# services
#############################
services:
+ # {{{ ############ basic networking ############
-
name: PING
check: "check_ping!350.0,20%!600.0,40%"
normal_check_interval: 5
max_check_attempts: 4
retry_check_interval: 1
-
- ############ Services ############
- ###
-
- ############ Disk Usage ############
- ####
-
+ # }}}
+ # {{{ ############ Disk Usage ############
-
name: disk usage - all
servicegroups: diskspace
servicegroups: diskspace
nrpe: "/usr/lib/nagios/plugins/check_disk 85 95 /srv/bacula"
hosts: beethoven
+ # }}}
- ############ All Computers ############
- ####
+ # {{{ ############ All Computers ############
+ ####
-
name: apt - security updates
servicegroups: apt
hostgroups: computers
normal_check_interval: 60
retry_check_interval: 15
- ####
+ ####
-
name: backup
servicegroups: backup
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:3 -c 1: -u root -C bacula-fd -a '/usr/sbin/bacula-fd -c /etc/bacula/bacula-fd.conf'"
hostgroups: freebsd
- ####
+ ####
-
name: running kernel
servicegroups: kernel
normal_check_interval: 60
retry_check_interval: 5
- ####
+ ####
# - name: afs - space
# hostgroups: bosserver
# nrpe: "/usr/lib/nagios/plugins/dsa-check-afs-space -H localhost"
# 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/ferm.conf"
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
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:8 -c 1: -u root -C samhain -a '/usr/sbin/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
nrpe: "/usr/lib/nagios/plugins/check_load -w 30,28,26 -c 50,45,50"
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
nrpe: "/usr/lib/nagios/plugins/check_procs 3 6 -s Z -u root -a samhain"
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
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:20 -c 1: -u root -C sshd -a '/usr/sbin/sshd'"
depends: process - sshd
normal_check_interval: 60
notification_interval: 1440
- ####
+ ####
-
name: network service - nrpe
check: check_tcp!5666
hostgroups: computers
max_check_attempts: -1
depends: network service - nrpe
- ###
+ ###
-
name: process - munin-node
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:3 -c 1: -u root -C munin-node -a '/usr/sbin/munin-node'"
check: check_tcp!4949
hostgroups: computers
depends: process - munin-node
- ###
+ ###
-
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'"
depends: process - xinetd
servicegroups: time
- ###
+ ###
-
name: process - atd
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u daemon -C atd -a /usr/sbin/atd"
hostgroups: computers
- ###
+ ###
-
name: process - cron
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:3 -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'"
normal_check_interval: 60
retry_check_interval: 15
excludehostgroups: alioth
- ### MAIL STUFF
- ###
+ # }}}
+ # {{{ ############ MAIL STUFF ############
-
name: process - exim
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:10 -c 1: -u Debian-exim -C exim4 -a '/usr/sbin/exim4 -bd -q'"
name: mail queue
nrpe: "/usr/lib/nagios/plugins/check_mailq -M exim -w 1000 -c 2000"
hostgroups: heavy-exim
- ###
+ ###
-
name: process - clamav - clamd
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:2 -c 1: -u clamav -C clamd -a '/usr/sbin/clamd'"
nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C freshclam"
hostgroups: computers
excludehostgroups: heavy-exim, heavy-postfix
- ###
+ ###
-
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'"
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'"
nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C greylistd"
hostgroups: computers
- ###
+ ###
-
name: process - postgrey
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postgrey -a '/usr/sbin/postgrey --pidfile=/var/run/postgrey.pid --daemonize --unix=/var/run/postgrey/socket --retry-window=4 --auto-whitelist-clients=10 --exim'"
nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C postgrey"
hostgroups: computers
excludehostgroups: heavy-postfix, heavy-exim
- ###
+ ###
-
name: process - amavis - master
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u amavis -a 'amavisd-new (master)'"
nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C amavisd-new"
hostgroups: computers
