X-Git-Url: https://git.adam-barratt.org.uk/?a=blobdiff_plain;f=nagios-master.cfg;h=3b7dfce007d70836b8b1ade5d0e45a716fd0b3c6;hb=7c8dd175df117b379348725ca50ca6adb8bd5ab4;hp=8a1db58a92618afc64aa8ec1f1093ddb9fbe0c86;hpb=7193f6eb2d1f2a8a360fd6da66f7334ff1c335e7;p=mirror%2Fdsa-nagios.git diff --git a/nagios-master.cfg b/nagios-master.cfg index 8a1db58..3b7dfce 100644 --- a/nagios-master.cfg +++ b/nagios-master.cfg @@ -14,18 +14,11 @@ # - goetz: gmond/gmetad # - verdi: pg upgrade, openvpn # - mundy: salinfo_decode -# - puccini: mailgraph -# - lebrun: ippl -# - -# - piatti -# - tartini # down: -# - ravel # - sarti # - goedel # - leisner -# - schulz --- ############################# @@ -91,10 +84,6 @@ servers: parents: gw-HP-ftc hostgroups: routing-infrastructure contacts: tjrc1 - gw-cst: - address: 213.188.99.215 - parents: gw-HP-ftc - hostgroups: routing-infrastructure gw-lrz: address: 129.187.0.150 parents: gw-HP-ftc @@ -113,7 +102,7 @@ servers: parents: gw-HP-ftc hostgroups: routing-infrastructure gw-xandros: - address: 142.46.212.33 + address: 67.210.160.81 parents: gw-HP-ftc hostgroups: routing-infrastructure gw-nmmn: @@ -136,30 +125,44 @@ servers: address: 137.82.84.41 parents: gw-HP-ftc hostgroups: routing-infrastructure + contacts: lfilipoz gw-carnet: address: 161.53.160.1 parents: gw-HP-ftc hostgroups: routing-infrastructure + gw-telegraaf: + address: 82.94.249.153 + parents: gw-HP-ftc + hostgroups: routing-infrastructure + gw-helsinki: + address: 128.214.173.25 + parents: gw-HP-ftc + hostgroups: routing-infrastructure + contacts: holger + gw-telefonica: + address: 195.71.99.193 + parents: gw-HP-ftc + hostgroups: routing-infrastructure samosa: address: 192.25.206.57 - hostgroups: computers, service, dl380, apache2-hosts, bind9-hosts, heavy-exim + hostgroups: computers, no-udev, service, dl380, apache2-hosts, bind9-hosts, heavy-exim raff: address: 192.25.206.59 parents: samosa - hostgroups: computers, service, dl380, apache1-hosts, bind9-hosts, rsyncd-hosts, heavy-exim + hostgroups: computers, no-udev, service, dl380, apache1-hosts, bind9-hosts, rsyncd-hosts, heavy-exim, ulogd-hosts, nfs-client gluck: address: 192.25.206.10 parents: samosa - hostgroups: computers, general, dl380, apache1-hosts, bind9-hosts, rsyncd-hosts, heavy-exim, highload + hostgroups: computers, no-udev, general, dl380, apache1-hosts, bind9-hosts, heavy-exim, highload, nfs-client, ulogd-hosts merkel: address: 192.25.206.16 parents: samosa - hostgroups: computers, general, apache1-hosts, bind9-hosts, rsyncd-hosts, sw-raid, postgres81-hosts, heavy-exim + hostgroups: computers, general, apache1-hosts, bind9-hosts, rsyncd-hosts, sw-raid, postgres81-hosts, heavy-exim, nfs-client, ulogd-hosts spohr: address: 192.25.206.33 parents: samosa - hostgroups: computers, service, dl380, apache2-hosts, postgres81-hosts + hostgroups: computers, service, dl380, apache2-hosts, postgres81-hosts, ulogd-hosts, nfs-server peri: address: 192.25.206.15 parents: samosa @@ -173,21 +176,26 @@ servers: mundy: address: 192.25.206.62 parents: samosa - hostgroups: computers, buildd + hostgroups: computers, no-udev, buildd paer: address: 192.25.206.11 parents: samosa - hostgroups: computers, porterbox, bind9-hosts + hostgroups: computers, porterbox, bind9-hosts, single-cpu merulo: address: 192.25.206.58 parents: samosa - hostgroups: computers, porterbox + hostgroups: computers, no-udev, porterbox bartok: address: 82.195.75.91 parents: gw-man-da - hostgroups: computers, service, syslog-ng-hosts, postfix-hosts, dl385 + hostgroups: computers, service, syslog-ng-hosts, postfix-hosts, dl385, bind9-hosts contacts: joerg, bzed + morales: + address: 82.195.75.97 + parents: gw-man-da + hostgroups: computers, porterbox, single-cpu + contacts: bzed sperger: address: 82.195.75.98 parents: gw-man-da @@ -196,41 +204,46 @@ servers: agricola: address: 82.195.75.86 parents: gw-man-da - hostgroups: