[project @ peter@palfrader.org-20081207205759-lu909ppkhky56ufv]
[mirror/dsa-nagios.git] / nagios-master.cfg
index 8708a13..acf94e1 100644 (file)
@@ -14,7 +14,6 @@
 #  - goetz: gmond/gmetad
 #  - verdi: pg upgrade, openvpn
 #  - mundy: salinfo_decode
-#  - puccini: mailgraph
 
 # down:
 #  - sarti
@@ -98,6 +97,10 @@ servers:
     parents: gw-HP-ftc
     hostgroups: routing-infrastructure
     contacts: joerg
+  gw-1und1-karlsruhe:
+    address: 212.227.120.29
+    parents: gw-HP-ftc
+    hostgroups: routing-infrastructure
   gw-blackcat:
     address: 193.201.200.129
     parents: gw-HP-ftc
@@ -111,7 +114,7 @@ servers:
     parents: gw-HP-ftc
     hostgroups: routing-infrastructure
   gw-utwente:
-    address: 130.89.160.1
+    address: 130.89.149.1
     parents: gw-HP-ftc
     hostgroups: routing-infrastructure
   #gw-ughent:
@@ -140,6 +143,14 @@ servers:
     parents: gw-HP-ftc
     hostgroups: routing-infrastructure
     contacts: holger
+  gw-telefonica:
+    address: 195.71.99.193
+    parents: gw-HP-ftc
+    hostgroups: routing-infrastructure
+  gw-ball:
+    address: 78.32.9.209
+    parents: gw-HP-ftc
+    hostgroups: routing-infrastructure
 
   samosa:
     address: 192.25.206.57
@@ -147,19 +158,19 @@ servers:
   raff:
     address: 192.25.206.59
     parents: samosa
-    hostgroups: computers, no-udev, service, dl380, apache1-hosts, bind9-hosts, rsyncd-hosts, heavy-exim
+    hostgroups: computers, no-udev, service, dl380, apache1-hosts, bind9-hosts, rsyncd-hosts, heavy-exim, ulogd-hosts, nfs-client
   gluck:
     address: 192.25.206.10
     parents: samosa
-    hostgroups: computers, no-udev, general, dl380, apache1-hosts, bind9-hosts, rsyncd-hosts, heavy-exim, highload
+    hostgroups: computers, no-udev, general, dl380, apache2-hosts, bind9-hosts, heavy-exim, highload, nfs-client, ulogd-hosts
   merkel:
     address: 192.25.206.16
     parents: samosa
-    hostgroups: computers, general, apache1-hosts, bind9-hosts, rsyncd-hosts, sw-raid, postgres81-hosts, heavy-exim
+    hostgroups: computers, general, apache1-hosts, bind9-hosts, rsyncd-hosts, sw-raid, postgres81-hosts, heavy-exim, nfs-client, ulogd-hosts
   spohr:
     address: 192.25.206.33
     parents: samosa
-    hostgroups: computers, service, dl380, apache2-hosts, postgres81-hosts
+    hostgroups: computers, service, dl380, apache2-hosts, postgres81-hosts, ulogd-hosts, nfs-server
   peri:
     address: 192.25.206.15
     parents: samosa
@@ -177,7 +188,7 @@ servers:
   paer:
     address: 192.25.206.11
     parents: samosa
-    hostgroups: computers, porterbox, bind9-hosts
+    hostgroups: computers, porterbox, bind9-hosts, single-cpu
   merulo:
     address: 192.25.206.58
     parents: samosa
@@ -201,23 +212,23 @@ servers:
   agricola:
     address: 82.195.75.86
     parents: gw-man-da
-    hostgroups: computers, porterbox, sw-raid, single-cpu, lenny
+    hostgroups: computers, porterbox, sw-raid, single-cpu, lenny, no-samhain
     contacts: bzed
   arcadelt:
     address: 82.195.75.87
     parents: gw-man-da
-    hostgroups: computers, buildd, sw-raid, single-cpu, lenny
+    hostgroups: computers, buildd, sw-raid, single-cpu, lenny, no-samhain
     contacts: bzed
   liszt:
     address: 82.195.75.100
     parents: gw-man-da
     hostgroups: computers, service, apache2-hosts, bind9-hosts, postfix-hosts, heavy-postfix, amavis-hosts, dl385, acpid-hosts
     contacts: bzed
-  auber:
-    address: 82.195.75.101
-    parents: gw-man-da
-    hostgroups: computers, no-udev, buildd, sw-raid
-    contacts: bzed
+#  auber:
+#    address: 82.195.75.101
+#    parents: gw-man-da
+#    hostgroups: computers, no-udev, buildd, sw-raid
+#    contacts: bzed
 
