X-Git-Url: https://git.adam-barratt.org.uk/?a=blobdiff_plain;f=config%2Fnagios-master.cfg;h=c84a5388262354928892bd3129098b1389b1f2aa;hb=aab05b213145d092a13a7cf3c63162296f71b58d;hp=84129c4d90553d98c772849c1f52023e5d569ab7;hpb=45d089eab67c5c776ee54255b722c3e9f2eb339a;p=mirror%2Fdsa-nagios.git diff --git a/config/nagios-master.cfg b/config/nagios-master.cfg index 84129c4..c84a538 100644 --- a/config/nagios-master.cfg +++ b/config/nagios-master.cfg @@ -85,18 +85,10 @@ servers: address: 72.52.94.70 parents: gw-ubcece hostgroups: layer3-infrastructure - gw-karlsruhe: - address: 129.143.59.214 - parents: gw-ubcece - hostgroups: layer3-infrastructure gw-leaseweb: address: 185.17.185.190 parents: gw-ubcece hostgroups: layer3-infrastructure - gw-linaro: - address: 64.28.108.36 - parents: gw-ubcece - hostgroups: layer3-infrastructure gw-manda: address: 82.195.78.118 parents: gw-ubcece @@ -174,18 +166,19 @@ servers: schumann: address: 212.227.126.54 parents: gw-1und1-sec - hostgroups: computers, service, stretch + hostgroups: computers, service, apache2-hosts, rsyncd-hosts, stretch, security_mirror, hassrvfs, pe1950 wieck: address: 195.20.242.89 parents: gw-1und1-sec - hostgroups: computers, service, apache2-hosts, rsyncd-hosts, stretch, security_mirror, hasvarlogfs, no-bacula + hostgroups: computers, service, apache2-hosts, rsyncd-hosts, stretch, security_mirror, hasvarlogfs, no-bacula, pe1950 # }}} # {{{ gw-accumu pettersson: address: 130.239.18.123 parents: gw-accumu - hostgroups: computers, hasbootfs, aacraid, nfs-client, service, apache2-hosts, jessie, autofs, sw-raid - ## No need to update to Stretch, casulana replaces it. It should eventually die. + hostgroups: computers, hasbootfs, aacraid, nfs-client, service, apache2-hosts, stretch, autofs, sw-raid + contacts: zobel, tfheen, lfilipoz, zumbi, jcristau, pabs, aurel32, dsa-nsa + contact_groups: "" mirror-accumu: address: 130.242.6.199 parents: gw-accumu2 @@ -342,7 +335,7 @@ servers: picconi: address: 5.153.231.3 parents: gw-bytemark - hostgroups: computers, service, kvmdomains, jessie, apache2-hosts, nfs-client, autofs, heavy-exim, spamd, apache-https, systemd-timesyncd + hostgroups: computers, service, kvmdomains, stretch, apache2-hosts, nfs-client, autofs, heavy-exim, spamd, apache-https, systemd-timesyncd senfter: address: 5.153.231.4 parents: gw-bytemark @@ -370,7 +363,7 @@ servers: parents: gw-bytemark hostgroups: computers, hassrvfs, kvmdomains, stretch, postgres96-hosts, systemd-timesyncd ganeti-bytemark: - address: 82.195.75.111 + address: 5.153.231.1 parents: gw-bytemark hostgroups: notacomputer coccia: @@ -384,7 +377,7 @@ servers: philp: address: 5.153.231.13 parents: ganeti-bytemark - hostgroups: computers, hassrvfs, kvmdomains, jessie, apache2-hosts, apache-https, systemd-timesyncd + hostgroups: computers, hassrvfs, kvmdomains, stretch, apache2-hosts, apache-https, systemd-timesyncd, broken_https_default_vhost rainier: address: 5.153.231.16 parents: ganeti-bytemark @@ -408,7 +401,7 @@ servers: donizetti: address: 5.153.231.20 parents: ganeti-bytemark - hostgroups: computers, general, kvmdomains, jessie, nfs-client, autofs, systemd-timesyncd + hostgroups: computers, general, kvmdomains, stretch, nfs-client, autofs, systemd-timesyncd moszumanska: address: 5.153.231.21 parents: ganeti-bytemark @@ -422,11 +415,11 @@ servers: ticharich: address: 5.153.231.23 parents: ganeti-bytemark - hostgroups: computers, general, kvmdomains, jessie, nfs-client, autofs, apache2-hosts, apache-https, service, broken_https_default_vhost, systemd-timesyncd + hostgroups: computers, general, kvmdomains, stretch, nfs-client, autofs, apache2-hosts, apache-https, service, broken_https_default_vhost, systemd-timesyncd petrova: address: 5.153.231.25 parents: ganeti-bytemark - hostgroups: computers, kvmdomains, jessie, apache2-hosts, apache-https, systemd-timesyncd + hostgroups: computers, kvmdomains, stretch, apache2-hosts, apache-https, systemd-timesyncd olin: address: 5.153.231.26 parents: ganeti-bytemark @@ -450,31 +443,19 @@ servers: x86-bm-01: address: 5.153.231.32 parents: ganeti-bytemark - hostgroups: computers, kvmdomains, stretch, no-bacula, systemd-timesyncd + hostgroups: computers, pybuildd, hassrvfs, kvmdomains, stretch, systemd-timesyncd tate: address: 5.153.231.33 parents: ganeti-bytemark - hostgroups: computers, service, kvmdomains, jessie, autofs, nfs-client, apache2-hosts, apache-https, systemd-timesyncd + hostgroups: