Merge pull request #22 from brancz/update-configs

Update configs/alerts

assets/prometheus/prometheus.yaml

@@ -1,3 +1,22 @@
+alerting:
+  alertmanagers:
+  - kubernetes_sd_configs:
+    - role: endpoints
+    relabel_configs:
+    - action: keep
+      regex: alertmanager-main
+      source_labels:
+      - __meta_kubernetes_service_name
+    - action: keep
+      regex: monitoring
+      source_labels:
+      - __meta_kubernetes_namespace
+    - action: keep
+      regex: web
+      source_labels:
+      - __meta_kubernetes_endpoint_port_name
+    scheme: http
+
 global:
   scrape_interval: 15s
   evaluation_interval: 15s

assets/prometheus/rules/kubernetes.rules

@@ -286,18 +286,6 @@ ALERT K8SControllerManagerDown
     description = "There is no running K8S controller manager. Deployments and replication controllers are not making progress.",
   }
 
-ALERT K8SMoreThanOneController
-  IF count by (job,cluster) (up{job=~"kube-scheduler|kube-controller-manager"}) > 1
-  FOR 5m
-  LABELS {
-    service = "k8s",
-    severity = "critical",
-  }
-  ANNOTATIONS {
-    summary = "More than one controller node is active",
-    description = "There is more than one {{ $labels.job }} managing the cluster. Cluster behaviour is undefined.",
-  }
-
 ALERT K8SConntrackTableFull
   IF 100*node_nf_conntrack_entries / node_nf_conntrack_entries_limit > 50
   FOR 10m

manifests/prometheus/prometheus-k8s-rules.yaml

@@ -341,18 +341,6 @@ data:
         description = "There is no running K8S controller manager. Deployments and replication controllers are not making progress.",
       }
 
-    ALERT K8SMoreThanOneController
-      IF count by (job,cluster) (up{job=~"kube-scheduler|kube-controller-manager"}) > 1
-      FOR 5m
-      LABELS {
-        service = "k8s",
-        severity = "critical",
-      }
-      ANNOTATIONS {
-        summary = "More than one controller node is active",
-        description = "There is more than one {{ $labels.job }} managing the cluster. Cluster behaviour is undefined.",
-      }
-
     ALERT K8SConntrackTableFull
       IF 100*node_nf_conntrack_entries / node_nf_conntrack_entries_limit > 50
       FOR 10m