X-Git-Url: https://git.adam-barratt.org.uk/?a=blobdiff_plain;f=config%2Fnagios-master.cfg;h=f943cf4d03111c890eec70199331294594f6b542;hb=9282a9c45b7541095bfb43d09fb5894f9ce6b81b;hp=f6e56d1774bbb3cb8809b0a22a73728b09c259ef;hpb=392d9c7763863d349e3438b36f1d653aecf3cb02;p=mirror%2Fdsa-nagios.git diff --git a/config/nagios-master.cfg b/config/nagios-master.cfg index f6e56d1..f943cf4 100644 --- a/config/nagios-master.cfg +++ b/config/nagios-master.cfg @@ -28,6 +28,10 @@ servers: address: 130.239.18.97 parents: gw-ubcece hostgroups: layer3-infrastructure + gw-accumu2: + address: 130.242.6.198 + parents: gw-ubcece + hostgroups: layer3-infrastructure gw-aql: address: 141.170.2.17 parents: gw-ubcece @@ -77,7 +81,8 @@ servers: parents: gw-ubcece hostgroups: layer3-infrastructure gw-isc: - address: 149.20.65.129 + # really henet, because of something weird + address: 72.52.94.70 parents: gw-ubcece hostgroups: layer3-infrastructure gw-karlsruhe: @@ -176,6 +181,10 @@ servers: address: 130.239.18.121 parents: gw-accumu hostgroups: computers, buildd, hassrvfs, jessie + mirror-accumu: + address: 130.242.6.199 + parents: gw-accumu2 + hostgroups: computers, service, jessie, apache2-hosts, hassrvfs, xinetd-hosts # }}} # {{{ gw-aql eller: @@ -261,7 +270,7 @@ servers: fasolo: address: 138.16.160.17 parents: gw-brown - hostgroups: computers, service, apache2-hosts, apache-https, dl380, hpnewraid, rsyncd-hosts, xinetd-hosts, jessie, hassrvfs, postgres94-hosts + hostgroups: computers, service, apache2-hosts, apache-https, dl380, hpnewraid, rsyncd-systemd-hosts, jessie, hassrvfs, postgres94-hosts # }}} # {{{ gw-bytemark bm-bl1: @@ -456,7 +465,19 @@ servers: lindsay: address: 5.153.231.36 parents: ganeti-bytemark - hostgroups: computers, service, kvmdomains, jessie, autofs, nfs-client, systemd-timesyncd + hostgroups: computers, service, kvmdomains, stretch, autofs, nfs-client, systemd-timesyncd + mirror-bytemark: + address: 5.153.231.37 + parents: ganeti-bytemark + hostgroups: computers, service, kvmdomains, jessie, systemd-timesyncd, apache2-hosts, hassrvfs, xinetd-hosts + 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 @@ -481,6 +502,11 @@ servers: address: 5.153.231.44 parents: ganeti-bytemark hostgroups: computers, service, kvmdomains, jessie, autofs, nfs-client, apache2-hosts, apache-https, systemd-timesyncd + + casulana: + address: 5.153.231.41 + parents: gw-bytemark + hostgroups: computers, service, stretch, hpnewraid, hassrvfs, dl380 # }}} # {{{ gw-c3sl santoro: @@ -515,7 +541,24 @@ servers: acker: address: 217.196.149.228 parents: gw-conova - hostgroups: computers, jessie, service, sw-raid + hostgroups: computers, stretch, service, sw-raid + mirror-conova: + address: 217.196.149.229 + parents: gw-conova + hostgroups: computers, jessie, service, apache2-hosts, xinetd-hosts + mirror-conova-debian: + address: 217.196.149.232 + hostgroups: secondary-IPs + parents: mirror-conova + mirror-conova-security: + address: 217.196.149.233 + hostgroups: secondary-IPs + parents: mirror-conova + + arm-conova-01: + address: 217.196.149.230 + parents: aagaard + hostgroups: computers, hassrvfs, buildd, jessie # }}} # {{{ gw-csail csail-node01: @@ -624,11 +667,11 @@ servers: porta: address: 194.177.211.207 parents: ganeti-grnet - hostgroups: computers, service, hassrvfs, kvmdomains, jessie, rsyncd-hosts, xinetd-hosts, systemd-timesyncd + hostgroups: computers, service, hassrvfs, kvmdomains, jessie, rsyncd-systemd-hosts, xinetd-hosts, systemd-timesyncd melartin: address: 194.177.211.208 parents: ganeti-grnet - hostgroups: computers, service, kvmdomains, jessie, systemd-timesyncd + hostgroups: computers, service, kvmdomains, jessie, systemd-timesyncd, postgres96-hosts # }}} # {{{ gw-isc mirror-isc: @@ -741,11 +784,11 @@ servers: handel: address: 82.195.75.104 parents: ganeti3 - hostgroups: computers, service, kvmdomains, apache2-hosts, jessie + hostgroups: computers, service, kvmdomains, apache2-hosts, stretch, postgres96-hosts kaufmann: address: 82.195.75.107 parents: ganeti3 - hostgroups: computers, service, apache2-hosts, rsyncd-hosts, kvmdomains, xinetd-hosts, jessie, apache-https + hostgroups: computers, service, apache2-hosts, rsyncd-systemd-hosts, kvmdomains, jessie, apache-https stockhausen: address: 82.195.75.108 parents: ganeti3 @@ -793,7 +836,7 @@ servers: seger: address: 82.195.75.93 parents: ganeti3 - hostgroups: computers, service, apache2-hosts, hassrvfs, hasbootfs, rsyncd-hosts, uploadqueue, kvmdomains, xinetd-hosts, apache-https, postgres94-hosts, jessie + hostgroups: computers, service, apache2-hosts, hassrvfs, hasbootfs, rsyncd-systemd-hosts, uploadqueue, kvmdomains, xinetd-hosts, apache-https, postgres94-hosts, jessie # }}} # {{{ gw-marist zani: @@ -803,7 +846,7 @@ servers: # }}} # {{{ gw-osuosl busoni: - address: 140.211.15.34 + address: 140.211.166.202 parents: gw-osuosl hostgroups: computers, service, dl360, hassrvfs, jessie, hasvarlogfs, apache2-hosts, no-bacula, apache-https @@ -838,10 +881,14 @@ servers: hostgroups: computers, jessie, hassrvfs, porterbox, sw-raid # }}} # {{{ gw-sanger + sallinen: + address: 193.62.202.26 + parents: gw-sanger + hostgroups: computers, service, jessie, dl380, hpnewraid sibelius: address: 193.62.202.28 parents: gw-sanger - hostgroups: computers, postgres94-hosts, service, apache2-hosts, sw-raid, jessie, rsyncd-hosts, xinetd-hosts, hasvarlogfs, multipath-hosts + hostgroups: computers, postgres94-hosts, service, apache2-hosts, sw-raid, jessie, rsyncd-systemd-hosts, hasvarlogfs, multipath-hosts contacts: tjrc1, dave smetana: address: 193.62.202.29 @@ -920,10 +967,6 @@ servers: address: 206.12.19.218 parents: sw-ubcece-kais hostgroups: computers, bl460, acpid-hosts, service, jessie, drbd-hosts, multipath-hosts - ganeti2: - address: 206.12.19.23 - parents: sw-ubcece-kais - hostgroups: notacomputer # MSA 2000 (2012i) giustini: address: 192.168.2.6 @@ -936,10 +979,6 @@ servers: # address: 206.12.19.120 # parents: sw-ubcece-kais # hostgroups: computers, service, hasbootfs, kvmdomains, squeeze, hasvicepa - glinka: - address: 206.12.19.126 - parents: ganeti2 - hostgroups: computers, service, kvmdomains, jessie, apache2-hosts, apache-https, nfs-client, autofs, xinetd-hosts # }}} # {{{ ubc-gateway ubc-enc2bl01: @@ -958,14 +997,15 @@ servers: address: 209.87.16.10 parents: ubc-gateway hostgroups: computers, bl460g8, service, jessie, multipath-hosts, hpnewraid + rachmaninoff: address: 209.87.16.20 parents: ubc-gateway - hostgroups: computers, service, kvmdomains, jessie + hostgroups: computers, service, kvmdomains, jessie, systemd-timesyncd x86-ubc-01: address: 209.87.16.21 parents: ubc-gateway - hostgroups: computers, buildd, hassrvfs, kvmdomains, jessie + hostgroups: computers, buildd, hassrvfs, kvmdomains, jessie, systemd-timesyncd finzi: address: 209.87.16.22 parents: ubc-gateway @@ -979,67 +1019,72 @@ servers: elgar: address: 209.87.16.24 parents: ubc-gateway - hostgroups: computers, service, kvmdomains, jessie + hostgroups: computers, service, kvmdomains, jessie, systemd-timesyncd gombert: address: 209.87.16.25 parents: ubc-gateway - hostgroups: computers, service, kvmdomains, jessie, apache2-hosts, apache-https + hostgroups: computers, service, kvmdomains, jessie, apache2-hosts, apache-https, systemd-timesyncd nono: address: 209.87.16.26 parents: ubc-gateway - hostgroups: computers, service, kvmdomains, jessie, heavy-exim, xinetd-hosts, apache2-hosts, apache-https, broken_https_default_vhost, hassrvfs + hostgroups: computers, service, kvmdomains, jessie, heavy-exim, xinetd-hosts, apache2-hosts, apache-https, broken_https_default_vhost, hassrvfs, systemd-timesyncd reger: address: 209.87.16.27 parents: ubc-gateway - hostgroups: computers, service, kvmdomains, jessie, apache2-hosts, apache-https, heavy-exim + hostgroups: computers, service, kvmdomains, jessie, apache2-hosts, apache-https, heavy-exim, systemd-timesyncd diabelli: address: 209.87.16.28 parents: ubc-gateway - hostgroups: computers, service, kvmdomains, jessie, apache2-hosts, apache-https, broken_https_default_vhost + hostgroups: computers, service, kvmdomains, jessie, apache2-hosts, apache-https, broken_https_default_vhost, systemd-timesyncd menotti: address: 209.87.16.29 parents: ubc-gateway - hostgroups: computers, service, kvmdomains, jessie, hassrvfs, apache2-hosts, apache-https + hostgroups: computers, service, kvmdomains, jessie, hassrvfs, apache2-hosts, apache-https, systemd-timesyncd danzi: address: 209.87.16.30 parents: ubc-gateway - hostgroups: computers, service, kvmdomains, jessie, postgres94-hosts, xinetd-hosts + hostgroups: computers, service, kvmdomains, jessie, postgres94-hosts, xinetd-hosts, systemd-timesyncd geo2: address: 209.87.16.31 parents: ubc-gateway - hostgroups: computers, service, bind9-hosts, kvmdomains, jessie + hostgroups: computers, service, bind9-hosts, kvmdomains, jessie, systemd-timesyncd lotti: address: 209.87.16.32 parents: ubc-gateway - hostgroups: computers, service, kvmdomains, jessie, hassrvfs + hostgroups: computers, service, kvmdomains, jessie, hassrvfs, systemd-timesyncd muffat: address: 209.87.16.33 parents: ubc-gateway - hostgroups: computers, service, kvmdomains, jessie, spamd, heavy-exim, mail-relay + hostgroups: computers, service, kvmdomains, jessie, spamd, heavy-exim, mail-relay, systemd-timesyncd sonntag: address: 209.87.16.34 parents: ubc-gateway - hostgroups: computers, service, kvmdomains, jessie, nfs-client, autofs + hostgroups: computers, service, kvmdomains, jessie, nfs-client, autofs, systemd-timesyncd tchaikovsky: address: 209.87.16.35 parents: ubc-gateway - hostgroups: computers, general, apache2-hosts, kvmdomains, apache-https, jessie + hostgroups: computers, general, apache2-hosts, kvmdomains, apache-https, jessie, systemd-timesyncd gretchaninov: address: 209.87.16.36 parents: ubc-gateway - hostgroups: computers, general, kvmdomains, jessie, hassrvfs, nfs-server, apache2-hosts, xinetd-hosts + hostgroups: computers, general, kvmdomains, jessie, hassrvfs, nfs-server, apache2-hosts, xinetd-hosts, apache-https, systemd-timesyncd tye: address: 209.87.16.37 parents: ubc-gateway - hostgroups: computers, service, kvmdomains, jessie, heavy-exim, apache2-hosts, apache-https, nfs-client, autofs, hassrvfs + hostgroups: computers, service, kvmdomains, jessie, heavy-exim, apache2-hosts, apache-https, nfs-client, autofs, hassrvfs, systemd-timesyncd ullmann: address: 209.87.16.38 parents: ubc-gateway - hostgroups: computers, service, kvmdomains, jessie, postgres94-hosts, nfs-client, apache2-hosts, autofs, apache-https + hostgroups: computers, service, kvmdomains, jessie, postgres94-hosts, nfs-client, apache2-hosts, autofs, apache-https, systemd-timesyncd buxtehude: address: 209.87.16.39 parents: ubc-gateway - hostgroups: computers, service, kvmdomains, jessie, hassrvfs, apache2-hosts, heavy-exim, postgres94-hosts, hasvarlogfs, apache-https, spamd, nfs-server + hostgroups: computers, service, kvmdomains, jessie, hassrvfs, apache2-hosts, heavy-exim, postgres94-hosts, hasvarlogfs, apache-https, spamd, nfs-server, systemd-timesyncd + piu-slave-ubc-01: + address: 209.87.16.42 + parents: ubc-gateway + hostgroups: computers, service, kvmdomains, jessie, nfs-client, autofs, systemd-timesyncd + contacts: holger # }}} # {{{ gw-umn #saens: @@ -1116,10 +1161,6 @@ servers: address: 144.32.168.78 parents: gw-ynic hostgroups: computers, buildd, sw-raid, hassrvfs, jessie - poulenc: - address: 144.32.168.77 - parents: gw-ynic - hostgroups: computers, buildd, sw-raid, hassrvfs, jessie #antheil: # address: 217.140.96.60 # parents: gw-arm @@ -1226,6 +1267,8 @@ hostgroups: alias: Hosts running jessie jessie-freebsd: alias: kFreebsd hosts running jessie + stretch: + alias: Hosts running stretch kvmdomains: alias: Hosts that are KVM domains @@ -1262,6 +1305,9 @@ hostgroups: rsyncd-hosts: alias: hosts providing rsync services via xinetd private: 1 + rsyncd-systemd-hosts: + alias: hosts providing rsync services via systemd + private: 1 xinetd-hosts: alias: hosts providing services via xinetd private: 1 @@ -1271,6 +1317,9 @@ hostgroups: postgres94-hosts: alias: hosts running postgres94 private: 1 + postgres96-hosts: + alias: hosts running postgres96 + private: 1 no-ulogd: alias: hosts not running ulogd private: 1 @@ -1397,21 +1446,21 @@ services: excludehostgroups: layer3-infrastructure, high-RTT check_interval: 5 max_check_attempts: 4 - retry_check_interval: 1 + retry_interval: 1 - name: PING check: "check_ping!600.0,20%!900.0,40%" hostgroups: high-RTT check_interval: 5 max_check_attempts: 4 - retry_check_interval: 1 + retry_interval: 1 - name: PING check: "check_ping!2000.0,60%!3000.0,80%" hostgroups: layer3-infrastructure check_interval: 5 max_check_attempts: 4 - retry_check_interval: 1 + retry_interval: 1 # }}} # {{{ ### disk usage - @@ -1439,7 +1488,7 @@ services: - name: disk usage on /srv servicegroups: diskspace - nrpe: "/usr/lib/nagios/plugins/check_disk 95 98 /srv" + nrpe: "/usr/lib/nagios/plugins/check_disk 90 95 /srv" hostgroups: hassrvfs - name: disk usage on /var/lib/postgresql @@ -1569,11 +1618,11 @@ services: name: processes - total nrpe: "/usr/lib/nagios/plugins/check_procs 620 700" hostgroups: computers - excludehosts: prokofiev, pieta, ubc-enc2bl01, ubc-enc2bl02, ubc-enc2bl09, ubc-enc2bl10, fasolo + excludehosts: prokofiev, pieta, ubc-enc2bl01, ubc-enc2bl02, ubc-enc2bl09, ubc-enc2bl10, fasolo, casulana - name: processes - total nrpe: "/usr/lib/nagios/plugins/check_procs 1500 1700" - hosts: prokofiev, pieta, ubc-enc2bl01, ubc-enc2bl02, ubc-enc2bl09, ubc-enc2bl10, fasolo + hosts: prokofiev, pieta, ubc-enc2bl01, ubc-enc2bl02, ubc-enc2bl09, ubc-enc2bl10, fasolo, casulana - name: swap usage - percent nrpe: "/usr/lib/nagios/plugins/check_swap -w 20% -c 10%" @@ -1582,12 +1631,20 @@ services: name: swap usage - mb nrpe: "/usr/lib/nagios/plugins/check_swap -w 20000 -c 5000" hostgroups: computers + - + name: free memory - mb + nrpe: "/usr/lib/nagios/plugins/dsa-check-memory -m mb" + hostgroups: computers + - + 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 + 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" @@ -1595,7 +1652,7 @@ services: - name: process - getty nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:8 -c 1: -u root -C agetty -a /sbin/agetty" - hostgroups: jessie + hostgroups: jessie, stretch excludehostgroups: freebsd - @@ -1612,7 +1669,7 @@ services: name: system - filesystem check nrpe: "/usr/bin/sudo /usr/lib/nagios/plugins/dsa-check-filesystems" check_interval: 60 - retry_check_interval: 15 + retry_interval: 15 hostgroups: computers # }}} # {{{ backup @@ -1624,7 +1681,7 @@ services: excludehosts: backuphost, storace check_interval: 60 max_check_attempts: 2 - retry_check_interval: 5 + retry_interval: 5 - name: backup server config servicegroups: backup @@ -1632,7 +1689,7 @@ services: hosts: storace check_interval: 60 max_check_attempts: 2 - retry_check_interval: 5 + retry_interval: 5 - name: backup - bacula - last backup servicegroups: backup @@ -1641,7 +1698,7 @@ services: hostgroups: computers excludehostgroups: buildd, porterbox, no-bacula check_interval: 60 - retry_check_interval: 15 + retry_interval: 15 - name: backup - bacula - last full backup servicegroups: backup @@ -1650,7 +1707,7 @@ services: hostgroups: computers excludehostgroups: buildd, porterbox, no-bacula check_interval: 60 - retry_check_interval: 15 + retry_interval: 15 - name: process - bacula-dir servicegroups: backup @@ -1668,6 +1725,12 @@ services: 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 + servicegroups: backup + nrpe: "/usr/lib/nagios/plugins/dsa-check-statusfile -a 2h /home/debbackup/nagios-status" + hosts: draghi + #### - name: process - acc.umu.se backup @@ -1681,14 +1744,14 @@ services: nrpe: "/usr/lib/nagios/plugins/dsa-check-running-kernel" hostgroups: computers check_interval: 60 - retry_check_interval: 5 + retry_interval: 5 - name: apt - security updates servicegroups: apt nrpe: "/usr/lib/nagios/plugins/dsa-check-statusfile /var/cache/dsa/nagios/apt" hostgroups: computers check_interval: 60 - retry_check_interval: 15 + retry_interval: 15 - name: unexpected file - apt sources.list servicegroups: apt @@ -1697,12 +1760,11 @@ services: - name: upgraded libraries servicegroups: security - nrpe: "sudo /usr/local/sbin/dsa-check-libs" - #nrpe: "sudo /usr/lib/nagios/plugins/dsa-check-libs" + nrpe: "sudo /usr/lib/nagios/plugins/dsa-check-libs" hostgroups: computers excludehostgroups: freebsd check_interval: 60 - retry_check_interval: 15 + retry_interval: 15 notification_interval: 10080 - name: installed firewall @@ -1718,11 +1780,11 @@ services: name: process - ulogd nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C ulogd -a '/usr/sbin/ulogd -d'" hostgroups: computers - excludehostgroups: freebsd, sparc, jessie + 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 + hostgroups: jessie, stretch excludehostgroups: freebsd - name: unexpected process - ulogd @@ -1741,7 +1803,7 @@ services: hostgroups: computers depends: process - samhain check_interval: 60 - retry_check_interval: 5 + retry_interval: 5 excludehostgroups: brokensamhain - name: processes - samhain zombies @@ -1755,7 +1817,7 @@ services: name: process - syslog-ng nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C syslog-ng -a '/sbin/syslog-ng -p /var/run/syslog-ng.pid'" hostgroups: computers - excludehostgroups: freebsd, jessie + 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'" @@ -1763,7 +1825,7 @@ services: - name: process - syslog-ng nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C syslog-ng -a '/sbin/syslog-ng -F'" - hostgroups: jessie + hostgroups: jessie, stretch excludehostgroups: freebsd - @@ -1808,6 +1870,13 @@ services: name: process - nrpe nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:25 -c 1: -u nagios -C nrpe -a '/usr/sbin/nrpe -c /etc/nagios/nrpe.cfg -d'" hostgroups: computers + excludehostgroups: stretch + max_check_attempts: -1 + depends: network service - nrpe + - + name: process - nrpe + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:25 -c 1: -u nagios -C nrpe -a '/usr/sbin/nrpe -c /etc/nagios/nrpe.cfg -f'" + hostgroups: stretch max_check_attempts: -1 depends: network service - nrpe ### @@ -1856,6 +1925,15 @@ services: nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u daemon -C atd -a /usr/sbin/atd" hostgroups: computers ### + - + 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 + ### - name: process - cron nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:3 -c 1: -u root -C cron -a /usr/sbin/cron" @@ -1875,7 +1953,7 @@ services: name: process - monit nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u root -C monit -a '/usr/bin/monit -d 300 -I -c /etc/monit/monitrc -s /var/lib/monit/monit.state'" hostgroups: computers - excludehostgroups: alioth, jessie + excludehostgroups: alioth, jessie, stretch ### - name: MQ connection on rainier @@ -1884,7 +1962,7 @@ services: runfrom: rainier hostgroups: computers check_interval: 60 - retry_check_interval: 15 + retry_interval: 15 excludehostgroups: alioth, broken_mq - name: MQ connection on rapoport @@ -1893,7 +1971,7 @@ services: runfrom: rapoport hostgroups: computers check_interval: 60 - retry_check_interval: 15 + retry_interval: 15 excludehostgroups: alioth, broken_mq ### - @@ -1916,11 +1994,11 @@ services: name: process - udevd nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -p 1 -C udevd -a 'udevd'" hostgroups: computers - excludehostgroups: freebsd, jessie + 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 + hostgroups: jessie, stretch excludehostgroups: freebsd - name: unexpected process - udev @@ -1931,7 +2009,7 @@ services: 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 + excludehostgroups: jessie, stretch - name: unexpected process - acpid nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C acpid" @@ -1951,7 +2029,7 @@ services: - name: process - stunnel4 - puppet-ekeyd nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:6 -c 1: -u stunnel4 -C stunnel4 -a '/usr/bin/stunnel4 /etc/stunnel/puppet-ekeyd.conf'" - hostgroups: wheezy, jessie + hostgroups: wheezy, jessie, stretch excludehostgroups: freebsd, alioth - name: process - stunnel4 - puppet-ekeyd is crazy @@ -1970,10 +2048,6 @@ services: 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: unwanted process - irqbalance - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C irqbalance" - hostgroups: computers - name: unwanted process - openvpn nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C openvpn" @@ -2032,7 +2106,7 @@ services: servicegroups: raid nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u root -C mdadm -a '/sbin/mdadm --monitor --pid-file /run/mdadm/monitor.pid --daemonise --scan'" hostgroups: sw-raid - excludehostgroups: jessie + excludehostgroups: jessie, stretch - name: process - mdadm monitor servicegroups: raid @@ -2095,7 +2169,7 @@ services: nrpe: "/usr/lib/nagios/plugins/dsa-check-hpasm" check_interval: 120 hostgroups: dl380, dl360, bl460, bm-bl - excludehosts: villa, lobos, storace, mirror-anu + excludehosts: villa, lobos, storace, mirror-anu, sallinen - name: HW - hpasmcli status nrpe: "/usr/lib/nagios/plugins/dsa-check-hpasm --ps-no-redundant" @@ -2110,7 +2184,7 @@ services: name: HW - hpasmcli status nrpe: "/usr/lib/nagios/plugins/dsa-check-hpasm --fan-ignore-not-present" check_interval: 120 - hosts: storace + hosts: storace, sallinen - name: HW - hpasmcli status nrpe: "/usr/lib/nagios/plugins/dsa-check-hpasm --fan-ignore-not-present --ps-no-redundant --ignore-failed='PS1'" @@ -2177,7 +2251,7 @@ services: 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 + 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'" @@ -2200,7 +2274,7 @@ services: 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 + excludehostgroups: jessie, stretch - name: process - spamd - master nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C spamd -a '/usr/sbin/spamd -d --pidfile=/var/run/spamassassin.pid --create-prefs --max-children 5 --helper-home-dir'" @@ -2239,7 +2313,7 @@ services: 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 + 