arm-arm-0[12] run jessie now
[mirror/dsa-nagios.git] / config / nagios-master.cfg
index e9c4c8f..2b03415 100644 (file)
@@ -118,6 +118,10 @@ servers:
     address: 193.201.200.129
     parents: gw-ubcece
     hostgroups: layer3-infrastructure
+  gw-sakura:
+    address: 133.242.99.65
+    parents: gw-ubcece
+    hostgroups: layer3-infrastructure
   gw-sanger:
     address: 193.62.202.20
     parents: gw-ubcece
@@ -195,10 +199,6 @@ servers:
     address: 195.20.242.124
     parents: schumann
     hostgroups: computers, service, apache2-hosts, hassrvfs, hasbootfs, rsyncd-hosts, uploadqueue, kvmdomains, xinetd-hosts, apache-https, postgres91-hosts, wheezy
-  geo3:
-    address: 195.20.242.125
-    parents: schumann
-    hostgroups: computers, service, hasbootfs, bind9-hosts, kvmdomains, wheezy
   soler:
     address: 195.20.242.126
     parents: schumann
@@ -212,7 +212,7 @@ servers:
   pettersson:
     address: 130.239.18.123
     parents: gw-accumu
-    hostgroups: computers, hasbootfs, aacraid, nfs-client, acpid-hosts, service, apache2-hosts, wheezy, autofs
+    hostgroups: computers, hasbootfs, aacraid, nfs-client, acpid-hosts, service, apache2-hosts, wheezy, autofs, sw-raid
   praetorius:
     address: 130.239.18.121
     parents: gw-accumu
@@ -222,11 +222,23 @@ servers:
   mips-aql-01:
     address: 141.170.6.149
     parents: gw-aql
-    hostgroups: computers, buildd, wheezy
+    hostgroups: computers, buildd, wheezy, nfs-client
   mips-aql-02:
     address: 141.170.6.150
     parents: gw-aql
-    hostgroups: computers, buildd, wheezy
+    hostgroups: computers, buildd, wheezy, nfs-client
+  minkus:
+    address: 141.170.6.151
+    parents: gw-aql
+    hostgroups: computers, porterbox, jessie, nfs-client
+  mipsel-aql-01:
+    address: 141.170.6.152
+    parents: gw-aql
+    hostgroups: computers, buildd, jessie, hassrvfs, hasbootfs, sw-raid
+  mipsel-aql-02:
+    address: 141.170.6.153
+    parents: gw-aql
+    hostgroups: computers, buildd, jessie, hassrvfs, hasbootfs, sw-raid
   # }}}
   # {{{ gw-arm
   abel:
@@ -240,11 +252,11 @@ servers:
   arm-arm-01:
     address: 217.140.96.58
     parents: gw-arm
-    hostgroups: computers, hasbootfs, hassrvfs, buildd, wheezy, broken_mq
+    hostgroups: computers, hasbootfs, hassrvfs, buildd, jessie, broken_mq
   arm-arm-02:
     address: 217.140.96.59
     parents: gw-arm
-    hostgroups: computers, hasbootfs, hassrvfs, buildd, wheezy, broken_mq
+    hostgroups: computers, hasbootfs, hassrvfs, buildd, jessie, broken_mq
   harris:
     address: 217.140.96.66
     parents: gw-arm
@@ -260,7 +272,7 @@ servers:
   ia64-arm-01:
     address: 217.140.96.61
     parents: gw-arm
-    hostgroups: computers, hasbootfs, hassrvfs, wheezy, buildd, broken_mq, sw-raid
+    hostgroups: computers, hasbootfs, hassrvfs, wheezy, buildd, broken_mq, sw-raid, acpid-hosts
   # }}}
   # {{{ gw-brown
   franck:
@@ -363,11 +375,7 @@ servers:
   coccia:
     address: 5.153.231.11
     parents: ganeti-bytemark
-    hostgroups: computers, hassrvfs, kvmdomains, wheezy, autofs, nfs-client, uploadqueue, xinetd-hosts
-  backuphost:
-    address: 5.153.231.12
-    parents: ganeti-bytemark
-    hostgroups: computers, hassrvfs, kvmdomains, wheezy
+    hostgroups: computers, hassrvfs, kvmdomains, wheezy, autofs, nfs-client, uploadqueue, xinetd-hosts, apache-https, apache2-hosts
   philp:
     address: 5.153.231.13
     parents: ganeti-bytemark
@@ -421,7 +429,7 @@ servers:
   oyens:
     address: 5.153.231.26
     parents: ganeti-bytemark
-    hostgroups: computers, kvmdomains, wheezy, apache2-hosts, openstack-controller, apache-https, broken_mq
