X-Git-Url: https://git.adam-barratt.org.uk/?a=blobdiff_plain;f=nagios-master.cfg;h=fd0718e3fcf697642106e7963c7aad12be257d0b;hb=2246f5d7db410e64863dae2499bfc8b6594c2d5f;hp=00710e36077fb2ac85a3ad505c621bb35794e4e8;hpb=1cbb1a9d6c3773eda9725e99a84f4acf84f11128;p=mirror%2Fdsa-nagios.git diff --git a/nagios-master.cfg b/nagios-master.cfg index 00710e3..fd0718e 100644 --- a/nagios-master.cfg +++ b/nagios-master.cfg @@ -15,14 +15,10 @@ # - verdi: pg upgrade, openvpn # - mundy: salinfo_decode # - puccini: mailgraph +# - lebrun: ippl # - -# - agnesi -# - lebrun -# - murphy # - piatti # - tartini -#sarge: -# - spontini # down: # - ravel @@ -105,7 +101,7 @@ servers: parents: gw-HP-ftc hostgroups: routing-infrastructure gw-1und1: - address: 195.20.247.53 + address: 195.20.247.54 parents: gw-HP-ftc hostgroups: routing-infrastructure gw-blackcat: @@ -124,6 +120,22 @@ servers: address: 130.89.160.1 parents: gw-HP-ftc hostgroups: routing-infrastructure + #gw-ughent: + # address: 157.193.39.254 + # parents: gw-HP-ftc + # hostgroups: routing-infrastructure + gw-agnesi: + address: 65.173.90.18 + parents: gw-HP-ftc + hostgroups: routing-infrastructure + gw-ubc: + address: 137.82.84.41 + parents: gw-HP-ftc + hostgroups: routing-infrastructure + gw-carnet: + address: 161.53.160.1 + parents: gw-HP-ftc + hostgroups: routing-infrastructure samosa: address: 192.25.206.57 @@ -147,11 +159,11 @@ servers: peri: address: 192.25.206.15 parents: samosa - hostgroups: computers, buildd, sw-raid + hostgroups: computers, buildd, sw-raid, single-cpu penalosa: address: 192.25.206.68 parents: samosa - hostgroups: computers, buildd, sw-raid + hostgroups: computers, buildd, sw-raid, single-cpu mundy: address: 192.25.206.62 parents: samosa @@ -160,6 +172,10 @@ servers: address: 192.25.206.11 parents: samosa hostgroups: computers, porterbox, bind9-hosts + merulo: + address: 192.25.206.58 + parents: samosa + hostgroups: computers, porterbox bartok: address: 82.195.75.91 @@ -172,11 +188,11 @@ servers: agricola: address: 82.195.75.86 parents: gw-man-da - hostgroups: computers, porterbox, sw-raid + hostgroups: computers, porterbox, sw-raid, single-cpu arcadelt: address: 82.195.75.87 parents: gw-man-da - hostgroups: computers, buildd, sw-raid + hostgroups: computers, buildd, sw-raid, single-cpu liszt: address: 82.195.75.100 parents: gw-man-da @@ -186,6 +202,10 @@ servers: address: 70.103.162.29 parents: gw-brainfood hostgroups: computers, general, apache2-hosts, bind9-hosts, heavy-exim, highload + murphy: + address: 70.103.162.31 + parents: gw-brainfood + hostgroups: computers, general, apache2-hosts, bind9-hosts, postfix-hosts ries: address: 128.148.34.103 @@ -244,7 +264,7 @@ servers: argento: address: 195.49.152.174 parents: gw-dg-i.net - hostgroups: computers, buildd, sw-raid + hostgroups: computers, buildd, sw-raid, single-cpu pergolesi: address: 62.104.23.252 @@ -253,7 +273,7 @@ servers: bruckner: address: 62.104.23.253 parents: gw-freenet - hostgroups: computers, porterbox + hostgroups: computers, porterbox, single-cpu raptor: address: 195.243.109.162 @@ -272,7 +292,7 @@ servers: escher: address: 213.188.99.215 parents: gw-cst - hostgroups: computers, porterbox + hostgroups: computers, porterbox, single-cpu verdi: address: 192.54.42.193 @@ -288,6 +308,7 @@ servers: address: 87.106.4.56 parents: gw-1und1 hostgroups: computers, service, apache2-hosts, bind9-hosts, postfix-hosts, heavy-postfix, amavis-hosts + contacts: joerg caballero: address: 193.201.200.200 @@ -315,7 +336,27 @@ servers: kassia: address: 130.89.175.54 parents: gw-utwente - hostgroups: computers, service, apache2-hosts, ftpd-hosts, rsyncd-hosts, dl360 + hostgroups: computers, service, postfix-hosts, apache2-hosts, ftpd-hosts, rsyncd-hosts, dl360 + + allegri: + address: 157.193.39.233 + parents: gw-HP-ftc + hostgroups: computers, buildd, postfix-hosts, sw-raid, single-cpu + + agnesi: + address: 65.173.90.83 + parents: gw-agnesi + hostgroups: deadslow + + spontini: + address: 137.82.84.42 + parents: gw-ubc + hostgroups: computers, buildd + + lebrun: + address: 161.53.160.165 + parents: gw-carnet + hostgroups: computers, buildd ############################# # host groups @@ -367,6 +408,9 @@ hostgroups: sw-raid: alias: Hosts with Linux software raid private: 1 + single-cpu: + alias: Hosts with only one CPU + private: 1 syslog-ng-hosts: alias: hosts running syslog-ng instead of sysklogd @@ -427,7 +471,7 @@ services: retry_check_interval: 1 - name: PING - check: "check_ping!900.0,60%!1500.0,80%" + check: "check_ping!2000.0,60%!3000.0,80%" hostgroups: routing-infrastructure normal_check_interval: 5 max_check_attempts: 4 @@ -449,15 +493,15 @@ services: - name: disk usage on /boot nrpe: "/usr/lib/nagios/plugins/check_disk 75 85 /boot" - hosts: sperger, rietz, steffani, penalosa, peri, albeniz, escher, goetz, mayer, mayr, paer + hosts: sperger, rietz, steffani, penalosa, peri, albeniz, escher, goetz, mayer, mayr, paer, spontini - name: disk usage on /var nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /var" - hosts: bartok, samosa, raff, lobos, villa, gluck, saens, escher, voltaire, puccini + hosts: bartok, samosa, raff, lobos, villa, gluck, saens, escher, voltaire, puccini, lebrun - name: disk usage on /org nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /org" - hosts: bartok, sperger, samosa, raff, lobos, villa, steffani, saens, pergolesi, verdi, puccini + hosts: bartok, sperger, samosa, raff, lobos, villa, steffani, saens, pergolesi, verdi, puccini, spontini - name: disk usage on /org nrpe: "/usr/lib/nagios/plugins/check_disk 90 95 /org" @@ -465,27 +509,23 @@ services: - name: disk usage on /srv nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /srv" - hosts: agricola, arcadelt, argento - - - name: disk usage on /org/scratch2 - nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /org/scratch2" - hosts: merkel + hosts: agricola, arcadelt, argento, allegri - - name: disk usage on /oldorg - nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /oldorg" + name: disk usage on /org/scratch + nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /org/scratch" hosts: merkel - name: disk usage on /tmp nrpe: "/usr/lib/nagios/plugins/check_disk 60 80 /tmp" - hosts: samosa, raff, gluck, saens, escher, puccini + hosts: samosa, raff, gluck, saens, escher, puccini, merkel - name: disk usage on /usr nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /usr" - hosts: samosa, raff, lobos, villa, gluck, saens, pergolesi, puccini + hosts: samosa, raff, lobos, villa, gluck, saens, pergolesi, puccini, merulo - name: disk usage on /home nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /home" - hosts: raptor, escher, voltaire + hosts: raptor, escher, voltaire, lebrun - name: disk usage on /home nrpe: "/usr/lib/nagios/plugins/check_disk 90 95 /home" @@ -498,6 +538,10 @@ services: name: disk usage on /mnt/hdc nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /mnt/hdc" hosts: voltaire + - + name: disk usage on /mnt/sdb1 + nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /mnt/sdb1" + hosts: spontini - name: disk usage on /x nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /x" @@ -513,6 +557,15 @@ services: # notification_interval: 480 # max_check_attempts: 4 # retry_check_interval: 12 + #### + - + name: backup + nrpe: "sudo /usr/lib/nagios/plugins/dsa-check-dabackup" + hostgroups: computers + normal_check_interval: 180 + max_check_attempts: 2 + retry_check_interval: 5 + #### - name: users @@ -565,18 +618,22 @@ services: hostgroups: computers - name: "network service - sshd" - check: check_ssh + check: dsa_check_ssh