[project @ peter@palfrader.org-20080403173409-5p83lvwog8zjehy9]
[mirror/dsa-nagios.git] / nagios-master.cfg
index 28dbd93..ef2c682 100644 (file)
@@ -8,10 +8,62 @@
 # 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
+
+  samosa:
+    address: 192.25.206.57
+    hostgroups: computers, dl380, apache2-hosts, bind9-hosts
+  raff:
+    address: 192.25.206.59
+    parents: samosa
+    hostgroups: computers, dl380, apache1-hosts, bind9-hosts, rsyncd-hosts
+
   bartok:
     address: 82.195.75.91
-    parents: bartok-gw
-    hostgroups: computers
+    parents: gw-MAN-DA-debian
+    hostgroups: computers, syslog-ng-hosts, postfix-hosts, dl385
+  sperger:
+    address: 82.195.75.98
+    parents: gw-MAN-DA-debian
+    hostgroups: computers, porterbox, sw-raid
+
+  master:
+    address: 70.103.162.29
+    parents: gw-brainfood
+    hostgroups: computers, apache2-hosts, bind9-hosts
+
+  ries:
+    address: 128.148.34.103
+    parents: gw-brown.edu
+    hostgroups: computers, apache2-hosts, bind9-hosts, ftpd-hosts, dl385, rsyncd-hosts
+
+  rietz:
+    address: 140.211.166.43
+    parents: gw-brown.edu
+    hostgroups: computers, apache2-hosts, bind9-hosts, rsyncd-hosts, dl385
+  rietz2:
+    address: 140.211.166.44
+    parents: rietz
+    hostgroups: secondary-IPs
 
 #############################
 # host groups
@@ -22,6 +74,53 @@ 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
+
+  porterbox:
+    alias: developer accessible porter machien
+    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
+    private: 1
+  sw-raid:
+    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
+  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
+
+  secondary-IPs:
+    alias: secondary IP addresses
+    private: 1
 
 #############################
 # services
@@ -37,10 +136,34 @@ services:
 
  ############ Disk Usage ############
  ####
+  -
+    name: disk usage - all
+    nrpe: "/usr/lib/nagios/plugins/check_disk 90 95"
+    hostgroups: computers
   -
     name: disk usage on /
     nrpe: "/usr/lib/nagios/plugins/check_disk 60 80 /"
     hostgroups: computers
+  -
+    name: disk usage on /boot
+    nrpe: "/usr/lib/nagios/plugins/check_disk 60 80 /boot"
+    hosts: sperger
+  -
+    name: disk usage on /var
+    nrpe: "/usr/lib/nagios/plugins/check_disk 50 75 /var"
+    hosts: bartok, samosa
+  -
+    name: disk usage on /org
+    nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /org"
+    hosts: bartok, sperger, samosa
+  -
+    name: disk usage on /tmp
+    nrpe: "/usr/lib/nagios/plugins/check_disk 60 80 /tmp"
+    hosts: samosa
+  -
+    name: disk usage on /usr
+    nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /usr"
+    hosts: samosa
 
  ############ All Computers ############
  ####
@@ -87,11 +210,6 @@ services:
     name: process - getty
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:8 -c 1: -u root -C getty -a /sbin/getty"
     hostgroups: computers
- ####
-  -
-    name: process - inetd
-    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C inetd -a '/usr/sbin/inetd'"
-    hostgroups: computers
  ####
   -
     name: process - sshd
@@ -104,11 +222,6 @@ services:
     depends: process - sshd
     normal_check_interval:  60
     notification_interval:  60
- ####
-  -
-    name: process - udev
-    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C udevd -a 'udevd'"
-    hostgroups: computers
  ####
   -
     name: network service - nrpe
@@ -142,7 +255,6 @@ services:
     check: check_ntp
     hostgroups: computers
     depends: process - ntpd
-    excludehostgroups: vservers, xendomains
  ###
   -
     name: process - atd
@@ -154,3 +266,324 @@ services:
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C cron -a /usr/sbin/cron"
     hostgroups: computers
 
