X-Git-Url: https://git.adam-barratt.org.uk/?a=blobdiff_plain;f=config%2Fnagios-master.cfg;h=1a703bffe79746f86e22ee6bad59ed8dcf914b6b;hb=0df5d86276b190a2c44e9106351466fc014c98f7;hp=203efb76c4bebefec12666b9bbce2b47b7ec5ab7;hpb=199d36fe215059f842b078c3d8dccb2861ff0025;p=mirror%2Fdsa-nagios.git diff --git a/config/nagios-master.cfg b/config/nagios-master.cfg index 203efb7..ce5ee58 100644 --- a/config/nagios-master.cfg +++ b/config/nagios-master.cfg @@ -33,6 +33,10 @@ servers: address: 130.239.18.97 parents: gw-ubcece hostgroups: layer3-infrastructure + gw-aql: + address: 141.170.2.17 + parents: gw-ubcece + hostgroups: layer3-infrastructure gw-bytemark: address: 89.16.160.116 parents: gw-ubcece @@ -74,8 +78,8 @@ servers: address: 62.104.23.249 parents: gw-ubcece hostgroups: layer3-infrastructure - gw-ftcollins: - address: 192.25.206.1 + gw-gatech: + address: 128.61.240.1 parents: gw-ubcece hostgroups: layer3-infrastructure gw-grnet: @@ -94,6 +98,10 @@ servers: 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-man-da: address: 82.195.75.126 parents: gw-ubcece @@ -110,6 +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 @@ -139,6 +151,10 @@ servers: address: 128.101.240.222 parents: gw-ubcece hostgroups: layer3-infrastructure + gw-unicamp: + address: 143.106.167.234 + parents: gw-ubcece + hostgroups: layer3-infrastructure gw-utwente: address: 130.89.149.1 parents: gw-ubcece @@ -167,7 +183,12 @@ servers: babin: address: 213.165.95.6 parents: powell - hostgroups: computers, buildd, hassrvfs, kvmdomains, wheezy + hostgroups: computers, buildd, hassrvfs, kvmdomains, jessie + piu-slave-1und1-01: + address: 213.165.95.7 + parents: powell + hostgroups: computers, service, kvmdomains, jessie + contacts: holger # }}} # {{{ gw-1und1-sec schumann: @@ -178,10 +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 @@ -189,51 +206,77 @@ servers: wieck: address: 195.20.242.89 parents: gw-1und1-sec - hostgroups: computers, service, apache2-hosts, rsyncd-hosts, acpid-hosts, xinetd-hosts, wheezy, security_mirror, hasvarlogfs, no-bacula + hostgroups: computers, service, apache2-hosts, rsyncd-hosts, acpid-hosts, xinetd-hosts, jessie, security_mirror, hasvarlogfs, no-bacula # }}} # {{{ gw-accumu 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 hostgroups: computers, buildd, hassrvfs, wheezy # }}} + # {{{ gw-aql + mips-aql-01: + address: 141.170.6.149 + parents: gw-aql + hostgroups: computers, buildd, jessie, nfs-client + mips-aql-02: + address: 141.170.6.150 + parents: gw-aql + hostgroups: computers, buildd, wheezy, nfs-client + minkus: + address: 141.170.6.151 + parents: gw-aql + hostgroups: computers, porterbox, jessie, nfs-client + mipsel-aql-01: + address: 141.170.6.152 + parents: gw-aql + hostgroups: computers, buildd, jessie, hassrvfs, hasbootfs, sw-raid + mipsel-aql-02: + address: 141.170.6.153 + parents: gw-aql + hostgroups: computers, buildd, jessie, hassrvfs, hasbootfs, sw-raid + # }}} # {{{ gw-arm abel: address: 217.140.96.56 parents: gw-arm - hostgroups: computers, hasbootfs, hassrvfs, porterbox, wheezy - antheil: - address: 217.140.96.60 - parents: gw-arm - hostgroups: computers, hasbootfs, hassrvfs, buildd, wheezy + hostgroups: computers, hasbootfs, hassrvfs, porterbox, jessie, broken_mq arnold: address: 217.140.96.57 parents: gw-arm - hostgroups: computers, hasbootfs, hassrvfs, buildd, wheezy + hostgroups: computers, hasbootfs, hassrvfs, buildd, jessie, broken_mq + arm-arm-01: + address: 217.140.96.58 + parents: gw-arm + hostgroups: computers, hasbootfs, hassrvfs, buildd, jessie, broken_mq + arm-arm-02: + address: 217.140.96.59 + parents: gw-arm + 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 - hostgroups: computers, hasbootfs, hassrvfs, wheezy, armhf, porterbox + hostgroups: computers, hasbootfs, hassrvfs, jessie, armhf, porterbox, broken_mq hartmann: address: 217.140.96.67 parents: gw-arm - hostgroups: computers, hasbootfs, hassrvfs, wheezy, armhf, buildd - hasse: - address: 217.140.96.68 - parents: gw-arm - hostgroups: computers, hasbootfs, hassrvfs, wheezy, armhf, buildd - henze: - address: 217.140.96.70 - parents: gw-arm - hostgroups: computers, hasbootfs, hassrvfs, wheezy, armhf, buildd + hostgroups: computers, hasbootfs, hassrvfs, jessie, armhf, buildd, broken_mq hoiby: address: 217.140.96.71 parents: gw-arm - hostgroups: computers, hasbootfs, hassrvfs, armhf, wheezy, buildd + hostgroups: computers, hasbootfs, hassrvfs, armhf, jessie, buildd, broken_mq + ia64-arm-01: + address: 217.140.96.61 + parents: gw-arm + hostgroups: computers, hasbootfs, hassrvfs, wheezy, buildd, broken_mq, sw-raid, acpid-hosts # }}} # {{{ gw-brown franck: @@ -277,24 +320,24 @@ servers: bm-bl9: address: 5.153.231.249 parents: gw-bytemark - hostgroups: computers, bm-bl, acpid-hosts, service, wheezy, openstack-compute + hostgroups: computers, bm-bl, acpid-hosts, service, wheezy, openstack-compute, broken_mq bm-bl10: address: 5.153.231.250 parents: gw-bytemark - hostgroups: computers, bm-bl, acpid-hosts, service, wheezy, openstack-compute + hostgroups: computers, bm-bl, acpid-hosts, service, wheezy, openstack-compute, broken_mq bm-bl11: address: 5.153.231.251 parents: gw-bytemark - hostgroups: computers, bm-bl, acpid-hosts, service, wheezy, openstack-compute + hostgroups: computers, bm-bl, acpid-hosts, service, wheezy, openstack-compute, broken_mq bm-bl12: address: 5.153.231.252 parents: gw-bytemark - hostgroups: computers, bm-bl, acpid-hosts, service, wheezy, openstack-compute + hostgroups: computers, bm-bl, acpid-hosts, service, wheezy, openstack-compute, broken_mq milanollo: address: 5.153.231.2 parents: gw-bytemark - hostgroups: computers, service, kvmdomains, wheezy, apache2-hosts, nfs-server, xinetd-hosts + hostgroups: computers, service, kvmdomains, jessie, apache2-hosts, nfs-server, xinetd-hosts milanollo2: address: 5.153.231.9 parents: milanollo @@ -314,17 +357,17 @@ servers: pejacevic: address: 5.153.231.6 parents: gw-bytemark - hostgroups: computers, service, kvmdomains, wheezy, apache2-hosts, nfs-client, autofs, apache-https + hostgroups: computers, service, kvmdomains, jessie, apache2-hosts, nfs-client, autofs, apache-https contacts: holger piu-slave-bm-a: address: 5.153.231.7 parents: gw-bytemark - hostgroups: computers, service, kvmdomains, wheezy, nfs-client, autofs + hostgroups: computers, service, kvmdomains, jessie, nfs-client, autofs contacts: holger binet: address: 5.153.231.8 parents: gw-bytemark - hostgroups: computers, buildd, hassrvfs, kvmdomains, wheezy + hostgroups: computers, buildd, hassrvfs, kvmdomains, jessie bmdb1: address: 5.153.231.10 parents: gw-bytemark @@ -336,11 +379,7 @@ servers: coccia: address: 5.153.231.11 parents: ganeti-bytemark - hostgroups: computers, hassrvfs, kvmdomains, wheezy, autofs, nfs-client - backuphost: - address: 5.153.231.12 - parents: ganeti-bytemark - hostgroups: computers, hassrvfs, kvmdomains, wheezy + hostgroups: computers, hassrvfs, kvmdomains, wheezy, autofs, nfs-client, uploadqueue, xinetd-hosts, apache-https, apache2-hosts philp: address: 5.153.231.13 parents: ganeti-bytemark @@ -368,7 +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 @@ -382,15 +421,11 @@ servers: dillon: address: 5.153.231.22 parents: ganeti-bytemark - hostgroups: computers, general, kvmdomains, wheezy, nfs-client, autofs, hassrvfs + hostgroups: computers, general, kvmdomains, jessie, nfs-client, autofs, hassrvfs ticharich: address: 5.153.231.23 parents: ganeti-bytemark - hostgroups: computers, general, kvmdomains, wheezy, nfs-client, autofs, apache2-hosts, apache-https, service - diamond: - address: 5.153.231.24 - parents: ganeti-bytemark - hostgroups: computers, service, kvmdomains, wheezy, bind9-hosts, no-bacula + hostgroups: computers, general, kvmdomains, jessie, nfs-client, autofs, apache2-hosts, apache-https, service, broken_https_default_vhost petrova: address: 5.153.231.25 parents: ganeti-bytemark @@ -398,25 +433,56 @@ servers: oyens: address: 5.153.231.26 parents: ganeti-bytemark - hostgroups: computers, kvmdomains, wheezy, apache2-hosts, openstack-controller, apache-https + 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 - hostgroups: