X-Git-Url: https://git.adam-barratt.org.uk/?a=blobdiff_plain;f=config%2Fnagios-master.cfg;h=cf8594ce7261ac8aa44d7a12df977cd95d5267a0;hb=40389fe7ad8028bedd698e6d804e9474e1156594;hp=0bd082ade59b345d8dd5a05d4fa006f37563c7a4;hpb=1b390cdbb6a8c246b0877301b34550b2c6619c60;p=mirror%2Fdsa-nagios.git diff --git a/config/nagios-master.cfg b/config/nagios-master.cfg index 0bd082a..cf8594c 100644 --- a/config/nagios-master.cfg +++ b/config/nagios-master.cfg @@ -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, jessie, autofs, sw-raid praetorius: address: 130.239.18.121 parents: gw-accumu @@ -222,11 +222,15 @@ servers: mips-aql-01: address: 141.170.6.149 parents: gw-aql - hostgroups: computers, buildd, wheezy + hostgroups: computers, buildd, jessie, 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 @@ -244,15 +248,19 @@ servers: arnold: address: 217.140.96.57 parents: gw-arm - hostgroups: computers, hasbootfs, hassrvfs, buildd, wheezy, broken_mq + hostgroups: computers, hasbootfs, hassrvfs, buildd, jessie, broken_mq 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 + arm-arm-03: + address: 217.140.96.60 + parents: gw-arm + hostgroups: computers, hasbootfs, hassrvfs, buildd, jessie, broken_mq harris: address: 217.140.96.66 parents: gw-arm @@ -264,7 +272,7 @@ servers: hoiby: address: 217.140.96.71 parents: gw-arm - hostgroups: computers, hasbootfs, hassrvfs, armhf, wheezy, buildd, broken_mq + hostgroups: computers, hasbootfs, hassrvfs, armhf, jessie, buildd, broken_mq ia64-arm-01: address: 217.140.96.61 parents: gw-arm @@ -399,7 +407,7 @@ servers: dinis: address: 5.153.231.19 parents: ganeti-bytemark - hostgroups: computers, general, kvmdomains, wheezy + hostgroups: computers, general, kvmdomains, wheezy, hassrvfs donizetti: address: 5.153.231.20 parents: ganeti-bytemark @@ -425,11 +433,11 @@ 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 - hostgroups: computers, service, kvmdomains, wheezy, hassrvfs, porterbox + hostgroups: computers, service, kvmdomains, jessie, hassrvfs, porterbox quantz: address: 5.153.231.28 parents: ganeti-bytemark @@ -457,13 +465,24 @@ servers: lindsay: address: 5.153.231.36 parents: ganeti-bytemark - hostgroups: computers, service, kvmdomains, jessie + hostgroups: computers, service, kvmdomains, jessie, autofs, nfs-client + fede: + address: 5.153.231.37 + hostgroups: computers, service, kvmdomains, jessie, hassrvfs + sor: + address: 5.153.231.38 + parents: ganeti-bytemark + hostgroups: computers, service, kvmdomains, jessie, hassrvfs, apache2-hosts, autofs, nfs-client + jerea: + address: 5.153.231.39 + parents: ganeti-bytemark + hostgroups: computers, service, kvmdomains, jessie, hassrvfs, apache2-hosts # }}} # {{{ gw-c3sl santoro: address: 200.17.202.197 parents: gw-c3sl - hostgroups: computers, service, apache2-hosts, rsyncd-hosts, xinetd-hosts, hassrvfs, wheezy, high-RTT, security_mirror, no-bacula, apache-https + hostgroups: computers, service, apache2-hosts, rsyncd-hosts, xinetd-hosts, hassrvfs, jessie, high-RTT, security_mirror, no-bacula, apache-https contacts: faw # }}} # {{{ gw-carnet @@ -493,10 +512,6 @@ servers: hostgroups: computers, buildd, hassrvfs, sw-raid, wheezy, sparc # }}} # {{{ gw-csail - senfl: - address: 128.31.0.51 - parents: gw-csail - hostgroups: computers, service, dl360, acpid-hosts, hassrvfs, apache2-hosts, rsyncd-hosts, xinetd-hosts, squeeze, apache-https steffani: address: 128.31.0.36 parents: gw-csail @@ -531,6 +546,10 @@ servers: address: 128.31.0.50 parents: ganeti-csail hostgroups: computers, buildd, hassrvfs, kvmdomains, wheezy + httpredir-csail-01: + address: 128.31.0.66 + parents: ganeti-csail + hostgroups: computers, service, kvmdomains, jessie, apache2-hosts # }}} # {{{ gw-dgi storace: @@ -564,7 +583,19 @@ 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, apache-https + x86-grnet-01: + address: 194.177.211.203 + parents: ganeti-grnet + hostgroups: computers, buildd, hassrvfs, kvmdomains, jessie # }}} # {{{ gw-isc schein: @@ -624,7 +655,7 @@ 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 @@ -675,7 +706,7 @@ servers: geo1: address: 82.195.75.105 parents: ganeti3 - hostgroups: computers, service, bind9-hosts, kvmdomains, wheezy + hostgroups: computers, service, bind9-hosts, kvmdomains, jessie handel: address: 82.195.75.104 parents: ganeti3 @@ -687,7 +718,7 @@ 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 @@ -725,7 +756,7 @@ servers: zani: address: 148.100.88.22 parents: gw-marist - hostgroups: computers, buildd, hassrvfs, wheezy, incomingmailrelayed, ping-suckers + hostgroups: computers, buildd, hassrvfs, jessie, incomingmailrelayed # }}} # {{{ gw-osuosl busoni: @@ -739,7 +770,7 @@ servers: buxtehude: address: 140.211.166.26 parents: byrd - hostgroups: computers, service, hassrvfs, acpid-hosts, apache2-hosts, heavy-exim, postgres91-hosts, wheezy, hasvarlogfs, apache-https + hostgroups: computers, service, hassrvfs, acpid-hosts, apache2-hosts, heavy-exim, postgres91-hosts, wheezy, hasvarlogfs, apache-https, spamd # malo TODO mayer: address: 140.211.166.78 @@ -756,11 +787,11 @@ 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, jessie, hassrvfs, porterbox, sw-raid rietz: address: 140.211.166.43 parents: gw-osuosl @@ -798,7 +829,7 @@ 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: @@ -812,7 +843,7 @@ servers: eberlin: address: 86.59.118.155 parents: gw-sil - hostgroups: computers, buildd, wheezy + hostgroups: computers, buildd, wheezy, sw-raid # }}} # {{{ gw-ubcece sw-ubcece: @@ -884,7 +915,7 @@ servers: # MSA 2000 (2012i) giustini: address: 192.168.2.6 - parents: dijkstra + parents: sw-ubcece-kais hostgroups: notacomputer # unless we implement runfrom for host alive checks pingable: false @@ -911,14 +942,6 @@ servers: address: 206.12.19.15 parents: sw-ubcece-kais hostgroups: computers, buildd, wheezy - rossini: - address: 206.12.19.19 - parents: sw-ubcece-kais - hostgroups: computers, dl585, acpid-hosts, service, wheezy - salieri: - address: 206.12.19.20 - parents: sw-ubcece-kais - hostgroups: computers, dl585, acpid-hosts, service, wheezy traetta: address: 206.12.19.21 parents: sw-ubcece-kais @@ -929,11 +952,11 @@ servers: # hostgroups: computers, service, hasbootfs, kvmdomains, squeeze, hasvicepa lotti: address: 206.12.19.121 - parents: sw-ubcece-kais + parents: ganeti2 hostgroups: computers, service, hasbootfs, kvmdomains, wheezy, hassrvfs nono: address: 206.12.19.123 - parents: traetta + parents: ganeti2 hostgroups: computers, service, kvmdomains, wheezy, heavy-exim, xinetd-hosts, apache2-hosts, apache-https, broken_https_default_vhost reger: address: 206.12.19.124 @@ -945,7 +968,7 @@ servers: hostgroups: computers, service, kvmdomains, wheezy, postgres91-hosts, xinetd-hosts glinka: address: 206.12.19.126 - parents: traetta + parents: ganeti2 hostgroups: computers, service, kvmdomains, wheezy, apache2-hosts, nfs-client, autofs, xinetd-hosts tye: address: 206.12.19.129 @@ -953,7 +976,7 @@ servers: hostgroups: computers, service, kvmdomains, wheezy, heavy-exim, apache2-hosts, nfs-client, autofs, hassrvfs elgar: address: 206.12.19.130 - parents: salieri + parents: ganeti2 hostgroups: computers, service, kvmdomains, wheezy gombert: address: 206.12.19.132 @@ -961,7 +984,7 @@ servers: hostgroups: computers, service, kvmdomains, wheezy, apache2-hosts jenkins: address: 206.12.19.133 - parents: salieri + parents: ganeti2 hostgroups: computers, service, kvmdomains, wheezy blavet: address: 206.12.19.134 @@ -969,16 +992,12 @@ servers: hostgroups: computers, service, kvmdomains, wheezy, xinetd-hosts, nfs-client, autofs diabelli: address: 206.12.19.136 - parents: traetta + parents: ganeti2 hostgroups: computers, service, hasbootfs, kvmdomains, wheezy, apache2-hosts, apache-https, broken_https_default_vhost bizet: address: 206.12.19.137 parents: ganeti2 hostgroups: computers, service, kvmdomains, wheezy, hassrvfs, no-bacula - lilburn: - address: 206.12.19.138 - parents: ganeti2 - hostgroups: computers, service, kvmdomains, wheezy, hassrvfs, apache2-hosts, nfs-client, autofs popov: address: 206.12.19.119 parents: ganeti2 @@ -1020,11 +1039,19 @@ servers: prokofiev: address: 143.106.167.147 parents: gw-unicamp - hostgroups: computers, jessie, acpid-hosts, service + hostgroups: computers, jessie, service powerpc-unicamp-01: address: 143.106.167.149 parents: prokofiev - hostgroups: computers, hasbootfs, hassrvfs, buildd, wheezy + hostgroups: computers, hasbootfs, hassrvfs, buildd, jessie + ppc64el-unicamp-01: + address: 143.106.167.135 + parents: prokofiev + hostgroups: computers, hasbootfs, hassrvfs, buildd, jessie + plummer: + address: 143.106.167.146 + parents: prokofiev + hostgroups: computers, porterbox, hassrvfs, jessie # }}} # {{{ gw-utwente klecker: @@ -1048,7 +1075,7 @@ servers: henze: address: 144.32.168.74 parents: gw-ynic - hostgroups: computers, hasbootfs, hassrvfs, armhf, wheezy, buildd + hostgroups: computers, hasbootfs, hassrvfs, armhf, jessie, buildd hasse: address: 144.32.168.75 parents: gw-ynic @@ -1088,6 +1115,11 @@ 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 ############################# @@ -1095,6 +1127,9 @@ 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 @@ -1109,6 +1144,7 @@ hostgroups: freebsd: alias: freebsd private: 1 + extinfo-icon_image_alt: Debian GNU/kFreeBSD armhf: alias: armhf private: 1 @@ -1118,24 +1154,12 @@ 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 @@ -1171,8 +1195,6 @@ hostgroups: alias: Hosts with LSI Logic MegaRAID private: 1 - squeeze: - alias: Hosts running squeeze wheezy: alias: Hosts running wheezy jessie: @@ -1202,9 +1224,6 @@ 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 @@ -1296,9 +1315,6 @@ hostgroups: high-RTT: alias: machines with high round trip times private: 1 - ping-suckers: - alias: machines that just suck at icmp - private: 1 alioth: alias: machines that just are just awkward private: 1 @@ -1348,7 +1364,7 @@ services: name: PING check: "check_ping!350.0,20%!600.0,40%" hostgroups: pingable - excludehostgroups: layer3-infrastructure, high-RTT, ping-suckers + excludehostgroups: layer3-infrastructure, high-RTT normal_check_interval: 5 max_check_attempts: 4 retry_check_interval: 1 @@ -1359,13 +1375,6 @@ services: normal_check_interval: 5 max_check_attempts: 4 retry_check_interval: 1 - - - name: PING - check: "check_ping!600.0,90%!900.0,95%" - hostgroups: ping-suckers - normal_check_interval: 5 - max_check_attempts: 4 - retry_check_interval: 1 - name: PING check: "check_ping!2000.0,60%!3000.0,80%" @@ -1540,6 +1549,11 @@ 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%" @@ -1553,6 +1567,12 @@ 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" @@ -1639,6 +1659,16 @@ 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" @@ -1653,7 +1683,12 @@ 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" @@ -1685,12 +1720,16 @@ 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 @@ -1783,21 +1822,17 @@ services: name: process - ud-replicated nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u root -C ud-replicated -a '/usr/bin/python /usr/bin/ud-replicated'" hostgroups: computers - excludehostgroups: squeeze, freebsd, alioth + excludehostgroups: freebsd, alioth - name: process - ud-replicated nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u root -C python2.7 -a '/usr/bin/python /usr/bin/ud-replicated'" hostgroups: freebsd ### - - - name: process - monit - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u root -C monit -a '/usr/sbin/monit -d 300 -I -c /etc/monit/monitrc -s /var/lib/monit/monit.state'" - hostgroups: squeeze - 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: alioth, jessie ### - name: MQ connection on rainier @@ -1838,7 +1873,11 @@ 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" @@ -1856,7 +1895,7 @@ 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 @@ -1867,8 +1906,14 @@ 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, jessie + hostgroups: wheezy, jessie excludehostgroups: freebsd, alioth + - + name: process - stunnel4 - puppet-ekeyd is crazy + nrpe: "sudo /usr/lib/nagios/plugins/dsa-check-stunnel-sanity" + hostgroups: computers + excludehostgroups: freebsd, alioth + excludehosts: czerny, grnet-node01, storace # }}} # {{{ anti-services - @@ -1908,6 +1953,14 @@ services: name: "host SSL cert" nrpe: "if [ -e /etc/ssl/certs/thishost.pem ]; then /usr/lib/nagios/plugins/dsa-check-cert-expire /etc/ssl/certs/thishost.pem; else echo 'No thishost.pem on this host.'; fi" hostgroups: computers + - + name: "host SSL cert - debian server" + nrpe: "if [ -e /etc/ssl/debian/certs/thishost-server.crt ]; then /usr/lib/nagios/plugins/dsa-check-cert-expire /etc/ssl/debian/certs/thishost-server.crt; else echo 'No thishost-server.crt on this host.'; fi" + hostgroups: computers + - + name: "host SSL cert - debian client" + nrpe: "if [ -e /etc/ssl/debian/certs/thishost.crt ]; then /usr/lib/nagios/plugins/dsa-check-cert-expire /etc/ssl/debian/certs/thishost.crt; else echo 'No thishost.crt on this host.'; fi" + hostgroups: computers # }}} # {{{ HW health/raid - @@ -1921,12 +1974,18 @@ services: 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 - hostgroups: jessie + 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 @@ -1965,13 +2024,13 @@ services: # nrpe: "/usr/lib/nagios/plugins/dsa-check-edac" # normal_check_interval: 120 #hostgroups: computers - #excludehosts: villa, lobos, senfl, schein + #excludehosts: villa, lobos, schein - name: HW - hpasmcli status nrpe: "/usr/lib/nagios/plugins/dsa-check-hpasm" normal_check_interval: 120 hostgroups: dl385, dl380, dl360, bl460, dl585, bm-bl - excludehosts: villa, lobos, senfl, schein, storace + excludehosts: villa, lobos, schein, storace - name: HW - hpasmcli status nrpe: "/usr/lib/nagios/plugins/dsa-check-hpasm --ps-no-redundant" @@ -1986,7 +2045,7 @@ services: name: HW - hpasmcli status nrpe: "/usr/lib/nagios/plugins/dsa-check-hpasm --fan-no-redundant" normal_check_interval: 120 - hosts: senfl, schein + hosts: schein - name: HW - hpasmcli status nrpe: "/usr/lib/nagios/plugins/dsa-check-hpasm --fan-ignore-not-present" @@ -2091,21 +2150,12 @@ services: hostgroups: spamd depends: process - spamd - master # - - - name: process - spamd - master - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u debbugs -C spamd -a '/usr/sbin/spamd -d '" - hosts: buxtehude - - - name: process - spamd - child - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:6 -c 1: -u debbugs -C spamd -a 'spamd child'" - hosts: buxtehude - # - name: unwanted process - spamd nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C spamd" hostgroups: computers excludehostgroups: spamd - excludehosts: bendel, busoni, buxtehude + excludehosts: bendel, busoni - name: unwanted process - greylistd @@ -2450,7 +2500,7 @@ 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 @@ -2575,6 +2625,14 @@ 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'" @@ -2619,16 +2677,6 @@ 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"