[project @ peter@palfrader.org-20080406103524-kptbd4xe8y50kbua]
[mirror/dsa-nagios.git] / nagios-master.cfg
index 15f5e18..91f86f4 100644 (file)
@@ -14,6 +14,7 @@
 #  - goetz: gmond/gmetad
 #  - verdi: pg upgrade, openvpn
 #  - mundy: salinfo_decode
+#  - puccini: mailgraph
 #  -
 #  - agnesi
 #  - casals
 #  - kassia
 #  - kullervo
 #  - lebrun
-#  - liszt
 #  - murphy
 #  - piatti
-#  - puccini
-#  - spontini
 #  - tartini
 #sarge:
 #  - caballero
+#  - spontini
 
 # down:
 #  - ravel
@@ -44,7 +43,7 @@
 # hosts
 #############################
 servers:
-  gw-MAN-DA-debian:
+  gw-man-da:
     address: 82.195.75.126
     parents: gw-HP-ftc
     hostgroups: routing-infrastructure
@@ -112,22 +111,26 @@ servers:
     address: 130.81.242.195
     parents: gw-HP-ftc
     hostgroups: routing-infrastructure
+  gw-1und1:
+    address: 195.20.247.53
+    parents: gw-HP-ftc
+    hostgroups: routing-infrastructure
 
   samosa:
     address: 192.25.206.57
-    hostgroups: computers, service, dl380, apache2-hosts, bind9-hosts, heavy-email
+    hostgroups: computers, service, dl380, apache2-hosts, bind9-hosts, heavy-exim
   raff:
     address: 192.25.206.59
     parents: samosa
-    hostgroups: computers, service, dl380, apache1-hosts, bind9-hosts, rsyncd-hosts, heavy-email
+    hostgroups: computers, service, dl380, apache1-hosts, bind9-hosts, rsyncd-hosts, heavy-exim
   gluck:
     address: 192.25.206.10
     parents: samosa
-    hostgroups: computers, general, dl380, apache1-hosts, bind9-hosts, rsyncd-hosts, heavy-email
+    hostgroups: computers, general, dl380, apache1-hosts, bind9-hosts, rsyncd-hosts, heavy-exim, highload
   merkel:
     address: 192.25.206.16
     parents: samosa
-    hostgroups: computers, general, apache1-hosts, bind9-hosts, rsyncd-hosts, sw-raid, postgres81-hosts, heavy-email
+    hostgroups: computers, general, apache1-hosts, bind9-hosts, rsyncd-hosts, sw-raid, postgres81-hosts, heavy-exim
   spohr:
     address: 192.25.206.33
     parents: samosa
@@ -151,30 +154,34 @@ servers:
 
   bartok:
     address: 82.195.75.91
-    parents: gw-MAN-DA-debian
+    parents: gw-man-da
     hostgroups: computers, service, syslog-ng-hosts, postfix-hosts, dl385
   sperger:
     address: 82.195.75.98
-    parents: gw-MAN-DA-debian
+    parents: gw-man-da
     hostgroups: computers, porterbox, sw-raid
   agricola:
     address: 82.195.75.86
-    parents: gw-MAN-DA-debian
+    parents: gw-man-da
     hostgroups: computers, porterbox, sw-raid
   arcadelt:
     address: 82.195.75.87
-    parents: gw-MAN-DA-debian
+    parents: gw-man-da
     hostgroups: computers, buildd, sw-raid
+  liszt:
+    address: 82.195.75.100
+    parents: gw-man-da
+    hostgroups: computers, service, apache2-hosts, bind9-hosts, postfix-hosts, heavy-postfix, dl385
 
   master:
     address: 70.103.162.29
     parents: gw-brainfood
-    hostgroups: computers, general, apache2-hosts, bind9-hosts, heavy-email
+    hostgroups: computers, general, apache2-hosts, bind9-hosts, heavy-exim
 
   ries:
     address: 128.148.34.103
     parents: gw-brown.edu
-    hostgroups: computers, service, apache2-hosts, bind9-hosts, ftpd-hosts, dl385, rsyncd-hosts, postgres81-hosts, heavy-email
+    hostgroups: computers, service, apache2-hosts, bind9-hosts, ftpd-hosts, dl385, rsyncd-hosts, postgres81-hosts, heavy-exim
 
   mayer:
     address: 140.211.166.78
@@ -191,7 +198,7 @@ servers:
   rietz:
     address: 140.211.166.43
     parents: gw-osuosl
-    hostgroups: computers, service, apache2-hosts, bind9-hosts, rsyncd-hosts, dl385, heavy-email
+    hostgroups: computers, service, apache2-hosts, bind9-hosts, rsyncd-hosts, dl385, heavy-exim, highload
   rietz2:
     address: 140.211.166.44
     parents: rietz
@@ -214,12 +221,12 @@ servers:
   klecker:
     address: 194.109.137.218
     parents: gw-xs4all
-    hostgroups: computers, service, apache2-hosts, ftpd-hosts, rsyncd-hosts, bind9-hosts, dl385, postgres81-hosts, heavy-email
+    hostgroups: computers, service, apache2-hosts, ftpd-hosts, rsyncd-hosts, bind9-hosts, dl385, postgres81-hosts, heavy-exim
 