+    hostgroups: computers, kvmdomains, jessie, apache2-hosts, openstack-controller, apache-https, broken_mq
   barriere:
     address: 5.153.231.27
     parents: ganeti-bytemark
@@ -450,6 +458,17 @@ servers:
     address: 5.153.231.35
     parents: ganeti-bytemark
     hostgroups: computers, service, kvmdomains, wheezy, apache2-hosts
+  lindsay:
+    address: 5.153.231.36
+    parents: ganeti-bytemark
+    hostgroups: computers, service, kvmdomains, jessie
+  fede:
+    address: 5.153.231.37
+    hostgroups: computers, service, kvmdomains, wheezy, hassrvfs
+  sor:
+    address: 5.153.231.38
+    parents: ganeti-bytemark
+    hostgroups: computers, service, kvmdomains, jessie, hassrvfs, apache2-hosts, autofs, nfs-client
   # }}}
   # {{{ gw-c3sl
   santoro:
@@ -556,7 +575,15 @@ servers:
   loghost-grnet-01:
     address: 194.177.211.200
     parents: gw-grnet
-    hostgroups: computers, service, kvmdomains, wheezy, hassrvfs
+    hostgroups: computers, service, kvmdomains, jessie, hassrvfs
+  geo3:
+    address: 194.177.211.201
+    parents: gw-grnet
+    hostgroups: computers, service, bind9-hosts, kvmdomains, jessie
+  cgi-grnet-01:
+    address: 194.177.211.202
+    parents: gw-grnet
+    hostgroups: computers, service, kvmdomains, jessie, hassrvfs, apache2-hosts
   # }}}
   # {{{ gw-isc
   schein:
@@ -616,7 +643,7 @@ servers:
   ball:
     address: 82.195.75.70
     parents: gw-man-da
-    hostgroups: computers, buildd, hasbootfs, wheezy
+    hostgroups: computers, buildd, hasbootfs, wheezy, sw-raid
   # bartok TODO
   czerny:
     address: 82.195.75.109
@@ -660,10 +687,6 @@ servers:
     address: 82.195.75.99
     parents: ganeti3
     hostgroups: computers, service, hasbootfs, kvmdomains, wheezy, hasvarlogfs
-  rem:
-    address: 82.195.75.68
-    parents: gw-man-da
-    hostgroups: computers, hasbootfs, hassrvfs, wheezy, no-bacula
   draghi:
     address: 82.195.75.106
     parents: ganeti3
@@ -683,7 +706,7 @@ servers:
   stockhausen:
     address: 82.195.75.108
     parents: ganeti3
-    hostgroups: computers, service, kvmdomains, wheezy, acpid-hosts, jetty-hosts
+    hostgroups: computers, service, kvmdomains, jessie, acpid-hosts
   ganeti3:
     address: 82.195.75.111
     parents: gw-man-da
@@ -704,6 +727,10 @@ servers:
     address: 82.195.75.92
     parents: ganeti3
     hostgroups: computers, service, kvmdomains, wheezy
+  wolkenstein:
+    address: 82.195.75.65
+    parents: ganeti3
+    hostgroups: computers, hasbootfs, hassrvfs, kvmdomains, service, xinetd-hosts, rsyncd-hosts, apache2-hosts, wheezy
   mipsel-manda-01:
     address: 82.195.75.72
     parents: gw-man-da
@@ -748,11 +775,11 @@ servers:
   parry:
     address: 140.211.15.153
     parents: gw-osuosl
-    hostgroups: computers, wheezy, buildd, hassrvfs
+    hostgroups: computers, wheezy, buildd, hassrvfs, sw-raid
   partch:
     address: 140.211.15.152
     parents: gw-osuosl
-    hostgroups: computers, wheezy, hassrvfs, porterbox
+    hostgroups: computers, wheezy, hassrvfs, porterbox, sw-raid
   rietz:
     address: 140.211.166.43
     parents: gw-osuosl
@@ -790,7 +817,7 @@ servers:
   villa:
     address: 212.211.132.32
     parents: gw-scanplus-villa
-    hostgroups: computers, service, apache2-hosts, rsyncd-hosts, dl380, hasvarfs, hasusrfs, hasorgfs, xinetd-hosts, wheezy, security_mirror, no-bacula
+    hostgroups: computers, service, apache2-hosts, rsyncd-hosts, dl360, hassrvfs, xinetd-hosts, jessie, security_mirror, acpid-hosts
   # }}}
   # {{{ gw-sil
   eder:
@@ -804,7 +831,7 @@ servers:
   eberlin:
     address: 86.59.118.155
     parents: gw-sil
-    hostgroups: computers, buildd, wheezy
+    hostgroups: computers, buildd, wheezy, sw-raid
