[project @ peter@palfrader.org-20081003180041-9yf125d0t8qbgg85]
[mirror/dsa-nagios.git] / nagios-master.cfg
index 5ef9c2a..27e34f7 100644 (file)
 #  - verdi: pg upgrade, openvpn
 #  - mundy: salinfo_decode
 #  - puccini: mailgraph
-#  - lebrun: ippl
 
 # down:
-#  - ravel
 #  - sarti
 #  - goedel
 #  - leisner
-#  - schulz
 
 ---
 #############################
@@ -88,10 +85,6 @@ servers:
     parents: gw-HP-ftc
     hostgroups: routing-infrastructure
     contacts: tjrc1
-  gw-cst:
-    address: 213.188.99.215
-    parents: gw-HP-ftc
-    hostgroups: routing-infrastructure
   gw-lrz:
     address: 129.187.0.150
     parents: gw-HP-ftc
@@ -193,7 +186,7 @@ servers:
   bartok:
     address: 82.195.75.91
     parents: gw-man-da
-    hostgroups: computers, service, syslog-ng-hosts, postfix-hosts, dl385
+    hostgroups: computers, service, syslog-ng-hosts, postfix-hosts, dl385, bind9-hosts
     contacts: joerg, bzed
   morales:
     address: 82.195.75.97
@@ -220,6 +213,11 @@ servers:
     parents: gw-man-da
     hostgroups: computers, service, apache2-hosts, bind9-hosts, postfix-hosts, heavy-postfix, amavis-hosts, dl385
     contacts: bzed
+  auber:
+    address: 82.195.75.101
+    parents: gw-man-da
+    hostgroups: computers, buildd, sw-raid
+    contacts: bzed
 
   master:
     address: 70.103.162.29
@@ -268,11 +266,11 @@ servers:
   steffani:
     address: 128.31.0.36
     parents: gw-mit-csail
-    hostgroups: computers, service, apache2-hosts, ftpd-hosts, rsyncd-hosts, sw-raid
-  casals:
-    address: 128.31.0.16
+    hostgroups: computers, service, apache2-hosts, ftpd-hosts, rsyncd-hosts, sw-raid, bind9-hosts
+  mahler:
+    address: 128.31.0.46
     parents: gw-mit-csail
-    hostgroups: deadslow
+    hostgroups: computers, single-cpu, lenny, porterbox, rsyslog-hosts
 
   klecker:
     address: 194.109.137.218
@@ -307,19 +305,16 @@ servers:
   albeniz:
     address: 193.62.202.27
     parents: gw-sanger
-    hostgroups: computers, porterbox, sw-raid
+    # SMP kernel doesn't run stable
+    hostgroups: computers, porterbox, sw-raid, single-cpu
     contacts: tjrc1
   goetz:
     address: 193.62.202.26
     parents: gw-sanger
-    hostgroups: computers, buildd, sw-raid
+    # SMP kernel doesn't run stable
+    hostgroups: computers, buildd, sw-raid, single-cpu
     contacts: tjrc1
 
-  escher:
-    address: 213.188.99.215
-    parents: gw-cst
-    hostgroups: computers, porterbox, single-cpu
-
   verdi:
     address: 192.54.42.193
     parents: gw-lrz
@@ -336,6 +331,11 @@ servers:
     parents: gw-1und1
     hostgroups: computers, service, apache2-hosts, bind9-hosts, postfix-hosts, heavy-postfix, amavis-hosts
     contacts: joerg
+  powell:
+    address: 87.106.64.223
+    parents: gw-1und1
+    hostgroups: computers, service, heavy-exim, rsyncd-hosts
+    contacts: joerg
 
   caballero:
     address: 193.201.200.200
@@ -383,11 +383,19 @@ servers:
     parents: gw-ubc
     hostgroups: computers, buildd
     contacts: lfilipoz
+  ravel:
+    address: 137.82.84.43
+    parents: gw-ubc
+    hostgroups: computers, general, dl385, apache2-hosts
 
   lebrun:
-    address: 161.53.160.165
+    address: 193.198.184.10
     parents: gw-carnet
     hostgroups: computers, buildd
+  schroeder:
+    address: 193.198.184.11
+    parents: gw-carnet
+    hostgroups: computers, buildd, sw-raid
 
   tartini:
     address: 82.94.249.158
@@ -461,6 +469,9 @@ hostgroups:
   syslog-ng-hosts:
     alias: hosts running syslog-ng instead of sysklogd
     private: 1
+  rsyslog-hosts:
+    alias: hosts running rsyslogd instead of sysklogd
+    private: 1
   postfix-hosts:
     alias: hosts running postfix instead of exim
     private: 1
@@ -523,9 +534,11 @@ servicegroups:
     alias: weak ssh keys
   apt:
     alias: apt upgrade status
+  samhain:
+    alias: samhain integrity status
   security:
     alias: security
-    servicegroup_members: apt, weaksshkeys, kernel
+    servicegroup_members: apt, weaksshkeys, kernel, samhain
 