+ ###
+  -
+    name: process - syslog-ng
+    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: syslog-ng-hosts
+ ###
+  -
+    name: process - syslogd
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C syslogd  -a '/sbin/syslogd'"
+    hostgroups: computers
+    excludehostgroups: syslog-ng-hosts
+  -
+    name: process - klogd
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C klogd  -a '/sbin/klogd -x'"
+    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 -q'"
+    hostgroups: computers
+    excludehostgroups: postfix-hosts
+    excludehosts: master, rietz
+  -
+    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
+  -
+    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
+ ###
+  -
+    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
+  -
+    name: service - clamav
+    nrpe: "/usr/lib/nagios/plugins/check_clamd -H /var/run/clamav/clamd.ctl"
+    hostgroups: computers
+    excludehostgroups: postfix-hosts
+    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: computers
+    excludehostgroups: postfix-hosts
+ ###
+  -
+    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
+    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
+    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: 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: computers
+    excludehostgroups: postfix-hosts
+
+ ###
+  -
+    name: process - postfix - master
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C master -a '/usr/lib/postfix/master'"
+    hostgroups: postfix-hosts
+  -
+    name: process - postfix - qmgr
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postfix -C qmgr -a 'qmgr -l -t fifo -u'"
+    hostgroups: postfix-hosts
+    depends: process - postfix - master
+  #-
+  #  name: process - postfix - tlsmgr
+  #  nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postfix -C tlsmgr -a 'tlsmgr -l -t fifo -u'"
+  #  hostgroups: postfix-hosts
+  #  depends: process - postfix - master
+  -
+    name: process - postfix - pickup
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postfix -C pickup -a 'pickup -l -t fifo -u -c'"
+    hostgroups: postfix-hosts
+    depends: process - postfix - master
+  -
+    name: process - postfix - anvil
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postfix -C anvil -a 'anvil -l -t unix -u'"
+    hostgroups: postfix-hosts
+    depends: process - postfix - master
+
+  -
+    name: process - postfix - trivial-rewrite
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:10 -c 0:15 -u postfix -C trivial-rewrite -a 'trivial-rewrite -n rewrite -t unix -u -c'"
+    hostgroups: postfix-hosts
+    depends: process - postfix - master
+  -
+    name: process - postfix - proxymap
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:10 -c 0:15 -u postfix -C proxymap -a 'proxymap -t unix -u'"
+    hostgroups: postfix-hosts
+    depends: process - postfix - master
+  -
+    name: process - postfix - smtpd
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:10 -c 0:15 -u postfix -C smtpd -a 'smtpd -n smtp -t inet -u -c'"
+    hostgroups: postfix-hosts
+    depends: process - postfix - master
+  -
+    name: process - postfix - cleanup
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:30 -c 0:50 -u postfix -C cleanup -a 'cleanup -z -t unix -u -c'"
+    hostgroups: postfix-hosts
+    depends: process - postfix - master
+  -
+    name: process - postfix - local
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:30 -c 0:50 -u postfix -C local -a 'local -t unix'"
+    hostgroups: postfix-hosts
+    depends: process - postfix - master
+
+
+
+ ###
+  -
+    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
+
+
+
+ ############ Processes/Services that only run on some computers ############
+ ####
+ # XXX - raff:  identd, hpasmd
+ ###
+  -
+    name: process - rngd
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C rngd  -a '/usr/sbin/rngd -r /dev/hwrng'"
+    hosts: bartok
+ ###
+  -
+    name: process - sensord
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C sensord  -a '/usr/sbin/sensord -f daemon'"
+    hosts: bartok
+
+ ###
+  -
+    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, dl380
+  -
+    name: RAID - arrayprobe
+    nrpe: "sudo /usr/bin/arrayprobe"
+    hostgroups: dl385, dl380
+
+ ###
+  -
+    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
+ ###
+  -
+    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
+
+ ###
+  -
+    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 2:50 -c 1:100 -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