   master:
     address: 70.103.162.29
@@ -285,7 +296,7 @@ servers:
   argento:
     address: 195.49.152.174
     parents: gw-dg-i.net
-    hostgroups: computers, buildd, sw-raid, single-cpu, lenny
+    hostgroups: computers, buildd, sw-raid, single-cpu, lenny, no-samhain
     contacts: bzed
 
   pergolesi:
@@ -295,7 +306,7 @@ servers:
   bruckner:
     address: 62.104.23.253
     parents: gw-freenet
-    hostgroups: computers, no-udev, porterbox, single-cpu
+    hostgroups: computers, no-udev, porterbox, single-cpu, deadslow
 
   raptor:
     address: 195.243.109.162
@@ -314,6 +325,11 @@ servers:
     # SMP kernel doesn't run stable
     hostgroups: computers, buildd, sw-raid, single-cpu
     contacts: tjrc1
+  smetana:
+    address: 193.62.202.29
+    parents: gw-sanger
+    hostgroups: computers, porterbox, sw-raid
+    contacts: tjrc1
 
   verdi:
     address: 192.54.42.193
@@ -329,7 +345,7 @@ servers:
   puccini:
     address: 87.106.4.56
     parents: gw-1und1
-    hostgroups: computers, no-udev, service, apache2-hosts, bind9-hosts, postfix-hosts, heavy-postfix, amavis-hosts, ulogd-hosts
+    hostgroups: computers, buildd, lenny, rsyslog-hosts, ulogd-hosts
     contacts: joerg
   powell:
     address: 87.106.64.223
@@ -337,6 +353,15 @@ servers:
     hostgroups: computers, service, heavy-exim, rsyncd-hosts, ulogd-hosts, acpid-hosts
     contacts: joerg
 
+  schumann:
+    address: 212.227.126.54
+    parents: gw-1und1-karlsruhe
+    hostgroups: computers, acpid-hosts, ulogd-hosts
+  wieck:
+    address: 195.20.242.89
+    parents: gw-1und1-karlsruhe
+    hostgroups: computers, service, apache2-hosts, ftpd-hosts, rsyncd-hosts, acpid-hosts, ulogd-hosts
+
   caballero:
     address: 193.201.200.200
     parents: gw-blackcat
@@ -361,16 +386,32 @@ servers:
     parents: gw-nmmn
     hostgroups: deadslow
     contacts: luk
+  pescetti:
+    address: 217.114.76.85
+    parents: gw-nmmn
+    hostgroups: computers, porterbox, single-cpu, smart
 
   kassia:
-    address: 130.89.175.54
+    address: 130.89.149.224
     parents: gw-utwente
-    hostgroups: computers, service, postfix-hosts, apache2-hosts, ftpd-hosts, rsyncd-hosts, dl360, acpid-hosts
+    hostgroups: computers, service, postfix-hosts, apache2-hosts, ftpd-hosts, rsyncd-hosts, dl360, acpid-hosts, ulogd-hosts
+  kassia2:
+    address: 130.89.149.225
+    parents: kassia
+    hostgroups: secondary-IPs
+  kassia3:
+    address: 130.89.149.226
+    parents: kassia
+    hostgroups: secondary-IPs
+  kassia4:
+    address: 130.89.149.227
+    parents: kassia
+    hostgroups: secondary-IPs
 
   allegri:
     address: 157.193.39.233
     parents: gw-HP-ftc
-    hostgroups: computers, buildd, postfix-hosts, sw-raid, single-cpu, lenny
+    hostgroups: computers, buildd, postfix-hosts, sw-raid, single-cpu, lenny, no-samhain
     contacts: luk
 
   agnesi:
@@ -408,6 +449,16 @@ servers:
     hostgroups: computers, postfix-hosts, dl385, ulogd-hosts, acpid-hosts
     contacts: holger
 
