Merge pull request 'Rework blackbox monitoring' (#2) from rework-blackbox-monitoring into main

Reviewed-on: #2
This commit was merged in pull request #2.
This commit is contained in:
2026-06-13 19:07:13 +02:00
6 changed files with 129 additions and 153 deletions
+3 -3
View File
@@ -22,6 +22,6 @@ all:
reverse-proxy.labolyon.dn42: reverse-proxy.labolyon.dn42:
wiki.labolyon.dn42: wiki.labolyon.dn42:
zigbee2mqtt.labolyon.dn42: zigbee2mqtt.labolyon.dn42:
# blackbox: monitoring:
# hosts: hosts:
# monitoring: monitoring.labolyon.dn42:
+2 -12
View File
@@ -12,21 +12,11 @@
become: yes become: yes
roles: roles:
- prometheus - prometheus
- blackbox-exporter
vars: vars:
blackbox: false
scrape_files: scrape_files:
- /etc/prometheus/scrape-main.yml - /etc/prometheus/scrape-main.yml
- /etc/prometheus/scrape-blackbox.yml
#- name: Install and configure Prometheus node - Blackbox nodes
# hosts: blackbox
# become: yes
# roles:
# - prometheus
# - blackbox-exporter
# vars:
# blackbox: true
# scrape_files:
# - /etc/prometheus/scrape-blackbox.yml
- name: Install and configure nodes - name: Install and configure nodes
hosts: all hosts: all
@@ -1,60 +1,65 @@
{{ ansible_managed | comment }} {{ ansible_managed | comment }}
modules: modules:
http_2xx: http_2xx:
prober: http prober: http
{% if inventory_hostname == 'check.home.arpa' %} {% if inventory_hostname == 'check.home.arpa' %}
http: http:
preferred_ip_protocol: "ip4" preferred_ip_protocol: "ip4"
ip_protocol_fallback: true ip_protocol_fallback: true
{% endif %} {% endif %}
http_post_2xx: http_2xx_selfsigned:
prober: http prober: http
{% if inventory_hostname == 'check.home.arpa' %} http:
http: tls_config:
method: POST insecure_skip_verify: true
preferred_ip_protocol: "ip4" http_post_2xx:
ip_protocol_fallback: true prober: http
{% endif %} {% if inventory_hostname == 'check.home.arpa' %}
tcp_connect: http:
prober: tcp method: POST
smtp_check: preferred_ip_protocol: "ip4"
prober: tcp ip_protocol_fallback: true
timeout: 5s {% endif %}
tcp: tcp_connect:
{% if inventory_hostname == 'check.home.arpa' %} prober: tcp
preferred_ip_protocol: "ip4" smtp_check:
ip_protocol_fallback: true prober: tcp
{% endif %} timeout: 5s
query_response: tcp:
- expect: "^220(.*)ESMTP(.*)$" {% if inventory_hostname == 'check.home.arpa' %}
- send: "EHLO prober\r" preferred_ip_protocol: "ip4"
- expect: "^250-STARTTLS" ip_protocol_fallback: true
- send: "STARTTLS\r" {% endif %}
- expect: "^220" query_response:
- starttls: true - expect: "^220(.*)ESMTP(.*)$"
- send: "EHLO prober\r" - send: "EHLO prober\r"
- expect: "^250-AUTH" - expect: "^250-STARTTLS"
- send: "QUIT\r" - send: "STARTTLS\r"
imap_check: - expect: "^220"
prober: tcp - starttls: true
timeout: 5s - send: "EHLO prober\r"
tcp: - expect: "^250-AUTH"
{% if inventory_hostname == 'check.home.arpa' %} - send: "QUIT\r"
preferred_ip_protocol: "ip4" imap_check:
ip_protocol_fallback: true prober: tcp
{% endif %} timeout: 5s
query_response: tcp:
- expect: "OK.*STARTTLS" {% if inventory_hostname == 'check.home.arpa' %}
- send: ". STARTTLS" preferred_ip_protocol: "ip4"
- expect: "OK" ip_protocol_fallback: true
- starttls: true {% endif %}
- send: ". capability" query_response:
- expect: "CAPABILITY IMAP4rev1" - expect: "OK.*STARTTLS"
icmp: - send: ". STARTTLS"
prober: icmp - expect: "OK"
{% if inventory_hostname == 'check.home.arpa' %} - starttls: true
icmp: - send: ". capability"
preferred_ip_protocol: "ip4" - expect: "CAPABILITY IMAP4rev1"
ip_protocol_fallback: true icmp:
{% endif %} prober: icmp
{% if inventory_hostname == 'check.home.arpa' %}
icmp:
preferred_ip_protocol: "ip4"
ip_protocol_fallback: true
{% endif %}
@@ -1,75 +1,31 @@
{{ ansible_managed | comment }} {{ ansible_managed | comment }}
# Global configuration # Global configuration
global: global:
scrape_interval: 15s # Set the scrape interval to every 15 seconds. Default is every 1 minute. scrape_interval: 15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute. evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
# scrape_timeout is set to the global default (10s). # scrape_timeout is set to the global default (10s).
# Alertmanager configuration # Alertmanager configuration
alerting: alerting:
alertmanagers: alertmanagers:
- static_configs: - static_configs:
- targets: - targets:
- localhost:9093 - localhost:9093
# Load rules once and periodically evaluate them according to the global 'evaluation_interval'. # Load rules once and periodically evaluate them according to the global 'evaluation_interval'.
