents: gw-aca
-    hostgroups: computers, hasbootfs, aacraid, nfs-client, acpid-hosts, service, apache2-hosts, squeeze
+    hostgroups: computers, hasbootfs, aacraid, nfs-client, acpid-hosts, service, apache2-hosts, squeeze, autofs
 
 #  lafayette:
 #    address: 147.215.7.160
@@ -757,7 +786,7 @@ servers:
   merikanto:
     address: 86.59.118.147
     parents: gw-sil
-    hostgroups: computers, dl360, acpid-hosts, spamd, heavy-exim, nfs-client, rsyncd-hosts, xinetd-hosts, service, mail-relay, squeeze
+    hostgroups: computers, dl360, acpid-hosts, spamd, heavy-exim, nfs-client, rsyncd-hosts, xinetd-hosts, service, mail-relay, squeeze, autofs
   merikanto2:
     address: 86.59.118.150
     parents: merikanto
@@ -765,7 +794,7 @@ servers:
   englund:
     address: 86.59.118.148
     parents: gw-sil
-    hostgroups: computers, acpid-hosts, service, apache2-hosts, squeeze
+    hostgroups: computers, acpid-hosts, service, apache2-hosts, squeeze, hassrvfs
     # which raid?
   lindberg:
     address: 86.59.118.149
@@ -801,11 +830,11 @@ servers:
   poulenc:
     address: 144.32.168.77
     parents: gw-ynic
-    hostgroups: computers, buildd, sw-raid, hassrvfs, lenny
+    hostgroups: computers, buildd, sw-raid, hassrvfs, squeeze
   porpora:
     address: 144.32.168.78
     parents: gw-ynic
-    hostgroups: computers, buildd, sw-raid, hassrvfs, lenny
+    hostgroups: computers, buildd, sw-raid, hassrvfs, squeeze
 
   santoro:
     address: 200.17.202.197
@@ -975,6 +1004,9 @@ hostgroups:
   nfs-server:
     alias: hosts serving filesystems using NFS
     private: 1
+  autofs:
+    alias: hosts running the automounter
+    private: 1
 
   highload:
     alias: "hosts on which high load is normal"
@@ -1309,17 +1341,20 @@ services:
     nrpe: "/usr/lib/nagios/plugins/dsa-check-file -w -f /etc/ferm/ferm.conf"
     hostgroups: computers
     excludehostgroups: freebsd
+    excludehosts: vasks, wagner
   -
     name: puppetized firewall
     nrpe: "/usr/lib/nagios/plugins/dsa-check-file -w -f /etc/ferm/conf.d/defs.conf"
     hostgroups: computers
     excludehostgroups: freebsd
+    excludehosts: vasks, wagner
 
  ####
   -
     name: process - samhain
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:8 -c 1: -u root -C samhain -a '/usr/sbin/samhain'"
     hostgroups: computers
+    excludehosts: vasks, wagner
   -
     name: samhain
     servicegroups: samhain
@@ -1328,6 +1363,7 @@ services:
     depends: process - samhain
     normal_check_interval: 60
     retry_check_interval: 5
+    excludehosts: vasks, wagner
 
  ####
   -
@@ -1424,33 +1460,35 @@ services:
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:2 -c 1: -u root -C munin-node -a '/usr/sbin/munin-node'"
     hostgroups: computers
     excludehostgroups: freebsd
+    excludehosts: vasks, wagner
   -
     name: process - munin-node
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:2 -c 1: -u root -C perl -a '/usr/bin/perl -wT /usr/sbin/munin-node'"
     hostgroups: freebsd
+    excludehosts: vasks, wagner
   -
     name: network service - munin-node
     check: check_tcp!4949
     hostgroups: computers
     depends: process - munin-node
+    excludehosts: vasks, wagner
  ###
   -
     name: process - ntpd
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -p 1 -C ntpd -a '/usr/sbin/ntpd -p /var/run/ntpd.pid'"
     hostgroups: computers
-    excludehosts: zelenka
   -
     name: network service - ntp
     check: dsa_check_ntp
     hostgroups: computers
     depends: process - ntpd
-    excludehosts: zelenka, ancina
+    excludehosts: ancina
     excludehostgroups: ntpsuckers
   #
   -
     name: network service - time
     check: dsa_check_time
-    hosts: zelenka, ancina
+    hosts: ancina
     depends: process - xinetd
 
  ###
@@ -1470,17 +1508,20 @@ services:
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C syslog-ng  -a '/sbin/syslog-ng -p /var/run/syslog-ng.pid'"
     hostgroups: computers
     excludehostgroups: freebsd
+    excludehosts: vasks, wagner
 