computers, service, kvmdomains, stretch, autofs, nfs-client, apache2-hosts, apache-https, systemd-timesyncd gideon: address: 5.153.231.34 parents: ganeti-bytemark - hostgroups: computers, service, kvmdomains, jessie, hassrvfs, systemd-timesyncd + hostgroups: computers, service, kvmdomains, stretch, hassrvfs, systemd-timesyncd lindsay: address: 5.153.231.36 parents: ganeti-bytemark hostgroups: computers, service, kvmdomains, stretch, autofs, nfs-client, systemd-timesyncd - mirror-bytemark: - address: 5.153.231.37 - parents: ganeti-bytemark - hostgroups: computers, service, kvmdomains, stretch, systemd-timesyncd, apache2-hosts, hassrvfs - mirror-bytemark-debian: - address: 5.153.231.45 - hostgroups: secondary-IPs - parents: mirror-bytemark - mirror-bytemark-security: - address: 5.153.231.46 - hostgroups: secondary-IPs - parents: mirror-bytemark sor: address: 5.153.231.38 parents: ganeti-bytemark @@ -494,7 +475,7 @@ servers: rusca: address: 5.153.231.43 parents: ganeti-bytemark - hostgroups: computers, service, kvmdomains, jessie, hassrvfs, systemd-timesyncd + hostgroups: computers, service, kvmdomains, stretch, hassrvfs, systemd-timesyncd manziarly: address: 5.153.231.44 parents: ganeti-bytemark @@ -503,7 +484,9 @@ servers: casulana: address: 5.153.231.41 parents: gw-bytemark - hostgroups: computers, service, stretch, hassrvfs, dl380, manyprocesses + hostgroups: computers, service, stretch, hassrvfs, dl380, manyprocesses, apache2-hosts + contacts: zobel, tfheen, lfilipoz, zumbi, jcristau, pabs, aurel32, dsa-nsa + contact_groups: "" # }}} # {{{ gw-c3sl santoro: @@ -546,7 +529,7 @@ servers: mirror-conova: address: 217.196.149.229 parents: gw-conova - hostgroups: computers, stretch, service, apache2-hosts, apache-https + hostgroups: computers, stretch, service, apache2-hosts mirror-conova-debian: address: 217.196.149.232 hostgroups: secondary-IPs @@ -561,7 +544,7 @@ servers: parents: mirror-conova mirror-conova-syncproxy4-eu: address: 217.196.149.237 - hostgroups: secondary-IPs, rsyncd-hosts + hostgroups: secondary-IPs, rsyncd-hosts, https-service parents: mirror-conova arm-conova-01: @@ -588,17 +571,9 @@ servers: hostgroups: computers, service, dl360, stretch, drbd-hosts ganeti-csail: address: 128.31.0.49 - parents: gw-bytemark + parents: gw-csail hostgroups: notacomputer - falla: - address: 128.31.0.65 - parents: ganeti-csail - hostgroups: computers, freebsd, hassrvfs, porterbox, jessie, jessie-freebsd - fischer: - address: 128.31.0.35 - parents: ganeti-csail - hostgroups: computers, freebsd, hassrvfs, porterbox, jessie mirror-csail: address: 128.31.0.62 parents: ganeti-csail @@ -618,7 +593,7 @@ servers: pkgmirror-csail: address: 128.31.0.51 parents: ganeti-csail - hostgroups: computers, service, kvmdomains, jessie, apache2-hosts, no-bacula, apache-https, hassrvfs, systemd-timesyncd + hostgroups: computers, service, kvmdomains, stretch, apache2-hosts, no-bacula, apache-https, hassrvfs, systemd-timesyncd usper: address: 128.31.0.69 parents: ganeti-csail @@ -660,11 +635,11 @@ servers: cgi-grnet-01: address: 194.177.211.202 parents: gw-grnet - hostgroups: computers, service, kvmdomains, jessie, hassrvfs, apache2-hosts, apache-https, xinetd-hosts, systemd-timesyncd + hostgroups: computers, service, kvmdomains, stretch, hassrvfs, apache2-hosts, apache-https, xinetd-hosts, systemd-timesyncd x86-grnet-01: address: 194.177.211.203 parents: ganeti-grnet - hostgroups: computers, buildd, hassrvfs, kvmdomains, stretch, systemd-timesyncd + hostgroups: computers, pybuildd, hassrvfs, kvmdomains, stretch, systemd-timesyncd vittoria: address: 194.177.211.205 parents: ganeti-grnet @@ -724,42 +699,29 @@ servers: lw07: address: 185.17.185.187 parents: gw-leaseweb - hostgroups: computers, service, jessie, dl180, nfs-client, autofs, hassrvfs, postgres94-hosts, apache2-hosts + hostgroups: computers, service, jessie, dl180, nfs-client, autofs, hassrvfs, postgres94-hosts, apache2-hosts lw08: address: 185.17.185.189 parents: gw-leaseweb - hostgroups: computers, service, jessie, dl180, nfs-client, autofs, hassrvfs, apache2-hosts - # }}} - # {{{ gw-linaro - arm-linaro-01: - address: 64.28.108.83 - parents: gw-linaro - hostgroups: computers, hasbootfs, hassrvfs, buildd, stretch, broken_mq - arm-linaro-03: - address: 64.28.108.85 - parents: gw-linaro - hostgroups: computers, hasbootfs, hassrvfs, buildd, stretch, broken_mq - asachi: - address: 64.28.108.84 - parents: gw-linaro - hostgroups: computers, hasbootfs, hassrvfs, porterbox, stretch, broken_mq - # }}} - # {{{ gw-karlsruhe - zemlinsky: - address: 129.143.160.6 - parents: gw-karlsruhe - hostgroups: computers, buildd, stretch - contacts: pkern + hostgroups: computers, service, jessie, dl180, nfs-client, autofs, hassrvfs, apache2-hosts + lw09: + address: 185.17.185.181 + parents: gw-leaseweb + hostgroups: computers, service, stretch, dl180 + lw10: + address: 185.17.185.182 + parents: gw-leaseweb + hostgroups: computers, service, stretch, dl180 # }}} # {{{ gw-manda czerny: address: 82.195.75.109 parents: gw-manda - hostgroups: computers, service, dl380, acpid-hosts, stretch, drbd-hosts + hostgroups: computers, service, dl380, acpid-hosts, stretch, drbd-hosts, manyprocesses clementi: address: 82.195.75.103 parents: gw-manda - hostgroups: computers, service, dl380, acpid-hosts, stretch, drbd-hosts + hostgroups: computers, service, dl380, acpid-hosts, stretch, drbd-hosts, manyprocesses bendel: address: 82.195.75.100 parents: ganeti3 @@ -768,16 +730,6 @@ servers: address: 82.195.75.110 parents: ganeti3 hostgroups: computers, service, kvmdomains, stretch, hassrvfs, spamd, heavy-exim, highload - fils: - address: 82.195.75.89 - parents: ganeti3 - hostgroups: computers, freebsd, jessie, buildd, hassrvfs - contacts: christoph - fayrfax: - address: 82.195.75.82 - parents: ganeti3 - hostgroups: computers, freebsd, jessie, buildd, hassrvfs - contacts: christoph vento: address: 82.195.75.98 parents: ganeti3 @@ -821,7 +773,7 @@ servers: vogler: address: 82.195.75.92 parents: ganeti3 - hostgroups: computers, service, kvmdomains, jessie + hostgroups: computers, service, kvmdomains, stretch wolkenstein: address: 82.195.75.65 parents: ganeti3 @@ -845,7 +797,7 @@ servers: seger: address: 82.195.75.93 parents: ganeti3 - hostgroups: computers, service, apache2-hosts, hassrvfs, hasbootfs, rsyncd-hosts, uploadqueue, kvmdomains, apache-https, postgres94-hosts, jessie + hostgroups: computers, service, apache2-hosts, hassrvfs, rsyncd-hosts, kvmdomains, apache-https, postgres96-hosts, stretch suchon: address: 82.195.75.68 parents: ganeti3 @@ -855,14 +807,9 @@ servers: zani: address: 148.100.88.22 parents: gw-marist - hostgroups: computers, buildd, hassrvfs, stretch, incomingmailrelayed + hostgroups: computers, pybuildd, hassrvfs, stretch, incomingmailrelayed # }}} # {{{ gw-osuosl - busoni: - address: 140.211.166.202 - parents: gw-osuosl - hostgroups: computers, service, dl360, hassrvfs, jessie, hasvarlogfs, apache2-hosts, no-bacula, apache-https - byrd: address: 140.211.166.200 parents: gw-osuosl @@ -884,10 +831,6 @@ servers: address: 140.211.166.197 parents: pieta hostgroups: computers, hassrvfs, buildd, jessie - pizzetti: - address: 140.211.166.198 - parents: pieta - hostgroups: computers, jessie, hassrvfs, porterbox partch: address: 140.211.15.152 parents: gw-osuosl @@ -897,7 +840,7 @@ servers: sallinen: address: 193.62.202.26 parents: gw-sanger - hostgroups: computers, service, stretch, dl380, nfs-client, autofs + hostgroups: computers, service, stretch, dl380, nfs-client, autofs, postgres96-hosts, apache2-hosts sibelius: address: 193.62.202.28 parents: gw-sanger @@ -939,66 +882,6 @@ servers: parents: gw-skroutz1, gw-skroutz2 hostgroups: computers, stretch, service, sw-raid, hassrvfs, apache2-hosts # }}} - # {{{ gw-ubcece - sw-ubcece: - hostgroups: layer2-infrastructure - contacts: lfilipoz - pingable: false - check_command: dsa_check_always_ok - sw-ubcece-mcld: - hostgroups: layer2-infrastructure - parents: sw-ubcece - contacts: lfilipoz - pingable: false - check_command: dsa_check_always_ok - sw-ubcece-kais: - hostgroups: layer2-infrastructure - parents: sw-ubcece - contacts: lfilipoz - pingable: false - check_command: dsa_check_always_ok - spontini: - address: 206.12.19.14 - parents: sw-ubcece-mcld - hostgroups: computers, buildd, hasbootfs, hassrvfs, sparc, wheezy - contacts: lfilipoz - ubc-bl7: - address: 206.12.19.217 - parents: sw-ubcece-kais - hostgroups: computers, bl460, acpid-hosts, service, jessie, drbd-hosts, multipath-hosts - ubc-bl6: - address: 206.12.19.216 - parents: sw-ubcece-kais - hostgroups: computers, bl460, acpid-hosts, service, jessie, drbd-hosts, multipath-hosts - ubc-bl2: - address: 206.12.19.212 - parents: sw-ubcece-kais - hostgroups: computers, bl460, acpid-hosts, service, jessie, drbd-hosts, multipath-hosts - ubc-bl3: - address: 206.12.19.213 - parents: sw-ubcece-kais - hostgroups: computers, bl460, acpid-hosts, service, jessie, drbd-hosts, multipath-hosts - ubc-bl4: - address: 206.12.19.214 - parents: sw-ubcece-kais - hostgroups: computers, bl460, acpid-hosts, service, jessie, drbd-hosts, multipath-hosts - ubc-bl8: - address: 206.12.19.218 - parents: sw-ubcece-kais - hostgroups: computers, bl460, acpid-hosts, service, jessie, drbd-hosts, multipath-hosts - # MSA 2000 (2012i) - giustini: - address: 192.168.2.6 - parents: sw-ubcece-kais - hostgroups: notacomputer - # unless we implement runfrom for host alive checks - pingable: false - check_command: dsa_check_always_ok -# locke: -# address: 206.12.19.120 -# parents: sw-ubcece-kais -# hostgroups: computers, service, hasbootfs, kvmdomains, squeeze, hasvicepa - # }}} # {{{ ubc-gateway ubc-enc2bl01: address: 209.87.16.1 @@ -1025,16 +908,6 @@ servers: address: 209.87.16.21 parents: ubc-gateway hostgroups: computers, buildd, hassrvfs, kvmdomains, stretch, systemd-timesyncd - finzi: - address: 209.87.16.22 - parents: ubc-gateway - hostgroups: computers, freebsd, jessie, buildd, hassrvfs - contacts: christoph - fano: - address: 209.87.16.23 - parents: ubc-gateway - hostgroups: computers, freebsd, jessie, buildd, hassrvfs - contacts: christoph elgar: address: 209.87.16.24 parents: ubc-gateway @@ -1090,7 +963,7 @@ servers: tye: address: 209.87.16.37 parents: ubc-gateway - hostgroups: computers, service, kvmdomains, jessie, heavy-exim, apache2-hosts, apache-https, nfs-client, autofs, hassrvfs, systemd-timesyncd + hostgroups: computers, service, kvmdomains, stretch, heavy-exim, apache2-hosts, apache-https, nfs-client, autofs, hassrvfs, systemd-timesyncd ullmann: address: 209.87.16.38 parents: ubc-gateway @@ -1111,11 +984,19 @@ servers: godard: address: 209.87.16.44 parents: ubc-gateway - hostgroups: computers, service, kvmdomains, stretch, hassrvfs, apache2-hosts, apache-https, systemd-timesyncd, postfix-hosts, postgres96-hosts + hostgroups: computers, service, kvmdomains, stretch, hassrvfs, apache2-hosts, apache-https, systemd-timesyncd, postfix-hosts, postgres96-hosts, crazymanyprocesses debussy: address: 209.87.16.46 parents: ubc-gateway - hostgroups: computers, service, kvmdomains, stretch, systemd-timesyncd + hostgroups: computers, service, kvmdomains, stretch, systemd-timesyncd, apache2-hosts, apache-https, broken_https_default_vhost + kantuser: + address: 209.87.16.47 + parents: ubc-gateway + hostgroups: computers, service, kvmdomains, stretch, systemd-timesyncd, apache2-hosts + grabbe: + address: 209.87.16.48 + parents: ubc-gateway + hostgroups: computers, service, kvmdomains, stretch, systemd-timesyncd, apache2-hosts, apache-https # }}} # {{{ gw-umn #saens: @@ -1211,24 +1092,11 @@ 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 - extinfo-icon_image_alt: switch layer3-infrastructure: alias: Layer 3 Devices - extinfo-icon_image: base/switch40.png - extinfo-icon_image_alt: router notacomputer: alias: Systems that are not really systems. Yeah :) private: 1 - freebsd: - alias: freebsd - private: 1 - extinfo-icon_image_alt: Debian GNU/kFreeBSD armhf: alias: armhf private: 1 @@ -1242,6 +1110,8 @@ hostgroups: alias: machines running services buildd: alias: buildd systems + pybuildd: + alias: buildd systems running pybuildd general: alias: general purpose developer accessible machines @@ -1272,13 +1142,14 @@ hostgroups: aacraid: alias: Hosts with Adaptec AACraid private: 1 + pe1950: + alias: Dell PowerEdge 1950 hosts + private: 1 wheezy: alias: Hosts running wheezy jessie: alias: Hosts running jessie - jessie-freebsd: - alias: kFreebsd hosts running jessie stretch: alias: Hosts running stretch @@ -1347,11 +1218,16 @@ hostgroups: apache-https: alias: hosts with https services private: 1 + https-service: + alias: https service for secondary addresses + private: 1 broken_https_default_vhost: alias: https default vhost does not say 200 OK private: 1 manyprocesses: alias: hosts with lots and lots of (kernel) processes + crazymanyprocesses: + alias: hosts with stupidly lots of processes no-bacula: alias: hosts which are not being backed up with bacula @@ -1472,6 +1348,12 @@ services: check_interval: 5 max_check_attempts: 4 retry_interval: 1 + - + name: network - v6 gw + nrpe: "/usr/lib/nagios/plugins/dsa-check-ipv6-default-gw" + hostgroups: computers + check_interval: 60 + excludehostgroups: alioth # }}} # {{{ ### disk usage - @@ -1505,7 +1387,7 @@ services: name: disk usage on /var/lib/postgresql servicegroups: diskspace nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /var/lib/postgresql" - hosts: sibelius, busoni, buxtehude, lw07, fasolo + hosts: sibelius, buxtehude, lw07, fasolo - name: disk usage on /var/log servicegroups: diskspace @@ -1527,24 +1409,44 @@ services: nrpe: "/usr/lib/nagios/plugins/check_disk 90 94 /srv/snapshot.debian.org" hosts: sibelius - - name: disk usage on /srv/farm-snapshot/farm-1 + name: disk usage on /srv/farm-snapshot/farm-2017-0 + servicegroups: diskspace + nrpe: "/usr/lib/nagios/plugins/check_disk 95 97 /srv/farm-snapshot/farm-2017-0" + hosts: sibelius + - + name: disk usage on /srv/farm-snapshot/farm-2017-1 + servicegroups: diskspace + nrpe: "/usr/lib/nagios/plugins/check_disk 95 97 /srv/farm-snapshot/farm-2017-1" + hosts: sibelius + - + name: disk usage on /srv/farm-snapshot/farm-2017-2 servicegroups: diskspace - nrpe: "/usr/lib/nagios/plugins/check_disk 97 95 /srv/farm-snapshot/farm-1" + nrpe: "/usr/lib/nagios/plugins/check_disk 95 97 /srv/farm-snapshot/farm-2017-2" hosts: sibelius - - name: disk usage on /srv/farm-snapshot/farm-2 + name: disk usage on /srv/farm-snapshot/farm-2017-3 servicegroups: diskspace - nrpe: "/usr/lib/nagios/plugins/check_disk 97 95 /srv/farm-snapshot/farm-2" + nrpe: "/usr/lib/nagios/plugins/check_disk 95 97 /srv/farm-snapshot/farm-2017-3" hosts: sibelius - - name: disk usage on /srv/farm-snapshot/farm-3 + name: disk usage on /srv/farm-snapshot/farm-2017-4 servicegroups: diskspace - nrpe: "/usr/lib/nagios/plugins/check_disk 97 95 /srv/farm-snapshot/farm-3" + nrpe: "/usr/lib/nagios/plugins/check_disk 95 97 /srv/farm-snapshot/farm-2017-4" hosts: sibelius - - name: disk usage on /srv/farm-snapshot/farm-4 + name: disk usage on /srv/farm-snapshot/farm-2017-5 servicegroups: diskspace - nrpe: "/usr/lib/nagios/plugins/check_disk 97 95 /srv/farm-snapshot/farm-4" + nrpe: "/usr/lib/nagios/plugins/check_disk 95 97 /srv/farm-snapshot/farm-2017-5" + hosts: sibelius + - + name: disk usage on /srv/farm-snapshot/farm-2017-6 + servicegroups: diskspace + nrpe: "/usr/lib/nagios/plugins/check_disk 95 97 /srv/farm-snapshot/farm-2017-6" + hosts: sibelius + - + name: disk usage on /srv/farm-snapshot/farm-2017-7 + servicegroups: diskspace + nrpe: "/usr/lib/nagios/plugins/check_disk 95 97 /srv/farm-snapshot/farm-2017-7" hosts: sibelius - name: disk usage on /srv/ftp-master.debian.org @@ -1554,37 +1456,47 @@ services: - name: disk usage on /storage/snapshot-farm-1 servicegroups: diskspace - nrpe: "/usr/lib/nagios/plugins/check_disk 98 92 /storage/snapshot-farm-1" + nrpe: "/usr/lib/nagios/plugins/check_disk 95 97 /storage/snapshot-farm-1" hosts: lw01 - name: disk usage on /storage/snapshot-farm-2 servicegroups: diskspace - nrpe: "/usr/lib/nagios/plugins/check_disk 98 92 /storage/snapshot-farm-2" + nrpe: "/usr/lib/nagios/plugins/check_disk 95 97 /storage/snapshot-farm-2" hosts: lw02 - name: disk usage on /storage/snapshot-farm-3 servicegroups: diskspace - nrpe: "/usr/lib/nagios/plugins/check_disk 98 92 /storage/snapshot-farm-3" + nrpe: "/usr/lib/nagios/plugins/check_disk 95 97 /storage/snapshot-farm-3" hosts: lw03 - name: disk usage on /storage/snapshot-farm-4 servicegroups: diskspace - nrpe: "/usr/lib/nagios/plugins/check_disk 98 92 /storage/snapshot-farm-4" + nrpe: "/usr/lib/nagios/plugins/check_disk 95 97 /storage/snapshot-farm-4" hosts: lw04 + - + name: disk usage on /storage/snapshot-farm-90 + servicegroups: diskspace + nrpe: "/usr/lib/nagios/plugins/check_disk 95 97 /storage/snapshot-farm-09" + hosts: lw09 + - + name: disk usage on /storage/snapshot-farm-10 + servicegroups: diskspace + nrpe: "/usr/lib/nagios/plugins/check_disk 95 97 /storage/snapshot-farm-10" + hosts: lw10 - name: disk usage on /srv/morgue.debian.org/ servicegroups: diskspace - nrpe: "/usr/lib/nagios/plugins/check_disk 95 90 /srv/morgue.debian.org" + nrpe: "/usr/lib/nagios/plugins/check_disk 90 95 /srv/morgue.debian.org" hosts: lw03 - name: disk usage on /srv/QNAP-big/ servicegroups: diskspace - nrpe: "/usr/lib/nagios/plugins/check_disk 90 80 /srv/QNAP-big" + nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /srv/QNAP-big" hosts: storace - name: disk usage on /srv/QNAP-tiny servicegroups: diskspace - nrpe: "/usr/lib/nagios/plugins/check_disk 90 80 /srv/QNAP-tiny" + nrpe: "/usr/lib/nagios/plugins/check_disk 90 95 /srv/QNAP-tiny" hosts: storace # }}} # {{{ ### system @@ -1624,19 +1536,15 @@ services: name: processes - total nrpe: "/usr/lib/nagios/plugins/check_procs 620 700" hostgroups: computers - excludehostgroups: manyprocesses + excludehostgroups: manyprocesses, crazymanyprocesses - name: processes - total hostgroups: manyprocesses nrpe: "/usr/lib/nagios/plugins/check_procs 1500 1700" - - name: swap usage - percent - nrpe: "/usr/lib/nagios/plugins/check_swap -w 20% -c 10%" - hostgroups: computers - - - name: swap usage - mb - nrpe: "/usr/lib/nagios/plugins/check_swap -w 20000 -c 5000" - hostgroups: computers + name: processes - total + hostgroups: crazymanyprocesses + nrpe: "/usr/lib/nagios/plugins/check_procs 15000 25000" - name: free memory - mb nrpe: "/usr/lib/nagios/plugins/dsa-check-memory -m mb" @@ -1651,15 +1559,10 @@ services: hostgroups: computers excludehosts: zelenka, zandonai excludehostgroups: jessie, stretch - - - name: process - getty - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:8 -c 1: -u root -C agetty -a /sbin/getty" - hostgroups: jessie-freebsd - name: process - getty nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:8 -c 1: -u root -C agetty -a /sbin/agetty" hostgroups: jessie, stretch - excludehostgroups: freebsd - name: processes - zombies @@ -1670,7 +1573,6 @@ services: nrpe: "/usr/lib/nagios/plugins/dsa-check-entropy" event_handler: dsa_event_handler_restart_ekey hostgroups: computers - excludehostgroups: freebsd - name: system - filesystem check nrpe: "/usr/bin/sudo /usr/lib/nagios/plugins/dsa-check-filesystems" @@ -1702,7 +1604,7 @@ services: remotecheck: "/usr/lib/nagios/plugins/dsa-check-bacula $HOSTNAME$.debian.org" runfrom: dinis hostgroups: computers - excludehostgroups: buildd, porterbox, no-bacula + excludehostgroups: buildd, pybuildd, porterbox, no-bacula check_interval: 60 retry_interval: 15 - @@ -1711,7 +1613,7 @@ services: remotecheck: "/usr/lib/nagios/plugins/dsa-check-bacula -w 1080 -c 1560 $HOSTNAME$.debian.org F" runfrom: dinis hostgroups: computers - excludehostgroups: buildd, porterbox, no-bacula + excludehostgroups: buildd, pybuildd, porterbox, no-bacula check_interval: 60 retry_interval: 15 - @@ -1724,12 +1626,7 @@ services: servicegroups: backup nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u bacula -C bacula-fd -a '/usr/sbin/bacula-fd -c /etc/bacula/bacula-fd.conf'" hostgroups: computers - excludehostgroups: freebsd, alioth - - - 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 + excludehostgroups: alioth - name: network backup status - draghi @@ -1766,9 +1663,8 @@ services: - name: upgraded libraries servicegroups: security - nrpe: "sudo /usr/lib/nagios/plugins/dsa-check-libs" + nrpe: "sudo /usr/lib/nagios/plugins/dsa-check-libs --ignore-younger=1h" hostgroups: computers - excludehostgroups: freebsd check_interval: 60 retry_interval: 15 notification_interval: 10080 @@ -1776,26 +1672,23 @@ services: name: installed firewall nrpe: "/usr/lib/nagios/plugins/dsa-check-file -w -f /etc/ferm/ferm.conf" hostgroups: computers - excludehostgroups: freebsd - name: puppetized firewall nrpe: "/usr/lib/nagios/plugins/dsa-check-file -w -f /etc/ferm/conf.d/defs.conf" hostgroups: computers - excludehostgroups: freebsd - 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, jessie, stretch + excludehostgroups: sparc, jessie, stretch - 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, stretch - excludehostgroups: freebsd - name: unexpected process - ulogd nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C ulogd" - hostgroups: freebsd, sparc + hostgroups: sparc #### - name: process - samhain @@ -1823,16 +1716,11 @@ 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, jessie, stretch - - - 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 + excludehostgroups: jessie, stretch - 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, stretch - excludehostgroups: freebsd - name: remote logging on lotti @@ -1890,11 +1778,6 @@ 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: computers - excludehostgroups: freebsd - - - name: process - munin-node - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:3 -c 1: -u root -C perl -a '/usr/bin/perl -wT /usr/sbin/munin-node'" - hostgroups: freebsd - name: network service - munin-node check: check_tcp!4949 @@ -1918,7 +1801,7 @@ services: name: system time synced nrpe: "/usr/lib/nagios/plugins/dsa-check-timedatectl -s" hostgroups: computers - excludehostgroups: systemd-timesyncd, freebsd, wheezy + excludehostgroups: systemd-timesyncd, wheezy servicegroups: time - name: system time synced @@ -1934,10 +1817,7 @@ services: - name: process - irqbalance nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C irqbalance -a '/usr/sbin/irqbalance'" - #hosts: casulana hostgroups: computers - #excludehostgroups: