Merge pull request #20 from Starttoaster/prometheusrules

Add some prometheus rules to the helm chart

README.md

@@ -72,7 +72,7 @@ config:
   # optional: If you change this, change the service.port value too
   port: '8080'
 
-# optional
+# optional: creates a ServiceMonitor that targets this exporter's service -- for use with the kube-prometheus operator
 serviceMonitor:
   enabled: false
   ## The label to use to retrieve the job name from.
@@ -82,6 +82,10 @@ serviceMonitor:
   targetLabels: []
   relabelings: []
   metricRelabelings: []
+
+# optional: creates a PrometheusRule with some basic alerts for proxmox clusters -- for use with the kube-prometheus operator
+prometheusRule:
+  enabled: false
 ```
 
 Install the chart:
@@ -143,7 +147,7 @@ A Grafana dashboard that implements this exporter with metrics from node_exporte
 
 ## Alerting
 
-Some Prometheus alert rules that use metrics from this exporter are in the works. Contributions are welcome for this as well.
+The Helm chart in this repository comes with some Prometheus rules for PVE servers. More alerts are being added to it over time. Find that in the `chart/proxmox-exporter/templates` directory.
 
 ## Metrics
 

chart/proxmox-exporter/Chart.yaml

@@ -15,7 +15,7 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.1.2
+version: 0.1.3
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to

chart/proxmox-exporter/templates/prometheusrule.yaml

@@ -0,0 +1,47 @@
+{{- if .Values.prometheusRule.enabled }}
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: {{ include "proxmox-exporter.fullname" . }}
+  labels:
+    {{- include "proxmox-exporter.labels" . | nindent 4 }}
+spec:
+  groups:
+    - name: ProxmoxNodes
+      rules:
+        - alert: ProxmoxNodeDown
+          annotations:
+            title: Proxmox node {{ $labels.node }} is down
+          expr: |
+            proxmox_node_up == 0
+          for: 1m
+          labels:
+            severity: critical
+        - alert: ProxmoxNodeTargetLost
+          annotations:
+            title: Proxmox node up metric absent for {{ $labels.node }}
+            description: Something wrong with the exporter, the Proxmox API server(s) it is configured to make requests to, or the server the exporter is running on
+          expr: |
+            absent_over_time(proxmox_node_up[1h])
+          for: 1m
+          labels:
+            severity: critical
+        - alert: ProxmoxGuestDown
+          annotations:
+            title: Proxmox guest {{ $labels.name }} is down
+            description: Guest {{ $labels.name }} of type {{ $labels.type }} on node {{ $labels.node }} is down
+          expr: |
+            proxmox_guest_up == 0
+          for: 1m
+          labels:
+            severity: critical
+        - alert: ProxmoxGuestTargetLost
+          annotations:
+            title: Proxmox guest up metric absent for {{ $labels.name }}
+            description:  Guest {{ $labels.name }} of type {{ $labels.type }} on node {{ $labels.node }} may be down
+          expr: |
+            absent_over_time(proxmox_guest_up[1h])
+          for: 1m
+          labels:
+            severity: critical
+{{- end }}

chart/proxmox-exporter/values.yaml

@@ -47,6 +47,9 @@ serviceMonitor:
   relabelings: []
   metricRelabelings: []
 
+prometheusRule:
+  enabled: false
+
 serviceAccount:
   # Specifies whether a service account should be created
   create: true