X-Git-Url: https://git.adam-barratt.org.uk/?a=blobdiff_plain;f=config%2Fnagios-master.cfg;h=1a3215eb68b9303f78ec1fada405ed73e1e35f9f;hb=bfbad4198bd0c2d091ec3bf92e29c95cea07d22d;hp=5405fc8906c767e55c41bb169f3831886008b413;hpb=3f4ed1df0ab02c30447d026a006e768d7671c6a2;p=mirror%2Fdsa-nagios.git diff --git a/config/nagios-master.cfg b/config/nagios-master.cfg index 5405fc8..1a3215e 100644 --- a/config/nagios-master.cfg +++ b/config/nagios-master.cfg @@ -27,6 +27,11 @@ servers: parents: gw-HP-ftc hostgroups: routing-infrastructure contacts: joerg, bzed + gw-man-da2: + address: 82.195.75.46 + parents: gw-man-da + hostgroups: routing-infrastructure + contacts: joerg, bzed gw-HP-ftc: address: 192.25.206.1 parents: spohr @@ -177,7 +182,7 @@ servers: gluck: address: 192.25.206.10 parents: spohr - hostgroups: computers, no-udev, general, dl380, apache2-hosts, bind9-hosts, heavy-exim, highload, nfs-client, ulogd-hosts, lenny, hasvarfs, hasusrfs + hostgroups: computers, no-udev, general, dl380, lenny, hassrvfs, rsyncd-hosts, acpid-hosts, apache2-hosts, ftpd-hosts merkel: address: 192.25.206.16 parents: spohr @@ -188,7 +193,7 @@ servers: hostgroups: secondary-IPs spohr: address: 192.25.206.33 - hostgroups: computers, service, dl380, apache2-hosts, postgres83-hosts, ulogd-hosts, nfs-server, lenny, heavy-exim + hostgroups: computers, service, dl380, apache2-hosts, postgres83-hosts, ulogd-hosts, nfs-server, lenny, heavy-exim, bind9-hosts spohr2: address: 192.25.206.38 parents: spohr @@ -227,8 +232,8 @@ servers: # hostgroups: computers, porterbox, single-cpu, no-samhain, hasbootfs, hassrvfs, lenny, hasvarfs, hasusrfs # contacts: bzed sperger: - address: 82.195.75.98 - parents: gw-man-da + address: 82.195.75.34 + parents: gw-man-da2 hostgroups: computers, porterbox, sw-raid, hasbootfs, lenny contacts: bzed agricola: @@ -270,7 +275,11 @@ servers: kaufmann: address: 82.195.75.107 parents: unger - hostgroups: computers, service, lenny, hasbootfs, apache2-hosts, single-cpu + hostgroups: computers, service, lenny, hasbootfs, apache2-hosts, single-cpu, rsyncd-hosts + byrd: + address: 82.195.75.101 + parents: unger + hostgroups: computers, service, lenny, hasbootfs, hassrvfs master: address: 70.103.162.29 @@ -331,7 +340,7 @@ servers: senfl: address: 128.31.0.51 parents: gw-mit-csail - hostgroups: computers, service, lenny, dl360, acpid-hosts, hassrvfs, ulogd-hosts, apache2-hosts + hostgroups: computers, service, lenny, dl360, acpid-hosts, hassrvfs, ulogd-hosts, apache2-hosts, rsyncd-hosts carver: address: 128.31.0.50 parents: gw-mit-csail @@ -385,7 +394,8 @@ servers: verdi: address: 192.54.42.193 parents: gw-lrz - hostgroups: computers, service, apache2-hosts, ftpd-hosts, rsyncd-hosts, postgres81-hosts, postfix-hosts + hostgroups: computers, service, postfix-hosts + #hostgroups: computers, service, apache2-hosts, ftpd-hosts, postgres81-hosts, postfix-hosts voltaire: address: 72.66.115.54 @@ -467,7 +477,7 @@ servers: ravel: address: 137.82.84.66 parents: gw-ubc - hostgroups: computers, general, dl385, apache2-hosts, acpid-hosts, ftpd-hosts, hasbootfs, lenny, nfs-server + hostgroups: computers, general, dl385, apache2-hosts, acpid-hosts, ftpd-hosts, hasbootfs, lenny, nfs-server, rsyncd-hosts dijkstra: address: 137.82.84.70 parents: gw-ubc @@ -487,19 +497,19 @@ servers: valente: address: 137.82.84.76 parents: dijkstra - hostgroups: computers, lenny, hasbootfs, single-cpu + hostgroups: computers, lenny, hasbootfs, single-cpu, hassrvfs, postgres83-hosts, ftpd-hosts, rsyncd-hosts bellini: address: 137.82.84.79 parents: gw-ubc - hostgroups: computers, lenny, hasbootfs, nfs-client, hashomefs, hassrvfs + hostgroups: computers, lenny, hasbootfs, nfs-client, hassrvfs, aacraid stabile: address: 137.82.84.72 parents: gw-ubc - hostgroups: computers, lenny, hashomefs, sw-raid + hostgroups: computers, lenny, hashomefs, sw-raid, rsyncd-hosts cimarosa: address: 137.82.84.80 parents: gw-ubc - hostgroups: computers, lenny, hasbootfs + hostgroups: computers, lenny, hasbootfs, aacraid, hassrvfs # MSA 2000 (2012i) giustini: address: 192.168.2.6 @@ -507,6 +517,7 @@ servers: hostgroups: notacomputer # unless we implement runfrom for host alive checks pingable: false + check_command: dsa_check_always_ok lebrun: address: 193.198.184.10 @@ -625,6 +636,9 @@ hostgroups: sw-raid: alias: Hosts with Linux software raid private: 1 + aacraid: + alias: Hosts with Adaptec AACraid + private: 1 single-cpu: alias: Hosts with only one CPU private: 1 @@ -670,9 +684,9 @@ hostgroups: rsyncd-hosts: alias: hosts providing rsync services via xinetd private: 1 - postgres81-hosts: - alias: hosts running postgres81 - private: 1 + #postgres81-hosts: + # alias: hosts running postgres81 + # private: 1 postgres83-hosts: alias: hosts running postgres83 private: 1 @@ -829,7 +843,7 @@ services: name: disk usage on /tmp servicegroups: diskspace nrpe: "/usr/lib/nagios/plugins/check_disk 60 80 /tmp" - hosts: raff, gluck, saens, puccini, merkel, tartini, powell, piatti, escher + hosts: raff, saens, puccini, merkel, tartini, powell, piatti, escher - name: disk usage on /usr servicegroups: diskspace @@ -840,11 +854,6 @@ services: servicegroups: diskspace nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /home" hostgroups: hashomefs - - - name: disk usage on /home - servicegroups: diskspace - nrpe: "/usr/lib/nagios/plugins/check_disk 90 95 /home" - hosts: gluck - name: disk usage on /mnt/hdc servicegroups: diskspace @@ -916,15 +925,9 @@ services: retry_check_interval: 5 #### - - - name: process - puppet - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:8 -c 1: -u root -C ruby -a 'ruby /usr/sbin/puppetd -w 5 --factsync'" - hostgroups: lenny - excludehosts: agnesi - - name: puppet - nrpe: "/usr/lib/nagios/plugins/dsa-check-file_age -f /var/lib/puppet/state/state.yaml" + nrpe: "/usr/lib/nagios/plugins/dsa-check-file_age -i 300 -f /var/lib/puppet/state/state.yaml" hostgroups: lenny excludehosts: agnesi @@ -1013,11 +1016,6 @@ services: check: dsa_check_ssh_port!2260 hosts: agnesi normal_check_interval: 180 - - - name: "network service - sshd - 443" - check: dsa_check_ssh_port!443 - hosts: gluck - normal_check_interval: 180 - name: "network service - sshd - version" @@ -1129,17 +1127,17 @@ services: nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:10 -c 1: -u Debian-exim -C exim4 -a '/usr/sbin/exim4 -bd -q'" hostgroups: computers excludehostgroups: postfix-hosts - excludehosts: master, rietz, merkel, gluck + excludehosts: master, rietz, merkel - 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, rietz, merkel, gluck + excludehosts: master, rietz, merkel - name: process - exim nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:300 -c 1:500 -C exim4 -a '/usr/sbin/exim4'" - hosts: master, rietz, merkel, gluck + hosts: master, rietz, merkel ### - name: process - clamav - clamd @@ -1154,12 +1152,6 @@ 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 - - - name: process - clamav - getsigs - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u clamav -C getclamsigs -a 'getclamsigs'" - hostgroups: heavy-exim, heavy-postfix - excludehosts: master, powell - # - name: unwanted process - clamav nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C clamd" @@ -1170,13 +1162,6 @@ services: nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C freshclam" hostgroups: computers excludehostgroups: heavy-exim, heavy-postfix - - - name: unwanted process - clamav - getsigs - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C getclamsigs" - hostgroups: computers - excludehostgroups: heavy-exim, heavy-postfix - hosts: master, powell - ### - 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'" @@ -1505,6 +1490,12 @@ services: servicegroups: raid nrpe: "/usr/lib/nagios/plugins/dsa-check-raid-dac960" hosts: verdi + ### + - + name: RAID - aacraid + servicegroups: raid + nrpe: "/usr/lib/nagios/plugins/dsa-check-raid-aacraid" + hostgroups: aacraid ### - name: RAID - 3ware @@ -1558,13 +1549,13 @@ 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: gluck, zelenka, ancina, draghi + hosts: zelenka, ancina, draghi hostgroups: rsyncd-hosts - name: unwanted process - xinetd nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C xinetd" hostgroups: computers - excludehosts: gluck, zelenka, ancina, draghi + excludehosts: zelenka, ancina, draghi excludehostgroups: rsyncd-hosts ### - @@ -1731,25 +1722,25 @@ services: hosts: ries, ravel, klecker ### - - - name: process - postresql81 - master - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postgres -C postmaster -a '/usr/lib/postgresql/8.1/bin/postmaster -D /var/lib/postgresql/8.1/main -c config_file=/etc/postgresql/8.1/main/postgresql.conf'" - hostgroups: postgres81-hosts - - - name: process - postresql81 - writer - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postgres -C postmaster -a 'postgres: writer process'" - hostgroups: postgres81-hosts - depends: process - postresql81 - master - - - name: process - postresql81 - buffer - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postgres -C postmaster -a 'postgres: stats buffer process'" - hostgroups: postgres81-hosts - depends: process - postresql81 - master - - - name: process - postresql81 - collector - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postgres -C postmaster -a 'postgres: stats collector process'" - hostgroups: postgres81-hosts - depends: process - postresql81 - master + #- + # name: process - postresql81 - master + # nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postgres -C postmaster -a '/usr/lib/postgresql/8.1/bin/postmaster -D /var/lib/postgresql/8.1/main -c config_file=/etc/postgresql/8.1/main/postgresql.conf'" + # hostgroups: postgres81-hosts + #- + # name: process - postresql81 - writer + # nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postgres -C postmaster -a 'postgres: writer process'" + # hostgroups: postgres81-hosts + # depends: process - postresql81 - master + #- + # name: process - postresql81 - buffer + # nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postgres -C postmaster -a 'postgres: stats buffer process'" + # hostgroups: postgres81-hosts + # depends: process - postresql81 - master + #- + # name: process - postresql81 - collector + # nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postgres -C postmaster -a 'postgres: stats collector process'" + # hostgroups: postgres81-hosts + # depends: process - postresql81 - master #### - name: process - postresql83 - master @@ -1857,10 +1848,6 @@ services: hostgroups: nfs-server # see if the nfs stuff works and doesn't hang. # the df check all script will also hang, but we don't appear to pay attention to that - - - name: nfs mount ftp archive - nrpe: "/usr/lib/nagios/plugins/check_disk 100 100 /home/org/ftp.root/debian" - hosts: gluck - name: nfs mount ftp archive nrpe: "/usr/lib/nagios/plugins/check_disk 100 100 /org/mirrors/ftp.debian.org/ftp" @@ -1888,6 +1875,13 @@ services: name: mirror sync - security.us check: "dsa_check_mirrorsync!security.us.debian.org!project/trace/security-master.debian.org" hosts: global + - + name: mirror sync - packages + check: "dsa_check_mirrorsync!packages.debian.org!Pics/.trace" + hosts: global + normal_check_interval: 15 + max_check_attempts: 5 + retry_check_interval: 5 - name: DNS SOA sync - security.geo.debian.org check: "dsa_check_soas!security.geo.debian.org" @@ -1917,8 +1911,16 @@ services: check: "dsa_check_soas_add!alioth.debian.org!alioth.debian.org" hosts: global ############ + - + name: ping alive check + remotecheck: "/usr/lib/nagios/plugins/check_ping -H $HOSTADDRESS$ -w 50,10% -c 200,30%" + runfrom: dijkstra + hosts: giustini + normal_check_interval: 5 + max_check_attempts: 4 + retry_check_interval: 1 - name: Overall Unit Status - remotecheck: "/usr/lib/nagios/plugins/check_snmp -H giustini-mnt -C public -P 2c -o connUnitStatus -n -c 3 -w 3" + remotecheck: "/usr/lib/nagios/plugins/check_snmp -H $HOSTADDRESS$ -C public -P 2c -o connUnitStatus -n -c 3 -w 3" runfrom: dijkstra hosts: giustini