ansible/playbooks/tags_nagios-nrpe.yml

68 lines
2.5 KiB
YAML
Executable File

#!/usr/bin/env ansible-playbook
# vim:ft=ansible:
---
- hosts: tags_nagios-nrpe
roles:
- role: git
vars:
git_repos:
- repo: https://git.desu.ltd/salt/monitoring-scripts
dest: /usr/local/bin/monitoring-scripts
tags: [ nrpe ]
- role: nrpe
vars:
nrpe_server_bind_address: 0.0.0.0
nrpe_server_allowed_hosts:
- 127.0.0.0/24 # Local machines
- 192.168.0.0/16
- 172.16.0.0/12
- 10.0.0.0/8
- 45.79.24.6/32 # web3.desu.ltd
nrpe_plugin_packages:
- monitoring-plugins
- nagios-plugins-contrib
nrpe_command:
check_disk_all:
script: check_disk
option: -M -u GB -X nfs -X tracefs -X cgroup -X tmpfs -X overlay -X shm -w 15% -c 10% -W 15% -K 10% -A -I '^/run/' -I '^udev$' -I '^/var/lib/kubelet/'
check_load:
script: check_load
option: -r -w 0.8,0.8,0.8 -c 1.0,0.9,0.9
check_pgsql:
script: check_pgsql
option: "-H localhost -l nagios -p {{ secret_postgresql_monitoring_password }} -w 2 -c 5"
check_swap:
script: check_swap
option: -w 20% -c 10%
check_users:
script: check_users
option: -w 3 -c 5
nrpe_command_extra:
check_reboot_required:
script: /usr/local/bin/monitoring-scripts/check_reboot_required
option: 604800
check_systemd_ansiblepull_service:
script: /usr/local/bin/monitoring-scripts/check_systemd_unit
option: ansible-pull.service
check_systemd_ansiblepull_timer:
script: /usr/local/bin/monitoring-scripts/check_systemd_unit
option: ansible-pull.timer
check_systemd_backup_service:
script: /usr/local/bin/monitoring-scripts/check_systemd_unit
option: backup.service
check_systemd_backup_timer:
script: /usr/local/bin/monitoring-scripts/check_systemd_unit
option: backup.timer
check_systemd_docker_service:
script: /usr/local/bin/monitoring-scripts/check_systemd_unit
option: docker.service
tags: [ nrpe ]
- hosts: all
tasks:
- name: disable nrped when not tagged
systemd: name={{ item }} state=stopped enabled=no
with_items:
- nagios-nrpe-server.service
when: "'tags_nagios-nrpe' not in group_names and item in services"
tags: [ nrpe, zerotier ]