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'" @@ -2449,19 +2523,29 @@ services: name: network service - ftp check: check_ftp hostgroups: uploadqueue, security_mirror - excludehosts: klecker + excludehosts: klecker, mirror-isc, mirror-umn - name: network service - ftp check: check_ftp hosts: klecker-ftp depends: klecker:process - xinetd + - + name: network service - ftp + check: check_ftp + hosts: mirror-umn2 + depends: mirror-umn:process - xinetd + - + name: network service - ftp + check: check_ftp + hosts: mirror-isc2 + depends: mirror-isc:process - xinetd # }}} # {{{ postgres - name: unwanted process - postgresql nrpe: "/usr/lib/nagios/plugins/check_procs -w 0 -C postgres" hostgroups: computers - excludehostgroups: postgres91-hosts, postgres94-hosts + excludehostgroups: postgres91-hosts, postgres94-hosts, postgres96-hosts - name: unwanted process - postgresql 9.0 nrpe: "/usr/lib/nagios/plugins/check_procs -w 0 -C postgres -a '9.0/bin/postgres'" @@ -2474,6 +2558,10 @@ services: 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'" + hostgroups: postgres96-hosts - name: postgresql backups nrpe: "/usr/bin/sudo -u debbackup /usr/lib/nagios/plugins/dsa-check-backuppg" @@ -2524,7 +2612,7 @@ services: contact_groups: +buildd check_interval: 5 max_check_attempts: 24 - retry_check_interval: 5 + retry_interval: 5 - name: processes - lvcreate nrpe: "/usr/lib/nagios/plugins/check_procs -m 'ELAPSED' -c 500 -C lvcreate -u root -a 'lvcreate'" @@ -2576,7 +2664,7 @@ services: hosts: global check_interval: 15 max_check_attempts: 5 - retry_check_interval: 5 + retry_interval: 5 servicegroups: mirror - name: mirror sync - snapshot @@ -2584,7 +2672,7 @@ services: hosts: global check_interval: 15 max_check_attempts: 5 - retry_check_interval: 5 + retry_interval: 5 servicegroups: mirror - @@ -2692,11 +2780,21 @@ services: check: "dsa_check_staticsync_nossl!metadata.ftp-master.debian.org" hosts: global servicegroups: mirror + - + name: mirror static sync - mirror-master + check: "dsa_check_staticsync_nossl!mirror-master.debian.org" + hosts: global + servicegroups: mirror - name: mirror static sync - deb check: "dsa_check_staticsync_nossl!deb.debian.org" hosts: global servicegroups: mirror + - + name: mirror static sync - manpages + check: "dsa_check_staticsync!manpages.debian.org" + hosts: global + servicegroups: mirror - name: mirror static sync - 10years @@ -2744,8 +2842,8 @@ services: hosts: global servicegroups: mirror - - name: mirror static sync - debconf1 - check: "dsa_check_staticsync!debconf1.debconf.org" + name: mirror static sync - debconf16 + check: "dsa_check_staticsync!debconf16.debconf.org" hosts: global servicegroups: mirror - @@ -2850,7 +2948,7 @@ services: hosts: giustini check_interval: 5 max_check_attempts: 4 - retry_check_interval: 1 + 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" @@ -2878,7 +2976,7 @@ services: nrpe: "/usr/lib/nagios/plugins/dsa-check-dchroots-current" hostgroups: porterbox check_interval: 60 - retry_check_interval: 15 + retry_interval: 15 # }}} # {{{ openstack # - @@ -2926,7 +3024,7 @@ services: - name: system - all services running nrpe: "/usr/bin/sudo /bin/systemctl is-system-running" - hostgroups: jessie + hostgroups: jessie, stretch excludehostgroups: freebsd ### - @@ -2946,6 +3044,10 @@ services: hosts: draghi depends: process - xinetd ### + - + name: network service - rsync + check: check_tcp!873 + hostgroups: rsyncd-systemd-hosts - name: network service - rsync check: check_tcp!873 @@ -3005,7 +3107,14 @@ services: hosts: handel check_interval: 60 max_check_attempts: 2 - retry_check_interval: 5 + retry_interval: 5 + - + 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 # }}} # }}}