+  rem:
+    address: 195.71.99.217
+    parents: gw-telefonica
+    hostgroups: computers, buildd
+
+  ball:
+    address: 78.32.9.213
+    parents: gw-ball
+    hostgroups: computers, buildd, no-udev, dialup
+
 #############################
 # host groups
 #
@@ -424,6 +475,8 @@ hostgroups:
     extinfo-icon_image_alt: router
   deadslow:
     alias: Systems too slow to run any real checks
+  dialup:
+    alias: Systems with slow network
 
   porterbox:
     alias: developer accessible porter machines
@@ -466,6 +519,10 @@ hostgroups:
     alias: Hosts running lenny, not etch
     private: 1
 
+  no-samhain:
+    alias: hosts not running samhain properly
+    private: 1
+
   syslog-ng-hosts:
     alias: hosts running syslog-ng instead of sysklogd
     private: 1
@@ -476,7 +533,7 @@ hostgroups:
     alias: hosts running postfix instead of exim
     private: 1
   heavy-exim:
-    alias: "hosts running the full mail stuff, including clamav, SA, and greylistd"
+    alias: "hosts running the full mail stuff, including clamav, SA, and postgrey"
     private: 1
   heavy-postfix:
     alias: "postfix hosts running the full mail stuff, including clamav, SA, postgrey, policyd-weight"
@@ -518,6 +575,13 @@ hostgroups:
     alias: hosts running acpid
     private: 1
 
+  nfs-client:
+    alias: hosts mounting filesystems using NFS
+    private: 1
+  nfs-server:
+    alias: hosts serving filesystems using NFS
+    private: 1
+
   highload:
     alias: "hosts on which high load is normal"
     private: 1
@@ -526,6 +590,10 @@ hostgroups:
     alias: secondary IP addresses
     private: 1
 
+  smart:
+    alias: hosts with smartd
+    private: 1
+
 
 #############################
 # servicegroups
@@ -557,14 +625,14 @@ services:
     name: PING
     check: "check_ping!300.0,20%!600.0,40%"
     hostgroups: all
-    excludehostgroups: routing-infrastructure
+    excludehostgroups: routing-infrastructure, dialup
     normal_check_interval: 5
     max_check_attempts: 4
     retry_check_interval: 1
   -
     name: PING
     check: "check_ping!2000.0,60%!3000.0,80%"
-    hostgroups: routing-infrastructure
+    hostgroups: routing-infrastructure, dialup
     normal_check_interval: 5
     max_check_attempts: 4
     retry_check_interval: 1
@@ -594,17 +662,17 @@ 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, goetz, mayer, mayr, paer, spontini, tartini, morales, ravel, auber, schroeder, piatti
+    hosts: sperger, rietz, steffani, penalosa, peri, albeniz, goetz, mayer, mayr, paer, spontini, tartini, morales, ravel, schroeder, piatti, rem, ball
   -
     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, voltaire, puccini, lebrun, tartini, morales, powell
+    hosts: bartok, samosa, raff, lobos, villa, gluck, saens, voltaire, 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, ravel, mahler, schroeder, piatti
+    hosts: sperger, samosa, raff, lobos, villa, steffani, saens, pergolesi, verdi, spontini, ravel, mahler, schroeder, piatti, pescetti
   -
     name: disk usage on /org
     servicegroups: diskspace
@@ -614,7 +682,7 @@ 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, auber, powell
+    hosts: agricola, arcadelt, argento, allegri, tartini, morales, powell, puccini
   -
     name: disk usage on /org/scratch
     servicegroups: diskspace
@@ -629,12 +697,12 @@ services:
     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, powell
+    hosts: samosa, raff, lobos, villa, gluck, saens, pergolesi, merulo, tartini, morales, powell
   -
     name: disk usage on /home
     servicegroups: diskspace
     nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /home"
-    hosts: raptor, voltaire, lebrun
+    hosts: raptor, voltaire, lebrun, rem, ball
   -
     name: disk usage on /home
     servicegroups: diskspace
@@ -700,11 +768,13 @@ services:
     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
+    excludehostgroups: no-samhain
   -
     name: samhain
     servicegroups: samhain
-    nrpe: "/usr/lib/nagios/plugins/dsa-check-samhain"
+    nrpe: "/usr/lib/nagios/plugins/dsa-check-samhain -t 45"
     hostgroups: computers
+    excludehostgroups: no-samhain
     depends: process - samhain
     normal_check_interval: 240
     retry_check_interval: 5
@@ -800,7 +870,7 @@ services:
     normal_check_interval:  360
   -
     name: "network service - sshd - version"
-    check: "dsa_check_ssh_port_version!22!OpenSSH_5.1p1 Debian-2"
+    check: "dsa_check_ssh_port_version!22!OpenSSH_5.1p1 Debian-3"
     depends: network service - sshd
     hostgroups: lenny
     normal_check_interval:  360
@@ -985,18 +1055,21 @@ services:
     hosts: merkel, raff
 
