[project @ peter@palfrader.org-20080404195211-jv8swbls9i41q7xr]
[mirror/dsa-nagios.git] / nagios-master.cfg
index 038459d..379faf6 100644 (file)
@@ -6,7 +6,40 @@
 
 # TODO
 #  - raff:  identd, hpasmd
+#  - spohr: hpasmd
 #  - *: mailq
+#  - *: check munin stats collection works
+#  - *: check backups are successful
+#  - goetz: gmond/gmetad
+#  -
+#  - agnesi
+#  - bruckner
+#  - caballero
+#  - casals
+#  - crest
+#  - elara
+#  - europa
+#  - goedel
+#  - kassia
+#  - kullervo
+#  - lebrun
+#  - leisner
+#  - liszt
+#  - malo
+#  - mayer
+#  - mayr
+#  - mundy
+#  - murphy
+#  - paer
+#  - piatti
+#  - puccini
+#  - ravel
+#  - sarti
+#  - schulz
+#  - spontini
+#  - tartini
+#  - verdi
+#  - voltaire
 
 ---
 #############################
@@ -33,43 +66,164 @@ servers:
     address: 140.211.166.1
     parents: gw-HP-ftc
     hostgroups: routing-infrastructure
+  gw-scanplus-villa:
+    address: 212.211.132.1
+    parents: gw-HP-ftc
+    hostgroups: routing-infrastructure
+  gw-scanplus-lobos:
+    address: 212.211.132.249
+    parents: gw-HP-ftc
+    hostgroups: routing-infrastructure
+  gw-mit-csail:
+    address: 128.30.0.254
+    parents: gw-HP-ftc
+    hostgroups: routing-infrastructure
+  gw-xs4all:
+    address: 194.109.137.217
+    parents: gw-HP-ftc
+    hostgroups: routing-infrastructure
+  gw-umn.edu:
+    address: 128.101.240.222
+    parents: gw-HP-ftc
+    hostgroups: routing-infrastructure
+  gw-dg-i.net:
+    address: 195.49.152.190
+    parents: gw-HP-ftc
+    hostgroups: routing-infrastructure
+  gw-freenet:
+    address: 62.104.23.249
+    parents: gw-HP-ftc
+    hostgroups: routing-infrastructure
+  gw-topalis:
+    address: 195.243.109.254
+    parents: gw-HP-ftc
+    hostgroups: routing-infrastructure
+  gw-sanger:
+    address: 193.62.202.18
+    parents: gw-HP-ftc
+    hostgroups: routing-infrastructure
+  gw-cst:
+    address: 213.188.99.215
+    parents: gw-HP-ftc
+    hostgroups: routing-infrastructure
 
   samosa:
     address: 192.25.206.57
-    hostgroups: computers, dl380, apache2-hosts, bind9-hosts
+    hostgroups: computers, service, dl380, apache2-hosts, bind9-hosts, heavy-email
   raff:
     address: 192.25.206.59
     parents: samosa
-    hostgroups: computers, dl380, apache1-hosts, bind9-hosts, rsyncd-hosts
+    hostgroups: computers, service, dl380, apache1-hosts, bind9-hosts, rsyncd-hosts, heavy-email
+  gluck:
+    address: 192.25.206.10
+    parents: samosa
+    hostgroups: computers, general, dl380, apache1-hosts, bind9-hosts, rsyncd-hosts, heavy-email
+  merkel:
+    address: 192.25.206.16
+    parents: samosa
+    hostgroups: computers, general, apache1-hosts, bind9-hosts, rsyncd-hosts, sw-raid, postgres81-hosts, heavy-email
+  spohr:
+    address: 192.25.206.33
+    parents: samosa
+    hostgroups: computers, service, dl380, apache2-hosts, postgres81-hosts
+  peri:
+    address: 192.25.206.15
+    parents: samosa
+    hostgroups: computers, buildd, sw-raid
+  penalosa:
+    address: 192.25.206.68
+    parents: samosa
+    hostgroups: computers, buildd, sw-raid
 
   bartok:
     address: 82.195.75.91
     parents: gw-MAN-DA-debian
-    hostgroups: computers, syslog-ng-hosts, postfix-hosts, dl385
+    hostgroups: computers, service, syslog-ng-hosts, postfix-hosts, dl385
   sperger:
     address: 82.195.75.98
     parents: gw-MAN-DA-debian
     hostgroups: computers, porterbox, sw-raid
+  agricola:
+    address: 82.195.75.86
+    parents: gw-MAN-DA-debian
+    hostgroups: computers, porterbox, sw-raid
+  arcadelt:
+    address: 82.195.75.87
+    parents: gw-MAN-DA-debian
+    hostgroups: computers, buildd, sw-raid
 
