Fix alertmanager mails

monitoring.yml

@@ -12,8 +12,14 @@
           - fy.adm.crans.org:9100
           - vulcain.adm.crans.org:9100
           # VM
+          - dhcp.adm.crans.org:9100
+          - nem.adm.crans.org:9100
+          - kenobi.adm.crans.org:9100
+          - roundcube-srv.adm.crans.org:9100
+          - kiwi.adm.crans.org:9100
+          - eap.adm.crans.org:9100
+          - radius.adm.crans.org:9100
           - frontdaur.adm.crans.org:9100
-          - gitzly.adm.crans.org:9100
           - ethercalc-srv.adm.crans.org:9100
           - ipv6-zayo.adm.crans.org:9100
           - prometheus.adm.crans.org:9100

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

@@ -2,10 +2,11 @@
 
 global:
   # The smarthost and SMTP sender used for mail notifications.
-  smtp_smarthost: 'localhost:25'
-  smtp_from: 'alertmanager@crans.org'
+  smtp_smarthost: 'smtp.adm.crans.org:25'
+  smtp_from: 'roots@crans.org'
   #smtp_auth_username: 'alertmanager'
   #smtp_auth_password: 'password'
+  smtp_require_tls: false
 
 # The directory from which notification templates are read.
 templates: 

roles/prometheus/templates/prometheus/alert.rules.j2

@@ -0,0 +1,13 @@
+# {{ ansible_managed }}
+
+{# As this is also Jinja2 it will conflict without a raw block #}
+{% raw %}
+ALERT InstanceDown
+  IF up == 0
+  FOR 5m
+  LABELS { severity = "page" }
+  ANNOTATIONS {
+    summary = "Instance {{ $labels.instance }} down",
+    description = "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 5 minutes.",
+  }
+{% endraw %}