Add monitoring

Signed-off-by: Yohann D'ANELLO <ynerant@crans.org>

roles/prometheus-alertmanager/handlers/main.yml

@@ -0,0 +1,5 @@
+---
+- name: Restart Prometheus Alertmanager
+  service:
+    name: prometheus-alertmanager
+    state: restarted

roles/prometheus-alertmanager/tasks/main.yml

@@ -0,0 +1,14 @@
+---
+- name: Install Prometheus Alertmanager
+  apt:
+    update_cache: true
+    name: prometheus-alertmanager
+  register: apt_result
+  retries: 3
+  until: apt_result is succeeded
+
+- name: Configure Prometheus Alertmanager
+  template:
+    src: prometheus/alertmanager.yml.j2
+    dest: /etc/prometheus/alertmanager.yml
+  notify: Restart Prometheus Alertmanager

roles/prometheus-alertmanager/templates/prometheus/alertmanager.yml.j2

@@ -0,0 +1,60 @@
+{{ ansible_header | comment }}
+# See https://prometheus.io/docs/alerting/configuration/ for documentation.
+
+global:
+  # The smarthost and SMTP sender used for mail notifications.
+  smtp_smarthost: 'localhost:25'
+  smtp_from: 'alertmanager@example.org'
+  #smtp_auth_username: 'alertmanager'
+  #smtp_auth_password: 'password'
+
+# The directory from which notification templates are read.
+templates: 
+- '/etc/prometheus/alertmanager_templates/*.tmpl'
+
+# The root route on which each incoming alert enters.
+route:
+  # The labels by which incoming alerts are grouped together. For example,
+  # multiple alerts coming in for cluster=A and alertname=LatencyHigh would
+  # be batched into a single group.
+  group_by: ['instance']  # group per instance
+
+  # When a new group of alerts is created by an incoming alert, wait at
+  # least 'group_wait' to send the initial notification.
+  # This way ensures that you get multiple alerts for the same group that start
+  # firing shortly after another are batched together on the first 
+  # notification.
+  group_wait: 30s
+
+  # When the first notification was sent, wait 'group_interval' to send a batch
+  # of new alerts that started firing for that group.
+  group_interval: 5m
+
+  # If an alert has successfully been sent, wait 'repeat_interval' to
+  # resend them.
+  repeat_interval: 24h
+
+  # A default receiver
+  receiver: webhook-ninjabot
+
+
+# Inhibition rules allow to mute a set of alerts given that another alert is
+# firing.
+# We use this to mute any warning-level notifications if the same alert is 
+# already critical.
+inhibit_rules:
+- source_match:
+    severity: 'critical'
+  target_match:
+    severity: 'warning'
+  # Apply inhibition if the alertname is the same.
+  equal: ['alertname', 'cluster', 'service']
+
+
+receivers:
+- name: 'webhook-ninjabot'
+  webhook_configs:
+  - url: 'http://localhost:5000/'
+    send_resolved: true
+  - url: 'http://localhost:8000/'
+    send_resolved: true