computers, porterbox, sw-raid, single-cpu + hostgroups: computers, porterbox, sw-raid, single-cpu, lenny, no-samhain contacts: bzed arcadelt: address: 82.195.75.87 parents: gw-man-da - hostgroups: computers, buildd, sw-raid, single-cpu + hostgroups: computers, buildd, sw-raid, single-cpu, lenny, no-samhain contacts: bzed liszt: address: 82.195.75.100 parents: gw-man-da - hostgroups: computers, service, apache2-hosts, bind9-hosts, postfix-hosts, heavy-postfix, dl385 + hostgroups: computers, service, apache2-hosts, bind9-hosts, postfix-hosts, heavy-postfix, amavis-hosts, dl385, acpid-hosts contacts: bzed +# auber: +# address: 82.195.75.101 +# parents: gw-man-da +# hostgroups: computers, no-udev, buildd, sw-raid +# contacts: bzed master: address: 70.103.162.29 parents: gw-brainfood - hostgroups: computers, general, apache2-hosts, bind9-hosts, heavy-exim, highload + hostgroups: computers, no-udev, 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 + hostgroups: computers, general, postfix-hosts, dl380, acpid-hosts ries: address: 128.148.34.103 parents: gw-brown.edu - hostgroups: computers, service, apache2-hosts, bind9-hosts, ftpd-hosts, dl385, rsyncd-hosts, postgres81-hosts, heavy-exim + hostgroups: computers, service, apache2-hosts, bind9-hosts, ftpd-hosts, dl385, rsyncd-hosts, postgres81-hosts, heavy-exim, acpid-hosts mayer: address: 140.211.166.78 parents: gw-osuosl - hostgroups: computers, buildd + hostgroups: computers, no-udev, buildd mayr: address: 140.211.166.58 parents: gw-osuosl - hostgroups: computers, buildd + hostgroups: computers, no-udev, buildd malo: address: 140.211.166.27 parents: gw-osuosl @@ -238,7 +251,7 @@ servers: rietz: address: 140.211.166.43 parents: gw-osuosl - hostgroups: computers, service, apache2-hosts, bind9-hosts, rsyncd-hosts, dl385, heavy-exim, highload + hostgroups: computers, no-udev, service, apache2-hosts, bind9-hosts, rsyncd-hosts, dl385, heavy-exim, highload rietz2: address: 140.211.166.44 parents: rietz @@ -256,11 +269,11 @@ servers: steffani: address: 128.31.0.36 parents: gw-mit-csail - hostgroups: computers, service, apache2-hosts, ftpd-hosts, rsyncd-hosts, sw-raid - casals: - address: 128.31.0.16 + hostgroups: computers, service, apache2-hosts, ftpd-hosts, rsyncd-hosts, sw-raid, bind9-hosts, acpid-hosts + mahler: + address: 128.31.0.46 parents: gw-mit-csail - hostgroups: deadslow + hostgroups: computers, single-cpu, lenny, porterbox, rsyslog-hosts klecker: address: 194.109.137.218 @@ -270,43 +283,45 @@ servers: saens: address: 128.101.240.212 parents: gw-umn.edu - hostgroups: computers, service, apache2-hosts, ftpd-hosts, rsyncd-hosts, dl380, heavy-exim + hostgroups: computers, no-udev, service, apache2-hosts, ftpd-hosts, rsyncd-hosts, dl380, heavy-exim argento: address: 195.49.152.174 parents: gw-dg-i.net - hostgroups: computers, buildd, sw-raid, single-cpu + hostgroups: computers, buildd, sw-raid, single-cpu, lenny, no-samhain contacts: bzed pergolesi: address: 62.104.23.252 parents: gw-freenet - hostgroups: computers, porterbox, sw-raid + hostgroups: computers, no-udev, porterbox, sw-raid bruckner: address: 62.104.23.253 parents: gw-freenet - hostgroups: computers, porterbox, single-cpu + hostgroups: computers, no-udev, porterbox, single-cpu, deadslow raptor: address: 195.243.109.162 parents: gw-topalis - hostgroups: computers, porterbox + hostgroups: computers, porterbox, postfix-hosts albeniz: address: 193.62.202.27 parents: gw-sanger - hostgroups: computers, porterbox, sw-raid + # SMP kernel doesn't run stable + hostgroups: computers, porterbox, sw-raid, single-cpu contacts: tjrc1 goetz: address: 193.62.202.26 parents: gw-sanger - hostgroups: computers, buildd, sw-raid + # SMP kernel doesn't run stable + hostgroups: computers, buildd, sw-raid, single-cpu + contacts: tjrc1 + smetana: + address: 193.62.202.29 + parents: gw-sanger + hostgroups: