feat(goldpinger): add PrometheusRule. (#44)

charts/goldpinger/Chart.yaml

@@ -11,4 +11,4 @@ name: goldpinger
 sources:
   - https://github.com/bloomberg/goldpinger
   - https://github.com/okgolove/helm-charts
-version: 4.2.1
+version: 4.3.0

charts/goldpinger/README.md

@@ -79,6 +79,9 @@ The following table lists the configurable parameters of the Goldpinger chart an
 | `serviceMonitor.honorLabels` | honorLabels chooses the metric's labels on collisions with target labels. | `false`|
 | `serviceMonitor.namespace` | namespace where servicemonitor resource should be created, same as Goldpinger if not specified | `` |
 | `serviceMonitor.scrapeInterval` | interval between Prometheus scraping | `30s` |
+| `prometheusRule.enabled`        | Create a custom prometheusRule Resource for scraping metrics using PrometheusOperator | `false`                  |
+| `prometheusRule.namespace`      | The namespace in which the prometheusRule will be created              | `""`                     |
+| `prometheusRule.rules`          | Custom Prometheus rules                      | `see values.yaml`     |
 
 Specify each parameter using the `--set key=value[,key=value]` argument to `helm install`. For example,
 

charts/goldpinger/templates/prometheusrule.yaml

@@ -0,0 +1,22 @@
+{{- if .Values.prometheusRule.enabled }}
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: {{ template "goldpinger.fullname" . }}
+  {{- if .Values.prometheusRule.namespace }}
+  namespace: {{ .Values.prometheusRule.namespace }}
+  {{- else }}
+  namespace: {{ .Release.Namespace | quote }}
+  {{- end }}
+  labels:
+    app.kubernetes.io/name: {{ include "goldpinger.name" . }}
+    helm.sh/chart: {{ include "goldpinger.chart" . }}
+    app.kubernetes.io/instance: {{ .Release.Name }}
+    app.kubernetes.io/managed-by: {{ .Release.Service }}
+spec:
+  {{- with .Values.prometheusRule.rules }}
+  groups:
+    - name: {{ template "goldpinger.name" $ }}
+      rules: {{- tpl (toYaml .) $ | nindent 8 }}
+  {{- end }}
+{{- end }}

charts/goldpinger/values.yaml

@@ -96,3 +96,17 @@ serviceMonitor:
   # namespace: monitoring
   interval: 30s
   # honorLabels: true
+
+## Custom PrometheusRule to be defined
+## ref: https://github.com/coreos/prometheus-operator#customresourcedefinitions
+prometheusRule:
+  enabled: false
+  rules:
+    - alert: goldpinger_nodes_unhealthy
+      expr: sum(goldpinger_nodes_health_total{job={{ template "goldpinger.fullname" . }}, status="unhealthy"})
+        BY (instance, goldpinger_instance) > 0
+      for: 5m
+      annotations:
+        description: |
+          Goldpinger instance {{ "{{ $labels.goldpinger_instance }}" }} has been reporting unhealthy nodes for at least 5 minutes.
+        summary: Instance {{ "{{ $labels.instance }}" }} down