excludehostgroups: amavis-hosts
- ###
+ ###
-
name: process - weightd - master
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u polw -a 'policyd-weight (master)'"
nrpe: "/usr/lib/nagios/plugins/check_procs -w 2:50 -c 1: -u polw -a 'policyd-weight (child)'"
hostgroups: heavy-postfix, alioth
depends: process - weightd - master
- ###
+ ###
-
name: unwanted process - policyd-weight
nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C policyd-weight"
excludehostgroups: heavy-postfix, alioth
- ###
+ ###
-
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'"
normal_check_interval: 120
- ###
+ ###
-
name: network service - smtp
check: dsa_check_smtp
normal_check_interval: 60
retry_check_interval: 15
hostgroups: computers
- ###
+ ###
-
name: local resolver
nrpe: "/usr/lib/nagios/plugins/dsa-check-resolver www.debian.org www.google.com"
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u unbound -C unbound -a '/usr/sbin/unbound'"
hostgroups: unbound-hosts, squeeze, wheezy
excludehostgroups: alioth
- ###
+ ###
-
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: unwanted process - irqbalance
nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C irqbalance"
hostgroups: computers
- ####
- ###
+ ####
+ ###
#-
# name: unwanted process - system-tools-backends
# nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C system-tools-ba"
nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C snmpd"
hostgroups: computers
- ####
+ ####
-
name: "host SSL cert"
nrpe: "if [ -e /etc/ssl/certs/thishost.pem ]; then /usr/lib/nagios/plugins/dsa-check-cert-expire /etc/ssl/certs/thishost.pem; else echo 'No thishost.pem on this host.'; fi"
hostgroups: computers
-
- ############ Processes/Services that only run on some computers ############
- ####
- ###
+ # }}}
+ # {{{ ############ Processes/Services that only run on some computers ############
-
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'"
hostgroups: dl385
- ###
+ ###
-
name: process - mdadm monitor
servicegroups: raid
nrpe: "/usr/lib/nagios/plugins/dsa-check-raid-sw"
hostgroups: sw-raid
- ###
+ ###
-
name: process - ud-replicated
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u root -C ud-replicated -a '/usr/bin/python /usr/bin/ud-replicated'"
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 - edac status
nrpe: "/usr/lib/nagios/plugins/dsa-check-edac"
nrpe: "/usr/lib/nagios/plugins/dsa-check-hpasm --fan-no-redundant"
normal_check_interval: 120
hosts: senfl, schein
- ###
+ ###
-
name: RAID - 3ware
servicegroups: raid
nrpe: "/usr/lib/nagios/plugins/dsa-check-raid-3ware"
hosts: powell
- ###
+ ###
-
name: RAID - aacraid
servicegroups: raid
nrpe: "/usr/lib/nagios/plugins/dsa-check-raid-aacraid"
hostgroups: aacraid
- ###
+ ###
-
name: RAID - megaraid
servicegroups: raid
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
nrpe: "/usr/lib/nagios/plugins/dsa-check-raid-mpt"
hostgroups: mptraid
- ###
+ ###
# -
# name: RAID - megactl
# servicegroups: raid
# nrpe: "/usr/lib/nagios/plugins/dsa-check-raid-megactl"
# hostgroups: megactl
- ###
+ ###
-
name: RAID - DRBD
servicegroups: raid
nrpe: "/usr/lib/nagios/plugins/dsa-check-drbd -d All"
hostgroups: drbd-hosts
- ###
+ ###
-
name: process - slapd
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:20 -c 1:50 -u openldap -C slapd -a '/usr/sbin/slapd -h ldap:/// ldaps:/// -g openldap -u openldap'"
depends: process - slapd
normal_check_interval: 60
hosts: draghi
- ###
+ ###
-
name: process - ulogd
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C ulogd -a '/usr/sbin/ulogd -d'"
nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C ulogd"
hostgroups: freebsd, sparc
- ###
+ ###
-
name: process - udevd
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -p 1 -C udevd -a 'udevd'"
name: unexpected process - udev
nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C udevd"
hostgroups: freebsd
- ###
+ ###
-
name: process - acpid
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C acpid -a '/usr/sbin/acpid'"
nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C acpid"
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'"
nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C xinetd"
