add alertmanager

prometheus/alert.rules

@@ -0,0 +1,7 @@
+ALERT instance_down
+IF up == 0
+FOR 5s
+LABELS {severity="page"}
+ANNOTATIONS {
+   DESCRIPTION="{{$labels.instance}} of job {{$labels.job}} has been down for more than 5 seconds.",
+   SUMMARY="Instance {{$labels.instance}} down"}

prometheus/prometheus.yml

@@ -11,6 +11,7 @@ global:
 
 # Load and evaluate rules in this file every 'evaluation_interval' seconds.
 rule_files:
+  - "alert.rules"
   # - "first.rules"
   # - "second.rules"