 #############################
 # services
@@ -572,17 +585,17 @@ services:
     name: disk usage on /boot
     servicegroups: diskspace
     nrpe: "/usr/lib/nagios/plugins/check_disk 75 85 /boot"
-    hosts: sperger, rietz, steffani, penalosa, peri, albeniz, escher, goetz, mayer, mayr, paer, spontini, tartini, morales
+    hosts: sperger, rietz, steffani, penalosa, peri, albeniz, goetz, mayer, mayr, paer, spontini, tartini, morales, ravel, auber, schroeder, piatti
   -
     name: disk usage on /var
     servicegroups: diskspace
     nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /var"
-    hosts: bartok, samosa, raff, lobos, villa, gluck, saens, escher, voltaire, puccini, lebrun, tartini, morales
+    hosts: bartok, samosa, raff, lobos, villa, gluck, saens, voltaire, puccini, lebrun, tartini, morales, powell
   -
     name: disk usage on /org
     servicegroups: diskspace
     nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /org"
-    hosts: sperger, samosa, raff, lobos, villa, steffani, saens, pergolesi, verdi, puccini, spontini
+    hosts: sperger, samosa, raff, lobos, villa, steffani, saens, pergolesi, verdi, puccini, spontini, ravel, mahler, schroeder, piatti
   -
     name: disk usage on /org
     servicegroups: diskspace
@@ -592,7 +605,7 @@ services:
     name: disk usage on /srv
     servicegroups: diskspace
     nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /srv"
-    hosts: agricola, arcadelt, argento, allegri, tartini, morales
+    hosts: agricola, arcadelt, argento, allegri, tartini, morales, auber, powell
   -
     name: disk usage on /org/scratch
     servicegroups: diskspace
@@ -602,17 +615,17 @@ services:
     name: disk usage on /tmp
     servicegroups: diskspace
     nrpe: "/usr/lib/nagios/plugins/check_disk 60 80 /tmp"
-    hosts: samosa, raff, gluck, saens, escher, puccini, merkel, tartini
+    hosts: samosa, raff, gluck, saens, puccini, merkel, tartini, powell, piatti
   -
     name: disk usage on /usr
     servicegroups: diskspace
     nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /usr"
-    hosts: samosa, raff, lobos, villa, gluck, saens, pergolesi, puccini, merulo, tartini, morales
+    hosts: samosa, raff, lobos, villa, gluck, saens, pergolesi, puccini, merulo, tartini, morales, powell
   -
     name: disk usage on /home
     servicegroups: diskspace
     nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /home"
-    hosts: raptor, escher, voltaire, lebrun
+    hosts: raptor, voltaire, lebrun
   -
     name: disk usage on /home
     servicegroups: diskspace
@@ -646,7 +659,8 @@ services:
     servicegroups: apt
     nrpe: "/usr/lib/nagios/plugins/dsa-check-statusfile /var/cache/dsa/nagios/apt"
     hostgroups: computers
-    normal_check_interval:  360
+    normal_check_interval:  60
+    retry_check_interval: 15
  ####
   -
     name: backup
@@ -655,6 +669,13 @@ services:
     normal_check_interval: 180
     max_check_attempts: 2
     retry_check_interval: 5
+  -
+    name: backup server config
+    nrpe: "/usr/lib/nagios/plugins/dsa-check-dabackup-server"
+    hosts: bartok
+    normal_check_interval: 180
+    max_check_attempts: 2
+    retry_check_interval: 5
 
  ####
   -
@@ -665,6 +686,20 @@ services:
     normal_check_interval: 180
     retry_check_interval: 5
 
+ ####
+  -
+    name: process - samhain
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:8 -c 1: -u root -C samhain -a '/usr/sbin/samhain'"
+    hostgroups: computers
+  -
+    name: samhain
+    servicegroups: samhain
+    nrpe: "/usr/lib/nagios/plugins/dsa-check-samhain"
+    hostgroups: computers
+    depends: process - samhain
+    normal_check_interval: 240
+    retry_check_interval: 5
+
  ####
   -
     name: users
@@ -742,7 +777,7 @@ services:
 
   -
     name: "network service - sshd - version"
-    check: "dsa_check_ssh_port_version!22!OpenSSH_4.3p2 Debian-9etch2"
+    check: "dsa_check_ssh_port_version!22!OpenSSH_4.3p2 Debian-9etch3"
     depends: network service - sshd
     hostgroups: computers, deadslow
     excludehosts: agnesi, crest, kullervo
@@ -756,13 +791,13 @@ services:
     normal_check_interval:  360
   -
     name: "network service - sshd - version"
-    check: "dsa_check_ssh_port_version!22!OpenSSH_4.7p1 Debian-12"
+    check: "dsa_check_ssh_port_version!22!OpenSSH_5.1p1 Debian-2"
     depends: network service - sshd
     hostgroups: lenny
     normal_check_interval:  360
   -
     name: "network service - sshd - version - 2260"
-    check: "dsa_check_ssh_port_version!2260!OpenSSH_4.3p2 Debian-9etch2"
+    check: "dsa_check_ssh_port_version!2260!OpenSSH_4.3p2 Debian-9etch3"
     depends: network service - sshd - 2260
     hosts: agnesi
     normal_check_interval:  360
@@ -833,17 +868,22 @@ services:
     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 - rsyslogd
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C rsyslogd  -a '/usr/sbin/rsyslogd -c3'"
+    hostgroups: rsyslog-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
+    excludehostgroups: syslog-ng-hosts, rsyslog-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
+    excludehostgroups: syslog-ng-hosts, rsyslog-hosts
 