   -
     name: process - syslog-ng
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 2:2 -c 2: -u root -C syslog-ng  -a '/sbin/syslog-ng -p /var/run/syslog-ng.pid'"
     hostgroups: freebsd
+    excludehosts: vasks, wagner
 
   -
     name: remote logging
     remotecheck: "/usr/lib/nagios/plugins/dsa-check-log-age-loghost $HOSTNAME$"
     runfrom: heininen
     hostgroups: computers
+    excludehosts: vasks, wagner
  ### MAIL STUFF
  ###
   -
@@ -1733,23 +1774,28 @@ services:
   -
     name: system - available entropy
     nrpe: "/usr/lib/nagios/plugins/dsa-check-entropy"
+    event_handler: dsa_event_handler_restart_ekey
     hostgroups: computers
+    excludehosts: vasks, wagner
     excludehostgroups: freebsd
  ###
   -
     name: local resolver
     nrpe: "/usr/lib/nagios/plugins/dsa-check-resolver www.debian.org www.google.com"
     hostgroups: computers
+    excludehosts: vasks, wagner
     normal_check_interval: 60
   -
     name: process - unbound
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u unbound -C unbound -a '/usr/sbin/unbound'"
+    excludehosts: vasks, wagner
     hostgroups: unbound-hosts, squeeze
  ###
   -
     name: process - uptimed
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u daemon -C uptimed -a '/usr/sbin/uptimed'"
     hostgroups: computers
+    excludehosts: vasks, wagner
  ###
   -
     name: unwanted process - irqbalance
@@ -1784,7 +1830,7 @@ services:
     name: unwanted process - inetd
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C inetd"
     hostgroups: computers
-    excludehosts: grieg, byrd
+    excludehosts: grieg, byrd, abel, alwyn
   -
     name: unwanted process - snmpd
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C snmpd"
@@ -1820,6 +1866,7 @@ services:
     name: process - monit
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u root -C monit -a '/usr/sbin/monit -d 300 -I -c /etc/monit/monitrc -s /var/lib/monit/monit.state'"
     hostgroups: computers
+    excludehosts: vasks, wagner
   -
     name: process - cpqarrayd
     servicegroups: raid
@@ -1843,6 +1890,7 @@ services:
     nrpe: "/usr/lib/nagios/plugins/dsa-check-hpacucli"
     normal_check_interval: 120
     hostgroups: dl385, dl380, dl360, bl460
+    excludehosts: kassia
   -
     name: HW - hpacucli enclosure status
     servicegroups: raid
@@ -1855,6 +1903,12 @@ services:
     nrpe: "/usr/lib/nagios/plugins/dsa-check-hpacucli --ignore-transfer-speed=1I:1:1 --ignore-transfer-speed=1I:1:2"
     normal_check_interval: 120
     hostgroups: dl585
+  -
+    name: HW - hpacucli status
+    servicegroups: raid
+    nrpe: "/usr/lib/nagios/plugins/dsa-check-hpacucli --ignore-transfer-speed=1I:1:2 --ignore-transfer-speed=1I:1:3 --ignore-transfer-speed=1I:1:4 --ignore-transfer-speed=2I:1:5 --ignore-transfer-speed=2I:1:6"
+    normal_check_interval: 120
+    hosts: kassia
  ###
   -
     name: HW - hpasmcli status
@@ -1925,10 +1979,12 @@ services:
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C ulogd -a '/usr/sbin/ulogd -d'"
     hostgroups: computers
     excludehostgroups: freebsd, sparc
+    excludehosts: vasks, wagner
   -
     name: unexpected process - ulogd
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C ulogd"
     hostgroups: freebsd, sparc
+    excludehosts: vasks, wagner
 
  ###
   -
@@ -2264,15 +2320,14 @@ services:
     servicegroups: buildd
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:5 -u buildd -C perl -a '/usr/bin/buildd'"
     hosts: fano, fasch, field, finzi
-    contacts: luk, pkern, HE
-
+    contact_groups: buildd
   -
     name: process - buildd
     servicegroups: buildd
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:5 -u buildd -C buildd -a '/usr/bin/buildd'"
     hostgroups: buildd
     excludehosts: fano, fasch, field, finzi
-    contacts: luk, pkern, HE
+    contact_groups: buildd
 
  ###
   #-
@@ -2327,6 +2382,16 @@ services:
     name: nfs server stabile reachable
     nrpe: "/usr/lib/nagios/plugins/check_ping -H 192.168.2.13 -w 50,10% -c 200,30%"
     hosts: quantz
+  #
+  -
+    name: process - automount
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C automount -a '/usr/sbin/automount'"
+    hostgroups: autofs
+  -
+    name: unwanted process - automount
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 0 -C automount"
+    hostgroups: computers
+    excludehostgroups: autofs
 
  ############ MISC OTHER Stuff ############
  #####