computers, porterbox, sw-raid contacts: tjrc1 - - escher: - address: 213.188.99.215 - parents: gw-cst - hostgroups: computers, porterbox, single-cpu verdi: address: 192.54.42.193 @@ -317,24 +332,30 @@ servers: address: 72.66.115.54 parents: gw-frost hostgroups: computers, buildd + contacts: sfrost puccini: address: 87.106.4.56 parents: gw-1und1 - hostgroups: computers, service, apache2-hosts, bind9-hosts, postfix-hosts, heavy-postfix, amavis-hosts + hostgroups: computers, buildd, lenny, rsyslog-hosts + contacts: joerg + powell: + address: 87.106.64.223 + parents: gw-1und1 + hostgroups: computers, service, heavy-exim, rsyncd-hosts, ulogd-hosts, acpid-hosts contacts: joerg caballero: address: 193.201.200.200 parents: gw-blackcat - hostgroups: computers, buildd, sw-raid + hostgroups: computers, no-udev, buildd, sw-raid, bind9-hosts elara: - address: 142.46.212.46 + address: 67.210.160.90 parents: gw-xandros hostgroups: deadslow europa: - address: 142.46.212.46 + address: 67.210.160.89 parents: gw-xandros hostgroups: deadslow @@ -352,12 +373,12 @@ servers: kassia: address: 130.89.175.54 parents: gw-utwente - hostgroups: computers, service, postfix-hosts, apache2-hosts, ftpd-hosts, rsyncd-hosts, dl360 + hostgroups: computers, service, postfix-hosts, apache2-hosts, ftpd-hosts, rsyncd-hosts, dl360, acpid-hosts allegri: address: 157.193.39.233 parents: gw-HP-ftc - hostgroups: computers, buildd, postfix-hosts, sw-raid, single-cpu + hostgroups: computers, buildd, postfix-hosts, sw-raid, single-cpu, lenny, no-samhain contacts: luk agnesi: @@ -369,10 +390,35 @@ servers: address: 137.82.84.42 parents: gw-ubc hostgroups: computers, buildd + contacts: lfilipoz + ravel: + address: 137.82.84.43 + parents: gw-ubc + hostgroups: computers, general, dl385, apache2-hosts, acpid-hosts lebrun: - address: 161.53.160.165 + address: 193.198.184.10 + parents: gw-carnet + hostgroups: computers, buildd + schroeder: + address: 193.198.184.11 parents: gw-carnet + hostgroups: computers, buildd, sw-raid + + tartini: + address: 82.94.249.158 + parents: gw-telegraaf + hostgroups: computers, sw-raid, apache2-hosts, mysql-hosts + + piatti: + address: 193.167.161.225 + parents: gw-helsinki + hostgroups: computers, postfix-hosts, dl385, ulogd-hosts, acpid-hosts + contacts: holger + + rem: + address: 195.71.99.217 + parents: gw-helsinki hostgroups: computers, buildd ############################# @@ -429,17 +475,28 @@ hostgroups: alias: Hosts with only one CPU private: 1 + lenny: + alias: Hosts running lenny, not etch + private: 1 + + no-samhain: + alias: hosts not running samhain properly + private: 1 + syslog-ng-hosts: alias: hosts running syslog-ng instead of sysklogd private: 1 + rsyslog-hosts: + alias: hosts running rsyslogd instead of sysklogd + private: 1 postfix-hosts: alias: hosts running postfix instead of exim private: 1 heavy-exim: - alias: "hosts running the full mail stuff, including clamav, SA, and greylistd" + alias: "hosts running the full mail stuff, including clamav, SA, and postgrey" private: 1 heavy-postfix: - alias: "postfix hosts running the full mail stuff, including clamav, SA, postgrey, amavis, policyd-weight" + alias: "postfix hosts running the full mail stuff, including clamav, SA, postgrey, policyd-weight" private: 1 apache2-hosts: alias: hosts running apache2 @@ -465,6 +522,25 @@ hostgroups: postgres81-hosts: alias: hosts running postgres81 private: 1 + mysql-hosts: + alias: hosts running mysql + private: 1 + no-udev: + alias: hosts not using udev + private: 1 + ulogd-hosts: + alias: hosts running ulogd + private: 1 + acpid-hosts: + alias: hosts running acpid + private: 1 + + nfs-client: + alias: hosts mounting filesystems using NFS + private: 1 + nfs-server: + alias: hosts serving filesystems using NFS + private: 1 highload: alias: "hosts on which high load is normal" @@ -483,6 +559,19 @@ servicegroups: alias: diskusage checks buildd: