Add byrd
[mirror/dsa-nagios.git] / config / nagios-master.cfg
index 227e539..1a3215e 100644 (file)
@@ -27,6 +27,11 @@ servers:
     parents: gw-HP-ftc
     hostgroups: routing-infrastructure
     contacts: joerg, bzed
+  gw-man-da2:
+    address: 82.195.75.46
+    parents: gw-man-da
+    hostgroups: routing-infrastructure
+    contacts: joerg, bzed
   gw-HP-ftc:
     address: 192.25.206.1
     parents: spohr
@@ -98,10 +103,6 @@ servers:
     address: 193.201.200.129
     parents: gw-HP-ftc
     hostgroups: routing-infrastructure
-  gw-xandros:
-    address: 67.210.160.81
-    parents: gw-HP-ftc
-    hostgroups: routing-infrastructure
   gw-nmmn:
     address: 217.114.76.81
     parents: gw-HP-ftc
@@ -181,7 +182,7 @@ servers:
   gluck:
     address: 192.25.206.10
     parents: spohr
-    hostgroups: computers, no-udev, general, dl380, apache2-hosts, bind9-hosts, heavy-exim, highload, nfs-client, ulogd-hosts, lenny, hasvarfs, hasusrfs
+    hostgroups: computers, no-udev, general, dl380, lenny, hassrvfs, rsyncd-hosts, acpid-hosts, apache2-hosts, ftpd-hosts
   merkel:
     address: 192.25.206.16
     parents: spohr
@@ -192,7 +193,7 @@ servers:
     hostgroups: secondary-IPs
   spohr:
     address: 192.25.206.33
-    hostgroups: computers, service, dl380, apache2-hosts, postgres83-hosts, ulogd-hosts, nfs-server, lenny, heavy-exim
+    hostgroups: computers, service, dl380, apache2-hosts, postgres83-hosts, ulogd-hosts, nfs-server, lenny, heavy-exim, bind9-hosts
   spohr2:
     address: 192.25.206.38
     parents: spohr
@@ -214,7 +215,7 @@ servers:
   paer:
     address: 192.25.206.11
     parents: spohr
-    hostgroups: computers, porterbox, lenny, hasbootfs
+    hostgroups: computers, porterbox, lenny, hasbootfs, hashomefs, single-cpu
   merulo:
     address: 192.25.206.58
     parents: spohr
@@ -231,8 +232,8 @@ servers:
   #  hostgroups: computers, porterbox, single-cpu, no-samhain, hasbootfs, hassrvfs, lenny, hasvarfs, hasusrfs
   #  contacts: bzed
   sperger:
-    address: 82.195.75.98
-    parents: gw-man-da
+    address: 82.195.75.34
+    parents: gw-man-da2
     hostgroups: computers, porterbox, sw-raid, hasbootfs, lenny
     contacts: bzed
   agricola:
@@ -271,6 +272,14 @@ servers:
     address: 82.195.75.106
     parents: unger
     hostgroups: computers, service, acpid-hosts, lenny, hasbootfs, hassrvfs, apache2-hosts, bind9-hosts, heavy-exim, ulogd-hosts
+  kaufmann:
+    address: 82.195.75.107
+    parents: unger
+    hostgroups: computers, service, lenny, hasbootfs, apache2-hosts, single-cpu, rsyncd-hosts
+  byrd:
+    address: 82.195.75.101
+    parents: unger
+    hostgroups: computers, service, lenny, hasbootfs, hassrvfs
 
   master:
     address: 70.103.162.29
@@ -328,6 +337,10 @@ servers:
     address: 128.31.0.49
     parents: gw-mit-csail
     hostgroups: computers, service, lenny, dl360, acpid-hosts, hassrvfs, ulogd-hosts, apache2-hosts
+  senfl:
+    address: 128.31.0.51
+    parents: gw-mit-csail
+    hostgroups: computers, service, lenny, dl360, acpid-hosts, hassrvfs, ulogd-hosts, apache2-hosts, rsyncd-hosts
   carver:
     address: 128.31.0.50
     parents: gw-mit-csail
@@ -381,12 +394,13 @@ servers:
   verdi:
     address: 192.54.42.193
     parents: gw-lrz
-    hostgroups: computers, service, apache2-hosts, ftpd-hosts, rsyncd-hosts, postgres81-hosts, postfix-hosts
+    hostgroups: computers, service, postfix-hosts
+    #hostgroups: computers, service, apache2-hosts, ftpd-hosts, postgres81-hosts, postfix-hosts
 
   voltaire:
     address: 72.66.115.54
     parents: gw-frost
-    hostgroups: computers, buildd, lenny, hasvarfs
+    hostgroups: computers, buildd, lenny, hasvarfs, hashomefs
     contacts: sfrost
 
   puccini:
@@ -422,15 +436,6 @@ servers:
     parents: gw-blackcat
     hostgroups: computers, no-udev, buildd, sw-raid, lenny
 