hostgroups: computers
excludehostgroups: xinetd-hosts
- ###
+ ###
-
name: network service - finger
check: check_tcp!79
hosts: draghi
depends: process - xinetd
- ###
+ ###
-
name: network service - rsync
check: check_tcp!873
hosts: milanollo2
depends: milanollo:process - xinetd
- ###
+ ###
-
name: process - icinga
# there is always one extra process per check currently running..
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:30 -c 1: -u nagios -C icinga -a '/usr/sbin/icinga -d /etc/icinga/icinga.cfg'"
hosts: tchaikovsky
- ###
+ ###
-
name: process - jetty - master
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u root -a 'jsvc.exec'"
hostgroups: jetty-hosts
depends: process - jetty - master
- ###
+ ###
-
name: process - apache2 - master
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u root -a /usr/sbin/apache2"
###
- ####
+ ####
-
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: computers
excludehostgroups: bind9-hosts
- ####
+ ####
-
name: network service - ftp
check: check_ftp
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"
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'"
# 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
nrpe: "/usr/lib/nagios/plugins/check_procs -w 0 -C postgres"
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'"
hostgroups: squeeze, wheezy
excludehostgroups: freebsd, alioth
- ####
+ ####
-
name: process - UPS - nut usbhid-ups - ups1
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u nut -C usbhid-ups -a '/lib/nut/usbhid-ups -a ups1'"
nrpe: "/usr/lib/nagios/plugins/dsa-check-ups"
hosts: franck
depends: process - UPS - nut upsd
- ###
+ ###
-
name: process - buildd
servicegroups: buildd
nrpe: "/usr/lib/nagios/plugins/check_procs -m 'ELAPSED' -c 500 -C lvcreate -u root -a 'lvcreate'"
hostgroups: buildd
contact_groups: +buildd
- ####
+ ####
-
name: network service - gobby
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 ############
- ####
+ ###
+ # }}}
+ # {{{ ############ NFS Stuff ############
-
name: process - statd
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u statd -C rpc.statd -a '/sbin/rpc.statd'"
nrpe: "/usr/lib/nagios/plugins/check_procs -w 0 -C automount"
hostgroups: computers
excludehostgroups: autofs
-
- ############ MISC OTHER Stuff ############
- #####
+ # }}}
+ # {{{ ############ MISC OTHER Stuff ############
-
name: puppetmaster cert
nrpe: "/usr/lib/nagios/plugins/dsa-check-cert-expire /var/lib/puppet/ssl/certs/ca.pem"
remotecheck: "/usr/lib/nagios/plugins/dsa-check-statusfile /srv/dns.debian.org/var/nagios/ds"
runfrom: denis
- ############
+ ############
-
name: ping alive check
remotecheck: "/usr/lib/nagios/plugins/check_ping -H $HOSTADDRESS$ -w 50,10% -c 200,30%"
remotecheck: "/usr/lib/nagios/plugins/dsa-check-msa-eventlog --start=8867 $HOSTADDRESS$ public"
runfrom: dijkstra
hosts: giustini
- ############
+ ############
-
name: current chroots
nrpe: "/usr/lib/nagios/plugins/dsa-check-dchroots-current"
hostgroups: porterbox
normal_check_interval: 60
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'"
name: process - openstack - neutron-server
nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:10 -c 1: -u neutron -C neutron-server -a '/usr/bin/python2.7 /usr/bin/neutron-server --config-file=/etc/neutron/neutron.conf --config-file /etc/neutron/plugins/openvswitch/ovs_neutron_plugin.ini --log-file=/var/log/neutron/neutron-server.log'"
hostgroups: openstack-controller
+ # }}}
# }}}
# vim: set ts=2 sw=2 et ai si fdm=marker: