aacraid:
alias: Hosts with Adaptec AACraid
private: 1
-# megactl:
-# alias: Hosts with LSI Logic MegaRAID, but not usable with megaraid check
-# private: 1
megaraid:
alias: Hosts with LSI Logic MegaRAID
private: 1
jetty-hosts:
alias: hosts running jetty
private: 1
- #varnish-hosts:
- # alias: hosts running varnish
- # private: 1
bind9-hosts:
alias: hosts running bind9
private: 1
amavis-hosts:
alias: hosts running amavis
private: 1
- #tftpd-hosts:
- # alias: hosts running a tftpd (tftpd-hpa as a daemon)
- # private: 1
rsyncd-hosts:
alias: hosts providing rsync services via xinetd
private: 1
xinetd-hosts:
alias: hosts providing services via xinetd
private: 1
- #postgres81-hosts:
- # alias: hosts running postgres81
- # private: 1
postgres91-hosts:
alias: hosts running postgres91
private: 1
hasusrfs:
alias: hosts with a /usr filesystem
private: 1
-# hasvicepa:
-# alias: hosts with a /vicepa
-# private: 1
incomingmailrelayed:
alias: incoming mail needs to go through a mail relay
alias: hosts that are security mirrors
private: 1
# }}}
-# {{{ servicegroups
-#############################
-# servicegroups
-#############################
+# {{{ ############################# servicegroups #############################
servicegroups:
diskspace:
alias: diskusage checks
servicegroup_members: apt, kernel, samhain
# }}}
-# {{{ services
-#############################
-# services
-#############################
+# {{{ ############################# # services #############################
services:
# {{{ ############ basic networking ############
-
# }}}
# {{{ ############ All Computers ############
- ####
-
name: apt - security updates
servicegroups: apt
normal_check_interval: 60
retry_check_interval: 5
- ####
-# - name: afs - space
-# hostgroups: bosserver
-# nrpe: "/usr/lib/nagios/plugins/dsa-check-afs-space -H localhost"
-# normal_check_interval: 60
-# max_check_attempts: 2
-# retry_check_interval: 5
-#
-# - name: afs - bos
-# hostgroups: bosserver
-# nrpe: "/usr/lib/nagios/plugins/dsa-check-afs-bos -H localhost"
-# normal_check_interval: 60
-# max_check_attempts: 2
-# retry_check_interval: 5
-#
-# - name: afs - waiting connections
-# hostgroups: bosserver
-# nrpe: "/usr/lib/nagios/plugins/dsa-check-afs-rxdebug -H localhost"
-# normal_check_interval: 60
-# max_check_attempts: 2
-# retry_check_interval: 5
-#
- #- name: afs - udebug
- # hostgroups: bosserver
- # nrpe: "/usr/lib/nagios/plugins/dsa-check-afs-udebug -H localhost"
- # normal_check_interval: 60
- # max_check_attempts: 2
- # retry_check_interval: 5
-
- ####
- #-
- # name: puppet
- # nrpe: "/usr/lib/nagios/plugins/dsa-check-file_age -i 540 -f /var/lib/puppet/state/state.yaml"
- # hostgroups: computers
-
####
-
name: installed firewall
nrpe: "/usr/lib/nagios/plugins/dsa-check-file -w -f /etc/ferm/conf.d/defs.conf"
hostgroups: computers
excludehostgroups: freebsd
+
####
- name: ganeti - job watcher paused
nrpe: "/usr/lib/nagios/plugins/negate /usr/lib/nagios/plugins/dsa-check-file -f /var/lib/ganeti/watcher.pause"
hostgroups: computers
+
####
-
name: process - samhain
normal_check_interval: 60
retry_check_interval: 5
excludehostgroups: brokensamhain
+
####
-
name: process - acc.umu.se backup
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:8 -c 1: -u root -a 'dsmc'"
hosts: sibelius
+
####
-
name: users
nrpe: "/usr/lib/nagios/plugins/check_users 30 35"
hostgroups: computers
+
####
-
name: load
name: load
nrpe: "/usr/lib/nagios/plugins/check_load -w 140,120,100 -c 240,220,200"
hostgroups: highload
+
####
-
name: uptime check
nrpe: "/usr/lib/nagios/plugins/dsa-check-uptime"
hostgroups: computers
+
####
-
name: processes - samhain zombies
name: processes - zombies
nrpe: "/usr/lib/nagios/plugins/check_procs 5 10 -s Z"
hostgroups: computers
+
####
-
name: processes - total
nrpe: "/usr/lib/nagios/plugins/check_procs 620 700"
hostgroups: computers
+
####
-
name: swap usage - percent
nrpe: "/usr/lib/nagios/plugins/check_swap -w 20% -c 10%"
hostgroups: computers
+
####
-
name: swap usage - mb
nrpe: "/usr/lib/nagios/plugins/check_swap -w 20000 -c 5000"
hostgroups: computers
+
####
-
name: process - getty
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:8 -c 1: -u root -C getty -a /sbin/getty"
hostgroups: computers
excludehosts: zelenka, zandonai
+
####
-
name: process - sshd
depends: process - sshd
normal_check_interval: 60
notification_interval: 1440
+
####
-
name: network service - nrpe
hostgroups: computers
max_check_attempts: -1
depends: network service - nrpe
+
###
-
name: process - munin-node
check: check_tcp!4949
hostgroups: computers
depends: process - munin-node
+
###
-
name: process - ntpd
depends: process - ntpd