   # }}}
   # {{{ gw-ubcece
   sw-ubcece:
@@ -865,10 +892,6 @@ servers:
     address: 206.12.19.118
     parents: ganeti2
     hostgroups: computers, general, apache2-hosts, hasbootfs, kvmdomains, apache-https, wheezy
-  wolkenstein:
-    address: 206.12.19.116
-    parents: ganeti2
-    hostgroups: computers, hasbootfs, hassrvfs, kvmdomains, service, xinetd-hosts, rsyncd-hosts, apache2-hosts, wheezy
   brahms:
     address: 206.12.19.115
     parents: ganeti2
@@ -1013,10 +1036,18 @@ servers:
     address: 143.106.167.145
     parents: gw-unicamp
     hostgroups: layer3-infrastructure
+  prokofiev:
+    address: 143.106.167.147
+    parents: gw-unicamp
+    hostgroups: computers, jessie, service
   powerpc-unicamp-01:
     address: 143.106.167.149
-    parents: asgard
+    parents: prokofiev
     hostgroups: computers, hasbootfs, hassrvfs, buildd, wheezy
+  ppc64el-unicamp-01:
+    address: 143.106.167.135
+    parents: prokofiev
+    hostgroups: computers, hasbootfs, hassrvfs, buildd, jessie
   # }}}
   # {{{ gw-utwente
   klecker:
@@ -1080,6 +1111,11 @@ servers:
     parents: gw-zivit
     hostgroups: computers, porterbox, hassrvfs, wheezy
   # }}}
+  # {{{ gw-sakura
+  setoguchi:
+    address: 133.242.99.74
+    parents: gw-sakura
+    hostgroups: computers, service, wheezy, no-bacula, hassrvfs, apache2-hosts, rsyncd-hosts, xinetd-hosts, security_mirror, acpid-hosts
   # }}}
 
 # {{{ ############################# host groups #############################
@@ -1087,6 +1123,9 @@ hostgroups:
   computers:
     alias: computers
     private: 1
+    extinfo-icon_image: base/debian.png
+    extinfo-icon_image_alt: Debian GNU/Linux
+    extinfo-notes_url: https://db.debian.org/machines.cgi?host=%s
   layer2-infrastructure:
     alias: Layer 2 Devices
     extinfo-icon_image: base/switch40.png
@@ -1101,6 +1140,7 @@ hostgroups:
   freebsd:
     alias: freebsd
     private: 1
+    extinfo-icon_image_alt: Debian GNU/kFreeBSD
   armhf:
     alias: armhf
     private: 1
@@ -1110,24 +1150,12 @@ hostgroups:
 
   porterbox:
     alias: developer accessible porter machines
-    extinfo-icon_image: base/debian.png
-    extinfo-icon_image_alt: Debian GNU/Linux
-    extinfo-notes_url: http://db.debian.org/machines.cgi?host=%s
   service:
     alias: machines running services
-    extinfo-icon_image: base/debian.png
-    extinfo-icon_image_alt: Debian GNU/Linux
-    extinfo-notes_url: http://db.debian.org/machines.cgi?host=%s
   buildd:
     alias: buildd systems
-    extinfo-icon_image: base/debian.png
-    extinfo-icon_image_alt: Debian GNU/Linux
-    extinfo-notes_url: http://db.debian.org/machines.cgi?host=%s
   general:
     alias: general purpose developer accessible machines
-    extinfo-icon_image: base/debian.png
-    extinfo-icon_image_alt: Debian GNU/Linux
-    extinfo-notes_url: http://db.debian.org/machines.cgi?host=%s
 
   dl380:
     alias: HP DL380 hosts
@@ -1167,6 +1195,8 @@ hostgroups:
     alias: Hosts running squeeze
   wheezy:
     alias: Hosts running wheezy
+  jessie:
+    alias: Hosts running jessie
 
   kvmdomains:
     alias: Hosts that are KVM domains
@@ -1192,9 +1222,6 @@ hostgroups:
   apache2-hosts:
     alias: hosts running apache2
     private: 1
-  jetty-hosts:
-    alias: hosts running jetty
-    private: 1
   bind9-hosts:
     alias: hosts running bind9
     private: 1
@@ -1530,6 +1557,11 @@ services:
     name: processes - total
     nrpe: "/usr/lib/nagios/plugins/check_procs 620 700"
     hostgroups: computers
+    excludehosts: prokofiev
+  -
+    name: processes - total
+    nrpe: "/usr/lib/nagios/plugins/check_procs 1500 1700"
+    hosts: prokofiev
   -
     name: swap usage - percent