single-cpu, freebsd - excludehostgroups: freebsd excludehosts: harris, smetana ### - @@ -1949,11 +1829,7 @@ 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: 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 + excludehostgroups: alioth ### - name: process - monit @@ -2000,16 +1876,11 @@ 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, jessie, stretch + excludehostgroups: jessie, stretch - 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, stretch - excludehostgroups: freebsd - - - name: unexpected process - udev - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C udevd" - hostgroups: freebsd ### - name: process - acpid @@ -2036,19 +1907,13 @@ 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: wheezy, jessie, stretch - excludehostgroups: freebsd, alioth + excludehostgroups: 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, ubc-bl2 - ### - - - 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'" - hostgroups: kvmdomains - excludehostgroups: stretch + excludehostgroups: alioth + excludehosts: czerny, grnet-node01, storace # }}} # {{{ anti-services - @@ -2101,11 +1966,6 @@ services: name: "sso CRL" nrpe: "if [ -e /var/lib/dsa/sso/ca.crl ]; then /usr/lib/nagios/plugins/dsa-check-crl-expire -w 129600 -c 86400 /var/lib/dsa/sso/ca.crl; else echo 'No sso/ca.crl on this host.'; fi" hostgroups: computers - - - name: SSL certs - puppet - hosts: global - remotecheck: "/usr/lib/nagios/plugins/dsa-check-cert-expire-dir /etc/puppet/modules/ssl/files/servicecerts" - runfrom: handel - name: SSL certs - LE hosts: global @@ -2149,12 +2009,6 @@ services: nrpe: "/usr/lib/nagios/plugins/dsa-check-hpacucli --no-controller-ok --ignore-controller='P700m'" check_interval: 120 hostgroups: bm-bl - - - name: HW - hpacucli status - servicegroups: raid - nrpe: "/usr/lib/nagios/plugins/dsa-check-hpacucli --no-battery" - check_interval: 120 - hosts: busoni ### # - # name: HW - edac status @@ -2205,12 +2059,10 @@ services: servicegroups: raid nrpe: "/usr/lib/nagios/plugins/dsa-check-drbd -d All" hostgroups: drbd-hosts - excludehosts: ubc-bl2, ubc-bl3, ubc-bl6, ubc-bl7, ubc-bl8 - - name: RAID - DRBD - servicegroups: raid - nrpe: "/usr/lib/nagios/plugins/dsa-check-drbd -d All --ok-no-devices" - hosts: ubc-bl2, ubc-bl3, ubc-bl6, ubc-bl7, ubc-bl8 + name: HW - OpenManage status + nrpe: "/usr/bin/sudo /usr/lib/nagios/plugins/dsa-check-openmanage" + hostgroups: pe1950 # }}} # }}} # {{{ ### mail stuff @@ -2220,7 +2072,7 @@ 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, mail-relay - excludehosts: master, busoni, quantz, buxtehude + excludehosts: master, quantz, buxtehude - name: process - exim nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:25 -c 1: -u Debian-exim -C exim4 -a '/usr/sbin/exim4 -bd -q'" @@ -2230,11 +2082,11 @@ services: nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:50 -c 1: -C exim4" hostgroups: computers excludehostgroups: postfix-hosts - excludehosts: master, busoni, quantz, buxtehude + excludehosts: master, quantz, buxtehude - name: process - exim nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:300 -c 1:500 -C exim4 -a '/usr/sbin/exim4'" - hosts: master, busoni, quantz, buxtehude + hosts: master, quantz, buxtehude - name: mail queue nrpe: "/usr/lib/nagios/plugins/check_mailq -M exim -w 1000 -c 2000" @@ -2280,17 +2132,17 @@ services: excludehostgroups: jessie, stretch - name: process - spamd - master - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C spamd -a '/usr/sbin/spamd -d --pidfile=/var/run/spamassassin.pid --create-prefs --max-children 5 --helper-home-dir'" + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C spamd -a '/usr/sbin/spamd -d --pidfile=/var/run/spamd.pid --create-prefs --max-children 5 --helper-home-dir'" hostgroups: spamd excludehosts: picconi excludehostgroups: wheezy - name: process - spamd - master - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C spamd -a '/usr/sbin/spamd -d --pidfile=/var/run/spamassassin.pid --create-prefs --max-children 20 --min-spare=5 --helper-home-dir'" + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C spamd -a '/usr/sbin/spamd -d --pidfile=/var/run/spamd.pid --create-prefs --max-children 20 --min-spare=5 --helper-home-dir'" hosts: picconi - name: process - spamd - master - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C spamd -a '/usr/sbin/spamd -d --pidfile=/var/run/spamassassin.pid --create-prefs --max-children 10 --helper-home-dir'" + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C