   master:
     address: 70.103.162.29
     parents: gw-brainfood
-    hostgroups: computers, apache2-hosts, bind9-hosts
+    hostgroups: computers, general, apache2-hosts, bind9-hosts, heavy-email
 
   ries:
     address: 128.148.34.103
     parents: gw-osuosl
-    hostgroups: computers, apache2-hosts, bind9-hosts, ftpd-hosts, dl385, rsyncd-hosts
+    hostgroups: computers, service, apache2-hosts, bind9-hosts, ftpd-hosts, dl385, rsyncd-hosts, postgres81-hosts, heavy-email
 
   rietz:
     address: 140.211.166.43
     parents: gw-brown.edu
-    hostgroups: computers, apache2-hosts, bind9-hosts, rsyncd-hosts, dl385
+    hostgroups: computers, service, apache2-hosts, bind9-hosts, rsyncd-hosts, dl385, heavy-email
   rietz2:
     address: 140.211.166.44
     parents: rietz
     hostgroups: secondary-IPs
 
+  villa:
+    address: 212.211.132.32
+    parents: gw-scanplus-villa
+    hostgroups: computers, service, apache2-hosts, ftpd-hosts, rsyncd-hosts, dl380
+  lobos:
+    address: 212.211.132.250
+    parents: gw-scanplus-lobos
+    hostgroups: computers, service, apache2-hosts, ftpd-hosts, rsyncd-hosts, dl380
+
+  steffani:
+    address: 128.31.0.36
+    parents: gw-mit-csail
+    hostgroups: computers, service, apache2-hosts, ftpd-hosts, rsyncd-hosts, sw-raid
+
+  klecker:
+    address: 194.109.137.218
+    parents: gw-xs4all
+    hostgroups: computers, service, apache2-hosts, ftpd-hosts, rsyncd-hosts, bind9-hosts, dl385, postgres81-hosts, heavy-email
+
+  saens:
+    address: 128.101.240.212
+    parents: gw-umn.edu
+    hostgroups: computers, service, apache2-hosts, ftpd-hosts, rsyncd-hosts, dl380, heavy-email
+
+  argento:
+    address: 195.49.152.174
+    parents: gw-dg-i.net
+    hostgroups: computers, buildd, sw-raid
+
+  pergolesi:
+    address: 62.104.23.252
+    parents: gw-freenet
+    hostgroups: computers, porterbox, sw-raid
+
+  raptor:
+    address: 195.243.109.162
+    parents: gw-topalis
+    hostgroups: computers, porterbox
+
+  albeniz:
+    address: 193.62.202.27
+    parents: gw-sanger
+    hostgroups: computers, porterbox, sw-raid
+  goetz:
+    address: 193.62.202.26
+    parents: gw-sanger
+    hostgroups: computers, buildd, sw-raid
+
+  escher:
+    address: 213.188.99.215
+    parents: gw-cst
+    hostgroups: computers, porterbox
+
 #############################
 # host groups
 #
@@ -86,7 +240,22 @@ hostgroups:
     extinfo-icon_image_alt: router
 
   porterbox:
-    alias: developer accessible porter machien
+    alias: developer accessible porter machines
+    extinfo-icon_image: base/debian.png
+    extinfo-icon_image_alt: Debian GNU/Linux
+    extinfo-notes_url: http://db.debian.org/machines.cgi?host=%s
+  service:
+    alias: machines running services
+    extinfo-icon_image: base/debian.png
+    extinfo-icon_image_alt: Debian GNU/Linux
+    extinfo-notes_url: http://db.debian.org/machines.cgi?host=%s
+  buildd:
+    alias: buildd systems
+    extinfo-icon_image: base/debian.png
+    extinfo-icon_image_alt: Debian GNU/Linux
+    extinfo-notes_url: http://db.debian.org/machines.cgi?host=%s
+  general:
+    alias: general purpose developer accessible machines
     extinfo-icon_image: base/debian.png
     extinfo-icon_image_alt: Debian GNU/Linux
     extinfo-notes_url: http://db.debian.org/machines.cgi?host=%s
@@ -107,6 +276,9 @@ hostgroups:
   postfix-hosts:
     alias: hosts running postfix instead of exim
     private: 1
+  heavy-email:
+    alias: "hosts running the full mail stuff, including clamav, SA, and greylistd"
+    private: 1
   apache2-hosts:
     alias: hosts running apache2
     private: 1
@@ -122,6 +294,9 @@ hostgroups:
   rsyncd-hosts:
     alias: hosts providing rsync services via xinetd
     private: 1
+  postgres81-hosts:
+    alias: hosts running postgres81
+    private: 1
 
