# - puccini: mailgraph
# -
# - agnesi
-# - lebrun
-# - murphy
# - piatti
# - tartini
#sarge:
address: 130.89.160.1
parents: gw-HP-ftc
hostgroups: routing-infrastructure
+ gw-ughent:
+ address: 157.193.39.254
+ parents: gw-HP-ftc
+ hostgroups: routing-infrastructure
samosa:
address: 192.25.206.57
master:
address: 70.103.162.29
parents: gw-brainfood
- hostgroups: computers, general, apache2-hosts, bind9-hosts, heavy-exim
+ hostgroups: computers, general, apache2-hosts, bind9-hosts, heavy-exim, highload
+ murphy:
+ address: 70.103.162.31
+ parents: gw-brainfood
+ hostgroups: computers, general, apache2-hosts, bind9-hosts, postfix-hosts
ries:
address: 128.148.34.103
kassia:
address: 130.89.175.54
parents: gw-utwente
- hostgroups: computers, service, apache2-hosts, ftpd-hosts, rsyncd-hosts, dl360
+ hostgroups: computers, service, postfix-hosts, apache2-hosts, ftpd-hosts, rsyncd-hosts, dl360
+
+ allegri:
+ address: 157.193.39.233
+ parents: gw-ughent
+ hostgroups: computers, buildd, postfix-hosts, sw-raid
#############################
# host groups
name: PING
check: "check_ping!300.0,20%!600.0,40%"
hostgroups: all
+ excludehostgroups: routing-infrastructure
+ normal_check_interval: 5
+ max_check_attempts: 4
+ retry_check_interval: 1
+ -
+ name: PING
+ check: "check_ping!900.0,60%!1500.0,80%"
+ hostgroups: routing-infrastructure
+ normal_check_interval: 5
+ max_check_attempts: 4
+ retry_check_interval: 1
############ Services ############
###
-
name: disk usage on /org
nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /org"
- hosts: bartok, sperger, samosa, raff, lobos, villa, steffani, merkel, saens, pergolesi, verdi, puccini
+ hosts: bartok, sperger, samosa, raff, lobos, villa, steffani, saens, pergolesi, verdi, puccini
+ -
+ name: disk usage on /org
+ nrpe: "/usr/lib/nagios/plugins/check_disk 90 95 /org"
+ hosts: merkel
-
name: disk usage on /srv
nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /srv"
- hosts: agricola, arcadelt, argento
+ hosts: agricola, arcadelt, argento, allegri
-
name: disk usage on /org/scratch2
nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /org/scratch2"
-
name: disk usage on /home
nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /home"
- hosts: gluck, raptor, escher, voltaire
+ hosts: raptor, escher, voltaire
+ -
+ name: disk usage on /home
+ nrpe: "/usr/lib/nagios/plugins/check_disk 90 95 /home"
+ hosts: gluck
-
name: disk usage on /chroot
nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /chroot"
####
-
name: load
- nrpe: "/usr/lib/nagios/plugins/check_load -w 12,10,8 -c 22,18,14"
+ nrpe: "/usr/lib/nagios/plugins/check_load -w 30,28,26 -c 50,45,50"
hostgroups: computers
excludehostgroups: highload
-
name: load
- nrpe: "/usr/lib/nagios/plugins/check_load -w 100,80,60 -c 200,160,140"
+ nrpe: "/usr/lib/nagios/plugins/check_load -w 140,120,100 -c 240,220,200"
hostgroups: highload
+ excludehosts: rietz
+ -
+ name: load
+ nrpe: "/usr/lib/nagios/plugins/check_load -w 200,200,200 -c 350,350,350"
+ hosts: rietz
####
-
name: processes - zombies
hostgroups: computers
-
name: "network service - sshd"
- check: check_ssh
+ check: dsa_check_ssh
hostgroups: computers
depends: process - sshd
normal_check_interval: 60
- notification_interval: 60
-
name: "network service - sshd"
- check: check_ssh
+ check: dsa_check_ssh
hostgroups: deadslow
normal_check_interval: 180
- notification_interval: 180
####
-
name: network service - nrpe
depends: process - weightd - master
-
name: process - weightd - child
- nrpe: "/usr/lib/nagios/plugins/check_procs -w 2:10 -c 1: -u polw -C policyd-weight -a 'policyd-weight (child)'"
+ nrpe: "/usr/lib/nagios/plugins/check_procs -w 2:50 -c 1: -u polw -C policyd-weight -a 'policyd-weight (child)'"
hostgroups: heavy-postfix
- excludehosts: liszt
- depends: process - weightd - master
- -
- name: process - weightd - child
- nrpe: "/usr/lib/nagios/plugins/check_procs -w 2:40 -c 1: -u polw -C policyd-weight -a 'policyd-weight (child)'"
- hosts: liszt
depends: process - weightd - 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'"
+ nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:20 -c 0:50 -u postfix -C smtpd -a 'smtpd -n smtp -t inet -u -c'"
hostgroups: postfix-hosts
excludehosts: liszt
depends: process - postfix - master
-
name: process - postfix - smtpd
- nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:100 -c 0:150 -u postfix -C smtpd -a 'smtpd -n smtp -t inet -u -c'"
+ nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:150 -c 0:200 -u postfix -C smtpd -a 'smtpd -n smtp -t inet -u -c'"
hosts: liszt
depends: process - postfix - master
-
depends: process - postfix - master
###
- -
- name: network service - smtp
- check: dsa_check_smtp
- hostgroups: postfix-hosts
- depends: process - postfix - master
-
name: network service - smtp
check: dsa_check_smtp
excludehostgroups: postfix-hosts
depends: process - exim
+ -
+ name: network service - smtp
+ check: dsa_check_smtp
+ hostgroups: postfix-hosts
+ excludehosts: verdi, kassia, allegri
+ depends: process - postfix - master
+ -
+ name: network service - smtp - port 2025
+ check: dsa_check_smtp_port!2025
+ hosts: verdi, kassia, murphy
+ depends: process - postfix - master
+ -
+ name: network service - smtp - port 8080
+ check: dsa_check_smtp_port!8080
+ hosts: allegri
+ depends: process - postfix - master
+
+ -
+ name: network service local - smtps cert
+ nrpe: "/usr/lib/nagios/plugins/check_http -H localhost -p 465 -S -C 14 -t 45"
+ hostgroups: postfix-hosts
+ depends: process - postfix - master
+ normal_check_interval: 1440
+
+ -
+ name: setup - debian-admin in etc aliases
+ nrpe: "/usr/lib/nagios/plugins/dsa-check-da-in-aliases"
+ hostgroups: computers
+ normal_check_interval: 1440
###
-
name: process - uptimed
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, bruckner
+ excludehosts: arcadelt, agricola, argento, penalosa, peri, escher, bruckner, allegri
####
###
- -
- 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 - 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"
-
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, albeniz, escher, verdi, liszt, kassia
+ hosts: sperger, ries, steffani, merkel, spohr, peri, penalosa, albeniz, escher, verdi, liszt, kassia, agricola, arcadelt, argento, allegri
###
-
name: process - acpid
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
hostgroups: ftpd-hosts
-
name: process - vsftp - instance
- nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:30 -c 0:50 -u ftp -C vsftpd -a 'vsftpd: '"
+ nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:80 -c 0:100 -u ftp -C vsftpd -a 'vsftpd: '"
hostgroups: ftpd-hosts
-
name: network service - ftp
###
-
name: process - monit
- nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C monit -a '/usr/sbin/monit -d 180 -c /etc/monit/monitrc -s /var/lib/monit/monit.state'"
+ nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C monit -a '/usr/sbin/monit -d 30 -c /etc/monit/monitrc -s /var/lib/monit/monit.state'"
hosts: villa, lobos, steffani, kassia, master