[project @ peter@palfrader.org-20080404155756-n0s42jq7enwqhve2]
[mirror/dsa-nagios.git] / nagios-master.cfg
index 8637c8a..1a06b3d 100644 (file)
@@ -3,6 +3,48 @@
 # Strings ought to be in double quotes, but it works in most cases if they aren't :)
 #
 # vim:set syntax=yaml:
+
+# TODO
+#  - raff:  identd, hpasmd
+#  - spohr: hpasmd
+#  - *: mailq
+#  - *: check munin stats collection works
+#  - *: check backups are successful
+#  -
+#  - agnesi
+#  - albeniz
+#  - bruckner
+#  - caballero
+#  - casals
+#  - crest
+#  - elara
+#  - escher
+#  - europa
+#  - goedel
+#  - goetz
+#  - kassia
+#  - kullervo
+#  - lebrun
+#  - leisner
+#  - liszt
+#  - malo
+#  - mayer
+#  - mayr
+#  - mundy
+#  - murphy
+#  - paer
+#  - pergolesi
+#  - piatti
+#  - puccini
+#  - raptopr
+#  - ravel
+#  - sarti
+#  - schulz
+#  - spontini
+#  - tartini
+#  - verdi
+#  - voltaire
+
 ---
 #############################
 # hosts
 servers:
   gw-MAN-DA-debian:
     address: 82.195.75.126
+    parents: gw-HP-ftc
+    hostgroups: routing-infrastructure
+  gw-HP-ftc:
+    address: 192.25.206.1
+    parents: samosa
+    hostgroups: routing-infrastructure
+  gw-brainfood:
+    address: 70.103.162.1
+    parents: gw-HP-ftc
+    hostgroups: routing-infrastructure
+  gw-brown.edu:
+    address: 128.148.34.1
+    parents: gw-HP-ftc
+    hostgroups: routing-infrastructure
+  gw-osuosl:
+    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
+
+  samosa:
+    address: 192.25.206.57
+    hostgroups: computers, service, dl380, apache2-hosts, bind9-hosts, heavy-email
+  raff:
+    address: 192.25.206.59
+    parents: samosa
+    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
+  penalosa:
+    address: 192.25.206.68
+    parents: samosa
+    hostgroups: computers, buildd
 
   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, sw-raid
+    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, general, apache2-hosts, bind9-hosts, heavy-email
+
+  ries:
+    address: 128.148.34.103
+    parents: gw-osuosl
+    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, 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
 
 #############################
 # host groups
@@ -30,14 +197,35 @@ servers:
 hostgroups:
   computers:
     alias: computers
+    private: 1
   routing-infrastructure:
     alias: Internet routers and friends
+    extinfo-icon_image: base/switch40.png
+    extinfo-icon_image_alt: router
 
-  syslog-ng-hosts:
-    alias: syslog-ng-hosts
-    private: 1
-  postfix-hosts:
-    alias: postfix-hosts
+  porterbox:
+    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
+
+  dl380:
+    alias: HP DL380 hosts
     private: 1
   dl385:
     alias: HP DL385 hosts
@@ -46,6 +234,38 @@ hostgroups:
     alias: Hosts with Linux software raid
     private: 1
 
+  syslog-ng-hosts:
+    alias: hosts running syslog-ng instead of sysklogd
+    private: 1
+  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
+  apache1-hosts:
+    alias: hosts running apache1
+    private: 1
+  bind9-hosts:
+    alias: hosts running bind9
+    private: 1
+  ftpd-hosts:
+    alias: hosts running vsftpd
+    private: 1
+  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
+    private: 1
+
 #############################
 # services
 #############################
@@ -71,15 +291,39 @@ services:
   -
     name: disk usage on /boot
     nrpe: "/usr/lib/nagios/plugins/check_disk 60 80 /boot"
-    hosts: sperger
+    hosts: sperger, rietz, steffani, penalosa, peri
   -
     name: disk usage on /var
     nrpe: "/usr/lib/nagios/plugins/check_disk 50 75 /var"
-    hosts: bartok
+    hosts: bartok, samosa, raff, lobos, villa, gluck, saens
   -
     name: disk usage on /org
     nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /org"
-    hosts: bartok, sperger
+    hosts: bartok, sperger, samosa, raff, lobos, villa, steffani, merkel, saens
+  -
+    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, raff, gluck, saens
+  -
+    name: disk usage on /usr
+    nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /usr"
+    hosts: samosa, raff, lobos, villa, gluck, saens
+  -
+    name: disk usage on /home
+    nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /home"
+    hosts: gluck
 
  ############ All Computers ############
  ####
@@ -199,29 +443,90 @@ services:
     hostgroups: computers
     excludehostgroups: syslog-ng-hosts
 
+ ### MAIL STUFF
  ###
   -
     name: process - exim
-    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u Debian-exim -C exim4 -a '/usr/sbin/exim4 -bd -q30m'"
+    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, 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, 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, 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: 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: heavy-email
+    depends: process - spamd - master
+    excludehosts: rietz
+  #
+  -
+    name: process - spamd - master
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u debbugs -C spamd -a '/usr/sbin/spamd -d '"
+    hosts: rietz
+  -
+    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: heavy-email
+
 
  ###
   -
@@ -276,6 +581,33 @@ 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
+
+
+ ###
+  -
+    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
+ ###
+  -
+    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
+
+
 
  ############ Processes/Services that only run on some computers ############
  ####
@@ -295,19 +627,188 @@ services:
     name: process - mdadm monitor
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u root -C mdadm -a '/sbin/mdadm --monitor --pid-file /var/run/mdadm/monitor.pid --daemonise --scan'"
     hostgroups: sw-raid
+  -
+    name: RAID - sw raid
+    nrpe: "/usr/lib/nagios/plugins/dsa-check-raid-sw"
+    hostgroups: sw-raid
 
  ###
   -
     name: process - cpqarrayd
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u root -C cpqarrayd -a '/usr/sbin/cpqarrayd'"
-    hostgroups: dl385
- ###
+    hostgroups: dl385, dl380
   -
     name: RAID - arrayprobe
     nrpe: "sudo /usr/bin/arrayprobe"
-    hostgroups: dl385
+    hostgroups: dl385, dl380
+
  ###
   -
-    name: RAID - sw raid
-    nrpe: "/usr/lib/nagios/plugins/dsa-check-raid-sw"
-    hostgroups: sw-raid
+    name: process - slapd
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:20 -c 1:50 -u openldap -C slapd -a '/usr/sbin/slapd -g openldap -u openldap'"
+    hosts: samosa
+ ###
+  -
+    name: process - udevd
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C udevd -a 'udevd'"
+    hosts: sperger, ries, steffani, merkel, spohr, peri, penalosa
+ ###
+  -
+    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, 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
+    hostgroups: rsyncd-hosts
+ ###
+  -
+    name: network service - finger
+    check: check_tcp!79
+    hosts: samosa
+    depends: process - xinetd
+ ###
+  -
+    name: network service - rsync
+    check: check_tcp!873
+    hostgroups: rsyncd-hosts
+    depends: process - xinetd
+
+  -
+    name: network service - rsync
+    check: check_tcp!873
+    hosts: rietz2
+    depends: rietz:process - xinetd
+
+ ###
+  -
+    name: process - nagios1
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u nagios -C nagios -a '/usr/sbin/nagios -d /etc/nagios/nagios.cfg'"
+    hosts: samosa
+  -
+    name: process - nagios3
+    # it forks one instance to check, so make it -w 1:2
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:2 -c 1: -u nagios -C nagios3 -a '/usr/sbin/nagios3 -d /etc/nagios3/nagios.cfg'"
+    hosts: samosa
+
+ ###
+  -
+    name: process - apache2 - master
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u root -C apache2 -a /usr/sbin/apache2"
+    hostgroups: apache2-hosts
+  -
+    name: process - apache2 - worker
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 2:50 -c 1:100 -u www-data -C apache2 -a /usr/sbin/apache2"
+    hostgroups: apache2-hosts
+    depends: process - apache2 - master
+  -
+    name: network service - http
+    check: check_http
+    hostgroups: apache2-hosts
+    depends: process - apache2 - master
+
+
+
+  -
+    name: process - apache - master
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u root -C apache -a /usr/sbin/apache"
+    hostgroups: apache1-hosts
+  -
+    name: process - apache - worker
+    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
+  -
+    name: network service - http
+    check: check_http
+    hostgroups: apache1-hosts
+    depends: process - apache - master
+
+  -
+    name: network service - http keyserver
+    check: dsa_check_http_port!11371
+    hosts: raff
+    depends: process - apache - master
+
+  -
+    name: network service - https
+    check: check_https
+    hosts: samosa
+    depends: "process - apache2 - master"
+    normal_check_interval: 120
+    notification_interval: 120
+  -
+    name: network service - https cert
+    check: dsa_check_cert!443
+    hosts: samosa
+    depends: network service - https
+    normal_check_interval: 240
+    notification_interval: 240
+ ####
+  -
+    name: process - named
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:15 -c 1: -u bind -C named -a '/usr/sbin/named -u bind'"
+    hostgroups: bind9-hosts
+  -
+    name: network service - dns
+    check: check_dns
+    hostgroups: bind9-hosts
+    depends: process - named
+
+ ####
+  -
+    name: process - vsftp - listener
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u root -C vsftpd -a 'vsftpd: LISTENER'"
+    hostgroups: ftpd-hosts
+  -
+    name: process - vsftp - instance
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:10 -c 0:30 -u ftp -C vsftpd -a 'vsftpd: '"
+    hostgroups: ftpd-hosts
+  -
+    name: network service - ftp
+    check: check_ftp
+    hostgroups: ftpd-hosts
+    depends: process - vsftp - listener
+
+ ####
+  -
+    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