X-Git-Url: https://git.adam-barratt.org.uk/?a=blobdiff_plain;f=nagios-master.cfg;h=8e1592cdfc421efe235baf7ad8e28ab475933631;hb=4b187121667cd9f23851924d13c2bf562b2855ce;hp=a7ee4cbd65aedc6c7e86b7fafed25f78c9b26605;hpb=66f952a1829280d9e44f4e3740644fafb731f8ba;p=mirror%2Fdsa-nagios.git diff --git a/nagios-master.cfg b/nagios-master.cfg index a7ee4cb..8e1592c 100644 --- a/nagios-master.cfg +++ b/nagios-master.cfg @@ -15,16 +15,11 @@ # - verdi: pg upgrade, openvpn # - mundy: salinfo_decode # - puccini: mailgraph -# - -# - piatti -# - tartini # down: -# - ravel # - sarti # - goedel # - leisner -# - schulz --- ############################# @@ -35,6 +30,7 @@ servers: address: 82.195.75.126 parents: gw-HP-ftc hostgroups: routing-infrastructure + contacts: joerg, bzed gw-HP-ftc: address: 192.25.206.1 parents: samosa @@ -75,6 +71,7 @@ servers: address: 195.49.152.190 parents: gw-HP-ftc hostgroups: routing-infrastructure + contacts: bzed gw-freenet: address: 62.104.23.249 parents: gw-HP-ftc @@ -87,10 +84,7 @@ servers: address: 193.62.202.18 parents: gw-HP-ftc hostgroups: routing-infrastructure - gw-cst: - address: 213.188.99.215 - parents: gw-HP-ftc - hostgroups: routing-infrastructure + contacts: tjrc1 gw-lrz: address: 129.187.0.150 parents: gw-HP-ftc @@ -100,15 +94,16 @@ 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 + contacts: joerg gw-blackcat: address: 193.201.200.129 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: @@ -131,18 +126,32 @@ 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 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 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 merkel: address: 192.25.206.16 parents: samosa @@ -150,71 +159,88 @@ servers: 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 peri: address: 192.25.206.15 parents: samosa hostgroups: computers, buildd, sw-raid, single-cpu + contacts: dannf penalosa: address: 192.25.206.68 parents: samosa hostgroups: computers, buildd, sw-raid, single-cpu + contacts: dannf 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 hostgroups: computers, porterbox, sw-raid + contacts: bzed 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 @@ -222,7 +248,7 @@ 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 @@ -240,11 +266,11 @@ 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 @@ -254,40 +280,40 @@ 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 - - escher: - address: 213.188.99.215 - parents: gw-cst - hostgroups: computers, porterbox, single-cpu + # SMP kernel doesn't run stable + hostgroups: computers, buildd, sw-raid, single-cpu + contacts: tjrc1 verdi: address: 192.54.42.193 @@ -297,24 +323,31 @@ servers: voltaire: address: 72.66.115.54 parents: gw-frost - hostgroups: computers, buildd + hostgroups: computers, buildd, no-samhain + 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, no-udev, service, apache2-hosts, bind9-hosts, postfix-hosts, heavy-postfix, amavis-hosts, ulogd-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 @@ -322,20 +355,23 @@ servers: address: 217.114.76.82 parents: gw-nmmn hostgroups: deadslow + contacts: luk crest: address: 217.114.76.83 parents: gw-nmmn hostgroups: deadslow + contacts: luk 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: address: 65.173.90.83 @@ -345,7 +381,32 @@ servers: spontini: address: 137.82.84.42 parents: gw-ubc - hostgroups: computers, buildd, single-cpu + hostgroups: computers, buildd + contacts: lfilipoz + ravel: + address: 137.82.84.43 + parents: gw-ubc + hostgroups: computers, general, dl385, apache2-hosts, acpid-hosts + + lebrun: + 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 ############################# # host groups @@ -401,9 +462,20 @@ 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 @@ -411,7 +483,7 @@ hostgroups: alias: "hosts running the full mail stuff, including clamav, SA, and greylistd" 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 @@ -437,6 +509,18 @@ 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 highload: alias: "hosts on which high load is normal" @@ -446,6 +530,29 @@ hostgroups: alias: secondary IP addresses private: 1 + +############################# +# servicegroups +############################# +servicegroups: + diskspace: + 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 ############################# @@ -473,79 +580,100 @@ services: #### - name: disk usage - all + servicegroups: diskspace nrpe: "/usr/lib/nagios/plugins/check_disk 90 95" hostgroups: computers - name: disk usage on / + 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 - 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 + hosts: bartok, samosa, raff, lobos, villa, gluck, saens, voltaire, puccini, 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, puccini, 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 - name: disk usage on /org/scratch + servicegroups: diskspace nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /org/scratch" hosts: merkel - 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, puccini, 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 + hosts: raptor, voltaire, lebrun - name: disk usage on /home + servicegroups: diskspace nrpe: "/usr/lib/nagios/plugins/check_disk 90 95 /home" hosts: gluck - name: disk usage on /chroot + servicegroups: diskspace nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /chroot" hosts: raptor - name: disk usage on /mnt/hdc + servicegroups: diskspace nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /mnt/hdc" hosts: voltaire - name: disk usage on /mnt/sdb1 + servicegroups: diskspace nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /mnt/sdb1" hosts: spontini - name: disk usage on /x + servicegroups: diskspace nrpe: "/usr/lib/nagios/plugins/check_disk 75 90 /x" hosts: caballero ############ 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 @@ -554,6 +682,38 @@ 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 #### - @@ -611,6 +771,7 @@ services: hostgroups: computers depends: process - sshd normal_check_interval: 60 + notification_interval: 1440 - name: "network service - sshd" @@ -623,16 +784,57 @@ 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-2" + 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 ### - @@ -673,7 +875,7 @@ services: ### - name: process - cron - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u root -C cron -a /usr/sbin/cron" + nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:2 -c 1: -u root -C cron -a /usr/sbin/cron" hostgroups: computers ### @@ -681,17 +883,22 @@ 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 ### @@ -725,6 +932,10 @@ 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 @@ -736,6 +947,11 @@ 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 @@ -859,7 +1075,7 @@ services: depends: process - postfix - master - name: process - postfix - anvil - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -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 @@ -920,12 +1136,23 @@ 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 - @@ -937,8 +1164,8 @@ 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 - @@ -957,7 +1184,7 @@ 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 @@ -1000,7 +1227,7 @@ 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 @@ -1010,38 +1237,92 @@ 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 ### - @@ -1075,10 +1356,6 @@ services: depends: rietz:process - xinetd ### - - - name: process - nagios1 - nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u nagios -C nagios -a '/usr/sbin/nagios -d /etc/nagios/nagios.cfg'" - hosts: samosa - name: process - nagios3 # there is always one extra process per check currently running.. @@ -1127,13 +1404,13 @@ 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 #### @@ -1170,8 +1447,8 @@ 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 ### - @@ -1193,9 +1470,33 @@ 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'" @@ -1204,6 +1505,7 @@ services: ### - name: process - buildd + servicegroups: buildd nrpe: "/usr/lib/nagios/plugins/check_procs -w 1:1 -c 1: -u buildd -C buildd '/usr/bin/perl /usr/bin/buildd'" hostgroups: buildd