[lidarr] metrics refactor (#1184)

* [lidarr] metrics refactor

* port protocol

* revert scraping intevals after testing

* update docs

charts/stable/lidarr/Chart.yaml

@@ -2,7 +2,7 @@ apiVersion: v2
 appVersion: v1.0.0.2255
 description: Looks and smells like Sonarr but made for music
 name: lidarr
-version: 12.0.1
+version: 13.0.0
 kubeVersion: ">=1.16.0-0"
 keywords:
 - lidarr

charts/stable/lidarr/README.md

@@ -1,6 +1,6 @@
 # lidarr
 
-![Version: 12.0.1](https://img.shields.io/badge/Version-12.0.1-informational?style=flat-square) ![AppVersion: v1.0.0.2255](https://img.shields.io/badge/AppVersion-v1.0.0.2255-informational?style=flat-square)
+![Version: 13.0.0](https://img.shields.io/badge/Version-13.0.0-informational?style=flat-square) ![AppVersion: v1.0.0.2255](https://img.shields.io/badge/AppVersion-v1.0.0.2255-informational?style=flat-square)
 
 Looks and smells like Sonarr but made for music
 
@@ -78,20 +78,22 @@ N/A
 |-----|------|---------|-------------|
 | env | object | See below | environment variables. |
 | env.TZ | string | `"UTC"` | Set the container timezone |
-| exporter.enabled | bool | See values.yaml | Enable and configure Exportarr sidecar and Prometheus podMonitor. |
-| exporter.env.additionalMetrics | bool | `false` | Set to true to enable gathering of additional metrics (slow) |
-| exporter.env.port | int | `32123` | metrics port |
-| exporter.env.unknownQueueItems | bool | `false` | Set to true to enable gathering unknown queue items |
-| exporter.image.pullPolicy | string | `"IfNotPresent"` | image pull policy |
-| exporter.image.repository | string | `"ghcr.io/onedr0p/exportarr"` | image repository |
-| exporter.image.tag | string | `"v0.6.1"` | image tag |
-| exporter.podMonitor.interval | string | `"3m"` |  |
-| exporter.podMonitor.labels | object | `{}` |  |
-| exporter.podMonitor.scrapeTimeout | string | `"1m"` |  |
 | image.pullPolicy | string | `"IfNotPresent"` | image pull policy |
 | image.repository | string | `"ghcr.io/k8s-at-home/lidarr"` | image repository |
 | image.tag | string | `"v1.0.0.2255"` | 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 Exportarr sidecar and Prometheus podMonitor. |
+| metrics.exporter.env.additionalMetrics | bool | `false` | Set to true to enable gathering of additional metrics (slow) |
+| metrics.exporter.env.port | int | `9792` | metrics port |
+| metrics.exporter.env.unknownQueueItems | bool | `false` | Set to true to enable gathering unknown queue items |
+| metrics.exporter.image.pullPolicy | string | `"IfNotPresent"` | image pull policy |
+| metrics.exporter.image.repository | string | `"ghcr.io/onedr0p/exportarr"` | image repository |
+| metrics.exporter.image.tag | string | `"v0.6.1"` | 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. |
 | probes | object | See values.yaml | Configures the probes for the main Pod. |
 | service | object | See values.yaml | Configures service settings for the chart. |
@@ -102,6 +104,12 @@ 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).
 
+### [13.0.0]
+
+#### Changed
+
+- **BREAKING**: Refactored Prometheus metrics section to add rules. Enabling metrics automatically enables the serviceMonitor.
+
 ### [12.0.0]
 
 #### Changed
@@ -134,6 +142,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 
 - Initial version
 
+[13.0.0]: #1300
 [12.0.0]: #1200
 [11.0.0]: #1100
 [10.0.0]: #1000

charts/stable/lidarr/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).
 
+### [13.0.0]
+
+#### Changed
+
+- **BREAKING**: Refactored Prometheus metrics section to add rules. Enabling metrics automatically enables the serviceMonitor and exporter sidecar.
+
 ### [12.0.0]
 
 #### Changed
@@ -41,6 +47,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 
 - Initial version
 
+[13.0.0]: #1300
 [12.0.0]: #1200
 [11.0.0]: #1100
 [10.0.0]: #1000

charts/stable/lidarr/templates/common.yaml

@@ -3,12 +3,12 @@
 
 {{/* Append the hardcoded settings */}}
 {{- define "lidarr.harcodedValues" -}}
-{{ 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 }}
     args: ["exportarr", "lidarr"]
     env:
       - name: URL
@@ -16,20 +16,29 @@ additionalContainers:
       - name: CONFIG
         value: "/config/config.xml"
       - name: PORT
-        value: "{{ .Values.exporter.env.port }}"
+        value: "{{ .Values.metrics.exporter.env.port }}"
       - name: ENABLE_ADDITIONAL_METRICS
-        value: "{{ .Values.exporter.env.additionalMetrics }}"
+        value: "{{ .Values.metrics.exporter.env.additionalMetrics }}"
       - name: ENABLE_UNKNOWN_QUEUE_ITEMS
-        value: "{{ .Values.exporter.env.unknownQueueItems }}"
+        value: "{{ .Values.metrics.exporter.env.unknownQueueItems }}"
     ports:
       - name: metrics
-        containerPort: {{ .Values.exporter.env.port }}
+        containerPort: {{ .Values.metrics.exporter.env.port }}
     volumeMounts:
       {{ if .Values.persistence.config.enabled }}
       - name: config
         mountPath: /config
         readOnly: true
       {{ end }}
+
+service:
+  metrics:
+    enabled: true
+    ports:
+      metrics:
+        enabled: true
+        protocol: TCP
+        port: {{ .Values.metrics.exporter.env.port }}
 {{ end }}
 {{- end -}}
 {{- $_ := mergeOverwrite .Values (include "lidarr.harcodedValues" . | fromYaml) -}}

