X-Git-Url: https://git.adam-barratt.org.uk/?a=blobdiff_plain;f=config%2Fnagios-master.cfg;h=15ffda5f61fa3b1b7c0f451e75f0814d53a508b0;hb=e31ddbaa216eac4daefff206bb126532c59cf7a7;hp=acf97df23acec34ef0525f068dc1b2d79934b1d0;hpb=230047393e510e9506c8e5b3309286444693ec2a;p=mirror%2Fdsa-nagios.git diff --git a/config/nagios-master.cfg b/config/nagios-master.cfg index acf97df..15ffda5 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 @@ -147,7 +139,7 @@ servers: parents: gw-ubcece hostgroups: layer3-infrastructure gw-unicamp: - address: 177.220.10.129 + address: 143.106.167.113 parents: gw-ubcece hostgroups: layer3-infrastructure gw-utwente: @@ -174,17 +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, 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 @@ -244,15 +238,15 @@ servers: arm-arm-01: address: 217.140.96.58 parents: gw-arm - hostgroups: computers, hassrvfs, buildd, stretch, broken_mq + hostgroups: computers, hassrvfs, buildd, stretch, broken_mq, sw-raid arm-arm-03: address: 217.140.96.60 parents: gw-arm - hostgroups: computers, hassrvfs, buildd, stretch, broken_mq + hostgroups: computers, hassrvfs, buildd, stretch, broken_mq, sw-raid arm-arm-04: address: 217.140.96.61 parents: gw-arm - hostgroups: computers, hassrvfs, buildd, stretch, broken_mq + hostgroups: computers, hassrvfs, buildd, stretch, broken_mq, sw-raid harris: address: 217.140.96.66 parents: gw-arm @@ -383,7 +377,7 @@ servers: philp: address: 5.153.231.13 parents: ganeti-bytemark - hostgroups: computers, hassrvfs, kvmdomains, stretch, 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 @@ -407,13 +401,7 @@ servers: donizetti: address: 5.153.231.20 parents: ganeti-bytemark - hostgroups: computers, general, kvmdomains, jessie, nfs-client, autofs, systemd-timesyncd - moszumanska: - address: 5.153.231.21 - parents: ganeti-bytemark - contact_groups: alioth-admins - hostgroups: computers, general, wheezy, postgres91-hosts, apache2-hosts, acpid-hosts, apache-https, brokensamhain, no-bacula, bind9-hosts, xinetd-hosts, alioth, heavy-exim, spamd - no-servicegroups: true + hostgroups: computers, general, kvmdomains, stretch, nfs-client, autofs, systemd-timesyncd dillon: address: 5.153.231.22 parents: ganeti-bytemark @@ -425,7 +413,7 @@ servers: 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 @@ -449,7 +437,7 @@ 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 @@ -457,23 +445,11 @@ servers: 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 @@ -502,7 +478,9 @@ 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: @@ -533,11 +511,11 @@ servers: conova-node01: address: 217.196.149.227 parents: gw-conova - hostgroups: computers, stretch, service, sw-raid + hostgroups: computers, stretch, service, sw-raid, drbd-hosts conova-node02: address: 217.196.149.228 parents: gw-conova - hostgroups: computers, stretch, service, sw-raid + hostgroups: computers, stretch, service, sw-raid, drbd-hosts ganeti-conova: address: 217.196.149.235 parents: gw-conova @@ -587,17 +565,9 @@ 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 @@ -617,7 +587,7 @@ servers: pkgmirror-csail: address: 128.31.0.51 parents: ganeti-csail - hostgroups: computers, service, kvmdomains, stretch, apache2-hosts, no-bacula, apache-https, hassrvfs, systemd-timesyncd + hostgroups: computers, service, kvmdomains, stretch, apache2-hosts, no-bacula, apache-https, hassrvfs, systemd-timesyncd, varnish-hosts usper: address: 128.31.0.69 parents: ganeti-csail @@ -659,11 +629,11 @@ 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 @@ -707,48 +677,40 @@ servers: lw01: address: 185.17.185.177 parents: gw-leaseweb - hostgroups: computers, service, jessie, dl180, nfs-server, rsyncd-hosts + hostgroups: computers, service, stretch, dl180, nfs-server, rsyncd-hosts lw02: address: 185.17.185.178 parents: gw-leaseweb - hostgroups: computers, service, jessie, dl180, nfs-server, rsyncd-hosts + hostgroups: computers, service, stretch, dl180, nfs-server, rsyncd-hosts lw03: address: 185.17.185.179 parents: gw-leaseweb - hostgroups: computers, service, jessie, dl180, nfs-server, rsyncd-hosts + hostgroups: computers, service, stretch, dl180, nfs-server, rsyncd-hosts lw04: address: 185.17.185.180 parents: gw-leaseweb - hostgroups: computers, service, jessie, dl180, nfs-server, rsyncd-hosts + hostgroups: computers, service, stretch, dl180, nfs-server, rsyncd-hosts 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, stretch, dl180, nfs-client, autofs, hassrvfs, postgres96-hosts, apache2-hosts, haproxy-hosts, haproxy-https-host, varnish-hosts + lw07-2: + address: 185.17.185.185 + parents: lw07 + hostgroups: secondary-IPs, https-service + 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, stretch, 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: @@ -759,6 +721,14 @@ servers: address: 82.195.75.103 parents: gw-manda hostgroups: computers, service, dl380, acpid-hosts, stretch, drbd-hosts, manyprocesses + manda-node03: + address: 82.195.75.69 + parents: gw-manda + hostgroups: computers, service, stretch, r540, drbd-hosts, manyprocesses + manda-node04: + address: 82.195.75.70 + parents: gw-manda + hostgroups: computers, service, stretch, r540, drbd-hosts, manyprocesses bendel: address: 82.195.75.100 parents: ganeti3 @@ -767,16 +737,6 @@ 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 @@ -788,7 +748,7 @@ servers: draghi: address: 82.195.75.106 parents: ganeti3 - hostgroups: computers, service, hasbootfs, hassrvfs, apache2-hosts, spamd, heavy-exim, kvmdomains, xinetd-hosts, apache-https, stretch + hostgroups: computers, service, hassrvfs, apache2-hosts, spamd, heavy-exim, kvmdomains, xinetd-hosts, apache-https, stretch geo1: address: 82.195.75.105 parents: ganeti3 @@ -796,7 +756,7 @@ servers: handel: address: 82.195.75.104 parents: ganeti3 - hostgroups: computers, service, kvmdomains, apache2-hosts, stretch, postgres96-hosts + hostgroups: computers, service, kvmdomains, apache2-hosts, stretch, postgres96-hosts, hassrvfs kaufmann: address: 82.195.75.107 parents: ganeti3 @@ -820,7 +780,7 @@ 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 @@ -854,14 +814,9 @@ 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 @@ -871,6 +826,10 @@ servers: parents: byrd hostgroups: computers, service, kvmdomains, stretch, apache2-hosts, hassrvfs, rsyncd-hosts, apache-https + pijper: + address: 140.211.166.194 + parents: gw-osuosl + hostgroups: computers, stretch, service, manyprocesses pieta: address: 140.211.166.195 parents: gw-osuosl @@ -879,33 +838,20 @@ servers: address: 140.211.166.196 parents: pieta hostgroups: computers, hassrvfs, buildd, stretch - powerpc-osuosl-01: - 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 - hostgroups: computers, jessie, hassrvfs, porterbox, sw-raid # }}} # {{{ gw-sanger 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, haproxy-hosts, haproxy-https-host, varnish-hosts + sallinen-2: + address: 193.62.202.27 + parents: sallinen + hostgroups: secondary-IPs, https-service sibelius: address: 193.62.202.28 parents: gw-sanger - hostgroups: computers, postgres94-hosts, service, apache2-hosts, sw-raid, jessie, rsyncd-hosts, hasvarlogfs, multipath-hosts, nfs-server - contacts: tjrc1, dave - smetana: - address: 193.62.202.29 - parents: gw-sanger - hostgroups: computers, sw-raid, sparc, wheezy, no-bacula + hostgroups: computers, service, apache2-hosts, sw-raid, jessie, rsyncd-hosts, hasvarlogfs, multipath-hosts, nfs-server, varnish-hosts contacts: tjrc1, dave # }}} # {{{ gw-scanplus @@ -938,66 +884,6 @@ 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 @@ -1024,16 +910,6 @@ 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 @@ -1089,7 +965,7 @@ 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 @@ -1110,11 +986,19 @@ 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: @@ -1140,19 +1024,15 @@ servers: # }}} # {{{ gw-unicamp prokofiev: - address: 177.220.10.140 + address: 143.106.167.124 parents: gw-unicamp hostgroups: computers, stretch, service, manyprocesses - powerpc-unicamp-01: - address: 177.220.10.141 - parents: prokofiev - hostgroups: computers, hassrvfs, buildd, jessie ppc64el-unicamp-01: - address: 177.220.10.142 + address: 143.106.167.121 parents: prokofiev hostgroups: computers, hassrvfs, buildd, stretch plummer: - address: 177.220.10.143 + address: 143.106.167.122 parents: prokofiev hostgroups: computers, porterbox, hassrvfs, stretch # }}} @@ -1210,30 +1090,14 @@ 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 - sparc: - alias: sparc - private: 1 porterbox: alias: developer accessible porter machines @@ -1241,6 +1105,8 @@ hostgroups: alias: machines running services buildd: alias: buildd systems + pybuildd: + alias: buildd systems running pybuildd general: alias: general purpose developer accessible machines @@ -1271,13 +1137,15 @@ hostgroups: aacraid: alias: Hosts with Adaptec AACraid private: 1 + pe1950: + alias: Dell PowerEdge 1950 hosts + private: 1 + r540: + alias: Dell PowerEdge R540 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 @@ -1319,12 +1187,6 @@ hostgroups: xinetd-hosts: alias: hosts providing services via xinetd private: 1 - postgres91-hosts: - alias: hosts running postgres91 - private: 1 - postgres94-hosts: - alias: hosts running postgres94 - private: 1 postgres96-hosts: alias: hosts running postgres96 private: 1 @@ -1354,6 +1216,17 @@ hostgroups: private: 1 manyprocesses: alias: hosts with lots and lots of (kernel) processes + crazymanyprocesses: + alias: hosts with stupidly lots of processes + varnish-hosts: + alias: hosts running varnish + private: 1 + haproxy-hosts: + alias: hosts running haproxy + private: 1 + haproxy-https-host: + alias: "host providing https on the standard port via haproxy" + private: 1 no-bacula: alias: hosts which are not being backed up with bacula @@ -1405,9 +1278,6 @@ hostgroups: high-RTT: alias: machines with high round trip times private: 1 - alioth: - alias: machines that just are just awkward - private: 1 #openstack-compute: # alias: nodes that run OpenStack compute # private: 1 @@ -1474,6 +1344,11 @@ 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 # }}} # {{{ ### disk usage - @@ -1507,7 +1382,7 @@ 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 @@ -1529,24 +1404,44 @@ 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 95 97 /srv/farm-snapshot/farm-2017-2" + hosts: sibelius + - + 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-1" + 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-2 + 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-2" + 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-3 + 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-3" + 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-4 + name: disk usage on /srv/farm-snapshot/farm-2017-6 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-2017-6" + 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 @@ -1556,37 +1451,79 @@ 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 nfs farm 1 + servicegroups: diskspace + nrpe: "/usr/lib/nagios/plugins/check_disk 95 97 /auto.dsa/snapshot-1" + hosts: lw07 + - + name: disk usage on nfs farm 2 + servicegroups: diskspace + nrpe: "/usr/lib/nagios/plugins/check_disk 95 97 /auto.dsa/snapshot-2" + hosts: lw07 + - + name: disk usage on nfs farm 3 + servicegroups: diskspace + nrpe: "/usr/lib/nagios/plugins/check_disk 95 97 /auto.dsa/snapshot-3" + hosts: lw07 + - + name: disk usage on nfs farm 4 + servicegroups: diskspace + nrpe: "/usr/lib/nagios/plugins/check_disk 95 97 /auto.dsa/snapshot-4" + hosts: lw07 + - + name: disk usage on nfs farm 09 + servicegroups: diskspace + nrpe: "/usr/lib/nagios/plugins/check_disk 95 97 /auto.dsa/snapshot-09" + hosts: lw07 + - + name: disk usage on nfs farm 10 + servicegroups: diskspace + nrpe: "/usr/lib/nagios/plugins/check_disk 95 97 /auto.dsa/snapshot-10" + hosts: lw07 + - 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 @@ -1596,7 +1533,6 @@ services: nrpe: "/usr/lib/nagios/plugins/dsa-check-config" hostgroups: computers check_interval: 60 - excludehostgroups: alioth - name: setup - local hostname etc-hosts nrpe: 'if getent ahosts `hostname` | grep -q 127.0; then echo "Warning: local hostname resolves to 127/8 address"; exit 1; else echo "OK: Hostname resolves to non-127/8 address."; exit 0; fi' @@ -1626,19 +1562,15 @@ 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" @@ -1647,21 +1579,10 @@ services: name: free memory - percent nrpe: "/usr/lib/nagios/plugins/dsa-check-memory -m pct" hostgroups: computers - - - name: process - getty - 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, 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 + hostgroups: computers - name: processes - zombies @@ -1672,7 +1593,6 @@ 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" @@ -1704,7 +1624,7 @@ 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 - @@ -1713,7 +1633,7 @@ 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 - @@ -1726,12 +1646,6 @@ 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 - name: network backup status - draghi @@ -1768,9 +1682,8 @@ 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 @@ -1778,26 +1691,14 @@ 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 - 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: computers #### - name: process - samhain @@ -1821,39 +1722,26 @@ services: excludehostgroups: brokensamhain # }}} # {{{ logging - - - 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 - 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 + hostgroups: computers - name: remote logging on lotti remotecheck: "/usr/lib/nagios/plugins/dsa-check-log-age-loghost $HOSTNAME$" runfrom: lotti hostgroups: computers - excludehostgroups: alioth - name: remote logging on lully remotecheck: "/usr/lib/nagios/plugins/dsa-check-log-age-loghost $HOSTNAME$" runfrom: lully hostgroups: computers - excludehostgroups: alioth - name: remote logging on loghost-grnet-01 remotecheck: "/usr/lib/nagios/plugins/dsa-check-log-age-loghost $HOSTNAME$" runfrom: loghost-grnet-01 hostgroups: computers - excludehostgroups: alioth # }}} # {{{ base service - @@ -1892,11 +1780,6 @@ 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 @@ -1920,7 +1803,7 @@ services: name: system time synced nrpe: "/usr/lib/nagios/plugins/dsa-check-timedatectl -s" hostgroups: computers - excludehostgroups: systemd-timesyncd, freebsd, wheezy + excludehostgroups: systemd-timesyncd servicegroups: time - name: system time synced @@ -1936,11 +1819,8 @@ 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 + excludehosts: harris ### - name: process - cron @@ -1951,17 +1831,6 @@ 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 - ### - - - 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: alioth, jessie, stretch ### - name: MQ connection on rainier @@ -1971,7 +1840,7 @@ services: hostgroups: computers check_interval: 60 retry_interval: 15 - excludehostgroups: alioth, broken_mq + excludehostgroups: broken_mq - name: MQ connection on rapoport servicegroups: MQ @@ -1980,7 +1849,7 @@ services: hostgroups: computers check_interval: 60 retry_interval: 15 - excludehostgroups: alioth, broken_mq + excludehostgroups: broken_mq ### - name: local resolver @@ -1991,33 +1860,21 @@ services: name: process - unbound nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u unbound -C unbound -a '/usr/sbin/unbound'" hostgroups: computers - excludehostgroups: alioth - ### - - name: process - uptimed - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u daemon -C uptimed -a '/usr/sbin/uptimed'" + name: unbound trust anchors + nrpe: "/usr/lib/nagios/plugins/dsa-check-unbound-anchors" hostgroups: computers + check_interval: 60 ### - - name: process - udevd - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -p 1 -C udevd -a 'udevd'" + name: process - uptimed + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u daemon -C uptimed -a '/usr/sbin/uptimed'" hostgroups: computers - excludehostgroups: freebsd, 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 + hostgroups: computers ### - - - name: process - acpid - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C acpid -a '/usr/sbin/acpid'" - hostgroups: acpid-hosts - excludehostgroups: jessie, stretch - name: unexpected process - acpid nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C acpid" @@ -2037,20 +1894,12 @@ 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 + hostgroups: computers - 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 + excludehosts: czerny, grnet-node01, storace # }}} # {{{ anti-services - @@ -2103,11 +1952,6 @@ 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 @@ -2115,18 +1959,11 @@ services: runfrom: handel # }}} # {{{ HW health/raid - - - 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'" - hostgroups: sw-raid - excludehostgroups: jessie, stretch - 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 @@ -2151,12 +1988,6 @@ 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 @@ -2207,12 +2038,19 @@ 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, r540 + excludehosts: wieck, schumann + - + name: HW - OpenManage status + nrpe: "/usr/bin/sudo /usr/lib/nagios/plugins/dsa-check-openmanage -b bp=0" + hosts: wieck + - + name: HW - OpenManage status + nrpe: "/usr/bin/sudo /usr/lib/nagios/plugins/dsa-check-openmanage -b bp=0 -b bat_charge=0:0" + hosts: schumann # }}} # }}} # {{{ ### mail stuff @@ -2222,7 +2060,7 @@ 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'" @@ -2232,15 +2070,24 @@ 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" hostgroups: heavy-exim + - + name: process - fail2ban + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -C fail2ban-server" + hostgroups: heavy-exim, heavy-postfix + - + name: unwanted process - fail2ban + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C fail2ban-server" + hostgroups: computers + excludehostgroups: heavy-exim, heavy-postfix # }}} # {{{ clamav - @@ -2252,16 +2099,10 @@ services: nrpe: "/usr/lib/nagios/plugins/check_clamd -H /var/run/clamav/clamd.ctl" 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-exim, heavy-postfix - excludehostgroups: jessie, stretch - 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 --foreground=true'" hostgroups: heavy-exim, heavy-postfix - excludehostgroups: wheezy - name: unwanted process - clamav nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C clamd" @@ -2274,18 +2115,11 @@ services: excludehostgroups: heavy-exim, heavy-postfix # }}} # {{{ anti-spam - - - 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'" - hostgroups: spamd - excludehosts: picconi - 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/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/spamd.pid --create-prefs --max-children 20 --min-spare=5 --helper-home-dir'" @@ -2306,7 +2140,7 @@ 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 @@ -2314,16 +2148,10 @@ services: hostgroups: computers ### - - - name: process - postgrey - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postgrey -a '/usr/sbin/postgrey --pidfile=/var/run/postgrey.pid --daemonize --unix=/var/run/postgrey/socket --retry-window=4 --auto-whitelist-clients=10 --exim'" - hostgroups: heavy-exim - excludehostgroups: jessie, stretch - name: process - postgrey nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postgrey -a 'postgrey --pidfile=/var/run/postgrey.pid --daemonize --unix=/var/run/postgrey/socket --retry-window=4 --auto-whitelist-clients=10 --exim'" hostgroups: heavy-exim - excludehostgroups: wheezy - name: process - postgrey nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postgrey -a 'postgrey --pidfile=/var/run/postgrey.pid --daemonize --inet=127.0.0.1:60000'" @@ -2354,23 +2182,23 @@ services: - name: process - weightd - master nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u polw -a 'policyd-weight (master)'" - hostgroups: heavy-postfix, alioth + hostgroups: heavy-postfix - name: process - weightd - cache nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u polw -a 'policyd-weight (cache)'" - hostgroups: heavy-postfix, alioth + hostgroups: heavy-postfix depends: process - weightd - master - name: process - weightd - child nrpe: "/usr/lib/nagios/plugins/check_procs -w 2:50 -c 1: -u polw -a 'policyd-weight (child)'" - hostgroups: heavy-postfix, alioth + hostgroups: heavy-postfix 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, alioth + excludehostgroups: heavy-postfix # }}} # {{{ postfix ### @@ -2477,7 +2305,7 @@ services: name: network service - http check: check_http hostgroups: apache2-hosts - excludehosts: klecker + excludehosts: klecker, casulana depends: process - apache2 - master - name: network service - http @@ -2522,15 +2350,52 @@ services: - name: network service - https cert check: dsa_check_cert!443 - hostgroups: apache-https, https-service + hostgroups: apache-https, https-service, haproxy-https-host depends: network service - https check_interval: 60 - name: unwanted network service - https check: dsa_check_port_closed!443 hostgroups: apache2-hosts - excludehostgroups: apache-https + excludehostgroups: apache-https, haproxy-https-host check_interval: 60 + + ### + - + name: process - haproxy - master + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u root -a '/usr/sbin/haproxy-systemd-wrapper'" + hostgroups: haproxy-hosts + - + name: process - haproxy - worker + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:6 -c 1:15 -u haproxy -a '/usr/sbin/haproxy '" + hostgroups: haproxy-hosts + depends: process - haproxy - master + - + name: network service - https + check: check_https + hostgroups: haproxy-https-host + depends: "process - haproxy - master" + check_interval: 120 + + - + name: unwanted process - haproxy + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0 -C haproxy" + hostgroups: computers + excludehostgroups: haproxy-hosts + + ### + - + name: process - varnish + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:2 -c 1:15 -u vcache -a '/usr/sbin/varnishd -j unix,user=vcache -F -a '" + hostgroups: varnish-hosts + excludehostgroups: jessie + - + name: unwanted process - varnish + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0 -C varnishd" + hostgroups: computers + excludehostgroups: varnish-hosts + + # }}} # {{{ FTP - @@ -2543,19 +2408,11 @@ services: name: unwanted process - postgresql nrpe: "/usr/lib/nagios/plugins/check_procs -w 0 -C postgres" hostgroups: computers - excludehostgroups: postgres91-hosts, postgres94-hosts, postgres96-hosts + excludehostgroups: postgres96-hosts - name: unwanted process - postgresql 9.0 nrpe: "/usr/lib/nagios/plugins/check_procs -w 0 -C postgres -a '9.0/bin/postgres'" hostgroups: computers - - - name: process - postgresql91 - master - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:10 -c 1: -u postgres -C postgres -a '/usr/lib/postgresql/9.1/bin/postgres'" - hostgroups: postgres91-hosts - - - name: process - postgresql94 - master - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:10 -c 1: -u postgres -C postgres -a '/usr/lib/postgresql/9.4/bin/postgres'" - hostgroups: postgres94-hosts - name: process - postgresql96 - master nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:10 -c 1: -u postgres -C postgres -a '/usr/lib/postgresql/9.6/bin/postgres'" @@ -2569,29 +2426,23 @@ 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 - @@ -2844,6 +2695,16 @@ services: check: "dsa_check_staticsync!miniconf10.debconf.org" hosts: global servicegroups: mirror + - + name: mirror static sync - wiki + check: "dsa_check_staticsync!wiki.debconf.org" + hosts: global + servicegroups: mirror + - + name: mirror static sync - www + check: "dsa_check_staticsync!www.debconf.org" + hosts: global + servicegroups: mirror # }}} # {{{ DNS - @@ -2877,10 +2738,6 @@ 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" @@ -2924,25 +2781,6 @@ 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'" @@ -3006,9 +2844,8 @@ services: # {{{ misc - name: system - all services running - nrpe: "/usr/bin/sudo /bin/systemctl is-system-running" - hostgroups: jessie, stretch - excludehostgroups: freebsd + nrpe: "/usr/bin/sudo /usr/lib/nagios/plugins/dsa-check-systemd-services" + hostgroups: computers ### - name: process - slapd @@ -3058,6 +2895,11 @@ 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 @@ -3070,10 +2912,42 @@ services: name: puppet - agent check nrpe: "/usr/lib/nagios/plugins/dsa-check-statusfile /var/cache/dsa/nagios/puppet-agent" hostgroups: computers - excludehosts: moszumanska check_interval: 60 retry_interval: 15 + #### + - + name: ping peer on mgmt network + nrpe: "/usr/lib/nagios/plugins/check_ping -H 172.29.184.12 -w 50,10% -c 200,30%" + hosts: conova-node01 + check_interval: 5 + max_check_attempts: 4 + retry_interval: 1 + - + name: ping peer on mgmt network + nrpe: "/usr/lib/nagios/plugins/check_ping -H 172.29.184.11 -w 50,10% -c 200,30%" + hosts: conova-node02 + check_interval: 5 + max_check_attempts: 4 + retry_interval: 1 + + - + name: ping peer on mgmt network + nrpe: "/usr/lib/nagios/plugins/check_ping -H 172.29.182.14 -w 50,10% -c 200,30%" + hosts: manda-node03 + check_interval: 5 + max_check_attempts: 4 + retry_interval: 1 + - + name: ping peer on mgmt network + nrpe: "/usr/lib/nagios/plugins/check_ping -H 172.29.182.13 -w 50,10% -c 200,30%" + hosts: manda-node04 + check_interval: 5 + max_check_attempts: 4 + retry_interval: 1 + # }}} # }}} # }}} # vim: set ts=2 sw=2 et ai si fdm=marker: + +