-  elara:
-    address: 67.210.160.90
-    parents: gw-xandros
-    hostgroups: deadslow
-  europa:
-    address: 67.210.160.89
-    parents: gw-xandros
-    hostgroups: deadslow
-
   pescetti:
     address: 217.114.76.85
     parents: gw-nmmn
@@ -453,11 +458,6 @@ servers:
     parents: kassia
     hostgroups: secondary-IPs
 
-  allegri:
-    address: 157.193.39.233
-    parents: gw-ghent
-    hostgroups: computers, buildd, sw-raid, single-cpu, lenny, hassrvfs, incomingmailrelayed2025
-    contacts: luk
   ancina:
     address: 157.193.39.13
     parents: gw-ghent
@@ -477,7 +477,7 @@ servers:
   ravel:
     address: 137.82.84.66
     parents: gw-ubc
-    hostgroups: computers, general, dl385, apache2-hosts, acpid-hosts, ftpd-hosts, hasbootfs, lenny
+    hostgroups: computers, general, dl385, apache2-hosts, acpid-hosts, ftpd-hosts, hasbootfs, lenny, nfs-server, rsyncd-hosts
   dijkstra:
     address: 137.82.84.70
     parents: gw-ubc
@@ -497,7 +497,27 @@ servers:
   valente:
     address: 137.82.84.76
     parents: dijkstra
-    hostgroups: computers, lenny, hasbootfs, single-cpu
+    hostgroups: computers, lenny, hasbootfs, single-cpu, hassrvfs, postgres83-hosts, ftpd-hosts, rsyncd-hosts
+  bellini:
+    address: 137.82.84.79
+    parents: gw-ubc
+    hostgroups: computers, lenny, hasbootfs, nfs-client, hassrvfs, aacraid
+  stabile:
+    address: 137.82.84.72
+    parents: gw-ubc
+    hostgroups: computers, lenny, hashomefs, sw-raid, rsyncd-hosts
+  cimarosa:
+    address: 137.82.84.80
+    parents: gw-ubc
+    hostgroups: computers, lenny, hasbootfs, aacraid, hassrvfs
+  # MSA 2000 (2012i)
+  giustini:
+    address: 192.168.2.6
+    parents: dijkstra
+    hostgroups: notacomputer
+    # unless we implement runfrom for host alive checks
+    pingable: false
+    check_command: dsa_check_always_ok
 
   lebrun:
     address: 193.198.184.10
@@ -522,12 +542,12 @@ servers:
   rem:
     address: 195.71.99.217
     parents: gw-telefonica
-    hostgroups: computers, buildd, hasbootfs, lenny
+    hostgroups: computers, buildd, hasbootfs, lenny, hashomefs
 
   ball:
     address: 78.32.9.213
     parents: gw-ball
-    hostgroups: computers, buildd, no-udev, dialup, hasbootfs, lenny
+    hostgroups: computers, buildd, no-udev, dialup, hasbootfs, lenny, hashomefs
 