computers, service, kvmdomains, wheezy, hassrvfs, nfs-client, xinetd-hosts, heavy-exim, apache2-hosts, autofs + hostgroups: computers, service, kvmdomains, wheezy, hassrvfs, nfs-client, xinetd-hosts, heavy-exim, apache2-hosts, autofs, apache-https portman: address: 5.153.231.29 parents: ganeti-bytemark - hostgroups: computers, service, kvmdomains, wheezy, hassrvfs + hostgroups: computers, service, kvmdomains, wheezy, hassrvfs, apache2-hosts + paradis: + address: 5.153.231.30 + parents: ganeti-bytemark + hostgroups: computers, service, kvmdomains, wheezy, hassrvfs, apache2-hosts, apache-https + x86-bm-01: + address: 5.153.231.32 + parents: ganeti-bytemark + hostgroups: computers, kvmdomains, wheezy, acpid-hosts, no-bacula + gideon: + address: 5.153.231.34 + parents: ganeti-bytemark + hostgroups: computers, service, kvmdomains, wheezy, hassrvfs, apache2-hosts, apache-https + httpredir-bm-01: + address: 5.153.231.35 + parents: ganeti-bytemark + hostgroups: computers, service, kvmdomains, wheezy, apache2-hosts + lindsay: + address: 5.153.231.36 + parents: ganeti-bytemark + hostgroups: computers, service, kvmdomains, jessie, 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 @@ -446,92 +512,136 @@ 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, bind9-hosts, xinetd-hosts, squeeze, apache-https steffani: address: 128.31.0.36 parents: gw-csail hostgroups: computers, service, apache2-hosts, rsyncd-hosts, sw-raid, acpid-hosts, hasbootfs, hasorgfs, xinetd-hosts, wheezy, security_mirror, no-bacula + + csail-node01: + address: 128.31.0.16 + parents: gw-csail + hostgroups: computers, service, dl360, acpid-hosts, wheezy, drbd-hosts + csail-node02: + address: 128.31.0.46 + parents: gw-csail + hostgroups: computers, service, dl360, acpid-hosts, wheezy, drbd-hosts + ganeti-csail: + address: 128.31.0.49 + parents: gw-bytemark + hostgroups: notacomputer + + falla: + address: 128.31.0.65 + parents: ganeti-csail + hostgroups: computers, freebsd, hassrvfs, porterbox, wheezy + fischer: + address: 128.31.0.35 + parents: ganeti-csail + hostgroups: computers, freebsd, hassrvfs, porterbox, wheezy + mirror-csail: + address: 128.31.0.62 + parents: ganeti-csail + hostgroups: computers, service, hassrvfs, kvmdomains, jessie, apache2-hosts, rsyncd-hosts, xinetd-hosts, apache-https + x86-csail-01: + 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 - argento: - address: 93.94.130.160 + storace: + address: 93.94.130.161 parents: gw-dgi - hostgroups: computers, sw-raid, hassrvfs, wheezy - # }}} - # {{{ gw-ftcollins - #alkman: - # address: 192.25.206.63 - # parents: gw-ftcollins - # hostgroups: computers, buildd, acpid-hosts, wheezy - #merulo: - # address: 192.25.206.58 - # parents: gw-ftcollins - # hostgroups: computers, porterbox, hasusrfs, wheezy - #mundy: - # address: 192.25.206.62 - # parents: gw-ftcollins - # hostgroups: computers, buildd, hassrvfs, sw-raid, acpid-hosts, wheezy - spohr: - address: 192.25.206.33 - parents: gw-ftcollins - hostgroups: computers, service, dl380, apache2-hosts, wheezy, no-bacula + hostgroups: computers, acpid-hosts, wheezy, dl380, nfs-client, hassrvfs + # }}} + # {{{ gw-gatech + sechter: + address: 128.61.240.73 + parents: gw-gatech + hostgroups: computers, service, apache2-hosts, rsyncd-hosts, sw-raid, acpid-hosts, hasbootfs, hassrvfs, xinetd-hosts, jessie, security_mirror # }}} # {{{ gw-grnet - barber: - address: 194.177.211.203 + ganeti-grnet: + address: 194.177.211.194 parents: gw-grnet - hostgroups: computers, acpid-hosts, buildd, hassrvfs, mptraid, wheezy - biber: - address: 194.177.211.204 + hostgroups: notacomputer + grnet-node01: + address: 194.177.211.195 parents: gw-grnet - hostgroups: computers, acpid-hosts, buildd, hassrvfs, mptraid, wheezy - orff: - address: 194.177.211.209 + hostgroups: computers, service, dl380, acpid-hosts, wheezy, drbd-hosts + grnet-node02: + address: 194.177.211.196 parents: gw-grnet - hostgroups: computers, acpid-hosts, bind9-hosts, mptraid, service, hassrvfs, apache2-hosts, squeeze + hostgroups: computers, service, dl380, acpid-hosts, wheezy, drbd-hosts rautavaara: address: 194.177.211.199 parents: gw-grnet - hostgroups: computers, acpid-hosts, megaraid, service, squeeze, nfs-server - vitry: - address: 194.177.211.206 + hostgroups: computers, acpid-hosts, megaraid, service, wheezy + loghost-grnet-01: + address: 194.177.211.200 parents: gw-grnet - hostgroups: computers, acpid-hosts, mptraid, no-bacula, wheezy + 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: address: 149.20.20.6 parents: gw-isc - hostgroups: computers, service, apache2-hosts, rsyncd-hosts, acpid-hosts, dl360, hasorgfs, xinetd-hosts, wheezy, security_mirror, no-bacula + hostgroups: computers, service, apache2-hosts, rsyncd-hosts, acpid-hosts, dl360, hasorgfs, xinetd-hosts, jessie, security_mirror, no-bacula # }}} # {{{ gw-leaseweb lw01: address: 185.17.185.177 parents: gw-leaseweb - hostgroups: computers, service, acpid-hosts, wheezy, dl180 + hostgroups: computers, service, acpid-hosts, jessie, dl180, nfs-server lw02: address: 185.17.185.178 parents: gw-leaseweb - hostgroups: computers, service, acpid-hosts, wheezy, dl180 + hostgroups: computers, service, acpid-hosts, jessie, dl180, nfs-server lw03: address: 185.17.185.179 parents: gw-leaseweb - hostgroups: computers, service, acpid-hosts, wheezy, dl180 + hostgroups: computers, service, acpid-hosts, jessie, dl180, nfs-server lw04: address: 185.17.185.180 parents: gw-leaseweb - hostgroups: computers, service, acpid-hosts, wheezy, dl180 - lw05: - address: 185.17.185.181 + hostgroups: computers, service, acpid-hosts, jessie, dl180, nfs-server + lw07: + address: 185.17.185.187 parents: gw-leaseweb - hostgroups: computers, service, acpid-hosts, wheezy, dl120, sw-raid - lw06: - address: 185.17.185.182 + hostgroups: computers, service, acpid-hosts, wheezy, dl180, nfs-client, autofs, hassrvfs, postgres91-hosts, apache2-hosts + lw08: + address: 185.17.185.189 parents: gw-leaseweb - hostgroups: computers, service, acpid-hosts, wheezy, dl120, sw-raid + hostgroups: computers, service, acpid-hosts, 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, jessie, broken_mq + arm-linaro-03: + address: 64.28.108.85 + parents: gw-linaro + hostgroups: computers, hasbootfs, hassrvfs, buildd, jessie, broken_mq + asachi: + address: 64.28.108.84 + parents: gw-linaro + hostgroups: computers, hasbootfs, hassrvfs, porterbox, wheezy, broken_mq # }}} # {{{ gw-karlsruhe zemlinsky: @@ -544,7 +654,7 @@ 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 @@ -562,6 +672,14 @@ servers: address: 82.195.75.110 parents: ganeti3 hostgroups: computers, service, kvmdomains, wheezy, hassrvfs, spamd, heavy-exim, highload + mipsel-manda-01: + address: 82.195.75.72 + parents: gw-man-da + hostgroups: computers, hasbootfs, hassrvfs, buildd, wheezy + mipsel-manda-02: + address: 82.195.75.74 + parents: gw-man-da + hostgroups: computers, hasbootfs, hassrvfs, buildd, wheezy fils: address: 82.195.75.89 parents: ganeti3 @@ -580,14 +698,6 @@ servers: address: 82.195.75.99 parents: ganeti3 hostgroups: computers, service, hasbootfs, kvmdomains, wheezy, hasvarlogfs - rem: - address: 82.195.75.68 - parents: gw-man-da - hostgroups: computers, buildd, hasbootfs, hassrvfs, wheezy - unger: - address: 82.195.75.102 - parents: gw-man-da - hostgroups: computers, service, dl360, acpid-hosts, wheezy draghi: address: 82.195.75.106 parents: ganeti3 @@ -595,7 +705,7 @@ 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 @@ -603,11 +713,11 @@ servers: kaufmann: address: 82.195.75.107 parents: ganeti3 - hostgroups: computers, service, apache2-hosts, rsyncd-hosts, kvmdomains, xinetd-hosts, wheezy + hostgroups: computers, service, apache2-hosts, rsyncd-hosts, kvmdomains, xinetd-hosts, jessie 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 @@ -628,18 +738,30 @@ servers: address: 82.195.75.92 parents: ganeti3 hostgroups: computers, service, kvmdomains, wheezy + wolkenstein: + address: 82.195.75.65 + parents: ganeti3 + hostgroups: computers, hasbootfs, hassrvfs, kvmdomains, service, xinetd-hosts, rsyncd-hosts, apache2-hosts, wheezy + mipsel-manda-01: + address: 82.195.75.72 + parents: gw-man-da + hostgroups: computers, buildd, wheezy, hassrvfs, sw-raid + mipsel-manda-02: + address: 82.195.75.74 + parents: gw-man-da + hostgroups: computers, buildd, wheezy, hassrvfs, sw-raid # }}} # {{{ gw-marist 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: address: 140.211.15.34 parents: gw-osuosl - hostgroups: computers, service, dl360, hassrvfs, acpid-hosts, wheezy, hasvarlogfs, apache2-hosts, no-bacula, apache-https + hostgroups: computers, service, dl360, hassrvfs, acpid-hosts, jessie, hasvarlogfs, apache2-hosts, no-bacula, apache-https byrd: address: 140.211.166.20 parents: gw-osuosl @@ -647,7 +769,7 @@ 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 @@ -657,14 +779,18 @@ servers: # address: 140.211.166.58 # parents: gw-osuosl # hostgroups: computers, buildd, hasbootfs + merulo: + address: 140.211.166.46 + parents: gw-osuosl + hostgroups: computers, porterbox, hasusrfs, wheezy 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 @@ -686,7 +812,7 @@ servers: sibelius: address: 193.62.202.28 parents: gw-sanger - hostgroups: computers, acpid-hosts, postgres91-hosts, service, apache2-hosts, sw-raid, squeeze, rsyncd-hosts, xinetd-hosts, hasvarlogfs + hostgroups: computers, acpid-hosts, postgres91-hosts, service, apache2-hosts, sw-raid, wheezy, rsyncd-hosts, xinetd-hosts, hasvarlogfs contacts: tjrc1, dave smetana: address: 193.62.202.29 @@ -702,13 +828,9 @@ 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 - beethoven: - address: 86.59.118.146 - parents: gw-sil - hostgroups: computers, hasbootfs, aacraid, service, acpid-hosts, wheezy eder: address: 86.59.118.151 parents: gw-sil @@ -720,7 +842,7 @@ servers: eberlin: address: 86.59.118.155 parents: gw-sil - hostgroups: computers, buildd, wheezy + hostgroups: computers, buildd, wheezy, sw-raid # }}} # {{{ gw-ubcece sw-ubcece: @@ -748,7 +870,7 @@ servers: ravel: address: 206.12.19.5 parents: sw-ubcece-kais - hostgroups: computers, general, dl385, apache2-hosts, acpid-hosts, hasbootfs, nfs-client, rsyncd-hosts, bind9-hosts, uploadqueue, hasorgfs, xinetd-hosts, wheezy, autofs + hostgroups: computers, general, dl385, apache2-hosts, acpid-hosts, hasbootfs, nfs-client, hasorgfs, wheezy, autofs dijkstra: address: 206.12.19.218 parents: sw-ubcece-kais @@ -781,38 +903,22 @@ servers: address: 206.12.19.118 parents: ganeti2 hostgroups: computers, general, apache2-hosts, hasbootfs, kvmdomains, apache-https, wheezy - wolkenstein: - address: 206.12.19.116 - parents: ganeti2 - hostgroups: computers, hasbootfs, hassrvfs, kvmdomains, service, xinetd-hosts, rsyncd-hosts, apache2-hosts, wheezy brahms: address: 206.12.19.115 parents: ganeti2 - hostgroups: computers, buildd, hassrvfs, kvmdomains, wheezy + hostgroups: computers, buildd, hassrvfs, kvmdomains, jessie geo2: address: 206.12.19.113 parents: ganeti2 - hostgroups: computers, service, bind9-hosts, kvmdomains, wheezy - stabile: - address: 206.12.19.13 - parents: sw-ubcece-kais - hostgroups: computers, hashomefs, sw-raid, rsyncd-hosts, apache2-hosts, xinetd-hosts, service, nfs-server, squeeze, hassrvfs - respighi: - address: 206.12.19.11 - parents: sw-ubcece-kais - hostgroups: computers, hasbootfs, aacraid, hassrvfs, service, apache2-hosts, squeeze + hostgroups: computers, service, bind9-hosts, kvmdomains, jessie # 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 check_command: dsa_check_always_ok - falla: - address: 206.12.19.117 - parents: ganeti2 - hostgroups: computers, freebsd, hassrvfs, porterbox, wheezy fano: address: 206.12.19.110 parents: ganeti2 @@ -823,10 +929,6 @@ servers: parents: ganeti2 hostgroups: computers, freebsd, wheezy, buildd, hassrvfs contacts: christoph - fischer: - address: 206.12.19.112 - parents: ganeti2 - hostgroups: computers, freebsd, hassrvfs, porterbox, wheezy gabrielli: address: 206.12.19.17 parents: sw-ubcece-kais @@ -839,14 +941,6 @@ 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 @@ -857,11 +951,11 @@ 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 @@ -873,7 +967,7 @@ 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 @@ -881,7 +975,7 @@ 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 @@ -889,7 +983,7 @@ 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 @@ -897,16 +991,12 @@ 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 + hostgroups: computers, service, kvmdomains, jessie, hassrvfs, no-bacula popov: address: 206.12.19.119 parents: ganeti2 @@ -933,11 +1023,6 @@ servers: hostgroups: computers, service, kvmdomains, wheezy, spamd, heavy-exim, mail-relay # }}} # {{{ gw-ugent - ancina: - address: 157.193.39.13 - parents: gw-ugent - hostgroups: computers, buildd, hassrvfs, hasbootfs, incomingmailrelayed2025, xinetd-hosts, wheezy - contacts: luk # }}} # {{{ gw-umn saens: @@ -945,6 +1030,28 @@ servers: parents: gw-umn hostgroups: computers, service, apache2-hosts, rsyncd-hosts, dl380, hasvarfs, hasusrfs, hasorgfs, xinetd-hosts, wheezy, security_mirror, no-bacula # }}} + # {{{ gw-unicamp + asgard: + address: 143.106.167.145 + parents: gw-unicamp + hostgroups: layer3-infrastructure + prokofiev: + address: 143.106.167.147 + parents: gw-unicamp + hostgroups: computers, jessie, service + powerpc-unicamp-01: + address: 143.106.167.149 + parents: prokofiev + 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: address: 130.89.148.10 @@ -964,11 +1071,15 @@ servers: hostgroups: secondary-IPs # }}} # {{{ gw-ynic - howells: + henze: + address: 144.32.168.74 + parents: gw-ynic + hostgroups: computers, hasbootfs, hassrvfs, armhf, jessie, buildd + hasse: address: 144.32.168.75 parents: gw-ynic - hostgroups: computers, hasbootfs, hassrvfs, armhf, wheezy, buildd - hummel: + hostgroups: computers, hasbootfs, hassrvfs, armhf, jessie, buildd + antheil: address: 144.32.168.76 parents: gw-ynic hostgroups: computers, hasbootfs, hassrvfs, armhf, wheezy, buildd @@ -980,6 +1091,18 @@ servers: address: 144.32.168.77 parents: gw-ynic hostgroups: computers, buildd, sw-raid, hassrvfs, wheezy + #antheil: + # address: 217.140.96.60 + # parents: gw-arm + # hostgroups: computers, hasbootfs, hassrvfs, buildd, wheezy, broken_mq + #hasse: + # address: 217.140.96.68 + # parents: gw-arm + # hostgroups: computers, hasbootfs, hassrvfs, wheezy, armhf, buildd, broken_mq + #henze: + # address: 217.140.96.70 + # parents: gw-arm + # hostgroups: computers, hasbootfs, hassrvfs, wheezy, armhf, buildd, broken_mq # }}} # {{{ gw-zivit zandonai: @@ -991,20 +1114,21 @@ 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 # }}} - -# {{{ hostgroups -############################# -# host groups -# -# hostgroups ircd and all are automatically defined -# -############################# +# {{{ ############################# host groups ############################# 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 @@ -1019,6 +1143,7 @@ hostgroups: freebsd: alias: freebsd private: 1 + extinfo-icon_image_alt: Debian GNU/kFreeBSD armhf: alias: armhf private: 1 @@ -1028,24 +1153,12 @@ 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 @@ -1080,14 +1193,11 @@ hostgroups: megaraid: alias: Hosts with LSI Logic MegaRAID private: 1 - mptraid: - alias: Hosts with LSI Logic Fusion-MPT - private: 1 - squeeze: - alias: Hosts running squeeze wheezy: alias: Hosts running wheezy + jessie: + alias: Hosts running jessie kvmdomains: alias: Hosts that are KVM domains @@ -1113,9 +1223,6 @@ 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 @@ -1182,9 +1289,6 @@ hostgroups: hasorgfs: alias: hosts with a /org filesystem private: 1 - hashomefs: - alias: hosts with a /home filesystem - private: 1 hasvarfs: alias: hosts with a /var filesystem private: 1 @@ -1210,9 +1314,6 @@ 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 @@ -1226,6 +1327,10 @@ hostgroups: security_mirror: alias: hosts that are security mirrors private: 1 + + broken_mq: + alias: hosts whose MQ is broken + private: 1 # }}} # {{{ ############################# servicegroups ############################# servicegroups: @@ -1248,16 +1353,17 @@ servicegroups: security: alias: security servicegroup_members: apt, kernel, samhain + MQ: + alias: rabbitMQ stuff # }}} - -# {{{ ############################# # services ############################# +# {{{ ############################# services ############################# services: - # {{{ ############ basic networking ############ + # {{{ ### basic networking - 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 @@ -1268,13 +1374,6 @@ 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%" @@ -1283,22 +1382,17 @@ services: max_check_attempts: 4 retry_check_interval: 1 # }}} - # {{{ ############ Disk Usage ############ + # {{{ ### disk usage - name: disk usage - all servicegroups: diskspace nrpe: "/usr/lib/nagios/plugins/check_disk -w 5% -c 2% -A -X devpts -X proc -X linprocfs -X devfs -X fdescfs -X sysfs -X nfs --ignore-eregi-path='/home/buildd/build-tr|/var/lib/schroot/mount'" hostgroups: computers - excludehosts: sibelius,stabile + excludehosts: sibelius - name: disk usage - all servicegroups: diskspace - nrpe: "/usr/lib/nagios/plugins/check_disk -w 5% -c 3% -A -X devpts -X proc -X linprocfs -X devfs -X fdescfs -X sysfs -X nfs --ignore-eregi-path=/srv/snapshot.debian.org" - hosts: stabile - - - name: disk usage - all - servicegroups: diskspace - nrpe: "/usr/lib/nagios/plugins/check_disk -X devpts -X proc -X linprocfs -X devfs -X fdescfs -X sysfs -X nfs 95 98" + nrpe: "/usr/lib/nagios/plugins/check_disk -X devpts -X proc -X linprocfs -X devfs -X fdescfs -X sysfs -X nfs -x /srv/farm-snapshot/farm-misc 95 98" hosts: sibelius - @@ -1306,12 +1400,6 @@ services: servicegroups: diskspace nrpe: "/usr/lib/nagios/plugins/check_disk 90 95 /" hostgroups: computers - excludehosts: spohr - - - name: disk usage on / - servicegroups: diskspace - nrpe: "/usr/lib/nagios/plugins/check_disk 90 93 /" - hosts: spohr - name: disk usage on /boot servicegroups: diskspace @@ -1342,16 +1430,11 @@ services: servicegroups: diskspace nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /usr" hostgroups: hasusrfs - - - name: disk usage on /home - servicegroups: diskspace - nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /home" - hostgroups: hashomefs - 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 + hosts: sibelius, busoni, buxtehude, lw07 - name: disk usage on /var/log servicegroups: diskspace @@ -1366,21 +1449,31 @@ services: name: disk usage on /srv/mirrors servicegroups: diskspace nrpe: "/usr/lib/nagios/plugins/check_disk 95 98 /srv/mirrors" - hosts: beethoven, sibelius + hosts: sibelius - name: disk usage on /srv/snapshot.debian.org servicegroups: diskspace - nrpe: "/usr/lib/nagios/plugins/check_disk 98 99 /srv/snapshot.debian.org" - hosts: stabile + nrpe: "/usr/lib/nagios/plugins/check_disk 90 94 /srv/snapshot.debian.org" + hosts: sibelius - - name: disk usage on /srv/snapshot.debian.org + name: disk usage on /srv/farm-snapshot/farm-1 servicegroups: diskspace - nrpe: "/usr/lib/nagios/plugins/check_disk 90 94 /srv/snapshot.debian.org" + nrpe: "/usr/lib/nagios/plugins/check_disk 97 95 /srv/farm-snapshot/farm-1" + hosts: sibelius + - + name: disk usage on /srv/farm-snapshot/farm-2 + servicegroups: diskspace + nrpe: "/usr/lib/nagios/plugins/check_disk 97 95 /srv/farm-snapshot/farm-2" hosts: sibelius - - name: disk usage on /srv/farm-snapshot/farm-misc + name: disk usage on /srv/farm-snapshot/farm-3 servicegroups: diskspace - nrpe: "/usr/lib/nagios/plugins/check_disk 97 95 /srv/farm-snapshot/farm-misc" + nrpe: "/usr/lib/nagios/plugins/check_disk 97 95 /srv/farm-snapshot/farm-3" + hosts: sibelius + - + name: disk usage on /srv/farm-snapshot/farm-4 + servicegroups: diskspace + nrpe: "/usr/lib/nagios/plugins/check_disk 97 95 /srv/farm-snapshot/farm-4" hosts: sibelius - name: disk usage on /var/lib/postgresql/9.1 @@ -1393,42 +1486,116 @@ services: nrpe: "/usr/lib/nagios/plugins/check_disk 85 95 /srv/ftp-master.debian.org" hosts: franck - - name: disk usage on /srv/pgbackup + name: disk usage on /storage/snapshot-farm-1 + servicegroups: diskspace + nrpe: "/usr/lib/nagios/plugins/check_disk 98 92 /storage/snapshot-farm-1" + hosts: lw01 + - + name: disk usage on /storage/snapshot-farm-2 servicegroups: diskspace - nrpe: "/usr/lib/nagios/plugins/check_disk 85 95 /srv/pgbackup" - hosts: beethoven + nrpe: "/usr/lib/nagios/plugins/check_disk 98 92 /storage/snapshot-farm-2" + hosts: lw02 - - name: disk usage on /srv/git-backup + name: disk usage on /storage/snapshot-farm-3 servicegroups: diskspace - nrpe: "/usr/lib/nagios/plugins/check_disk 85 95 /srv/git-backup" - hosts: beethoven + nrpe: "/usr/lib/nagios/plugins/check_disk 98 92 /storage/snapshot-farm-3" + hosts: lw03 - - name: disk usage on /srv/da-backup + name: disk usage on /storage/snapshot-farm-4 servicegroups: diskspace - nrpe: "/usr/lib/nagios/plugins/check_disk 85 95 /srv/da-backup" - hosts: beethoven + nrpe: "/usr/lib/nagios/plugins/check_disk 98 92 /storage/snapshot-farm-4" + hosts: lw04 - - name: disk usage on /srv/bacula + name: disk usage on /srv/morgue.debian.org/ servicegroups: diskspace - nrpe: "/usr/lib/nagios/plugins/check_disk 85 95 /srv/bacula" - hosts: beethoven + nrpe: "/usr/lib/nagios/plugins/check_disk 95 90 /srv/morgue.debian.org" + hosts: lw03 # }}} - - # {{{ ############ All Computers ############ + # {{{ ### system + # {{{ setup - - name: apt - security updates - servicegroups: apt - nrpe: "/usr/lib/nagios/plugins/dsa-check-statusfile /var/cache/dsa/nagios/apt" + name: setup - dsa config + nrpe: "/usr/lib/nagios/plugins/dsa-check-config" + hostgroups: computers + normal_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' + hostgroups: computers + normal_check_interval: 60 + # }}} + # {{{ os health + #### + - + name: users + nrpe: "/usr/lib/nagios/plugins/check_users 30 35" + hostgroups: computers + - + name: load + nrpe: "/usr/lib/nagios/plugins/check_load -w 30,28,26 -c 50,45,50" + hostgroups: computers + excludehostgroups: highload + - + name: load + nrpe: "/usr/lib/nagios/plugins/check_load -w 140,120,100 -c 240,220,200" + hostgroups: highload + - + name: uptime check + nrpe: "/usr/lib/nagios/plugins/dsa-check-uptime" + hostgroups: computers + - + 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%" + hostgroups: computers + - + name: swap usage - mb + nrpe: "/usr/lib/nagios/plugins/check_swap -w 20000 -c 5000" + 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 + - + 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" + hostgroups: computers + - + name: system - available entropy + 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" normal_check_interval: 60 retry_check_interval: 15 - #### + hostgroups: computers + # }}} + # {{{ backup - name: backup servicegroups: backup nrpe: "sudo /usr/lib/nagios/plugins/dsa-check-dabackup" hostgroups: computers - excludehosts: backuphost + excludehosts: storace normal_check_interval: 60 max_check_attempts: 2 retry_check_interval: 5 @@ -1436,7 +1603,7 @@ services: name: backup server config servicegroups: backup nrpe: "/usr/lib/nagios/plugins/dsa-check-dabackup-server" - hosts: beethoven, backuphost + hosts: storace normal_check_interval: 60 max_check_attempts: 2 retry_check_interval: 5 @@ -1471,6 +1638,12 @@ services: hostgroups: freebsd #### + - + name: process - acc.umu.se backup + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:8 -c 1: -u root -a 'dsmc'" + hosts: sibelius + # }}} + # {{{ security - name: running kernel servicegroups: kernel @@ -1478,8 +1651,23 @@ services: hostgroups: computers normal_check_interval: 60 retry_check_interval: 5 - - #### + - + name: apt - security updates + servicegroups: apt + nrpe: "/usr/lib/nagios/plugins/dsa-check-statusfile /var/cache/dsa/nagios/apt" + 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" @@ -1490,13 +1678,21 @@ services: nrpe: "/usr/lib/nagios/plugins/dsa-check-file -w -f /etc/ferm/conf.d/defs.conf" hostgroups: computers excludehostgroups: freebsd - - #### - - name: ganeti - job watcher paused - nrpe: "/usr/lib/nagios/plugins/negate /usr/lib/nagios/plugins/dsa-check-file -f /var/lib/ganeti/watcher.pause" - hostgroups: computers - - #### + - + 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 + - + 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" + hostgroups: freebsd, sparc + #### - name: process - samhain nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:8 -c 1: -u root -C samhain -a '/usr/sbin/samhain'" @@ -1511,74 +1707,49 @@ services: normal_check_interval: 60 retry_check_interval: 5 excludehostgroups: brokensamhain - - #### - - - name: process - acc.umu.se backup - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:8 -c 1: -u root -a 'dsmc'" - hosts: sibelius - - #### - - - name: users - nrpe: "/usr/lib/nagios/plugins/check_users 30 35" - hostgroups: computers - - #### - - - name: load - nrpe: "/usr/lib/nagios/plugins/check_load -w 30,28,26 -c 50,45,50" - hostgroups: computers - excludehostgroups: highload - - - name: load - nrpe: "/usr/lib/nagios/plugins/check_load -w 140,120,100 -c 240,220,200" - hostgroups: highload - - #### - - - name: uptime check - nrpe: "/usr/lib/nagios/plugins/dsa-check-uptime" - hostgroups: computers - - #### - name: processes - samhain zombies nrpe: "/usr/lib/nagios/plugins/check_procs 3 6 -s Z -u root -a samhain" event_handler: dsa_event_handler_restart_samhain hostgroups: computers excludehostgroups: brokensamhain + # }}} + # {{{ logging - - name: processes - zombies - nrpe: "/usr/lib/nagios/plugins/check_procs 5 10 -s Z" + 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 - #### - - name: processes - total - nrpe: "/usr/lib/nagios/plugins/check_procs 620 700" - hostgroups: computers + 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: swap usage - percent - nrpe: "/usr/lib/nagios/plugins/check_swap -w 20% -c 10%" + name: remote logging on lotti + remotecheck: "/usr/lib/nagios/plugins/dsa-check-log-age-loghost $HOSTNAME$" + runfrom: lotti hostgroups: computers - - #### + excludehostgroups: alioth - - name: swap usage - mb - nrpe: "/usr/lib/nagios/plugins/check_swap -w 20000 -c 5000" + name: remote logging on lully + remotecheck: "/usr/lib/nagios/plugins/dsa-check-log-age-loghost $HOSTNAME$" + runfrom: lully hostgroups: computers - - #### + excludehostgroups: alioth - - name: process - getty - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:8 -c 1: -u root -C getty -a /sbin/getty" + name: remote logging on loghost-grnet-01 + remotecheck: "/usr/lib/nagios/plugins/dsa-check-log-age-loghost $HOSTNAME$" + runfrom: loghost-grnet-01 hostgroups: computers - excludehosts: zelenka, zandonai - - #### + excludehostgroups: alioth + # }}} + # {{{ base service - name: process - sshd nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:20 -c 1: -u root -C sshd -a '/usr/sbin/sshd'" @@ -1590,7 +1761,6 @@ services: depends: process - sshd normal_check_interval: 60 notification_interval: 1440 - #### - name: network service - nrpe @@ -1604,7 +1774,6 @@ services: hostgroups: computers max_check_attempts: -1 depends: network service - nrpe - ### - name: process - munin-node @@ -1618,14 +1787,13 @@ services: - name: process - munin-node nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:3 -c 1: -u root -C munin-node -a 'munin-node'" - hostgroups: wheezy + hostgroups: wheezy, jessie excludehostgroups: freebsd - name: network service - munin-node check: check_tcp!4949 hostgroups: computers depends: process - munin-node - ### - name: process - ntpd @@ -1637,17 +1805,7 @@ services: check: dsa_check_ntp hostgroups: computers depends: process - ntpd - excludehosts: ancina - servicegroups: time - - ### - - - name: network service - time - check: dsa_check_time - hosts: ancina - depends: process - xinetd servicegroups: time - ### - name: process - atd @@ -1658,386 +1816,176 @@ services: name: process - cron nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:3 -c 1: -u root -C cron -a /usr/sbin/cron" hostgroups: computers - ### - - 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'" + 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 - + excludehostgroups: freebsd, alioth - - 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'" + 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: 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 + 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 + excludehostgroups: alioth, jessie + ### - name: MQ connection on rainier + servicegroups: MQ remotecheck: "/usr/lib/nagios/plugins/dsa-check-mq-connection $HOSTNAME$ ud dsa" runfrom: rainier hostgroups: computers normal_check_interval: 60 retry_check_interval: 15 - excludehostgroups: alioth + excludehostgroups: alioth, broken_mq - name: MQ connection on rapoport + servicegroups: MQ remotecheck: "/usr/lib/nagios/plugins/dsa-check-mq-connection $HOSTNAME$ ud dsa" runfrom: rapoport hostgroups: computers normal_check_interval: 60 retry_check_interval: 15 - excludehostgroups: alioth - # }}} - # {{{ ############ MAIL STUFF ############ + excludehostgroups: alioth, broken_mq + ### - - name: process - exim - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:10 -c 1: -u Debian-exim -C exim4 -a '/usr/sbin/exim4 -bd -q'" + name: local resolver + nrpe: "/usr/lib/nagios/plugins/dsa-check-resolver www.debian.org www.google.com" hostgroups: computers - excludehostgroups: postfix-hosts, mail-relay - excludehosts: master, busoni, 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'" - hostgroups: mail-relay + normal_check_interval: 60 - - name: process - exim - total - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:50 -c 1: -C exim4" + 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: postfix-hosts - excludehosts: master, busoni, 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 + excludehostgroups: alioth + ### - - name: mail queue - nrpe: "/usr/lib/nagios/plugins/check_mailq -M exim -w 1000 -c 2000" - hostgroups: heavy-exim + 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 ### - - name: process - clamav - clamd - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:2 -c 1: -u clamav -C clamd -a '/usr/sbin/clamd'" - hostgroups: heavy-exim, heavy-postfix + 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 - - name: service - clamav - nrpe: "/usr/lib/nagios/plugins/check_clamd -H /var/run/clamav/clamd.ctl" - hostgroups: heavy-exim, heavy-postfix - depends: process - clamav - clamd + 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: 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 + name: unexpected process - udev + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C udevd" + hostgroups: freebsd + ### - - name: unwanted process - clamav - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C clamd" - hostgroups: computers - excludehostgroups: heavy-exim, heavy-postfix + 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 - - name: unwanted process - freshclam - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C freshclam" + name: unexpected process - acpid + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C acpid" hostgroups: computers - excludehostgroups: heavy-exim, heavy-postfix + excludehostgroups: acpid-hosts, kvmdomains ### - - 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 + name: process - xinetd + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C xinetd -a '/usr/sbin/xinetd '" + hostgroups: xinetd-hosts - - 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 20 --min-spare=5 --helper-home-dir -d --pidfile=/var/run/spamd.pid'" - hosts: picconi + name: unwanted process - xinetd + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C xinetd" + hostgroups: computers + excludehostgroups: xinetd-hosts + ### - - 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 10 --helper-home-dir -d --pidfile=/var/run/spamd.pid'" - hosts: bendel + 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 + excludehostgroups: freebsd, alioth - - name: process - spamd - child - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:11 -c 1: -C spamd -a 'spamd child'" - hosts: bendel - hostgroups: spamd - depends: process - spamd - master - # + 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 - - 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: ganeti - job watcher paused + nrpe: "/usr/lib/nagios/plugins/negate /usr/lib/nagios/plugins/dsa-check-file -f /var/lib/ganeti/watcher.pause" + hostgroups: computers - - 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 - irqbalance + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C irqbalance" + hostgroups: computers - - name: unwanted process - spamd - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C spamd" + name: unwanted process - openvpn + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C openvpn" hostgroups: computers - excludehostgroups: spamd - excludehosts: bendel, busoni, buxtehude - + normal_check_interval: 120 - - name: unwanted process - greylistd - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C greylistd" + name: unwanted process - gkrellmd + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C gkrellmd" 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 + name: unwanted process - rpc.statd + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C rpc.statd" + hostgroups: computers + excludehostgroups: nfs-client, nfs-server - - 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 --inet=127.0.0.1:60000'" - hostgroups: heavy-postfix - # + name: unwanted process - inetd + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C inetd" + hostgroups: computers + excludehosts: abel - - name: unwanted process - postgrey - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C postgrey" + name: unwanted process - snmpd + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C snmpd" hostgroups: computers - excludehostgroups: heavy-postfix, heavy-exim - ### + # }}} + # {{{ ssl certs - - name: process - amavis - master - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u amavis -a 'amavisd-new (master)'" - hostgroups: amavis-hosts - - - name: process - amavis - all - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:10 -c 1:10 -u amavis -a 'amavisd-new '" - hostgroups: amavis-hosts - depends: process - amavis - master - # - - - name: unwanted process - amavis - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C amavisd-new" - hostgroups: computers - excludehostgroups: amavis-hosts - ### - - - 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 - - - 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 - 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 - 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 - - - ### - - - name: process - postfix - master - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C master -a '/usr/lib/postfix/master'" - hostgroups: postfix-hosts - - - name: process - postfix - qmgr - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postfix -C qmgr -a 'qmgr -l -t fifo -u'" - hostgroups: postfix-hosts - depends: process - postfix - master - - - name: process - postfix - pickup - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postfix -C pickup -a 'pickup -l -t fifo -u -c'" - hostgroups: postfix-hosts - depends: process - postfix - master - - - name: process - postfix - anvil - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:1 -c 0: -u postfix -C anvil -a 'anvil -l -t unix -u'" - hostgroups: postfix-hosts - depends: process - postfix - master - - - - name: process - postfix - trivial-rewrite - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:10 -c 0:15 -u postfix -C trivial-rewrite -a 'trivial-rewrite -n rewrite -t unix -u -c'" - hostgroups: postfix-hosts - depends: process - postfix - master - - - name: process - postfix - proxymap - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:10 -c 0:15 -u postfix -C proxymap -a 'proxymap -t unix -u'" - hostgroups: postfix-hosts - depends: process - postfix - master - - - name: process - postfix - cleanup - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:30 -c 0:50 -u postfix -C cleanup -a 'cleanup -z -t unix -u -c'" - hostgroups: postfix-hosts - depends: process - postfix - master - - - name: process - postfix - local - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:30 -c 0:50 -u postfix -C local -a 'local -t unix'" - hostgroups: postfix-hosts - depends: process - postfix - master - - - name: unwanted process - openvpn - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C openvpn" - hostgroups: computers - normal_check_interval: 120 - - - ### - - - name: network service - smtp - check: dsa_check_smtp - hostgroups: computers - excludehostgroups: postfix-hosts, incomingmailrelayed, incomingmailrelayed2025 - depends: process - exim - - - - name: network service - smtp - check: dsa_check_smtp - hostgroups: postfix-hosts - depends: process - postfix - master - - - name: network service - submission - check: dsa_check_smtp_port!587 - hostgroups: incomingmailrelayed - depends: process - exim - - - name: network service - smtp 2025 - check: dsa_check_smtp_port!2025 - hostgroups: incomingmailrelayed2025 - depends: process - exim - - - name: network service local - smtps cert - nrpe: "/usr/lib/nagios/plugins/check_http -H localhost -p 465 -S -C 14 -t 45" - hostgroups: postfix-hosts - depends: process - postfix - master - normal_check_interval: 120 - - - - name: setup - dsa config - nrpe: "/usr/lib/nagios/plugins/dsa-check-config" - hostgroups: computers - normal_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' - hostgroups: computers - normal_check_interval: 60 - - - name: system - available entropy - 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" - normal_check_interval: 60 - retry_check_interval: 15 - hostgroups: computers - ### - - - name: local resolver - nrpe: "/usr/lib/nagios/plugins/dsa-check-resolver www.debian.org www.google.com" - hostgroups: computers - normal_check_interval: 60 - - - 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'" - hostgroups: computers - ### - - - name: unwanted process - irqbalance - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C irqbalance" - hostgroups: computers - - #### - - - name: unwanted process - gkrellmd - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C gkrellmd" - hostgroups: computers - - - name: unwanted process - rpc.statd - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C rpc.statd" - hostgroups: computers - excludehostgroups: nfs-client, nfs-server - - - name: unwanted process - inetd - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C inetd" + 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 - excludehosts: abel - - name: unwanted process - snmpd - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C snmpd" + 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" - 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" + 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 # }}} - # {{{ ############ Processes/Services that only run on some computers ############ - - - 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: dl385 - ### + # {{{ 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 /var/run/mdadm/monitor.pid --daemonise --scan'" + 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: wheezy + excludehostgroups: jessie - - # wheezy: name: process - mdadm monitor servicegroups: raid - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u root -C mdadm -a '/sbin/mdadm --monitor --pid-file /run/mdadm/monitor.pid --daemonise --scan'" + 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: squeeze + excludehostgroups: wheezy - name: RAID - sw raid servicegroups: raid nrpe: "/usr/lib/nagios/plugins/dsa-check-raid-sw" hostgroups: sw-raid - - ### - - - 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 - - - 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'" + 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: squeeze, alioth + excludehostgroups: sw-raid + ### - name: HW - hpacucli status servicegroups: raid @@ -2070,29 +2018,38 @@ services: normal_check_interval: 120 hostgroups: dl585 ### - - - name: HW - edac status - nrpe: "/usr/lib/nagios/plugins/dsa-check-edac" - normal_check_interval: 120 - hosts: lw05, lw06 +# - +# name: HW - edac status +# 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 + excludehosts: villa, lobos, schein, storace - name: HW - hpasmcli status nrpe: "/usr/lib/nagios/plugins/dsa-check-hpasm --ps-no-redundant" normal_check_interval: 120 - hosts: villa, lobos + hosts: villa + - + name: HW - hpasmcli status + nrpe: "/usr/lib/nagios/plugins/dsa-check-hpasm --ps-no-redundant --ignore-failed='PS2'" + normal_check_interval: 120 + hosts: lobos - 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" + normal_check_interval: 120 + hosts: storace ### - name: RAID - 3ware @@ -2112,112 +2069,228 @@ services: nrpe: "/usr/lib/nagios/plugins/dsa-check-raid-megaraid" hostgroups: megaraid ### - - - name: RAID - MPT - servicegroups: raid - nrpe: "/usr/lib/nagios/plugins/dsa-check-raid-mpt" - hostgroups: mptraid - - ### - name: RAID - DRBD servicegroups: raid nrpe: "/usr/lib/nagios/plugins/dsa-check-drbd -d All" hostgroups: drbd-hosts + # }}} + # }}} + # {{{ ### mail stuff + # {{{ exim processes and mailq + - + name: process - exim + 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 + - + 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'" + hostgroups: mail-relay + - + name: process - exim - total + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:50 -c 1: -C exim4" + hostgroups: computers + excludehostgroups: postfix-hosts + excludehosts: master, busoni, 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 + - + name: mail queue + nrpe: "/usr/lib/nagios/plugins/check_mailq -M exim -w 1000 -c 2000" + hostgroups: heavy-exim + # }}} + # {{{ clamav + - + name: process - clamav - clamd + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:2 -c 1: -u clamav -C clamd -a '/usr/sbin/clamd'" + hostgroups: heavy-exim, heavy-postfix + - + name: service - clamav + 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 + - + name: unwanted process - clamav + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C clamd" + hostgroups: computers + excludehostgroups: heavy-exim, heavy-postfix + - + name: unwanted process - freshclam + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C freshclam" + hostgroups: computers + 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 + - + 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 20 --min-spare=5 --helper-home-dir -d --pidfile=/var/run/spamd.pid'" + 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 --create-prefs --max-children 10 --helper-home-dir -d --pidfile=/var/run/spamd.pid'" + hosts: bendel + - + name: process - spamd - child + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:11 -c 1: -C spamd -a 'spamd child'" + hosts: bendel + hostgroups: spamd + depends: process - spamd - master + # + - + name: unwanted process - spamd + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C spamd" + hostgroups: computers + excludehostgroups: spamd + excludehosts: bendel, busoni + + - + name: unwanted process - greylistd + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C greylistd" + hostgroups: computers + ### - - name: process - slapd - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:20 -c 1:50 -u openldap -C slapd -a '/usr/sbin/slapd -h ldap:/// ldaps:/// -g openldap -u openldap'" - hosts: draghi + 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 - - name: network service - ldaps cert - check: dsa_check_cert!636 - depends: process - slapd - normal_check_interval: 60 - hosts: draghi + 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 --inet=127.0.0.1:60000'" + hostgroups: heavy-postfix + # + - + name: unwanted process - postgrey + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C postgrey" + hostgroups: computers + excludehostgroups: heavy-postfix, heavy-exim ### - - name: process - ulogd - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C ulogd -a '/usr/sbin/ulogd -d'" + name: process - amavis - master + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u amavis -a 'amavisd-new (master)'" + hostgroups: amavis-hosts + - + name: process - amavis - all + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:10 -c 1:10 -u amavis -a 'amavisd-new '" + hostgroups: amavis-hosts + depends: process - amavis - master + # + - + name: unwanted process - amavis + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C amavisd-new" hostgroups: computers - excludehostgroups: freebsd, sparc + excludehostgroups: amavis-hosts + ### - - name: unexpected process - ulogd - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C ulogd" - hostgroups: freebsd, sparc - + 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 + - + 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 + 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 + 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 + # }}} + # {{{ postfix ### - - 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 + name: process - postfix - master + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C master -a '/usr/lib/postfix/master'" + hostgroups: postfix-hosts - - name: unexpected process - udev - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C udevd" - hostgroups: freebsd - ### + name: process - postfix - qmgr + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postfix -C qmgr -a 'qmgr -l -t fifo -u'" + hostgroups: postfix-hosts + depends: process - postfix - master - - 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 + name: process - postfix - pickup + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postfix -C pickup -a 'pickup -l -t fifo -u -c'" + hostgroups: postfix-hosts + depends: process - postfix - master - - name: unexpected process - acpid - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C acpid" - hostgroups: computers - excludehostgroups: acpid-hosts, kvmdomains - ### + name: process - postfix - anvil + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:1 -c 0: -u postfix -C anvil -a 'anvil -l -t unix -u'" + hostgroups: postfix-hosts + depends: process - postfix - master + - - 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'" - hostgroups: xinetd-hosts + name: process - postfix - trivial-rewrite + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:10 -c 0:15 -u postfix -C trivial-rewrite -a 'trivial-rewrite -n rewrite -t unix -u -c'" + hostgroups: postfix-hosts + depends: process - postfix - master - - name: unwanted process - xinetd - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C xinetd" - hostgroups: computers - excludehostgroups: xinetd-hosts - ### + name: process - postfix - proxymap + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:10 -c 0:15 -u postfix -C proxymap -a 'proxymap -t unix -u'" + hostgroups: postfix-hosts + depends: process - postfix - master - - name: network service - finger - check: check_tcp!79 - hosts: draghi - depends: process - xinetd - ### + name: process - postfix - cleanup + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:30 -c 0:50 -u postfix -C cleanup -a 'cleanup -z -t unix -u -c'" + hostgroups: postfix-hosts + depends: process - postfix - master - - name: network service - rsync - check: check_tcp!873 - hostgroups: rsyncd-hosts - depends: process - xinetd - excludehosts: rietz + name: process - postfix - local + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:30 -c 0:50 -u postfix -C local -a 'local -t unix'" + hostgroups: postfix-hosts + depends: process - postfix - master + - - name: network service - rsync - check: check_tcp!873 - hosts: rietz2 - depends: rietz:process - xinetd + name: network service local - smtps cert + nrpe: "/usr/lib/nagios/plugins/check_http -H localhost -p 465 -S -C 14 -t 45" + hostgroups: postfix-hosts + depends: process - postfix - master + normal_check_interval: 120 + # }}} + # {{{ mail - network service - - name: network service - rsync - check: check_tcp!873 - hosts: milanollo2 - depends: milanollo:process - xinetd + name: network service - smtp + check: dsa_check_smtp + hostgroups: computers + excludehostgroups: postfix-hosts, incomingmailrelayed, incomingmailrelayed2025 + depends: process - exim - ### - - name: process - icinga - # there is always one extra process per check currently running.. - 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: network service - smtp + check: dsa_check_smtp + hostgroups: postfix-hosts + depends: process - postfix - master - - 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: network service - submission + check: dsa_check_smtp_port!587 + hostgroups: incomingmailrelayed + depends: process - exim - - 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: network service - smtp 2025 + check: dsa_check_smtp_port!2025 + hostgroups: incomingmailrelayed2025 + depends: process - exim + # }}} + # }}} + # {{{ ### host specific services + # {{{ HTTP - name: process - apache2 - master nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u root -a /usr/sbin/apache2" @@ -2287,24 +2360,8 @@ services: # ravel does ssh on port 443 excludehosts: ravel normal_check_interval: 60 - - #### - - - 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'" - hostgroups: bind9-hosts - - - name: network service - dns - check: check_dns - hostgroups: bind9-hosts - depends: process - named - - - name: unwanted process - named - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C named" - hostgroups: computers - excludehostgroups: bind9-hosts - - #### + # }}} + # {{{ FTP - name: network service - ftp check: check_ftp @@ -2315,14 +2372,8 @@ services: check: check_ftp hosts: klecker-ftp depends: klecker:process - xinetd - - - - name: process - debianqueued - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:3 -c 1: -u dak-unpriv -C debianqueued" - hostgroups: uploadqueue - - - #### + # }}} + # {{{ postgres - name: unwanted process - postgresql nrpe: "/usr/lib/nagios/plugins/check_procs -w 0 -C postgres" @@ -2339,37 +2390,33 @@ services: - name: postgresql backups nrpe: "/usr/bin/sudo -u debbackup /usr/lib/nagios/plugins/dsa-check-backuppg" - hosts: backuphost - #### - - - 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 - excludehostgroups: freebsd, alioth - #### - - - name: process - UPS - nut usbhid-ups - ups1 - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u nut -C usbhid-ups -a '/lib/nut/usbhid-ups -a ups1'" - hosts: franck - - - name: process - UPS - nut upsd - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u nut -C upsd -a '/sbin/upsd'" - hosts: franck - - - name: process - UPS - nut upsmon master - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C upsmon -a '/sbin/upsmon'" - hosts: franck - - - name: process - UPS - nut upsmon worker - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u nut -C upsmon -a '/sbin/upsmon'" - hosts: franck - depends: process - UPS - nut upsmon master - - - name: UPS - on line power - nrpe: "/usr/lib/nagios/plugins/dsa-check-ups" - hosts: franck - depends: process - UPS - nut upsd - ### + hosts: storace + # }}} + # {{{ power +# - +# name: process - UPS - nut usbhid-ups - ups1 +# nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u nut -C usbhid-ups -a '/lib/nut/usbhid-ups -a ups1'" +# hosts: franck +# - +# name: process - UPS - nut upsd +# nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u nut -C upsd -a '/sbin/upsd'" +# hosts: franck +# - +# name: process - UPS - nut upsmon master +# nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C upsmon -a '/sbin/upsmon'" +# hosts: franck +# - +# name: process - UPS - nut upsmon worker +# nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u nut -C upsmon -a '/sbin/upsmon'" +# hosts: franck +# depends: process - UPS - nut upsmon master +# - +# name: UPS - on line power +# nrpe: "/usr/lib/nagios/plugins/dsa-check-ups" +# hosts: franck +# depends: process - UPS - nut upsd + # }}} + # {{{ buildd - name: process - buildd servicegroups: buildd @@ -2396,14 +2443,8 @@ services: nrpe: "/usr/lib/nagios/plugins/check_procs -m 'ELAPSED' -c 500 -C lvcreate -u root -a 'lvcreate'" hostgroups: buildd contact_groups: +buildd - #### - - - name: network service - gobby - check: check_tcp!6523 - hosts: gombert - contact_groups: gobby # }}} - # {{{ ############ NFS Stuff ############ + # {{{ NFS Stuff - name: process - statd nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u statd -C rpc.statd -a '/sbin/rpc.statd'" @@ -2431,14 +2472,7 @@ services: hostgroups: computers excludehostgroups: autofs # }}} - # {{{ ############ MISC OTHER Stuff ############ - - - name: puppetmaster cert - nrpe: "/usr/lib/nagios/plugins/dsa-check-cert-expire /var/lib/puppet/ssl/certs/ca.pem" - hosts: handel - normal_check_interval: 60 - max_check_attempts: 2 - retry_check_interval: 5 + # {{{ mirroring - name: mirror sync - bugs check: "dsa_check_mirrorsync_skew!bugs.debian.org!project/trace/bugs-master.debian.org!120:600" @@ -2461,6 +2495,23 @@ services: normal_check_interval: 15 max_check_attempts: 5 retry_check_interval: 5 + # }}} + # {{{ DNS + - + name: process - named + 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 + check: check_dns + hostgroups: bind9-hosts + depends: process - named + - + name: unwanted process - named + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C named" + hostgroups: computers + excludehostgroups: bind9-hosts + ### - name: DNS SOA sync - debian.org check: "dsa_check_soas_add!denis.debian.org!debian.org" @@ -2479,7 +2530,7 @@ services: hosts: global - name: DNS SOA sync - alioth.debian.org - check: "dsa_check_soas_add!alioth.debian.org!alioth.debian.org" + check: "dsa_check_soas_add!denis.debian.org!alioth.debian.org" hosts: global - name: DNS - delegation and signature expiry @@ -2501,8 +2552,8 @@ services: hosts: global remotecheck: "/usr/lib/nagios/plugins/dsa-check-statusfile /srv/dns.debian.org/var/nagios/ds" runfrom: denis - - ############ + # }}} + # {{{ storage - name: ping alive check remotecheck: "/usr/lib/nagios/plugins/check_ping -H $HOSTADDRESS$ -w 50,10% -c 200,30%" @@ -2518,10 +2569,11 @@ services: hosts: giustini - name: event log - remotecheck: "/usr/lib/nagios/plugins/dsa-check-msa-eventlog --start=8867 $HOSTADDRESS$ public" + remotecheck: "/usr/lib/nagios/plugins/dsa-check-msa-eventlog --start=9966 $HOSTADDRESS$ public" runfrom: dijkstra hosts: giustini - ############ + # }}} + # {{{ porterbox - name: current chroots nrpe: "/usr/lib/nagios/plugins/dsa-check-dchroots-current" @@ -2529,10 +2581,10 @@ services: normal_check_interval: 60 retry_check_interval: 15 # }}} - # {{{ ############ openstack ############ + # {{{ openstack - name: process - openstack - memcached - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:10 -c 1: -u nobody -C memcached -a '/usr/bin/memcached -m 64 -p 11211 -u nobody -l 127.0.0.1'" + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:10 -c 1: -u nobody -C memcached -a '/usr/bin/memcached -m 128 -p 11211 -u nobody -l 0.0.0.0'" hostgroups: openstack-controller - name: process - openstack - glance-registry @@ -2571,6 +2623,89 @@ services: nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:10 -c 1: -u neutron -C neutron-server -a '/usr/bin/python2.7 /usr/bin/neutron-server --config-file=/etc/neutron/neutron.conf --config-file /etc/neutron/plugins/openvswitch/ovs_neutron_plugin.ini --log-file=/var/log/neutron/neutron-server.log'" 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'" + hostgroups: dl385 + ### + - + name: process - slapd + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:20 -c 1:50 -u openldap -C slapd -a '/usr/sbin/slapd -h ldap:/// ldaps:/// -g openldap -u openldap'" + hosts: draghi + - + name: network service - ldaps cert + check: dsa_check_cert!636 + depends: process - slapd + normal_check_interval: 60 + hosts: draghi + ### + - + name: network service - finger + check: check_tcp!79 + hosts: draghi + depends: process - xinetd + ### + - + name: network service - rsync + check: check_tcp!873 + hostgroups: rsyncd-hosts + depends: process - xinetd + excludehosts: rietz + - + name: network service - rsync + check: check_tcp!873 + hosts: rietz2 + depends: rietz:process - xinetd + - + name: network service - rsync + check: check_tcp!873 + hosts: milanollo2 + depends: milanollo:process - xinetd + ### + - + name: process - icinga + 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 - debianqueued + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:3 -c 1: -u dak-unpriv -C debianqueued" + hostgroups: uploadqueue + #### + - + name: network service - gobby + check: check_tcp!6523 + hosts: gombert + contact_groups: gobby + #### + - + name: network service - sip-tls cert - 443 + check: dsa_check_cert!443 + normal_check_interval: 60 + hosts: vogler + - + name: network service - sip-tls cert - 5061 + check: dsa_check_cert!5061 + normal_check_interval: 60 + hosts: vogler + #### + - + name: puppetmaster cert + nrpe: "/usr/lib/nagios/plugins/dsa-check-cert-expire /var/lib/puppet/ssl/certs/ca.pem" + hosts: handel + normal_check_interval: 60 + max_check_attempts: 2 + retry_check_interval: 5 + # }}} # }}} # vim: set ts=2 sw=2 et ai si fdm=marker: