[network-ups-tools] metrics refactor (#1178)

* [network-ups-tools] metrics refactor

* add template to rules

* Update charts/stable/network-ups-tools/templates/prometheusrules.yaml

Co-authored-by: ᗪєνιη ᗷυнʟ <onedr0p@users.noreply.github.com>

* Update charts/stable/network-ups-tools/templates/prometheusrules.yaml

Co-authored-by: ᗪєνιη ᗷυнʟ <onedr0p@users.noreply.github.com>

* Update charts/stable/network-ups-tools/templates/prometheusrules.yaml

Co-authored-by: ᗪєνιη ᗷυнʟ <onedr0p@users.noreply.github.com>

* Update charts/stable/network-ups-tools/templates/prometheusrules.yaml

Co-authored-by: ᗪєνιη ᗷυнʟ <onedr0p@users.noreply.github.com>

Co-authored-by: ᗪєνιη ᗷυнʟ <onedr0p@users.noreply.github.com>

charts/stable/network-ups-tools/Chart.yaml

@@ -2,7 +2,7 @@ apiVersion: v2
 appVersion: v2.7.4-2479-g86a32237
 description: Network UPS Tools is a collection of programs which provide a common interface for monitoring and administering UPS, PDU and SCD hardware.
 name: network-ups-tools
-version: 5.1.0
+version: 6.0.0
 kubeVersion: ">=1.16.0-0"
 keywords:
 - nut

charts/stable/network-ups-tools/README.md

@@ -1,6 +1,6 @@
 # network-ups-tools
 
-![Version: 5.1.0](https://img.shields.io/badge/Version-5.1.0-informational?style=flat-square) ![AppVersion: v2.7.4-2479-g86a32237](https://img.shields.io/badge/AppVersion-v2.7.4--2479--g86a32237-informational?style=flat-square)
+![Version: 6.0.0](https://img.shields.io/badge/Version-6.0.0-informational?style=flat-square) ![AppVersion: v2.7.4-2479-g86a32237](https://img.shields.io/badge/AppVersion-v2.7.4--2479--g86a32237-informational?style=flat-square)
 
 Network UPS Tools is a collection of programs which provide a common interface for monitoring and administering UPS, PDU and SCD hardware.
 
@@ -79,19 +79,21 @@ N/A
 | config.mode | string | `"values"` | If set to 'values', the configuration will be read from these values. Otherwise you have to mount a volume to /etc/nut containing the configuration files. |
 | env | object | See below | environment variables. |
 | env.TZ | string | `"UTC"` | Set the container timezone |
-| exporter.enabled | bool | See values.yaml | Enable and configure prometheus-nut-exporter sidecar and Prometheus serviceMonitor. |
-| exporter.env.logLevel | string | `"info"` | log level [info|debug|trace] |
-| exporter.env.port | int | `9995` | metrics port |
-| exporter.image.pullPolicy | string | `"IfNotPresent"` | image pull policy |
-| exporter.image.repository | string | `"hon95/prometheus-nut-exporter"` | image repository |
-| exporter.image.tag | string | `"1.1.1"` | image tag |
-| exporter.serviceMonitor.interval | string | `"30s"` |  |
-| exporter.serviceMonitor.labels | object | `{}` |  |
-| exporter.serviceMonitor.scrapeTimeout | string | `"10s"` |  |
 | image.pullPolicy | string | `"IfNotPresent"` | image pull policy |
 | image.repository | string | `"ghcr.io/k8s-at-home/network-ups-tools"` | image repository |
 | image.tag | string | `"v2.7.4-2479-g86a32237"` | image tag |
 | ingress.main | object | See values.yaml | Enable and configure ingress settings for the chart under this key. |
+| metrics.enabled | bool | See values.yaml | Enable and configure prometheus-nut-exporter sidecar and Prometheus serviceMonitor. |
+| metrics.exporter.env.logLevel | string | `"info"` | log level [info|debug|trace] |
+| metrics.exporter.env.port | int | `9995` | metrics port |
+| metrics.exporter.image.pullPolicy | string | `"IfNotPresent"` | image pull policy |
+| metrics.exporter.image.repository | string | `"hon95/prometheus-nut-exporter"` | image repository |
+| metrics.exporter.image.tag | string | `"1.1.1"` | image tag |
+| metrics.prometheusRule | object | See values.yaml | Enable and configure Prometheus Rules for the chart under this key. |
+| metrics.prometheusRule.rules | list | See prometheusrules.yaml | Configure additionial rules for the chart under this key. |
+| metrics.serviceMonitor.interval | string | `"30s"` |  |
+| metrics.serviceMonitor.labels | object | `{}` |  |
+| metrics.serviceMonitor.scrapeTimeout | string | `"10s"` |  |
 | persistence | object | See values.yaml | Configure persistence settings for the chart under this key. |
 | persistence.ups.hostPath | string | `"/dev/bus/usb/001/001"` | The path of the usb ups on the host. |
 | persistence.ups.mountPath | string | `"/dev/bus/usb/001/001"` | Optional path for ups to mount in the container. |
@@ -104,6 +106,12 @@ All notable changes to this application Helm chart will be documented in this fi
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+### [6.0.0]
+
+#### Changed
+
+- **BREAKING**: Refactored Prometheus metrics section to add rules. Enabling metrics automatically enables the serviceMonitor and exporter sidecar.
+
 ### [5.1.0]
 