  ###
-  -
-    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: 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"
     hostgroups: computers
-    excludehostgroups: heavy-exim
 
  ###
+  -
+    name: process - postgrey
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postgrey -C postgrey -a '/usr/sbin/postgrey --pidfile=/var/run/postgrey.pid --daemonize --unix=/var/run/postgrey/socket --retry-window=4 --auto-whitelist-clients=10 --exim'"
+    hostgroups: heavy-exim
   -
     name: process - postgrey
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postgrey -C postgrey -a '/usr/sbin/postgrey --pidfile=/var/run/postgrey.pid --daemonize --inet=127.0.0.1:60000'"
@@ -1006,7 +1079,7 @@ services:
     name: unwanted process - postgrey
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C postgrey"
     hostgroups: computers
-    excludehostgroups: heavy-postfix
+    excludehostgroups: heavy-postfix, heavy-exim
  ###
   -
     name: process - amavis - master
@@ -1200,10 +1273,12 @@ services:
     name: unwanted process - portmap
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C portmap"
     hostgroups: computers
+    excludehostgroups: nfs-client, nfs-server
   -
     name: unwanted process - rpc.statd
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C rpc.statd"
     hostgroups: computers
+    excludehostgroups: nfs-client, nfs-server
   -
     name: unwanted process - inetd
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C inetd"
@@ -1322,13 +1397,13 @@ services:
   -
     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, raptor, allegri
+    hosts: samosa, raptor, allegri, gluck
     hostgroups: rsyncd-hosts
   -
     name: unwanted process - xinetd
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C xinetd"
     hostgroups: computers
-    excludehosts: samosa, raptor, allegri
+    excludehosts: samosa, raptor, allegri, gluck
     excludehostgroups: rsyncd-hosts
  ###
   -
@@ -1442,7 +1517,7 @@ services:
   -
     name: process - debianqueued
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u dak -C debianqueued"
-    hosts: ries, ravel
+    hosts: ries, ravel, klecker
 
  ###
   -
@@ -1524,3 +1599,41 @@ services:
     name: process - monit
     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
+ ###
+  -
+    name: process - smartd
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C smartd -a '/usr/sbin/smartd --pidfile /var/run/smartd.pid --interval=1800'"
+    hostgroups: smart
+
+ ############ NFS Stuff ############
+ ####
+  -
+    name: process - portmap
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u daemon -C portmap -a '/sbin/portmap'"
+    hostgroups: nfs-client, nfs-server
+  -
+    name: process - statd
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u statd -C rpc.statd -a '/sbin/rpc.statd'"
+    hostgroups: nfs-client, nfs-server
+  -
+    name: process - nfsd
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:10 -c 1: -u root -C nfsd -a '[nfsd]'"
+    hostgroups: nfs-server
+  -
+    name: process - lockd
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C lockd -a '[lockd]'"
+    hostgroups: nfs-server
+  -
+    name: process - mountd
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C rpc.mountd -a '/sbin/rpc.mountd'"
+    hostgroups: nfs-server
+ # see if the nfs stuff works and doesn't hang.
+  # the df check all script will also hang, but we don't appear to pay attention to that
+  -
+    name: nfs mount ftp archive
+    nrpe: "/usr/lib/nagios/plugins/check_disk 100 100 /home/org/ftp.root/debian"
+    hosts: gluck
+  -
+    name: nfs mount ftp archive
+    nrpe: "/usr/lib/nagios/plugins/check_disk 100 100 /org/mirrors/ftp.debian.org/ftp"
+    hosts: merkel, raff