     nrpe: "/usr/lib/nagios/plugins/check_swap -w 20% -c 10%"
@@ -1543,6 +1575,12 @@ services:
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:8 -c 1: -u root -C getty -a /sbin/getty"
     hostgroups: computers
     excludehosts: zelenka, zandonai
+    excludehostgroups: jessie
+  -
+    name: process - getty
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:8 -c 1: -u root -C agetty -a /sbin/agetty"
+    hostgroups: computers
+    hostgroups: jessie
   -
     name: processes - zombies
     nrpe: "/usr/lib/nagios/plugins/check_procs 5 10 -s Z"
@@ -1566,7 +1604,7 @@ services:
     servicegroups: backup
     nrpe: "sudo /usr/lib/nagios/plugins/dsa-check-dabackup"
     hostgroups: computers
-    excludehosts: backuphost, storace
+    excludehosts: storace
     normal_check_interval: 60
     max_check_attempts: 2
     retry_check_interval: 5
@@ -1574,7 +1612,7 @@ services:
     name: backup server config
     servicegroups: backup
     nrpe: "/usr/lib/nagios/plugins/dsa-check-dabackup-server"
-    hosts: backuphost, storace
+    hosts: storace
     normal_check_interval: 60
     max_check_attempts: 2
     retry_check_interval: 5
@@ -1629,6 +1667,16 @@ services:
     hostgroups: computers
     normal_check_interval:  60
     retry_check_interval: 15
+  -
+    name: upgraded libraries
+    servicegroups: security
+    nrpe: "sudo /usr/local/sbin/dsa-check-libs"
+    #nrpe: "sudo /usr/lib/nagios/plugins/dsa-check-libs"
+    hostgroups: computers
+    excludehostgroups: freebsd
+    normal_check_interval:  60
+    retry_check_interval: 15
+    notification_interval: 10080
   -
     name: installed firewall
     nrpe: "/usr/lib/nagios/plugins/dsa-check-file -w -f /etc/ferm/ferm.conf"
@@ -1643,7 +1691,12 @@ services:
     name: process - ulogd
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C ulogd -a '/usr/sbin/ulogd -d'"
     hostgroups: computers
-    excludehostgroups: freebsd, sparc
+    excludehostgroups: freebsd, sparc, jessie
+  -
+    name: process - ulogd
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u ulog -C ulogd -a '/usr/sbin/ulogd --daemon --uid ulog'"
+    hostgroups: jessie
+    excludehostgroups: freebsd
   -
     name: unexpected process - ulogd
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C ulogd"
@@ -1675,12 +1728,16 @@ 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: computers
-    excludehostgroups: freebsd
+    excludehostgroups: freebsd, jessie
 
   -
     name: process - syslog-ng
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 2:2 -c 2: -u root -C syslog-ng  -a '/sbin/syslog-ng -p /var/run/syslog-ng.pid'"
     hostgroups: freebsd
+  -
+    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 -F'"
+    hostgroups: jessie
 
   -
     name: remote logging on lotti
@@ -1739,7 +1796,7 @@ services:
   -
     name: process - munin-node
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:3 -c 1: -u root -C munin-node -a 'munin-node'"
-    hostgroups: wheezy
+    hostgroups: wheezy, jessie
     excludehostgroups: freebsd
   -
     name: network service - munin-node
@@ -1787,7 +1844,7 @@ services:
     name: process - monit
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u root -C monit -a '/usr/bin/monit -d 300 -I -c /etc/monit/monitrc -s /var/lib/monit/monit.state'"
     hostgroups: computers
-    excludehostgroups: squeeze, alioth
+    excludehostgroups: squeeze, alioth, jessie
   ###
   -
     name: MQ connection on rainier
@@ -1828,7 +1885,11 @@ services:
     name: process - udevd
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -p 1 -C udevd -a 'udevd'"
     hostgroups: computers
-    excludehostgroups: freebsd
+    excludehostgroups: freebsd, jessie