 ### Added
@@ -131,6 +139,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 
 - Initial version
 
+[6.0.0]: #600
 [5.1.0]: #510
 [5.0.0]: #500
 [4.0.0]: #400

charts/stable/network-ups-tools/README_CHANGELOG.md.gotmpl

@@ -9,6 +9,12 @@ All notable changes to this application Helm chart will be documented in this fi
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+### [6.0.0]
+
+#### Changed
+
+- **BREAKING**: Refactored Prometheus metrics section to add rules. Enabling metrics automatically enables the serviceMonitor and exporter sidecar.
+
 ### [5.1.0]
 
 ### Added
@@ -36,6 +42,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 
 - Initial version
 
+[6.0.0]: #600
 [5.1.0]: #510
 [5.0.0]: #500
 [4.0.0]: #400

charts/stable/network-ups-tools/templates/common.yaml

@@ -15,22 +15,22 @@ persistence:
         defaultMode: 256
         optional: true
 
-{{ if .Values.exporter.enabled }}
+{{ if .Values.metrics.enabled }}
 additionalContainers:
   exporter:
     name: exporter
-    image: "{{ .Values.exporter.image.repository }}:{{ .Values.exporter.image.tag }}"
+    image: "{{ .Values.metrics.exporter.image.repository }}:{{ .Values.metrics.exporter.image.tag }}"
-    imagePullPolicy: {{ .Values.exporter.image.pullPolicy }}
+    imagePullPolicy: {{ .Values.metrics.exporter.image.pullPolicy }}
     env:
       - name: HTTP_PORT
-        value: "{{ .Values.exporter.env.port }}"
+        value: "{{ .Values.metrics.exporter.env.port }}"
       - name: HTTP_PATH
         value: "/metrics"
       - name: RUST_LOG
-        value: "{{ .Values.exporter.env.logLevel }}"
+        value: "{{ .Values.metrics.exporter.env.logLevel }}"
     ports:
       - name: metrics
-        containerPort: {{ .Values.exporter.env.port }}
+        containerPort: {{ .Values.metrics.exporter.env.port }}
 
 service:
   metrics:
@@ -39,7 +39,7 @@ service:
       metrics:
         enabled: true
         protocol: TCP
-        port: {{ .Values.exporter.env.port }}
+        port: {{ .Values.metrics.exporter.env.port }}
 {{ end }}
 {{- end -}}
 {{- $_ := mergeOverwrite .Values (include "network-ups-tools.harcodedValues" . | fromYaml) -}}