charts/stable/lidarr/templates/podmonitor.yaml

@@ -1,29 +0,0 @@
-{{- if .Values.exporter.enabled }}
-apiVersion: monitoring.coreos.com/v1
-kind: PodMonitor
-metadata:
-  name: {{ template "common.names.fullname" . }}
-  labels:
-    {{- include "common.labels" . | nindent 4 }}
-    {{- with .Values.exporter.podMonitor.labels }}
-    {{- toYaml . | nindent 4 }}
-    {{- end }}
-spec:
-  selector:
-    matchLabels:
-      {{- include "common.labels.selectorLabels" . | nindent 6 }}
-  podMetricsEndpoints:
-    - port: metrics
-      {{- with .Values.exporter.podMonitor.interval }}
-      interval: {{ . }}
-      {{- end }}
-      {{- with .Values.exporter.podMonitor.scrapeTimeout }}
-      scrapeTimeout: {{ . }}
-      {{- end }}
-      path: /metrics
-      relabelings:
-        - sourceLabels: ['namespace', 'job']
-          regex: ".+/(.*)"
-          targetLabel: "job"
-          replacement: "$1"
-{{- end }}

charts/stable/lidarr/templates/prometheusrules.yaml

@@ -0,0 +1,37 @@
+{{- 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: lidarr
+      rules:
+        - alert: ExportarrAbsent
+          annotations:
+            description: Lidarr Exportarr has disappeared from Prometheus
+              service discovery.
+            summary: Exportarr is down.
+          expr: |
+            absent(up{job=~".*lidarr.*"} == 1)
+          for: 5m
+          labels:
+            severity: critical
+        - alert: LidarrDown
+          annotations:
+            description: Lidarr service is down.
+            summary: Lidarr is down.
+          expr: |
+            lidarr_system_status == 0
+          for: 5m
+          labels:
+            severity: critical
+        {{- with .Values.metrics.prometheusRule.rules }}
+        {{- toYaml . | nindent 8 }}
+        {{- end }}
+{{- end }}

charts/stable/lidarr/templates/servicemonitor.yaml

@@ -0,0 +1,24 @@
+{{- if .Values.metrics.enabled }}
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: {{ include "common.names.fullname" . }}
+  labels:
+    {{- include "common.labels" . | nindent 4 }}
+    {{- with .Values.metrics.serviceMonitor.labels }}
+    {{- toYaml . | nindent 4 }}
+    {{- end }}
+spec:
+  selector:
+    matchLabels:
+      {{- include "common.labels.selectorLabels" . | nindent 6 }}
+  endpoints:
+    - port: metrics
+      {{- with .Values.metrics.serviceMonitor.interval }}
+      interval: {{ . }}
+      {{- end }}
+      {{- with .Values.metrics.serviceMonitor.scrapeTimeout }}
+      scrapeTimeout: {{ . }}
+      {{- end }}
+      path: /metrics
+{{- end }}

charts/stable/lidarr/values.yaml

@@ -57,6 +57,7 @@ probes:
       timeoutSeconds: 10
 
 # -- Configure persistence settings for the chart under this key.
+## Config persistence is required for the Prometheus exporter sidecar.
 # @default -- See values.yaml
 persistence:
   config:
@@ -66,25 +67,43 @@ persistence:
     enabled: false
     mountPath: /media
 
-exporter:
+metrics:
-  # -- Enable and configure Exportarr sidecar and Prometheus podMonitor.
+  # -- Enable and configure Exportarr sidecar and Prometheus serviceMonitor.
   # @default -- See values.yaml
   enabled: false
-  podMonitor:
+  serviceMonitor:
     interval: 3m
     scrapeTimeout: 1m
     labels: {}
-  image:
+  # -- Enable and configure Prometheus Rules for the chart under this key.
-    # -- image repository
+  # @default -- See values.yaml
-    repository: ghcr.io/onedr0p/exportarr
+  prometheusRule:
-    # -- image tag
+    enabled: false
-    tag: v0.6.1
+    labels: {}
-    # -- image pull policy
+    # -- Configure additionial rules for the chart under this key.
-    pullPolicy: IfNotPresent
+    # @default -- See prometheusrules.yaml
-  env:
+    rules: []
-    # -- metrics port
+      # - alert: LidarrDown
-    port: 32123
+      #   annotations:
-    # -- Set to true to enable gathering of additional metrics (slow)
+      #     description: Lidarr service is down.
-    additionalMetrics: false
+      #     summary: Lidarr is down.
-    # -- Set to true to enable gathering unknown queue items
+      #   expr: |
-    unknownQueueItems: false
+      #     lidarr_system_status == 0
+      #   for: 5m
+      #   labels:
+      #     severity: critical
+  exporter:
+    image:
+      # -- image repository
+      repository: ghcr.io/onedr0p/exportarr
+      # -- image tag
+      tag: v0.6.1
+      # -- image pull policy
+      pullPolicy: IfNotPresent
+    env:
+      # -- metrics port
+      port: 9792
+      # -- Set to true to enable gathering of additional metrics (slow)
+      additionalMetrics: false
+      # -- Set to true to enable gathering unknown queue items
+      unknownQueueItems: false