   secondary-IPs:
     alias: secondary IP addresses
@@ -152,23 +327,43 @@ services:
   -
     name: disk usage on /boot
     nrpe: "/usr/lib/nagios/plugins/check_disk 60 80 /boot"
-    hosts: sperger
+    hosts: sperger, rietz, steffani, penalosa, peri, albeniz, escher, goetz
   -
     name: disk usage on /var
     nrpe: "/usr/lib/nagios/plugins/check_disk 50 75 /var"
-    hosts: bartok, samosa
+    hosts: bartok, samosa, raff, lobos, villa, gluck, saens, escher
   -
     name: disk usage on /org
     nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /org"
-    hosts: bartok, sperger, samosa
+    hosts: bartok, sperger, samosa, raff, lobos, villa, steffani, merkel, saens, pergolesi
+  -
+    name: disk usage on /srv
+    nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /srv"
+    hosts: agricola, arcadelt, argento
+  -
+    name: disk usage on /org/scratch2
+    nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /org/scratch2"
+    hosts: merkel
+  -
+    name: disk usage on /oldorg
+    nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /oldorg"
+    hosts: merkel
   -
     name: disk usage on /tmp
     nrpe: "/usr/lib/nagios/plugins/check_disk 60 80 /tmp"
-    hosts: samosa
+    hosts: samosa, raff, gluck, saens, escher
   -
     name: disk usage on /usr
     nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /usr"
-    hosts: samosa
+    hosts: samosa, raff, lobos, villa, gluck, saens, pergolesi
+  -
+    name: disk usage on /home
+    nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /home"
+    hosts: gluck, raptor, escher
+  -
+    name: disk usage on /chroot
+    nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /chroot"
+    hosts: raptor
 
  ############ All Computers ############
  ####
@@ -255,11 +450,20 @@ services:
     # etch: nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u ntp -C ntpd -a '/usr/sbin/ntpd -p /var/run/ntpd.pid'"
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -C ntpd -a '/usr/sbin/ntpd -p /var/run/ntpd.pid'"
     hostgroups: computers
+    excludehosts: raptor
   -
     name: network service - ntp
     check: check_ntp
     hostgroups: computers
     depends: process - ntpd
+    excludehosts: raptor
+  #
+  -
+    name: network service - time
+    check: check_time
+    hosts: raptor
+    depends: process - xinetd
+
  ###
   -
     name: process - atd
@@ -295,47 +499,53 @@ services:
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u Debian-exim -C exim4 -a '/usr/sbin/exim4 -bd -q'"
     hostgroups: computers
     excludehostgroups: postfix-hosts
-    excludehosts: master, rietz
+    excludehosts: master, rietz, merkel
   -
     name: process - exim - total
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:50 -c 1: -C exim4"
     hostgroups: computers
     excludehostgroups: postfix-hosts
-    excludehosts: master, rietz
+    excludehosts: master, rietz, merkel
   -
     name: process - exim
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:300 -c 1:500 -C exim4 -a '/usr/sbin/exim4'"
-    hosts: master, rietz
+    hosts: master, rietz, merkel
  ###
   -
     name: process - clamav - clamd
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:2 -c 1: -u clamav -C clamd -a '/usr/sbin/clamd'"
-    hostgroups: computers
-    excludehostgroups: postfix-hosts
+    hostgroups: heavy-email
   -
     name: service - clamav
     nrpe: "/usr/lib/nagios/plugins/check_clamd -H /var/run/clamav/clamd.ctl"
-    hostgroups: computers
-    excludehostgroups: postfix-hosts
+    hostgroups: heavy-email
     depends: process - clamav - clamd
   -
     name: process - clamav - freshclam
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u clamav -C freshclam -a '/usr/bin/freshclam -d --quiet'"
+    hostgroups: heavy-email
+  #
+  -
+    name: unwanted process - clamav
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C clamd"
     hostgroups: computers
-    excludehostgroups: postfix-hosts
+    excludehostgroups: heavy-email
+  -
+    name: unwanted process - freshclam
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C freshclam"
+    hostgroups: computers
+    excludehostgroups: heavy-email
  ###
   -
     name: process - spamd - master
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C spamd -a '/usr/sbin/spamd --create-prefs --max-children 5 --helper-home-dir -d --pidfile=/var/run/spamd.pid'"
     #hosts: samosa
-    hostgroups: computers
-    excludehostgroups: postfix-hosts
+    hostgroups: heavy-email
     excludehosts: rietz
   -
     name: process - spamd - child
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:6 -c 1: -C spamd -a 'spamd child'"
-    hostgroups: computers
-    excludehostgroups: postfix-hosts
+    hostgroups: heavy-email
     depends: process - spamd - master
     excludehosts: rietz
   #
@@ -347,13 +557,25 @@ services:
     name: process - spamd - child
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:6 -c 1: -u debbugs -C spamd -a 'spamd child'"
     hosts: rietz
+  #
+  -
+    name: unwanted process - spamd
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C spamd"
+    hostgroups: computers
+    excludehostgroups: heavy-email
 