+  -
+    name: process - udevd
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -p 1 -C systemd-udevd -a '/lib/systemd/systemd-udevd'"
+    hostgroups: jessie
   -
     name: unexpected process - udev
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C udevd"
@@ -1846,7 +1907,7 @@ 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'"
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C xinetd -a '/usr/sbin/xinetd '"
     hostgroups: xinetd-hosts
   -
     name: unwanted process - xinetd
@@ -1857,7 +1918,7 @@ services:
   -
     name: process - stunnel4 - puppet-ekeyd
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:6 -c 1: -u stunnel4 -C stunnel4 -a '/usr/bin/stunnel4 /etc/stunnel/puppet-ekeyd.conf'"
-    hostgroups: squeeze, wheezy
+    hostgroups: squeeze, wheezy, jessie
     excludehostgroups: freebsd, alioth
   # }}}
   # {{{ anti-services
@@ -1905,11 +1966,24 @@ 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 /run/mdadm/monitor.pid --daemonise --scan'"
     hostgroups: sw-raid
+    excludehostgroups: jessie
+  -
+    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 --scan'"
+    hostgroups: sw-raid
+    excludehostgroups: wheezy
   -
     name: RAID - sw raid
     servicegroups: raid
     nrpe: "/usr/lib/nagios/plugins/dsa-check-raid-sw"
     hostgroups: sw-raid
+  -
+    name: RAID - unexpected sw raid
+    servicegroups: raid
+    nrpe: "if [ -e /proc/mdstat ]; then echo 'Found /proc/mdstat'; exit 1; else echo 'No /proc/mdstat on this host.'; fi"
+    hostgroups: computers
+    excludehostgroups: sw-raid
   ###
   -
     name: HW - hpacucli status
@@ -2433,7 +2507,7 @@ services:
   # {{{ DNS
   -
     name: process - named
-    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:15 -c 1: -u bind -C named -a '/usr/sbin/named -u bind'"
+    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:15 -c 1: -u bind -C named -a '/usr/sbin/named '"
     hostgroups: bind9-hosts
   -
     name: network service - dns
@@ -2558,6 +2632,14 @@ services:
     hostgroups: openstack-controller
   # }}}
   # {{{ misc
+#  -
+#    Disable this check until logind and binfmt_misc issues are fixed
+#    something unknown is triggering mount of binfmt_misc
+#    https://bugs.debian.org/772700
+#    name: system - all services running
+#    nrpe: "/usr/bin/sudo /bin/systemctl is-system-running"
+#    hostgroups: jessie
+  ###
   -
     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'"
@@ -2602,16 +2684,6 @@ services:
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:30 -c 1: -u nagios -C icinga -a '/usr/sbin/icinga -d /etc/icinga/icinga.cfg'"
     hosts: tchaikovsky
   ###
-  -
-    name: process - jetty - master
-    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u root -a 'jsvc.exec'"
-    hostgroups: jetty-hosts
-  -
-    name: process - jetty - worker
-    nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:50 -c 1:100 -u jetty -a 'jsvc.exec -user jetty'"
-    hostgroups: jetty-hosts
-    depends: process - jetty - master
-  ###
   -
     name: process - debianqueued
     nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:3 -c 1: -u dak-unpriv -C debianqueued"
@@ -2623,6 +2695,17 @@ services:
     hosts: gombert
     contact_groups: gobby
   ####
+  -
+    name: network service - sip-tls cert - 443
+    check: dsa_check_cert!443
+    normal_check_interval: 60
+    hosts: vogler
+  -
+    name: network service - sip-tls cert - 5061
+    check: dsa_check_cert!5061
+    normal_check_interval: 60
+    hosts: vogler
+  ####
   -
     name: puppetmaster cert
     nrpe: "/usr/lib/nagios/plugins/dsa-check-cert-expire /var/lib/puppet/ssl/certs/ca.pem"