Configures alertmanger for heartbeat with standalone only

README.md

@@ -109,6 +109,7 @@ The operator's workflow can be described in two different architectural models:
             ModSecret[Include: modify_alertmanager_secret]
             Reencode[Re-encode Alertmanager Content]
             PatchSecret[Patch alertmanager-main Secret]
+            AddPrometheusRule[Add PrometheusRule]
             UpdateCR[Update CR Status to ConfigUpdated]
             Init --> GetClusterName
             GetClusterName --> CheckIntegration
@@ -129,8 +130,8 @@ The operator's workflow can be described in two different architectural models:
         GO -->|Return: Endpoint| ConfigureSlack
         ConfigureSlack --> ModSecret
         ModSecret --> PatchSecret
-        PatchSecret --> UpdateCR
-        CheckIntegration -- Integration exists --> UpdateCR
+        PatchSecret --> AddPrometheusRule
+        AddPrometheusRule --> UpdateCR
     ```
 
     *Operator Workflow in Standalone Cluster:*
@@ -142,7 +143,7 @@ The operator's workflow can be described in two different architectural models:
 
     *In-Cluster Configuration Management:*
     The operator directly applies configuration changes within the cluster, bypassing the need for `Syncsets`.
-    It ensures the Alertmanager's alert forwarding settings are correctly configured for seamless communication with Grafana On Call.
+    It ensures the Alertmanager's alert forwarding settings are correctly configured for seamless communication with Grafana On Call. Additionally, it adds option for On call Heartbeat which acts as a monitoring for monitoring systems. It also creates PrometheusRule that adds a Vector as heartbeat generator.
 
     *Local Secret Management:*
     Managing the `alertmanager-main-generated` secret locally, the operator updates its configurations.

bundle/manifests/grafana-cloud-ansible-operator.clusterserviceversion.yaml

@@ -157,6 +157,12 @@ spec:
           - patch
           - update
           - watch
+        - apiGroups:
+          - monitoring.coreos.com
+          resources:
+          - prometheusrules
+          verbs:
+          - '*'
         - apiGroups:
           - ""
           resources:

charts/grafana-oncall/templates/role.yaml

@@ -76,6 +76,9 @@ rules:
   - apiGroups: ["slack.stakater.com"]
     resources: ["channels"]
     verbs: ["get", "list", "watch"]
+  - apiGroups: ["monitoring.coreos.com"]
+    resources: ["prometheusrules"]
+    verbs: ["*"]
   - apiGroups: ["hive.openshift.io"]
     resources: ["syncsets"]
     verbs: ["*"]

config/rbac/role.yaml

@@ -78,6 +78,9 @@ rules:
   - apiGroups: ["slack.stakater.com"]
     resources: ["channels"]
     verbs: ["create", "get", "list", "patch", "update", "watch"]
+  - apiGroups: ["monitoring.coreos.com"]
+    resources: ["prometheusrules"]
+    verbs: ["*"]
   - apiGroups: [""]
     resources: ["secrets"]
     verbs: ["*"]

roles/grafana_cloud_operator/tasks/grafana_oncall_standalone.yml

@@ -103,6 +103,28 @@
         alertmanager.yaml: "{{ encoded_alertmanager_secret_content }}"
   when: not integration_exists_for_cluster
 
+- name: Add prometheus rule for cluster
+  kubernetes.core.k8s:
+    state: present
+    namespace: "openshift-monitoring"
+    definition:
+      apiVersion: monitoring.coreos.com/v1
+      kind: PrometheusRule
+      metadata:
+        name: "heartbeat-grafana-oncall"
+        namespace: "openshift-monitoring"
+      spec:
+        groups:
+          - name: meta
+            rules:
+              - alert: heartbeat
+                annotations:
+                  description: This is a heartbeat alert for Grafana OnCall
+                  summary: Heartbeat for Grafana OnCall
+                expr: vector(1)
+                labels:
+                  severity: none
+
 - name: Update CR status to ConfigUpdated
   kubernetes.core.k8s:
     state: present

roles/grafana_cloud_operator/tasks/modify_alertmanager_secret.yml

@@ -4,10 +4,21 @@
       {{ (fetched_alertmanager_secret.resources[0].data['alertmanager.yaml'] | b64decode | from_yaml) | combine({
           'receivers': [
             {
-              'name': receiver_name,
-              'webhook_configs': [{
-                'url': receiver_url
-              }]
+              "name": receiver_name,
+              "webhook_configs": [
+                {
+                  "url": receiver_url
+                }
+              ]
+            },
+            {
+              "name": "grafana-oncall-heartbeat",
+              "webhook_configs": [
+                {
+                  "url": receiver_url + "heartbeat/",
+                  "send_resolved": false
+                }
+              ]
             }
           ],
           'route': {
@@ -18,6 +29,15 @@
                 'match': {
                   'severity': 'info | warning | critical'
                 }
+              },
+              {
+                "match": {
+                  "alertname": "heartbeat"
+                },
+                "receiver": "grafana-oncall-heartbeat",
+                "group_wait": "0s",
+                "group_interval": "1m",
+                "repeat_interval": "50s"
               }
             ]
           }