alias: buildd checks + raid: + alias: raid checks + kernel: + alias: kernel checks + weaksshkeys: + alias: weak ssh keys + apt: + alias: apt upgrade status + samhain: + alias: samhain integrity status + security: + alias: security + servicegroup_members: apt, weaksshkeys, kernel, samhain ############################# # services @@ -519,31 +608,37 @@ services: servicegroups: diskspace nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /" hostgroups: computers + excludehosts: ries + - + name: disk usage on / + servicegroups: diskspace + nrpe: "/usr/lib/nagios/plugins/check_disk 90 95 /" + hosts: ries - name: disk usage on /boot servicegroups: diskspace nrpe: "/usr/lib/nagios/plugins/check_disk 75 85 /boot" - hosts: sperger, rietz, steffani, penalosa, peri, albeniz, escher, goetz, mayer, mayr, paer, spontini + hosts: sperger, rietz, steffani, penalosa, peri, albeniz, goetz, mayer, mayr, paer, spontini, tartini, morales, ravel, schroeder, piatti, rem - name: disk usage on /var servicegroups: diskspace nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /var" - hosts: bartok, samosa, raff, lobos, villa, gluck, saens, escher, voltaire, puccini, lebrun + hosts: bartok, samosa, raff, lobos, villa, gluck, saens, voltaire, lebrun, tartini, morales, powell - name: disk usage on /org servicegroups: diskspace nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /org" - hosts: bartok, sperger, samosa, raff, lobos, villa, steffani, saens, pergolesi, verdi, puccini, spontini + hosts: sperger, samosa, raff, lobos, villa, steffani, saens, pergolesi, verdi, spontini, ravel, mahler, schroeder, piatti - name: disk usage on /org servicegroups: diskspace nrpe: "/usr/lib/nagios/plugins/check_disk 90 95 /org" - hosts: merkel + hosts: merkel, bartok - name: disk usage on /srv servicegroups: diskspace nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /srv" - hosts: agricola, arcadelt, argento, allegri + hosts: agricola, arcadelt, argento, allegri, tartini, morales, powell, puccini - name: disk usage on /org/scratch servicegroups: diskspace @@ -553,17 +648,17 @@ services: name: disk usage on /tmp servicegroups: diskspace nrpe: "/usr/lib/nagios/plugins/check_disk 60 80 /tmp" - hosts: samosa, raff, gluck, saens, escher, puccini, merkel + hosts: samosa, raff, gluck, saens, puccini, merkel, tartini, powell, piatti - name: disk usage on /usr servicegroups: diskspace nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /usr" - hosts: samosa, raff, lobos, villa, gluck, saens, pergolesi, puccini, merulo + hosts: samosa, raff, lobos, villa, gluck, saens, pergolesi, merulo, tartini, morales, powell - name: disk usage on /home servicegroups: diskspace nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /home" - hosts: raptor, escher, voltaire, lebrun + hosts: raptor, voltaire, lebrun, rem - name: disk usage on /home servicegroups: diskspace @@ -592,14 +687,13 @@ services: ############ All Computers ############ #### - #- - # name: apt - security updates - # nrpe: "/usr/local/bin/nagios-check-apt-updates --warnifupdates" - # hostgroups: computers - # normal_check_interval: 480 - # notification_interval: 480 - # max_check_attempts: 4 - # retry_check_interval: 12 + - + 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: backup @@ -608,6 +702,38 @@ services: normal_check_interval: 180 max_check_attempts: 2 retry_check_interval: 5 + - + name: backup server config + nrpe: "/usr/lib/nagios/plugins/dsa-check-dabackup-server" + hosts: bartok + normal_check_interval: 180 + max_check_attempts: 2 + retry_check_interval: 5 + + #### + - + name: running kernel + servicegroups: kernel + nrpe: "/usr/lib/nagios/plugins/dsa-check-running-kernel" + hostgroups: computers + normal_check_interval: 180 + retry_check_interval: 5 + + #### + - + name: process - samhain + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:8 -c 1: -u root -C samhain -a '/usr/sbin/samhain'" + hostgroups: computers + excludehostgroups: no-samhain + - + name: samhain + servicegroups: samhain + nrpe: "/usr/lib/nagios/plugins/dsa-check-samhain -t 45" + hostgroups: computers + excludehostgroups: no-samhain + depends: process - samhain + normal_check_interval: 240 + retry_check_interval: 5 #### - @@ -665,6 +791,7 @@ services: hostgroups: computers depends: process - sshd normal_check_interval: 60 + notification_interval: 1440 - name: "network service - sshd" @@ -677,16 +804,57 @@ 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" + check: "dsa_check_ssh_port_version!22!OpenSSH_4.3p2 Debian-9etch3" + depends: network service - sshd + hostgroups: computers, deadslow + excludehosts: agnesi, crest, kullervo + excludehostgroups: lenny + normal_check_interval: 360 + - + name: "network service - sshd - version" + check: "dsa_check_ssh_port_version!22!OpenSSH_4.3p2 Debian-9etch2+m68k1" + depends: network service - sshd + hosts: crest, kullervo + normal_check_interval: 360 + - + name: "network service - sshd - version" + check: "dsa_check_ssh_port_version!22!OpenSSH_5.1p1 Debian-3" + depends: network service - sshd + hostgroups: lenny + normal_check_interval: 360 + - + name: "network service - sshd - version - 2260" + check: "dsa_check_ssh_port_version!2260!OpenSSH_4.3p2 Debian-9etch3" + depends: network service - sshd - 2260 + hosts: agnesi + normal_check_interval: 360 + # + - + name: ssh - weak keys + servicegroups: weaksshkeys + nrpe: "/usr/lib/nagios/plugins/dsa-check-statusfile /var/cache/dsa/nagios/weak-ssh-keys" + hostgroups: computers + normal_check_interval: 360 #### - name: network service - nrpe check: check_tcp!5666 hostgroups: computers - max_check_attempts: -1 + max_check_attempts: -2 + notification_interval: 1440 - 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 + max_check_attempts: -1 depends: network service - nrpe ### - @@ -735,17 +903,22 @@ 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: syslog-ng-hosts + ### + - + name: process - rsyslogd + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C rsyslogd -a '/usr/sbin/rsyslogd -c3'" + hostgroups: rsyslog-hosts ### - name: process - syslogd nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C syslogd -a '/sbin/syslogd'" hostgroups: computers - excludehostgroups: syslog-ng-hosts + excludehostgroups: syslog-ng-hosts, rsyslog-hosts - name: process - klogd nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C klogd -a '/sbin/klogd -x'" hostgroups: computers - excludehostgroups: syslog-ng-hosts + excludehostgroups: syslog-ng-hosts, rsyslog-hosts ### MAIL STUFF ### @@ -779,6 +952,10 @@ 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 # - name: unwanted process - clamav @@ -790,6 +967,11 @@ 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 ### - name: process - spamd - master @@ -829,18 +1011,21 @@ services: hosts: merkel, raff ### - - - name: process - greylistd - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u greylist -C greylistd -a '/usr/bin/python /usr/sbin/greylistd'" - hostgroups: heavy-exim + #- + # name: process - greylistd + # nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u greylist -C greylistd -a '/usr/bin/python /usr/sbin/greylistd'" + # hostgroups: heavy-exim # - name: unwanted process - greylistd nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C greylistd" hostgroups: computers - excludehostgroups: heavy-exim ### + - + name: process - postgrey + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postgrey -C 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: process - postgrey nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u postgrey -C postgrey -a '/usr/sbin/postgrey --pidfile=/var/run/postgrey.pid --daemonize --inet=127.0.0.1:60000'" @@ -850,7 +1035,7 @@ services: name: unwanted process - postgrey nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C postgrey" hostgroups: computers - excludehostgroups: heavy-postfix + excludehostgroups: heavy-postfix, heavy-exim ### - name: process - amavis - master @@ -913,7 +1098,7 @@ services: depends: process - postfix - master - name: process - postfix - anvil - nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:1 -c 1: -u postfix -C anvil -a 'anvil -l -t unix -u'" + 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 @@ -974,12 +1159,23 @@ services: name: network service - smtp check: dsa_check_smtp hostgroups: postfix-hosts - excludehosts: verdi, kassia, allegri + excludehosts: verdi, kassia, allegri, raptor, piatti depends: process - postfix - master - name: network service - smtp - port 2025 check: dsa_check_smtp_port!2025 - hosts: verdi, kassia, murphy, allegri + hosts: verdi, kassia, murphy, allegri, piatti + depends: process - postfix - master + - + name: network service - smtp - port 8080 + check: dsa_check_smtp_port!8080 + hosts: murphy + depends: process - postfix - master + - + name: network service - smtp - port 2025 + remotecheck: /usr/lib/nagios/plugins/check_smtp -t 40 -H $HOSTADDRESS$ -p 2025 + runfrom: murphy + hosts: raptor depends: process - postfix - master - @@ -991,8 +1187,8 @@ services: - - name: setup - debian-admin in etc aliases - nrpe: "/usr/lib/nagios/plugins/dsa-check-da-in-aliases" + name: setup - dsa config + nrpe: "/usr/lib/nagios/plugins/dsa-check-config" hostgroups: computers normal_check_interval: 120 - @@ -1011,7 +1207,7 @@ services: hostgroups: computers excludehostgroups: single-cpu - - name: unwanted process - named + name: unwanted process - irqbalance nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C irqbalance" hostgroups: single-cpu @@ -1033,10 +1229,12 @@ services: name: unwanted process - portmap nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C portmap" hostgroups: computers + excludehostgroups: nfs-client, nfs-server - 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" @@ -1054,7 +1252,7 @@ services: - 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'" - hosts: bartok + hostgroups: dl385 ### - name: process - sensord @@ -1064,50 +1262,104 @@ services: ### - 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'" hostgroups: sw-raid - name: RAID - sw raid + servicegroups: raid nrpe: "/usr/lib/nagios/plugins/dsa-check-raid-sw" hostgroups: sw-raid ### - name: process - cpqarrayd + servicegroups: raid nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u root -C cpqarrayd -a '/usr/sbin/cpqarrayd'" hostgroups: dl385, dl380, dl360 - name: RAID - arrayprobe + servicegroups: raid nrpe: "sudo /usr/bin/arrayprobe" hostgroups: dl385, dl380, dl360 + - + name: HW - hpacucli status + servicegroups: raid + nrpe: "/usr/lib/nagios/plugins/dsa-check-hpacucli" + normal_check_interval: 120 + hostgroups: dl385, dl380, dl360 + ### + - + name: RAID - areca + servicegroups: raid + nrpe: "/usr/lib/nagios/plugins/dsa-check-raid-areca" + hosts: powell + ### + - + name: RAID - DAC960 + servicegroups: raid + nrpe: "/usr/lib/nagios/plugins/dsa-check-raid-dac960" + hosts: verdi + ### + - + name: RAID - 3ware + servicegroups: raid + nrpe: "/usr/lib/nagios/plugins/dsa-check-raid-3ware" + hosts: puccini + ### + - + name: RAID - MPT + servicegroups: raid + nrpe: "/usr/lib/nagios/plugins/dsa-check-raid-mpt" + hosts: master ### - name: process - slapd - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:20 -c 1:50 -u openldap -C slapd -a '/usr/sbin/slapd -g openldap -u openldap'" + 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: samosa + ### + - + 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: ulogd-hosts + - + name: unexpected process - ulogd + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C ulogd" + hostgroups: computers + excludehostgroups: ulogd-hosts ### - 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, agricola, arcadelt, argento, allegri + hostgroups: computers + excludehostgroups: no-udev + - + name: unexpected process - udev + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C udevd" + hostgroups: no-udev ### - name: process - acpid nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C acpid -a '/usr/sbin/acpid -c /etc/acpi/events -s /var/run/acpid.socket'" - hosts: ries, steffani, liszt, kassia + hostgroups: acpid-hosts + - + name: unexpected process - acpid + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C acpid" + hostgroups: computers + excludehostgroups: acpid-hosts ### - 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, allegri + hosts: samosa, raptor, allegri, gluck hostgroups: rsyncd-hosts - name: unwanted process - xinetd nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C xinetd" hostgroups: computers - excludehosts: samosa, raptor, allegri + excludehosts: samosa, raptor, allegri, gluck excludehostgroups: rsyncd-hosts ### - @@ -1177,13 +1429,13 @@ services: - name: network service - https check: check_https - hosts: samosa + hosts: samosa, ries depends: "process - apache2 - master" normal_check_interval: 120 - name: network service - https cert check: dsa_check_cert!443 - hosts: samosa + hosts: samosa, ries depends: network service - https normal_check_interval: 240 #### @@ -1220,8 +1472,8 @@ services: #### - name: process - debianqueued - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u dak -C debianqueued -a '/usr/bin/perl -w ./debianqueued'" - hosts: ries + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u dak -C debianqueued" + hosts: ries, ravel, klecker ### - @@ -1243,9 +1495,33 @@ services: 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 - mysql - master + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:2 -c 1: -u root -C mysqld_safe -a '/bin/sh /usr/bin/mysqld_safe'" + hostgroups: mysql-hosts + - + name: process - mysql - workers + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:25 -c 1: -u mysql -C mysqld -a /usr/sbin/mysqld" + hostgroups: mysql-hosts + depends: process - mysql - master #### - # XXX is this needed + #- + # name: process - xenconsoled + # nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C xenconsoled -a 'xenconsoled'" + # hosts: piatti + #- + # name: process - xenstored + # nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C xenstored -a '/usr/lib/xen-3.0.3-1/bin/xenstored --pid-file /var/run/xenstore.pid'" + # hosts: piatti + #- + # name: process - xend + # nrpe: "/usr/lib/nagios/plugins/check_procs -w 2:2 -c 2: -u root -C python -a 'python /usr/lib/xen-3.0.3-1/bin/xend start'" + # hosts: piatti +# + #### + # XXX is this needed? - name: process - snmpd nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1:1 -u snmp -C snmpd -a '/usr/sbin/snmpd -Lsd -Lf /dev/null -u snmp -I -smux -p /var/run/snmpd.pid 127.0.0.1'" @@ -1279,3 +1555,36 @@ services: name: process - monit nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C monit -a '/usr/sbin/monit -d 30 -c /etc/monit/monitrc -s /var/lib/monit/monit.state'" hosts: villa, lobos, steffani, kassia, master + + ############ NFS Stuff ############ + #### + - + name: process - portmap + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u daemon -C portmap -a '/sbin/portmap'" + hostgroups: nfs-client, nfs-server + - + name: process - statd + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u statd -C rpc.statd -a '/sbin/rpc.statd'" + hostgroups: nfs-client, nfs-server + - + name: process - nfsd + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:10 -c 1: -u root -C nfsd -a '[nfsd]'" + hostgroups: nfs-server + - + name: process - lockd + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C lockd -a '[lockd]'" + hostgroups: nfs-server + - + name: process - mountd + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C rpc.mountd -a '/sbin/rpc.mountd'" + 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" + hosts: merkel, raff