   saens:
     address: 128.101.240.212
     parents: gw-umn.edu
-    hostgroups: computers, service, apache2-hosts, ftpd-hosts, rsyncd-hosts, dl380, heavy-email
+    hostgroups: computers, service, apache2-hosts, ftpd-hosts, rsyncd-hosts, dl380, heavy-exim
 
   argento:
     address: 195.49.152.174
@@ -264,6 +271,11 @@ servers:
     parents: gw-frost
     hostgroups: computers, buildd
 
+  puccini:
+    address: 87.106.4.56
+    parents: gw-frost
+    hostgroups: computers, service, apache2-hosts, bind9-hosts, postfix-hosts, heavy-postfix, amavis-hosts
+
 #############################
 # host groups
 #
@@ -316,9 +328,12 @@ hostgroups:
   postfix-hosts:
     alias: hosts running postfix instead of exim
     private: 1
-  heavy-email:
+  heavy-exim:
     alias: "hosts running the full mail stuff, including clamav, SA, and greylistd"
     private: 1
+  heavy-postfix:
+    alias: "postfix hosts running the full mail stuff, including clamav, SA, postgrey, amavis, policyd-weight"
+    private: 1
   apache2-hosts:
     alias: hosts running apache2
     private: 1
@@ -328,6 +343,9 @@ hostgroups:
   bind9-hosts:
     alias: hosts running bind9
     private: 1
+  amavis-hosts:
+    alias: hosts running amavis
+    private: 1
   ftpd-hosts:
     alias: hosts running vsftpd
     private: 1
@@ -341,6 +359,10 @@ hostgroups:
     alias: hosts running postgres81
     private: 1
 
+  highload:
+    alias: "hosts on which high load is normal"
+    private: 1
+
   secondary-IPs:
     alias: secondary IP addresses
     private: 1
@@ -365,7 +387,7 @@ services:
     hostgroups: computers
   -
     name: disk usage on /
-    nrpe: "/usr/lib/nagios/plugins/check_disk 60 80 /"
+    nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /"
     hostgroups: computers
   -
     name: disk usage on /boot
@@ -373,12 +395,12 @@ services:
     hosts: sperger, rietz, steffani, penalosa, peri, albeniz, escher, goetz, mayer, mayr, paer
   -
     name: disk usage on /var
-    nrpe: "/usr/lib/nagios/plugins/check_disk 50 75 /var"
-    hosts: bartok, samosa, raff, lobos, villa, gluck, saens, escher, voltaire
+    nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /var"
+    hosts: bartok, samosa, raff, lobos, villa, gluck, saens, escher, voltaire, puccini
   -
     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
+    hosts: bartok, sperger, samosa, raff, lobos, villa, steffani, merkel, saens, pergolesi, verdi, puccini
   -
     name: disk usage on /srv
     nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /srv"
@@ -394,11 +416,11 @@ services:
   -
     name: disk usage on /tmp
     nrpe: "/usr/lib/nagios/plugins/check_disk 60 80 /tmp"
-    hosts: samosa, raff, gluck, saens, escher
+    hosts: samosa, raff, gluck, saens, escher, puccini
   -
     name: disk usage on /usr
     nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /usr"
-    hosts: samosa, raff, lobos, villa, gluck, saens, pergolesi
+    hosts: samosa, raff, lobos, villa, gluck, saens, pergolesi, puccini
   -
     name: disk usage on /home
     nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /home"
@@ -432,6 +454,11 @@ services:
     name: load
     nrpe: "/usr/lib/nagios/plugins/check_load -w 12,10,8 -c 22,18,14"
     hostgroups: computers
+    excludehostgroups: highload
+  -
+    name: load
+    nrpe: "/usr/lib/nagios/plugins/check_load -w 100,80,60 -c 200,160,140"
+    hostgroups: highload
  ####
   -
     name: processes - zombies
@@ -543,7 +570,7 @@ services:
  ###
   -
     name: process - exim
-    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u Debian-exim -C exim4 -a '/usr/sbin/exim4 -bd -q'"
+    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
@@ -561,40 +588,44 @@ services:
   -
     name: process - clamav - clamd
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:2 -c 1: -u clamav -C clamd -a '/usr/sbin/clamd'"
-    hostgroups: heavy-email
+    hostgroups: heavy-exim, heavy-postfix
   -
     name: service - clamav
     nrpe: "/usr/lib/nagios/plugins/check_clamd -H /var/run/clamav/clamd.ctl"
-    hostgroups: heavy-email
+    hostgroups: heavy-exim, heavy-postfix
     depends: process - clamav - clamd
   -
     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-email
+    hostgroups: heavy-exim, heavy-postfix
   #
   -
     name: unwanted process - clamav
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C clamd"
     hostgroups: computers
-    excludehostgroups: heavy-email
+    excludehostgroups: heavy-exim, heavy-postfix
   -
     name: unwanted process - freshclam
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C freshclam"
     hostgroups: computers
-    excludehostgroups: heavy-email
+    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'"
-    #hosts: samosa
-    hostgroups: heavy-email
-    excludehosts: rietz
+    hostgroups: heavy-exim
+    excludehosts: rietz, merkel, raff
+  -
+    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'"
+    hosts: liszt
   -
     name: process - spamd - child
-    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:6 -c 1: -C spamd -a 'spamd child'"
-    hostgroups: heavy-email
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:11 -c 1: -C spamd -a 'spamd child'"
+    hosts: liszt
+    hostgroups: heavy-exim
     depends: process - spamd - master
-    excludehosts: rietz
+    excludehosts: rietz, merkel, raff
   #
   -
     name: process - spamd - master
@@ -609,19 +640,80 @@ services:
     name: unwanted process - spamd
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C spamd"
     hostgroups: computers
-    excludehostgroups: heavy-email
+    excludehostgroups: heavy-exim
+    excludehosts: liszt
+  -
+    name: unwanted process - spamd
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C spamd"
+    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-email
+    hostgroups: heavy-exim
   #
   -
     name: unwanted process - greylistd
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C greylistd"
     hostgroups: computers
-    excludehostgroups: heavy-email
+    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 --inet=127.0.0.1:60000'"
+    hostgroups: heavy-postfix
+  #
+  -
+    name: unwanted process - postgrey
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C postgrey"
+    hostgroups: computers
+    excludehostgroups: heavy-postfix
+ ###
+  -
+    name: process - amavis - master
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u amavis -C amavisd-new -a 'amavisd (master)'"
+    hostgroups: amavis-hosts
+  -
+    name: process - amavis - all
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:10 -c 1:10 -u amavis -C amavisd-new -a 'amavisd '"
+    hostgroups: amavis-hosts
+    depends: process - amavis - master
+  #
+  -
+    name: unwanted process - amavis
+    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 -C policyd-weight -a 'policyd-weight (master)'"
+    hostgroups: heavy-postfix
+  -
+    name: process - weightd - cache
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u polw -C policyd-weight -a 'policyd-weight (cache)'"
+    hostgroups: heavy-postfix
+    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)'"
+    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: unwanted process - policyd-weight
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C policyd-weight"
+    hostgroups: computers
+    excludehostgroups: heavy-postfix
+
 
