X-Git-Url: https://git.adam-barratt.org.uk/?a=blobdiff_plain;f=nagios-master.cfg;h=a3aa86f1f0d886b0214ca10fc8f4b0333ff9ed81;hb=35b57800427121013389d320f5f70b0e973c2c48;hp=6ababc2ff4fc7659d08fefa8da78d3c61947c8b7;hpb=1dd1b851ae5287dba25ab9afdaa7349ccfd4255d;p=mirror%2Fdsa-nagios.git diff --git a/nagios-master.cfg b/nagios-master.cfg index 6ababc2..a3aa86f 100644 --- a/nagios-master.cfg +++ b/nagios-master.cfg @@ -16,13 +16,8 @@ # - mundy: salinfo_decode # - puccini: mailgraph # - -# - agnesi -# - lebrun -# - murphy # - piatti # - tartini -#sarge: -# - spontini # down: # - ravel @@ -124,8 +119,16 @@ servers: address: 130.89.160.1 parents: gw-HP-ftc hostgroups: routing-infrastructure - gw-ughent: - address: 157.193.39.254 + #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 @@ -151,11 +154,11 @@ 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 @@ -164,6 +167,10 @@ 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 @@ -176,11 +183,11 @@ 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 @@ -190,6 +197,10 @@ 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 @@ -248,7 +259,7 @@ 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 @@ -257,7 +268,7 @@ servers: bruckner: address: 62.104.23.253 parents: gw-freenet - hostgroups: computers, porterbox + hostgroups: computers, porterbox, single-cpu raptor: address: 195.243.109.162 @@ -276,7 +287,7 @@ servers: escher: address: 213.188.99.215 parents: gw-cst - hostgroups: computers, porterbox + hostgroups: computers, porterbox, single-cpu verdi: address: 192.54.42.193 @@ -323,8 +334,18 @@ servers: allegri: address: 157.193.39.233 - parents: gw-ughent - hostgroups: computers, buildd, postfix-hosts, sw-raid + 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, single-cpu ############################# # host groups @@ -376,6 +397,9 @@ 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 @@ -436,7 +460,7 @@ 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 @@ -476,21 +500,17 @@ services: nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /srv" hosts: agricola, arcadelt, argento, allegri - - name: disk usage on /org/scratch2 - nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /org/scratch2" - hosts: merkel - - - 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" @@ -522,6 +542,15 @@ 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 @@ -574,18 +603,22 @@ 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 @@ -620,12 +653,12 @@ 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 ### @@ -849,7 +882,7 @@ 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 @@ -872,6 +905,13 @@ services: depends: process - postfix - master ### + - + name: network service - smtp + check: dsa_check_smtp + hostgroups: computers + excludehostgroups: postfix-hosts + depends: process - exim + - name: network service - smtp check: dsa_check_smtp @@ -881,21 +921,26 @@ services: - name: network service - smtp - port 2025 check: dsa_check_smtp_port!2025 - hosts: verdi, kassia + hosts: verdi, kassia, murphy, allegri depends: process - postfix - master + - - name: network service - smtp - port 8080 - check: dsa_check_smtp_port!8080 - hosts: allegri + 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 - - - name: network service - smtp - check: dsa_check_smtp - hostgroups: computers - excludehostgroups: postfix-hosts - depends: process - exim + 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 @@ -906,8 +951,11 @@ 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, allegri - + excludehostgroups: single-cpu + - + name: unwanted process - named + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C irqbalance" + hostgroups: single-cpu #### ### @@ -995,13 +1043,13 @@ 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 ### - @@ -1078,14 +1126,12 @@ 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