[speedtest-exporter] metrics refactor (#1183)

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

charts/stable/speedtest-exporter/Chart.yaml

@@ -2,7 +2,7 @@ apiVersion: v2
 appVersion: v3.2.2
 description: Speedtest Exporter made in python using the official speedtest bin
 name: speedtest-exporter
-version: 4.0.1
+version: 5.0.0
 kubeVersion: ">=1.16.0-0"
 keywords:
 - speedtest-exporter

charts/stable/speedtest-exporter/README.md

@@ -1,6 +1,6 @@
 # speedtest-exporter
 
-![Version: 4.0.1](https://img.shields.io/badge/Version-4.0.1-informational?style=flat-square) ![AppVersion: v3.2.2](https://img.shields.io/badge/AppVersion-v3.2.2-informational?style=flat-square)
+![Version: 5.0.0](https://img.shields.io/badge/Version-5.0.0-informational?style=flat-square) ![AppVersion: v3.2.2](https://img.shields.io/badge/AppVersion-v3.2.2-informational?style=flat-square)
 
 Speedtest Exporter made in python using the official speedtest bin
 
@@ -80,7 +80,16 @@ N/A
 | image.pullPolicy | string | `"IfNotPresent"` | image pull policy |
 | image.repository | string | `"ghcr.io/miguelndecarvalho/speedtest-exporter"` | image repository |
 | image.tag | string | `"v3.2.2"` | image tag |
-| prometheus.serviceMonitor | object | See values.yaml | Enable and configure a Prometheus serviceMonitor for the chart under this key. |
+| metrics.enabled | bool | See values.yaml | Enable and configure a Prometheus serviceMonitor for the chart under this key. |
+| metrics.prometheusRule | object | See values.yaml | Enable and configure Prometheus Rules for the chart under this key. |
+| metrics.prometheusRule.downloadLimit | int | `400` | Download speed you want alerts to be triggered in Mbps |
+| metrics.prometheusRule.jitterLimit | int | `30` | Jitter latency you want alerts to be triggered in ms |
+| metrics.prometheusRule.pingLimit | int | `10` | Ping latency you want alerts to be triggered in ms |
+| metrics.prometheusRule.rules | list | See prometheusrules.yaml | Configure additionial rules for the chart under this key. |
+| metrics.prometheusRule.uploadLimit | int | `400` | Upload speed you want alerts to be triggered in Mbps |
+| metrics.serviceMonitor.interval | string | `"1h"` |  |
+| metrics.serviceMonitor.labels | object | `{}` |  |
+| metrics.serviceMonitor.scrapeTimeout | string | `"1m"` |  |
 | service | object | See values.yaml | Configures service settings for the chart. |
 
 ## Changelog
@@ -89,6 +98,12 @@ 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).
 
+### [5.0.0]
+
+#### Changed
+
+- **BREAKING**: Refactored Prometheus metrics section to add rules. Enabling metrics automatically enables the serviceMonitor.
+
 ### [4.0.0]
 
 ##### Changed
@@ -123,6 +138,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 
 - N/A
 
+[5.0.0]: #500
 [4.0.0]: #400
 [3.0.0]: #300
 [2.0.0]: #200

charts/stable/speedtest-exporter/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).
 
+### [5.0.0]
+
+#### Changed
+
+- **BREAKING**: Refactored Prometheus metrics section to add rules. Enabling metrics automatically enables the serviceMonitor.
+
 ### [4.0.0]
 
