raise check interval
[mirror/dsa-nagios.git] / config / nagios-master.cfg
index 7b85fcd..f05b767 100644 (file)
@@ -140,6 +140,7 @@ servers:
     parents: gw-ubcece
     hostgroups: layer3-infrastructure
     contact_groups: +alioth-admins
+    no-servicegroups: true
   gw-ubcece:
     address: 206.12.19.254
     hostgroups: layer3-infrastructure
@@ -254,9 +255,9 @@ servers:
   old-master:
     address: 97.107.116.29
     parents: gw-brainfood
-    hostgroups: computers, general, apache2-hosts, spamd, heavy-exim, highload, xinetd-hosts, mptraid, squeeze, bacula-client
+    hostgroups: computers, general, spamd, heavy-exim, highload, xinetd-hosts, mptraid, squeeze, bacula-client
   murphy:
-    address: 70.103.162.31
+    address: 97.107.116.31
     parents: gw-brainfood
     hostgroups: computers, general, dl380, acpid-hosts, buildd, hasbootfs, hassrvfs, squeeze
   # }}}
@@ -460,23 +461,23 @@ servers:
     hostgroups: computers, service, dl360, acpid-hosts, squeeze
   diamond:
     address: 82.195.75.108
-    parents: unger
+    parents: ganeti3
     hostgroups: computers, service, hasbootfs, kvmdomains, squeeze, bind9-hosts
   draghi:
     address: 82.195.75.106
-    parents: unger
+    parents: ganeti3
     hostgroups: computers, service, hasbootfs, hassrvfs, apache2-hosts, bind9-hosts, spamd, heavy-exim, kvmdomains, xinetd-hosts, apache-https, squeeze, bacula-client
   geo1:
     address: 82.195.75.105
-    parents: unger
+    parents: ganeti3
     hostgroups: computers, service, hasbootfs, bind9-hosts, kvmdomains, squeeze
   handel:
     address: 82.195.75.104
-    parents: unger
+    parents: ganeti3
     hostgroups: computers, service, hasbootfs, kvmdomains, apache2-hosts, squeeze, apache-https, hasvarfs
   kaufmann:
     address: 82.195.75.107
-    parents: unger
+    parents: ganeti3
     hostgroups: computers, service, hasbootfs, apache2-hosts, rsyncd-hosts, kvmdomains, xinetd-hosts, squeeze
   ganeti3:
     address: 82.195.75.111
@@ -486,11 +487,14 @@ servers:
     address: 82.195.75.112
     parents: ganeti3
     hostgroups: computers, service, hassrvfs, apache2-hosts, kvmdomains, wheezy, acpid-hosts, apache2-hosts, apache-https, bacula-client
-
-#  lamb:
-#    address: 82.195.75.101
-#    parents: unger
-#    hostgroups: computers, service, hasbootfs, kvmdomains, squeeze, hasvicepa, bosserver
+  vieuxtemps:
+    address: 82.195.75.113
+    parents: ganeti3
+    hostgroups: computers, service, kvmdomains, wheezy, varnish-hosts
+  mailly:
+    address: 82.195.75.114
+    parents: ganeti3
+    hostgroups: computers, service, kvmdomains, wheezy, spamd, heavy-exim, mail-relay
   # }}}
   # {{{ gw-marist
   zappa:
@@ -506,11 +510,11 @@ servers:
   byrd:
     address: 140.211.166.20
     parents: gw-osuosl
-    hostgroups: computers, service, dl380, acpid-hosts, squeeze
+    hostgroups: computers, service, dl380, acpid-hosts, wheezy
   buxtehude:
     address: 140.211.166.26
     parents: byrd
-    hostgroups: computers, service, hassrvfs, acpid-hosts, apache2-hosts, heavy-exim, postgres91-hosts, squeeze, hasvarlogfs
+    hostgroups: computers, service, hassrvfs, acpid-hosts, apache2-hosts, heavy-exim, postgres91-hosts, wheezy, hasvarlogfs
   # malo TODO
   mayer:
     address: 140.211.166.78
@@ -609,11 +613,19 @@ servers:
     parents: gw-telegraaf2
     hostgroups: computers, nfs-server, postgres84-hosts, apache2-hosts, acpid-hosts, apache-https, brokensamhain
     contact_groups: alioth-admins
+    no-servicegroups: true
   wagner:
     address: 217.196.43.132
     parents: gw-telegraaf2
     hostgroups: computers, bind9-hosts, apache2-hosts, nfs-client, xinetd-hosts, postgres91-hosts, apache-https, dl385, brokensamhain
     contact_groups: alioth-admins
+    no-servicegroups: true
+  anonscm:
+    address: 217.196.43.132
+    parents: wagner
+    contact_groups: alioth-admins
+    hostgroups: secondary-IPs
+    no-servicegroups: true
   # }}}
   # {{{ gw-ubcece
   sw-ubcece:
@@ -733,7 +745,7 @@ servers:
   gabrielli:
     address: 206.12.19.17
     parents: sw-ubcece-kais
-    hostgroups: computers, porterbox, squeeze
+    hostgroups: computers, porterbox, wheezy
   corelli:
     address: 206.12.19.16
     parents: sw-ubcece-kais
@@ -745,7 +757,7 @@ servers:
   rossini:
     address: 206.12.19.19
     parents: sw-ubcece-kais
-    hostgroups: computers, dl585, acpid-hosts, service, squeeze
+    hostgroups: computers, dl585, acpid-hosts, service, wheezy
   salieri:
     address: 206.12.19.20
     parents: sw-ubcece-kais
@@ -855,6 +867,10 @@ servers:
     address: 206.12.19.145
     parents: ganeti2
     hostgroups: computers, service, kvmdomains, wheezy, hassrvfs, apache2-hosts
+  muffat:
+    address: 206.12.19.146