rule_files: rule_files:
- "{{ alertmanager_rules }}/prometheus.rules.yml" - "{{ alertmanager_rules }}/prometheus.rules.yml"
- "{{ alertmanager_rules }}/blackbox.rules.yml" - "{{ alertmanager_rules }}/blackbox.rules.yml"
- "{{ alertmanager_rules }}/hosts.rules.yml" - "{{ alertmanager_rules }}/hosts.rules.yml"
# A scrape configuration containing exactly one endpoint to scrape: # A scrape configuration containing exactly one endpoint to scrape:
scrape_config_files:
#scrape_config_files: {% for item in scrape_files %}
#{% for item in scrape_files %} - "{{ item }}"
# - "{{ item }}" {% endfor %}
#{% endfor %}
scrape_configs:
scrape_configs: - job_name: "prometheus"
- job_name: "prometheus" static_configs:
static_configs: - targets: ["localhost:9090"]
- targets: ["localhost:9090"]
{% if blackbox %}
- job_name: "blackbox"
metrics_path: /probe
params:
module: [http_2xx]
scrape_interval: 5s
static_configs:
- targets:
- https://labolyon.fr
- https://mail.labolyon.fr
- https://wiki.labolyon.fr
- https://git.labolyon.fr
relabel_configs:
- source_labels: [__address__]
target_label: __param_target
- source_labels: [__param_target]
target_label: target
- target_label: __address__
replacement: 127.0.0.1:9115 # The blackbox exporter's real hostname:port.
{% else %}
- job_name: "linux-nodes"
static_configs:
- targets:
- ansible.labolyon.dn42:9100
- dn42-router.labolyon.dn42:9100
- dns.labolyon.dn42:9100
- git.labolyon.dn42:9100
- i2p.labolyon.dn42:9100
- labolyon-fr.labolyon.dn42:9100
- lolix-ixpman.labolyon.dn42:9100
- lolix-rs1.labolyon.dn42:9100
- lolmox.labolyon.dn42:9100
- lolmox2.labolyon.dn42:9100
- mail.labolyon.dn42:9100
- matrix.labolyon.dn42:9100
- monitoring.labolyon.dn42:9100
- mosquitto.labolyon.dn42:9100
- radius.labolyon.dn42:9100
- reverse-proxy.labolyon.dn42:9100
- wiki.labolyon.dn42:9100
- zigbee2mqtt.labolyon.dn42:9100
{% endif %}
@@ -1,4 +1,8 @@
- job_name: "blackbox" # managed by ansible
scrape_configs:
- job_name: "blackbox-public-https"
metrics_path: /probe metrics_path: /probe
params: params:
module: [http_2xx] module: [http_2xx]
@@ -6,13 +10,33 @@
static_configs: static_configs:
- targets: - targets:
- https://labolyon.fr - https://labolyon.fr
- https://mail.labolyon.fr - https://webmail.labolyon.fr
- https://wiki.labolyon.fr - https://wiki.labolyon.fr
- https://git.labolyon.fr - https://git.labolyon.fr
- https://sso.labolyon.fr
- https://chat.labolyon.fr
- https://grafana.labolyon.fr
relabel_configs: relabel_configs:
- source_labels: [__address__] - source_labels: [__address__]
target_label: __param_target target_label: __param_target
- source_labels: [__param_target] - source_labels: [__param_target]
target_label: target target_label: instance
- target_label: __address__
replacement: 127.0.0.1:9115 # The blackbox exporter's real hostname:port.
- job_name: "blackbox-internal-https"
metrics_path: /probe
params:
module: [http_2xx_selfsigned]
scrape_interval: 5s
static_configs:
- targets:
- https://octoprint.labolyon.dn42/login/
- https://stickers.labolyon.dn42
relabel_configs:
- source_labels: [__address__]
target_label: __param_target
- source_labels: [__param_target]
target_label: instance
- target_label: __address__ - target_label: __address__
replacement: 127.0.0.1:9115 # The blackbox exporter's real hostname:port. replacement: 127.0.0.1:9115 # The blackbox exporter's real hostname:port.
@@ -1,3 +1,4 @@
scrape_configs:
- job_name: "linux-nodes" - job_name: "linux-nodes"
static_configs: static_configs:
- targets: - targets: