X-Git-Url: https://git.adam-barratt.org.uk/?a=blobdiff_plain;f=nagios-master.cfg;h=c1bd9b42b3bbd68324502bbffcee95e55c028b70;hb=b36974d74955429568d271ff72bad85b4c023bca;hp=ef171bd8f2fbe3f410f25db5434aee423749e366;hpb=f310fc018dc94ca54243c11aeaf564bb6f5acf0a;p=mirror%2Fdsa-nagios.git diff --git a/nagios-master.cfg b/nagios-master.cfg index ef171bd..c1bd9b4 100644 --- a/nagios-master.cfg +++ b/nagios-master.cfg @@ -15,19 +15,11 @@ # - verdi: pg upgrade, openvpn # - mundy: salinfo_decode # - puccini: mailgraph -# - -# - agnesi -# - piatti -# - tartini -#sarge: -# - spontini # down: -# - ravel # - sarti # - goedel # - leisner -# - schulz --- ############################# @@ -38,6 +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 @@ -78,6 +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 @@ -90,10 +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 @@ -103,15 +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: @@ -122,10 +114,32 @@ 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 + 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 @@ -149,11 +163,13 @@ servers: peri: address: 192.25.206.15 parents: samosa - hostgroups: computers, buildd, sw-raid + hostgroups: computers, buildd, sw-raid, single-cpu + contacts: dannf penalosa: address: 192.25.206.68 parents: samosa - hostgroups: computers, buildd, sw-raid + hostgroups: computers, buildd, sw-raid, single-cpu + contacts: dannf mundy: address: 192.25.206.62 parents: samosa @@ -162,27 +178,46 @@ 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 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 + hostgroups: computers, porterbox, sw-raid, single-cpu, lenny + contacts: bzed arcadelt: address: 82.195.75.87 parents: gw-man-da - hostgroups: computers, buildd, sw-raid + hostgroups: computers, buildd, sw-raid, single-cpu, lenny + 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 + contacts: bzed + auber: + address: 82.195.75.101 + parents: gw-man-da + hostgroups: computers, buildd, sw-raid + contacts: bzed master: address: 70.103.162.29 @@ -191,7 +226,7 @@ servers: murphy: address: 70.103.162.31 parents: gw-brainfood - hostgroups: computers, general, apache2-hosts, bind9-hosts, postfix-hosts + hostgroups: computers, general, postfix-hosts, dl380 ries: address: 128.148.34.103 @@ -231,11 +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 + 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 @@ -250,7 +285,8 @@ servers: argento: address: 195.49.152.174 parents: gw-dg-i.net - hostgroups: computers, buildd, sw-raid + hostgroups: computers, buildd, sw-raid, single-cpu, lenny + contacts: bzed pergolesi: address: 62.104.23.252 @@ -259,26 +295,25 @@ servers: bruckner: address: 62.104.23.253 parents: gw-freenet - hostgroups: computers, porterbox + hostgroups: computers, porterbox, single-cpu 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 + # SMP kernel doesn't run stable + hostgroups: computers, buildd, sw-raid, single-cpu + contacts: tjrc1 verdi: address: 192.54.42.193 @@ -289,23 +324,30 @@ 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 + contacts: joerg + powell: + address: 87.106.64.223 + parents: gw-1und1 + hostgroups: computers, service, heavy-exim, rsyncd-hosts + contacts: joerg caballero: address: 193.201.200.200 parents: gw-blackcat - hostgroups: computers, buildd, sw-raid + hostgroups: computers, 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 @@ -313,10 +355,12 @@ 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 @@ -325,8 +369,44 @@ 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, lenny + contacts: luk + + agnesi: + address: 65.173.90.83 + parents: gw-agnesi + hostgroups: deadslow + + spontini: + 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 + + 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 + contacts: holger ############################# # host groups @@ -378,10 +458,20 @@ hostgroups: sw-raid: alias: Hosts with Linux software raid private: 1 + single-cpu: + alias: Hosts with only one CPU + private: 1 + + lenny: + alias: Hosts running lenny, not etch + 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 @@ -389,7 +479,7 @@ 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 @@ -415,6 +505,9 @@ hostgroups: postgres81-hosts: alias: hosts running postgres81 private: 1 + mysql-hosts: + alias: hosts running mysql + private: 1 highload: alias: "hosts on which high load is normal" @@ -424,6 +517,29 @@ 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 ############################# @@ -438,7 +554,7 @@ 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 @@ -451,79 +567,139 @@ 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 + hosts: sperger, rietz, steffani, penalosa, peri, albeniz, goetz, mayer, mayr, paer, spontini, tartini, morales, ravel, auber, 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 + 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 - - - name: disk usage on /org/scratch2 - nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /org/scratch2" - hosts: merkel + hosts: agricola, arcadelt, argento, allegri, tartini, morales, auber, powell - - name: disk usage on /oldorg - nrpe: "/usr/lib/nagios/plugins/check_disk 80 90 /oldorg" + 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 + 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 + 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 + nrpe: "sudo /usr/lib/nagios/plugins/dsa-check-dabackup" + hostgroups: computers + 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 + - + name: samhain + servicegroups: samhain + nrpe: "/usr/lib/nagios/plugins/dsa-check-samhain" + hostgroups: computers + depends: process - samhain + normal_check_interval: 240 + retry_check_interval: 5 + #### - name: users @@ -580,22 +756,70 @@ services: hostgroups: computers depends: process - sshd normal_check_interval: 60 + notification_interval: 1440 - name: "network service - sshd" 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 + - + 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 ### - @@ -620,12 +844,12 @@ 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 ### @@ -636,7 +860,7 @@ 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 ### @@ -644,17 +868,22 @@ 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 ### @@ -688,6 +917,10 @@ 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 @@ -699,6 +932,11 @@ 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 @@ -822,7 +1060,7 @@ 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 @@ -849,7 +1087,7 @@ 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 @@ -883,17 +1121,23 @@ 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 + hosts: verdi, kassia, murphy, allegri, piatti depends: process - postfix - master - name: network service - smtp - port 8080 check: dsa_check_smtp_port!8080 - hosts: allegri + 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 - @@ -901,14 +1145,18 @@ services: 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: 1440 + normal_check_interval: 120 - - 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 + - + name: setup - ud-ldap freshness + nrpe: "/usr/lib/nagios/plugins/dsa-check-udldap-freshness" hostgroups: computers - normal_check_interval: 1440 ### - name: process - uptimed @@ -919,8 +1167,11 @@ 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 - irqbalance + nrpe: "/usr/lib/nagios/plugins/check_procs -w 0:0 -C irqbalance" + hostgroups: single-cpu #### ### @@ -961,7 +1212,7 @@ 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 @@ -971,33 +1222,67 @@ 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 - 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 + hosts: sperger, ries, steffani, merkel, spohr, peri, penalosa, albeniz, verdi, liszt, kassia, agricola, arcadelt, argento, allegri, morales, bartok, schroeder ### - name: process - acpid @@ -1008,13 +1293,13 @@ 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 ### - @@ -1036,10 +1321,6 @@ 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.. @@ -1088,13 +1369,13 @@ 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 #### @@ -1131,8 +1412,8 @@ 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 ### - @@ -1154,9 +1435,33 @@ 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'" @@ -1165,6 +1470,7 @@ 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