+    parents: ganeti2
+    hostgroups: computers, service, kvmdomains, wheezy, spamd, heavy-exim, mail-relay
   # }}}
   # {{{ gw-ugent
   ancina:
@@ -873,7 +889,7 @@ servers:
   klecker:
     address: 130.89.148.10
     parents: gw-utwente
-    hostgroups: computers, service, apache2-hosts, rsyncd-hosts, dl380, acpid-hosts, xinetd-hosts, squeeze, incomingmailrelayed, hassrvfs
+    hostgroups: computers, service, apache2-hosts, rsyncd-hosts, dl380, acpid-hosts, xinetd-hosts, squeeze, incomingmailrelayed2025, hassrvfs
   klecker-ftp:
     address: 130.89.148.12
     parents: klecker
@@ -1028,6 +1044,9 @@ hostgroups:
   apache2-hosts:
     alias: hosts running apache2
     private: 1
+  varnish-hosts:
+    alias: hosts running varnish
+    private: 1
   bind9-hosts:
     alias: hosts running bind9
     private: 1
@@ -1155,6 +1174,8 @@ servicegroups:
     alias: buildd checks
   raid:
     alias: raid checks
+  backup:
+    alias: backup checks
   kernel:
     alias: kernel checks
   weaksshkeys:
@@ -1365,6 +1386,7 @@ services:
  ####
   -
     name: backup
+    servicegroups: backup
     nrpe: "sudo /usr/lib/nagios/plugins/dsa-check-dabackup"
     hostgroups: computers
     normal_check_interval: 60
@@ -1372,6 +1394,7 @@ services:
     retry_check_interval: 5
   -
     name: backup server config
+    servicegroups: backup
     nrpe: "/usr/lib/nagios/plugins/dsa-check-dabackup-server"
     hosts: beethoven
     normal_check_interval: 60
@@ -1379,17 +1402,38 @@ services:
     retry_check_interval: 5
   -
     name: backup - bacula
+    servicegroups: backup
     remotecheck: "sudo /usr/lib/nagios/plugins/dsa-check-bacula -H $HOSTNAME$"
     runfrom: dinis
     hostgroups: bacula-client
+    normal_check_interval:  60
+    retry_check_interval: 15
+  -
+    name: backup - bacula - last backup
+    servicegroups: backup
+    remotecheck: "sudo /usr/lib/nagios/plugins/dsa-check-bacula-lastbackup-wrap any $HOSTNAME$"
+    runfrom: dinis
+    hostgroups: bacula-client
+    normal_check_interval:  60
+    retry_check_interval: 15
+  -
+    name: backup - bacula - last full backup
+    servicegroups: backup
+    remotecheck: "sudo /usr/lib/nagios/plugins/dsa-check-bacula-lastbackup-wrap full $HOSTNAME$"
+    runfrom: dinis
+    hostgroups: bacula-client
+    normal_check_interval:  60
+    retry_check_interval: 15
   -
     name: process - bacula-fd
+    servicegroups: backup
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C bacula-fd -a '/usr/sbin/bacula-fd -c /etc/bacula/bacula-fd.conf'"
     hostgroups: computers
     excludehostgroups: freebsd
     excludehosts: wagner, vasks
   -
     name: process - bacula-fd
+    servicegroups: backup
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:3 -c 1: -u root -C bacula-fd -a '/usr/sbin/bacula-fd -c /etc/bacula/bacula-fd.conf'"
     hostgroups: freebsd
 
@@ -1978,6 +2022,13 @@ services:
     servicegroups: raid
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u root -C mdadm -a '/sbin/mdadm --monitor --pid-file /var/run/mdadm/monitor.pid --daemonise --scan'"
     hostgroups: sw-raid
+    excludehosts: argento
+  -
+    # wheezy:
+    name: process - mdadm monitor
+    servicegroups: raid
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u root -C mdadm -a '/sbin/mdadm --monitor --pid-file /run/mdadm/monitor.pid --daemonise --scan'"
+    hosts: argento
   -
     name: RAID - sw raid
     servicegroups: raid
@@ -2001,6 +2052,7 @@ services:
     nrpe: "sudo /usr/bin/arrayprobe"
     hostgroups: dl385, dl380, dl360, bl460, dl585
     excludehosts: franck
+    excludehostgroups: wheezy
   -
     name: RAID - arrayprobe
     servicegroups: raid
@@ -2250,6 +2302,33 @@ services:
     excludehosts: ravel
     normal_check_interval: 60
 
+###
+  -
+    name: process - varnish - master
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u root -C varnishd -a '/usr/sbin/varnishd -P /var/run/varnishd.pid -a :80 -T localhost:6082 -f /etc/varnish/default.vcl'"
+    hostgroups: varnish-hosts
+  -
+    name: process - varnish - worker
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u nobody -C varnishd -a '/usr/sbin/varnishd -P /var/run/varnishd.pid -a :80 -T localhost:6082 -f /etc/varnish/default.vcl'"
+    hostgroups: varnish-hosts
+    depends: process - varnish - master
+  -
+    name: network service - http
+    check: check_http
+    hostgroups: varnish-hosts
+    depends: process - varnish - master
+
+###
+
+# Alioth web URLs
+
+  -
+    name: network service - loggerhead
+    remotecheck: "/usr/lib/nagios/plugins/check_http -H anonscm.debian.org -u /loggerhead/"
+    hosts: anonscm
+    runfrom: tchaikovsky
+    depends: wagner:process - apache2 - master
+
  ####
   -
     name: process - named