  ### MAIL STUFF
  ###
@@ -877,6 +917,10 @@ services:
     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-exim, heavy-postfix
+  -
+    name: process - clamav - getsigs
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u clamav -C getclamsigs -a 'getclamsigs'"
+    hostgroups: heavy-exim, heavy-postfix
   #
   -
     name: unwanted process - clamav
@@ -888,6 +932,11 @@ services:
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C freshclam"
     hostgroups: computers
     excludehostgroups: heavy-exim, heavy-postfix
+  -
+    name: unwanted process - clamav - getsigs
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C getclamsigs"
+    hostgroups: computers
+    excludehostgroups: heavy-exim, heavy-postfix
  ###
   -
     name: process - spamd - master
@@ -1082,7 +1131,7 @@ services:
   -
     name: network service - smtp - port 8080
     check: dsa_check_smtp_port!8080
-    hosts: murphy, piatti
+    hosts: murphy
     depends: process - postfix - master
   -
     name: network service - smtp - port 2025
@@ -1100,8 +1149,8 @@ services:
 
 
   -
-    name: setup - debian-admin in etc aliases
-    nrpe: "/usr/lib/nagios/plugins/dsa-check-da-in-aliases"
+    name: setup - dsa config
+    nrpe: "/usr/lib/nagios/plugins/dsa-check-config"
     hostgroups: computers
     normal_check_interval: 120
   -
@@ -1163,7 +1212,7 @@ services:
   -
     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
+    hostgroups: dl385
  ###
   -
     name: process - sensord
@@ -1197,7 +1246,14 @@ services:
     name: HW - hpacucli status
     servicegroups: raid
     nrpe: "/usr/lib/nagios/plugins/dsa-check-hpacucli"
+    normal_check_interval: 120
     hostgroups: dl385, dl380, dl360
+ ###
+  -
+    name: RAID - areca
+    servicegroups: raid
+    nrpe: "/usr/lib/nagios/plugins/dsa-check-raid-areca"
+    hosts: powell
  ###
   -
     name: RAID - DAC960
@@ -1226,7 +1282,7 @@ services:
   -
     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, agricola, arcadelt, argento, allegri, morales
+    hosts: sperger, ries, steffani, merkel, spohr, peri, penalosa, albeniz, verdi, liszt, kassia, agricola, arcadelt, argento, allegri, morales, bartok, schroeder
  ###
   -
     name: process - acpid
@@ -1313,13 +1369,13 @@ services:
   -
     name: network service - https
     check: check_https
-    hosts: samosa
+    hosts: samosa, ries
     depends: "process - apache2 - master"
     normal_check_interval: 120
   -
     name: network service - https cert
     check: dsa_check_cert!443
-    hosts: samosa
+    hosts: samosa, ries
     depends: network service - https
     normal_check_interval: 240
  ####
@@ -1357,7 +1413,7 @@ services:
   -
     name: process - debianqueued
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u dak -C debianqueued"
-    hosts: ries
+    hosts: ries, ravel
 
  ###
   -
@@ -1391,19 +1447,19 @@ services:
     depends: process - mysql - master
 
  ####
-  -
-    name: process - xenconsoled
-    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C xenconsoled -a 'xenconsoled'"
-    hosts: piatti
-  -
-    name: process - xenstored
-    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C xenstored -a '/usr/lib/xen-3.0.3-1/bin/xenstored --pid-file /var/run/xenstore.pid'"
-    hosts: piatti
-  -
-    name: process - xend
-    nrpe: "/usr/lib/nagios/plugins/check_procs -w 2:2 -c 2: -u root -C python -a 'python /usr/lib/xen-3.0.3-1/bin/xend start'"
-    hosts: piatti
-
+  #-
+  #  name: process - xenconsoled
+  #  nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C xenconsoled -a 'xenconsoled'"
+  #  hosts: piatti
+  #-
+  #  name: process - xenstored
+  #  nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C xenstored -a '/usr/lib/xen-3.0.3-1/bin/xenstored --pid-file /var/run/xenstore.pid'"
+  #  hosts: piatti
+  #-
+  #  name: process - xend
+  #  nrpe: "/usr/lib/nagios/plugins/check_procs -w 2:2 -c 2: -u root -C python -a 'python /usr/lib/xen-3.0.3-1/bin/xend start'"
+  #  hosts: piatti
+#
  ####
   # XXX is this needed?
   -