charts/stable/network-ups-tools/templates/prometheusrules.yaml

@@ -0,0 +1,55 @@
+{{- if and .Values.metrics.enabled .Values.metrics.prometheusRule.enabled }}
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: {{ include "common.names.fullname" . }}
+  labels:
+    {{- include "common.labels" . | nindent 4 }}
+    {{- with .Values.metrics.prometheusRule.labels }}
+    {{- toYaml . | nindent 4 }}
+    {{- end }}
+spec:
+  groups:
+    - name: {{ include "common.names.fullname" . }}
+      rules:
+        - alert: NutExporterAbsent
+          annotations:
+            description: NUT Exporter has disappeared from Prometheus target discovery.
+            summary: NUT Exporter is down.
+          expr: |
+            absent(up{job=~".*{{ include "common.names.fullname" . }}.*"} == 1)
+          for: 5m
+          labels:
+            severity: critical
+        - alert: UpsStatusUnknown
+          annotations:
+            description: UPS {{ "{{ $labels.ups }}" }} is reporting a status of unknown.
+            summary: UPS status unknown.
+          expr: |
+            nut_status{job=~".*{{ include "common.names.fullname" . }}.*"} == 0
+          for: 10s
+          labels:
+            severity: critical
+        - alert: UpsOnBattery
+          annotations:
+            description: UPS {{ "{{ $labels.ups }}" }} has lost power and is running on battery.
+            summary: UPS is running on battery.
+          expr: |
+            nut_status{job=~".*{{ include "common.names.fullname" . }}.*"} == 2
+          for: 10s
+          labels:
+            severity: critical
+        - alert: UpsLowBattery
+          annotations:
+            description: UPS {{ "{{ $labels.ups }}" }} battery is low and the system is getting
+              ready to shutdown.
+            summary: UPS battery is low.
+          expr: |
+            nut_status{job=~".*{{ include "common.names.fullname" . }}.*"} == 3
+          for: 5s
+          labels:
+            severity: critical
+        {{- with .Values.metrics.prometheusRule.rules }}
+        {{- toYaml . | nindent 8 }}
+        {{- end }}
+{{- end }}

charts/stable/network-ups-tools/templates/servicemonitor.yaml

@@ -1,11 +1,11 @@
-{{- if .Values.exporter.enabled }}
+{{- if .Values.metrics.enabled }}
 apiVersion: monitoring.coreos.com/v1
 kind: ServiceMonitor
 metadata:
   name: {{ template "common.names.fullname" . }}
   labels:
     {{- include "common.labels" . | nindent 4 }}
-    {{- with .Values.exporter.serviceMonitor.labels }}
+    {{- with .Values.metrics.serviceMonitor.labels }}
     {{- toYaml . | nindent 4 }}
     {{- end }}
 spec:
@@ -14,10 +14,10 @@ spec:
       {{- include "common.labels.selectorLabels" . | nindent 6 }}
   endpoints:
     - port: metrics
-      {{- with .Values.exporter.serviceMonitor.interval }}
+      {{- with .Values.metrics.serviceMonitor.interval }}
       interval: {{ . }}
       {{- end }}
-      {{- with .Values.exporter.serviceMonitor.scrapeTimeout }}
+      {{- with .Values.metrics.serviceMonitor.scrapeTimeout }}
       scrapeTimeout: {{ . }}
       {{- end }}
       path: /metrics

charts/stable/network-ups-tools/values.yaml

@@ -74,7 +74,7 @@ config:
         port = dummy-ups.dev
         desc = "dummy-ups in dummy mode"
 
-exporter:
+metrics:
   # -- Enable and configure prometheus-nut-exporter sidecar and Prometheus serviceMonitor.
   # @default -- See values.yaml
   enabled: false
@@ -82,15 +82,33 @@ exporter:
     interval: 30s
     scrapeTimeout: 10s
     labels: {}
-  image:
+  # -- Enable and configure Prometheus Rules for the chart under this key.
-    # -- image repository
+  # @default -- See values.yaml
-    repository: hon95/prometheus-nut-exporter
+  prometheusRule:
-    # -- image tag
+    enabled: false
-    tag: 1.1.1
+    labels: {}
-    # -- image pull policy
+    # -- Configure additionial rules for the chart under this key.
-    pullPolicy: IfNotPresent
+    # @default -- See prometheusrules.yaml
-  env:
+    rules: []
-    # -- metrics port
+      # - alert: UpsStatusUnknown
-    port: 9995
+      #   annotations:
-    # -- log level [info|debug|trace]
+      #     description: UPS {{ "{{ $labels.ups }}" }} is reporting a status of unknown.
-    logLevel: info
+      #     summary: UPS status unknown.
+      #   expr: |
+      #     nut_status == 0
+      #   for: 10s
+      #   labels:
+      #     severity: critical
+  exporter:
+    image:
+      # -- image repository
+      repository: hon95/prometheus-nut-exporter
+      # -- image tag
+      tag: 1.1.1
+      # -- image pull policy
+      pullPolicy: IfNotPresent
+    env:
+      # -- metrics port
+      port: 9995
+      # -- log level [info|debug|trace]
+      logLevel: info