excludehosts: ancina
servicegroups: time
- #
+
+ ###
-
name: network service - time
check: dsa_check_time
excludehostgroups: spamd
excludehosts: bendel, busoni, buxtehude
- ###
- #-
- # 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-exim
- #
-
name: unwanted process - greylistd
nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C greylistd"
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: computers
####
- ###
- #-
- # name: unwanted process - system-tools-backends
- # nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C system-tools-ba"
- # hostgroups: computers
- #-
- # name: unwanted process - dbus-daemon
- # nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C dbus-daemon"
- # hostgroups: computers
-
name: unwanted process - gkrellmd
nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C gkrellmd"
nrpe: "/usr/lib/nagios/plugins/dsa-check-raid-megaraid"
hostgroups: megaraid
###
- #-
- # name: RAID - 3ware
- # servicegroups: raid
- # nrpe: "/usr/lib/nagios/plugins/dsa-check-raid-3ware"
- # hosts: puccini
- ###
-
name: RAID - MPT
servicegroups: raid
hostgroups: mptraid
###
-# -
-# name: RAID - megactl
-# servicegroups: raid
-# nrpe: "/usr/lib/nagios/plugins/dsa-check-raid-megactl"
-# hostgroups: megactl
- ###
-
name: RAID - DRBD
servicegroups: raid
hostgroups: computers
excludehostgroups: acpid-hosts, kvmdomains
###
-# -
-# name: process - bosserver
-# nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C bosserver -a '/usr/sbin/bosserver'"
-# hostgroups: bosserver
-#
- ###
-
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'"
excludehosts: ravel
normal_check_interval: 60
-###
- #-
- # name: process - varnish - master
- # nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u root -C varnishd -a '/usr/sbin/varnishd -P /var/run/varnishd.pid -a :80 -T localhost:6082 -f /etc/varnish/default.vcl'"
- # hostgroups: varnish-hosts
- #-
- # name: process - varnish - worker
- # nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u nobody -C varnishd -a '/usr/sbin/varnishd -P /var/run/varnishd.pid -a :80 -T localhost:6082 -f /etc/varnish/default.vcl'"
- # hostgroups: varnish-hosts
- # depends: process - varnish - master
- #-
- # name: network service - http
- # check: check_http
- # hostgroups: varnish-hosts
- # depends: process - varnish - master
-
-###
-
####
-
name: process - named
hosts: klecker-ftp
depends: klecker:process - xinetd
- ####
- #-
- # name: process - debianqueued
- # nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:3 -c 1: -u dak -C debianqueued"
-
name: process - debianqueued
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:3 -c 1: -u dak-unpriv -C debianqueued"
hostgroups: uploadqueue
- ###
- #-
- # name: process - postgresql81 - 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 - postgresql81 - 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 - postgresql81 - master
- #-
- # name: process - postgresql81 - 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 - postgresql81 - master
- #-
- # name: process - postgresql81 - 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 - postgresql81 - master
####
-
name: unwanted process - postgresql
-
name: postgresql backups
nrpe: "/usr/bin/sudo -u debbackup /usr/lib/nagios/plugins/dsa-check-backuppg"
- #hosts: beethoven
hosts: backuphost
####
- ####
-
name: process - stunnel4 - puppet-ekeyd
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:6 -c 1: -u stunnel4 -C stunnel4 -a '/usr/bin/stunnel4 /etc/stunnel/puppet-ekeyd.conf'"
contact_groups: buildd
-
name: processes - zombie schroot
- #nrpe: "/usr/lib/nagios/plugins/check_procs -a schroot -s Zs -c 0"
nrpe: "(/usr/lib/nagios/plugins/check_procs -a schroot -s Zs -c 0 > /dev/null || /usr/lib/nagios/plugins/check_procs -a schroot -s Zs -c 0) && /usr/lib/nagios/plugins/check_procs -a schroot -s ZNs -c 0"
hostgroups: buildd
contact_groups: +buildd
check: check_tcp!6523
hosts: gombert
contact_groups: gobby
- ####
- #-
- # name: process - tftpd
- # nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C in.tftpd -a '/usr/sbin/in.tftpd -l -B 1450 -s /var/lib/tftpboot'"
- # hostgroups: tftpd-hosts
- ###
# }}}
# {{{ ############ NFS Stuff ############
-
retry_check_interval: 15
# }}}
# {{{ ############ openstack ############
-# -
-# name: process - openstack - keystone
-# nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:10 -c 1: -u root -C keystone-all -a '/usr/bin/python /usr/bin/keystone-all'"
-# hostgroups: openstack-controller
-
name: process - openstack - memcached
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:10 -c 1: -u nobody -C memcached -a '/usr/bin/memcached -m 64 -p 11211 -u nobody -l 127.0.0.1'"