   zelenka:
     address: 80.245.147.40
@@ -537,7 +557,7 @@ servers:
   escher:
     address: 213.188.99.215
     parents: gw-cst
-    hostgroups: computers, single-cpu, hasbootfs, lenny, hasvarfs
+    hostgroups: computers, single-cpu, hasbootfs, lenny, hasvarfs, hashomefs
   goedel:
     address: 213.188.99.214
     parents: gw-cst
@@ -616,6 +636,9 @@ hostgroups:
   sw-raid:
     alias: Hosts with Linux software raid
     private: 1
+  aacraid:
+    alias: Hosts with Adaptec AACraid
+    private: 1
   single-cpu:
     alias: Hosts with only one CPU
     private: 1
@@ -661,9 +684,9 @@ hostgroups:
   rsyncd-hosts:
     alias: hosts providing rsync services via xinetd
     private: 1
-  postgres81-hosts:
-    alias: hosts running postgres81
-    private: 1
+  #postgres81-hosts:
+  #  alias: hosts running postgres81
+  #  private: 1
   postgres83-hosts:
     alias: hosts running postgres83
     private: 1
@@ -704,6 +727,9 @@ hostgroups:
   hassrvfs:
     alias: hosts with a /srv filesystem
     private: 1
+  hashomefs:
+    alias: hosts with a /home filesystem
+    private: 1
   hasvarfs:
     alias: hosts with a /var filesystem
     private: 1
@@ -817,7 +843,7 @@ services:
     name: disk usage on /tmp
     servicegroups: diskspace
     nrpe: "/usr/lib/nagios/plugins/check_disk 60 80 /tmp"
-    hosts: raff, gluck, saens, puccini, merkel, tartini, powell, piatti, escher
+    hosts: raff, saens, puccini, merkel, tartini, powell, piatti, escher
   -
     name: disk usage on /usr
     servicegroups: diskspace
@@ -827,12 +853,7 @@ services:
     name: disk usage on /home
     servicegroups: diskspace
     nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /home"
-    hosts: voltaire, rem, ball, paer, escher
-  -
-    name: disk usage on /home
-    servicegroups: diskspace
-    nrpe: "/usr/lib/nagios/plugins/check_disk 90 95 /home"
-    hosts: gluck
+    hostgroups: hashomefs
   -
     name: disk usage on /mnt/hdc
     servicegroups: diskspace
@@ -853,6 +874,21 @@ services:
     servicegroups: diskspace
     nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /var/lib/postgresql"
     hosts: samosa
+  -
+    name: disk usage on /srv/morgue.debian.org
+    servicegroups: diskspace
+    nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /srv/morgue.debian.org"
+    hosts: stabile
+  -
+    name: disk usage on /srv/mirrors
+    servicegroups: diskspace
+    nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /srv/mirrors"
+    hosts: stabile
+  -
+    name: disk usage on /srv/ftp-master.debian.org
+    servicegroups: diskspace
+    nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /srv/ftp-master.debian.org"
+    hosts: stabile
 
  ############ All Computers ############
  ####
@@ -889,15 +925,9 @@ services:
     retry_check_interval: 5
 
  ####
-  -
-    name: process - puppet
-    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:8 -c 1: -u root -C ruby -a 'ruby /usr/sbin/puppetd -w 5 --factsync'"
-    hostgroups: lenny
-    excludehosts: agnesi
-
   -
     name: puppet
-    nrpe: "/usr/lib/nagios/plugins/dsa-check-file_age -f /var/lib/puppet/state/state.yaml"
+    nrpe: "/usr/lib/nagios/plugins/dsa-check-file_age -i 300 -f /var/lib/puppet/state/state.yaml"
     hostgroups: lenny
     excludehosts: agnesi
 
@@ -981,22 +1011,11 @@ services:
     normal_check_interval:  60
     notification_interval: 1440
 
-  -
-    name: "network service - sshd"
-    check: dsa_check_ssh
-    hostgroups: deadslow
-    excludehosts: agnesi
-    normal_check_interval:  180
   -
     name: "network service - sshd - 2260"
     check: dsa_check_ssh_port!2260
     hosts: agnesi
     normal_check_interval:  180
-  -
-    name: "network service - sshd - 443"
-    check: dsa_check_ssh_port!443
-    hosts: gluck
-    normal_check_interval:  180
 
   -
     name: "network service - sshd - version"
@@ -1061,12 +1080,12 @@ services:
     check: dsa_check_ntp
     hostgroups: computers
     depends: process - ntpd
-    excludehosts: allegri, zelenka, ancina
+    excludehosts: zelenka, ancina
   #
   -
     name: network service - time
     check: dsa_check_time
-    hosts: allegri, zelenka, ancina
+    hosts: zelenka, ancina
     depends: process - xinetd
 