hostgroups: computers depends: process - sshd normal_check_interval: 60 - notification_interval: 60 - name: "network service - sshd" - check: check_ssh + check: dsa_check_ssh hostgroups: deadslow + excludehosts: agnesi + normal_check_interval: 180 + - + name: "network service - sshd - 2260" + check: dsa_check_ssh_port!2260 + hosts: agnesi normal_check_interval: 180 - notification_interval: 180 #### - name: network service - nrpe @@ -611,12 +668,12 @@ services: check: check_ntp hostgroups: computers depends: process - ntpd - excludehosts: raptor + excludehosts: raptor, allegri # - name: network service - time - check: check_time - hosts: raptor + check: dsa_check_time + hosts: raptor, allegri depends: process - xinetd ### @@ -840,7 +897,7 @@ services: - name: process - postfix - smtpd - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:20 -c 0:50 -u postfix -C smtpd -a 'smtpd -n smtp -t inet -u -c'" + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:40 -c 0:90 -u postfix -C smtpd -a 'smtpd -n smtp -t inet -u -c'" hostgroups: postfix-hosts excludehosts: liszt depends: process - postfix - master @@ -863,11 +920,6 @@ services: depends: process - postfix - master ### - - - name: network service - smtp - check: dsa_check_smtp - hostgroups: postfix-hosts - depends: process - postfix - master - name: network service - smtp check: dsa_check_smtp @@ -875,7 +927,35 @@ services: excludehostgroups: postfix-hosts depends: process - exim + - + name: network service - smtp + check: dsa_check_smtp + hostgroups: postfix-hosts + excludehosts: verdi, kassia, allegri + depends: process - postfix - master + - + name: network service - smtp - port 2025 + check: dsa_check_smtp_port!2025 + hosts: verdi, kassia, murphy, allegri + depends: process - postfix - master + + - + 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 - debian-admin in etc aliases + nrpe: "/usr/lib/nagios/plugins/dsa-check-da-in-aliases" + hostgroups: computers + normal_check_interval: 120 + - + name: setup - ud-ldap freshness + nrpe: "/usr/lib/nagios/plugins/dsa-check-udldap-freshness" + hostgroups: computers ### - name: process - uptimed @@ -886,8 +966,11 @@ services: name: process - irqbalance nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C irqbalance -a '/usr/sbin/irqbalance'" hostgroups: computers - excludehosts: arcadelt, agricola, argento, penalosa, peri, escher, bruckner - + excludehostgroups: single-cpu + - + name: unwanted process - named + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C irqbalance" + hostgroups: single-cpu #### ### @@ -964,7 +1047,7 @@ services: - name: process - udevd nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C udevd -a 'udevd'" - hosts: sperger, ries, steffani, merkel, spohr, peri, penalosa, albeniz, escher, verdi, liszt, kassia + hosts: sperger, ries, steffani, merkel, spohr, peri, penalosa, albeniz, escher, verdi, liszt, kassia, agricola, arcadelt, argento, allegri ### - name: process - acpid @@ -975,13 +1058,13 @@ services: - name: process - xinetd nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C xinetd -a '/usr/sbin/xinetd -pidfile /var/run/xinetd.pid -stayalive'" - hosts: samosa, raptor + hosts: samosa, raptor, allegri hostgroups: rsyncd-hosts - name: unwanted process - xinetd nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C xinetd" hostgroups: computers - excludehosts: samosa, raptor + excludehosts: samosa, raptor, allegri excludehostgroups: rsyncd-hosts ### - @@ -1058,14 +1141,12 @@ services: hosts: samosa depends: "process - apache2 - master" normal_check_interval: 120 - notification_interval: 120 - name: network service - https cert check: dsa_check_cert!443 hosts: samosa depends: network service - https normal_check_interval: 240 - notification_interval: 240 #### - name: process - named