spamd -a '/usr/sbin/spamd -d --pidfile=/var/run/spamd.pid --create-prefs --max-children 10 --helper-home-dir'" hosts: bendel - name: process - spamd - child @@ -2304,7 +2156,7 @@ services: nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C spamd" hostgroups: computers excludehostgroups: spamd - excludehosts: bendel, busoni + excludehosts: bendel - name: unwanted process - greylistd @@ -2475,7 +2327,7 @@ services: name: network service - http check: check_http hostgroups: apache2-hosts - excludehosts: klecker + excludehosts: klecker, casulana depends: process - apache2 - master - name: network service - http @@ -2499,6 +2351,12 @@ services: excludehostgroups: broken_https_default_vhost depends: "process - apache2 - master" check_interval: 120 + - + name: network service - https + check: check_https + hostgroups: https-service + excludehostgroups: broken_https_default_vhost + check_interval: 120 - name: network service - https check: dsa_check_https_want_auth @@ -2514,7 +2372,7 @@ services: - name: network service - https cert check: dsa_check_cert!443 - hostgroups: apache-https + hostgroups: apache-https, https-service depends: network service - https check_interval: 60 - @@ -2528,11 +2386,7 @@ services: - name: network service - ftp check: check_ftp - hostgroups: uploadqueue, security_mirror - - - name: network service - ftp - check: check_ftp - hosts: klecker-ftp + hostgroups: uploadqueue # }}} # {{{ postgres - @@ -2565,29 +2419,23 @@ services: - name: process - buildd servicegroups: buildd - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:5 -u buildd -C perl -a '/usr/bin/buildd'" - hosts: fano, finzi, fils, fayrfax + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:5 -u buildd -C buildd -a '/usr/bin/buildd'" + hostgroups: buildd contact_groups: buildd - name: process - buildd servicegroups: buildd - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:5 -u buildd -C buildd -a '/usr/bin/buildd'" - hostgroups: buildd - excludehosts: fano, finzi, fils, fayrfax + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:5 -u buildd -C python3 -a 'buildd.py'" + hostgroups: pybuildd contact_groups: buildd - name: processes - zombie schroot nrpe: "(/usr/lib/nagios/plugins/check_procs -a schroot -s Zs -c 0 > /dev/null || /usr/lib/nagios/plugins/check_procs -a schroot -s Zs -c 0) && /usr/lib/nagios/plugins/check_procs -a schroot -s ZNs -c 0" - hostgroups: buildd + hostgroups: buildd, pybuildd contact_groups: +buildd check_interval: 5 max_check_attempts: 24 retry_interval: 5 - - - name: processes - lvcreate - nrpe: "/usr/lib/nagios/plugins/check_procs -m 'ELAPSED' -c 500 -C lvcreate -u root -a 'lvcreate'" - hostgroups: buildd - contact_groups: +buildd # }}} # {{{ NFS Stuff - @@ -2873,10 +2721,6 @@ services: name: DNS SOA sync - 144-28.118.59.86.in-addr.arpa check: "dsa_check_soas_add!denis.debian.org!144-28.118.59.86.in-addr.arpa" hosts: global - - - name: DNS SOA sync - alioth.debian.org - check: "dsa_check_soas_add!denis.debian.org!alioth.debian.org" - hosts: global - name: DNS SOA sync - debconf.net check: "dsa_check_soas_add!denis.debian.org!debconf.net" @@ -2920,25 +2764,6 @@ services: runfrom: denis # }}} # {{{ storage - - - name: ping alive check - remotecheck: "/usr/lib/nagios/plugins/check_ping -H $HOSTADDRESS$ -w 50,10% -c 200,30%" - runfrom: ubc-bl8 - hosts: giustini - check_interval: 5 - max_check_attempts: 4 - retry_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: ubc-bl8 - hosts: giustini - - - name: event log - remotecheck: "/usr/lib/nagios/plugins/dsa-check-msa-eventlog --start=11298 $HOSTADDRESS$ public" - runfrom: ubc-bl8 - hosts: giustini - ### - name: process - multipathd nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:15 -c 1: -u root -C multipathd -a '/sbin/multipathd'" @@ -3002,9 +2827,8 @@ services: # {{{ misc - name: system - all services running - nrpe: "/usr/bin/sudo /bin/systemctl is-system-running" + nrpe: "/usr/bin/sudo /usr/lib/nagios/plugins/dsa-check-systemd-services" hostgroups: jessie, stretch - excludehostgroups: freebsd ### - name: process - slapd @@ -3054,6 +2878,11 @@ services: check: dsa_check_cert!5061 check_interval: 60 hosts: vogler + - + name: freeradius process + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u freerad -C freeradius -a '/usr/sbin/freeradius -xx'" + check_interval: 60 + hosts: vogler #### - name: puppetmaster cert @@ -3073,3 +2902,5 @@ services: # }}} # vim: set ts=2 sw=2 et ai si fdm=marker: + +