 
  ###
@@ -660,11 +752,6 @@ services:
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:10 -c 0:15 -u postfix -C proxymap -a 'proxymap -t unix -u'"
     hostgroups: postfix-hosts
     depends: process - postfix - 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'"
-    hostgroups: postfix-hosts
-    depends: process - postfix - master
   -
     name: process - postfix - cleanup
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:30 -c 0:50 -u postfix -C cleanup -a 'cleanup -z -t unix -u -c'"
@@ -676,6 +763,29 @@ services:
     hostgroups: postfix-hosts
     depends: process - postfix - 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'"
+    hostgroups: postfix-hosts
+    excludehosts: liszt
+    depends: process - postfix - master
+  -
+    name: process - postfix - smtp
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:10 -c 0:15 -u postfix -C smtp -a 'smtp -t unix -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'"
+    hosts: liszt
+    depends: process - postfix - master
+  -
+    name: process - postfix - smtp
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:350 -c 0:500 -u postfix -C smtp -a 'smtp -t unix -u -c'"
+    hosts: liszt
+    depends: process - postfix - master
 
  ###
   -
@@ -774,12 +884,12 @@ 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
+    hosts: sperger, ries, steffani, merkel, spohr, peri, penalosa, albeniz, escher, verdi, liszt
  ###
   -
     name: process - acpid
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C acpid -a '/usr/sbin/acpid -c /etc/acpi/events -s /var/run/acpid.socket'"
-    hosts: ries, steffani
+    hosts: ries, steffani, liszt
 
  ###
   -
@@ -819,8 +929,8 @@ services:
     hosts: samosa
   -
     name: process - nagios3
-    # it forks one instance to check, so make it -w 1:2
-    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:2 -c 1: -u nagios -C nagios3 -a '/usr/sbin/nagios3 -d /etc/nagios3/nagios.cfg'"
+    # 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 nagios3 -a '/usr/sbin/nagios3 -d /etc/nagios3/nagios.cfg'"
     hosts: samosa
 
  ###
@@ -830,7 +940,7 @@ services:
     hostgroups: apache2-hosts
   -
     name: process - apache2 - worker
-    nrpe: "/usr/lib/nagios/plugins/check_procs -w 2:50 -c 1:100 -u www-data -C apache2 -a /usr/sbin/apache2"
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:50 -c 1:100 -u www-data -C apache2 -a /usr/sbin/apache2"
     hostgroups: apache2-hosts
     depends: process - apache2 - master
   -