  ###
   -
     name: process - greylistd
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u greylist -C greylistd -a '/usr/bin/python /usr/sbin/greylistd'"
+    hostgroups: heavy-email
+  #
+  -
+    name: unwanted process - greylistd
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C greylistd"
     hostgroups: computers
-    excludehostgroups: postfix-hosts
+    excludehostgroups: heavy-email
+
 
  ###
   -
@@ -408,6 +630,19 @@ services:
     depends: process - postfix - master
 
 
+ ###
+  -
+    name: network service - smtp
+    check: check_smtp
+    hostgroups: postfix-hosts
+    depends: process - postfix - master
+  -
+    name: network service - smtp
+    check: check_smtp
+    hostgroups: computers
+    excludehostgroups: postfix-hosts
+    depends: process - exim
+
 
  ###
   -
@@ -419,6 +654,7 @@ services:
     name: process - irqbalance
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C irqbalance -a '/usr/sbin/irqbalance'"
     hostgroups: computers
+    excludehosts: arcadelt, agricola, argento, penalosa, peri, escher
 
 
 
@@ -464,18 +700,18 @@ services:
   -
     name: process - udevd
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C udevd -a 'udevd'"
-    hosts: sperger, ries
+    hosts: sperger, ries, steffani, merkel, spohr, peri, penalosa, albeniz, escher
  ###
   -
     name: process - acpid
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C acpid -a '/usr/sbin/acpid -c /etc/acpi/events -s /var/run/acpid.socket'"
-    hosts: ries
+    hosts: ries, steffani
 
  ###
   -
     name: process - xinetd
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C xinetd -a '/usr/sbin/xinetd -pidfile /var/run/xinetd.pid -stayalive'"
-    hosts: samosa
+    hosts: samosa, raptor
     hostgroups: rsyncd-hosts
  ###
   -
@@ -531,7 +767,7 @@ services:
     hostgroups: apache1-hosts
   -
     name: process - apache - worker
-    nrpe: "/usr/lib/nagios/plugins/check_procs -w 2:50 -c 1:100 -u www-data -C apache -a /usr/sbin/apache"
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 2:75 -c 1:150 -u www-data -C apache -a /usr/sbin/apache"
     hostgroups: apache1-hosts
     depends: process - apache - master
   -
@@ -591,3 +827,43 @@ services:
     name: process - debianqueued
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u dak -C debianqueued -a '/usr/bin/perl -w ./debianqueued'"
     hosts: ries
+
+ ###
+  -
+    name: process - postresql81 - master
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postgres -C postmaster -a '/usr/lib/postgresql/8.1/bin/postmaster -D /var/lib/postgresql/8.1/main -c config_file=/etc/postgresql/8.1/main/postgresql.conf'"
+    hostgroups: postgres81-hosts
+  -
+    name: process - postresql81 - writer
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postgres -C postmaster -a 'postgres: writer process'"
+    hostgroups: postgres81-hosts
+    depends: process - postresql81 - master
+  -
+    name: process - postresql81 - buffer
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postgres -C postmaster -a 'postgres: stats buffer process'"
+    hostgroups: postgres81-hosts
+    depends: process - postresql81 - master
+  -
+    name: process - postresql81 - collector
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postgres -C postmaster -a 'postgres: stats collector process'"
+    hostgroups: postgres81-hosts
+    depends: process - postresql81 - master
+
+ ####
+  # XXX is this needed
+  -
+    name: process - snmpd
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u snmp -C snmpd -a '/usr/sbin/snmpd -Lsd -Lf /dev/null -u snmp -I -smux -p /var/run/snmpd.pid 127.0.0.1'"
+    hosts: lobos, villa
+
+ ###
+  -
+    name: process - buildd
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u buildd -C buildd '/usr/bin/perl /usr/bin/buildd'"
+    hostgroups: buildd
+
+ ###
+  -
+    name: process - iscsid
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 2:2 -c 1: -u root -C iscsid '/usr/sbin/iscsid'"
+    hosts: raptor