  ###
@@ -1108,17 +1127,17 @@ services:
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:10 -c 1: -u Debian-exim -C exim4 -a '/usr/sbin/exim4 -bd -q'"
     hostgroups: computers
     excludehostgroups: postfix-hosts
-    excludehosts: master, rietz, merkel, gluck
+    excludehosts: master, rietz, merkel
   -
     name: process - exim - total
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:50 -c 1: -C exim4"
     hostgroups: computers
     excludehostgroups: postfix-hosts
-    excludehosts: master, rietz, merkel, gluck
+    excludehosts: master, rietz, merkel
   -
     name: process - exim
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:300 -c 1:500 -C exim4 -a '/usr/sbin/exim4'"
-    hosts: master, rietz, merkel, gluck
+    hosts: master, rietz, merkel
  ###
   -
     name: process - clamav - clamd
@@ -1133,11 +1152,6 @@ 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
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C clamd"
@@ -1148,17 +1162,15 @@ 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
     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'"
     hostgroups: heavy-exim
-    excludehosts: rietz, merkel, raff
+    excludehosts: rietz, merkel, raff, powell
+  -
+    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 20 --min-spare=5 --helper-home-dir -d --pidfile=/var/run/spamd.pid'"
+    hosts: powell
   -
     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 10 --helper-home-dir -d --pidfile=/var/run/spamd.pid'"
@@ -1478,6 +1490,12 @@ services:
     servicegroups: raid
     nrpe: "/usr/lib/nagios/plugins/dsa-check-raid-dac960"
     hosts: verdi
+ ###
+  -
+    name: RAID - aacraid
+    servicegroups: raid
+    nrpe: "/usr/lib/nagios/plugins/dsa-check-raid-aacraid"
+    hostgroups: aacraid
  ###
   -
     name: RAID - 3ware
@@ -1531,13 +1549,13 @@ 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: allegri, gluck, zelenka, ancina, draghi
+    hosts: zelenka, ancina, draghi
     hostgroups: rsyncd-hosts
   -
     name: unwanted process - xinetd
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C xinetd"
     hostgroups: computers
-    excludehosts: allegri, gluck, zelenka, ancina, draghi
+    excludehosts: zelenka, ancina, draghi
     excludehostgroups: rsyncd-hosts
  ###
   -
@@ -1704,25 +1722,25 @@ services:
     hosts: ries, ravel, klecker
 
  ###
-  -
-    name: process - postresql81 - 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 - postresql81 - 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 - postresql81 - master
-  -
-    name: process - postresql81 - 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 - postresql81 - master
-  -
-    name: process - postresql81 - 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 - postresql81 - master
+  #-
+  #  name: process - postresql81 - 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 - postresql81 - 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 - postresql81 - master
+  #-
+  #  name: process - postresql81 - 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 - postresql81 - master
+  #-
+  #  name: process - postresql81 - 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 - postresql81 - master
  ####
   -
     name: process - postresql83 - master
@@ -1830,14 +1848,14 @@ services:
     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
+  -
+    name: nfs mount ftp archive
+    nrpe: "/usr/lib/nagios/plugins/check_disk 100 100 /srv/ftp.debian.org/ftp"
+    hosts: bellini
 
  ############ MISC OTHER Stuff ############
  #####
@@ -1857,6 +1875,13 @@ services:
     name: mirror sync - security.us
     check: "dsa_check_mirrorsync!security.us.debian.org!project/trace/security-master.debian.org"
     hosts: global
+  -
+    name: mirror sync - packages
+    check: "dsa_check_mirrorsync!packages.debian.org!Pics/.trace"
+    hosts: global
+    normal_check_interval: 15
+    max_check_attempts: 5
+    retry_check_interval: 5
   -
     name: DNS SOA sync - security.geo.debian.org
     check: "dsa_check_soas!security.geo.debian.org"
@@ -1885,3 +1910,17 @@ services:
     name: DNS SOA sync - alioth.debian.org
     check: "dsa_check_soas_add!alioth.debian.org!alioth.debian.org"
     hosts: global
+ ############
+  -
+    name: ping alive check
+    remotecheck: "/usr/lib/nagios/plugins/check_ping -H $HOSTADDRESS$ -w 50,10% -c 200,30%"
+    runfrom: dijkstra
+    hosts: giustini
+    normal_check_interval: 5
+    max_check_attempts: 4
+    retry_check_interval: 1
+  -
+    name: Overall Unit Status
+    remotecheck: "/usr/lib/nagios/plugins/check_snmp -H $HOSTADDRESS$ -C public -P 2c -o connUnitStatus -n -c 3 -w 3"
+    runfrom: dijkstra
+    hosts: giustini