 ##### Changed
@@ -43,6 +49,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 
 - N/A
 
+[5.0.0]: #500
 [4.0.0]: #400
 [3.0.0]: #300
 [2.0.0]: #200

charts/stable/speedtest-exporter/templates/prometheusrules.yaml

@@ -0,0 +1,67 @@
+{{- 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: SpeedtestExporterAbsent
+          annotations:
+            description: Speedtest Exporter has disappeared from Prometheus target discovery.
+            summary: Speedtest Exporter is down.
+          expr: |
+            absent(up{job=~".*{{ include "common.names.fullname" . }}.*"} == 1)
+          for: {{ .Values.metrics.serviceMonitor.interval }}
+          labels:
+            severity: critical
+        - alert: SpeedtestSlowInternetDownload
+          annotations:
+            description: Internet download speed is averaging {{ "{{ humanize $value }}" }} Mbps.
+            summary: SpeedTest slow internet download.
+          expr: |
+            avg_over_time(speedtest_download{job=~".*{{ include "common.names.fullname" . }}.*"}[4h])
+              < {{ .Values.metrics.prometheusRule.downloadLimit }}
+          for: 0m
+          labels:
+            severity: warning
+        - alert: SpeedtestSlowInternetUpload
+          annotations:
+            description: Internet upload speed is averaging {{ "{{ humanize $value }}" }} Mbps.
+            summary: SpeedTest slow internet upload.
+          expr: |
+            avg_over_time(speedtest_upload{job=~".*{{ include "common.names.fullname" . }}.*"}[4h])
+              < {{ .Values.metrics.prometheusRule.uploadLimit }}
+          for: 0m
+          labels:
+            severity: warning
+        - alert: SpeedtestHighPingLatency
+          annotations:
+            description: Internet ping latency is averaging {{ "{{ humanize $value }}" }} ms.
+            summary: SpeedTest high ping latency.
+          expr: |
+            avg_over_time(speedtest_ping_latency_milliseconds{job=~".*{{ include "common.names.fullname" . }}.*"}[2h])
+              > {{ .Values.metrics.prometheusRule.pingLimit }}
+          for: 0m
+          labels:
+            severity: warning
+        - alert: SpeedtestHighJitterLatency
+          annotations:
+            description: Internet jitter latency is averaging {{ "{{ humanize $value }}" }} ms.
+            summary: SpeedTest high jitter latency.
+          expr: |
+            avg_over_time(speedtest_jitter_latency_milliseconds{job=~".*{{ include "common.names.fullname" . }}.*"}[2h])
+              > {{ .Values.metrics.prometheusRule.jitterLimit }}
+          for: 0m
+          labels:
+            severity: warning
+        {{- with .Values.metrics.prometheusRule.rules }}
+        {{- toYaml . | nindent 8 }}
+        {{- end }}
+{{- end }}

charts/stable/speedtest-exporter/templates/servicemonitor.yaml

@@ -1,11 +1,11 @@
-{{- if .Values.prometheus.serviceMonitor.enabled }}
+{{- 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.prometheus.serviceMonitor.additionalLabels }}
+    {{- 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.prometheus.serviceMonitor.interval }}
+      {{- with .Values.metrics.serviceMonitor.interval }}
       interval: {{ . }}
       {{- end }}
-      {{- with .Values.prometheus.serviceMonitor.scrapeTimeout }}
+      {{- with .Values.metrics.serviceMonitor.scrapeTimeout }}
       scrapeTimeout: {{ . }}
       {{- end }}
       path: /metrics

charts/stable/speedtest-exporter/values.yaml

@@ -31,11 +31,37 @@ service:
         protocol: TCP
         port: 9798
 
-prometheus:
+metrics:
   # -- Enable and configure a Prometheus serviceMonitor for the chart under this key.
   # @default -- See values.yaml
-  serviceMonitor:
   enabled: false
+  serviceMonitor:
     interval: 1h
     scrapeTimeout: 1m
-    additionalLabels: {}
+    labels: {}
+  # -- Enable and configure Prometheus Rules for the chart under this key.
+  # @default -- See values.yaml
+  prometheusRule:
+    enabled: false
+    # -- Download speed you want alerts to be triggered in Mbps
+    downloadLimit: 400
+    # -- Upload speed you want alerts to be triggered in Mbps
+    uploadLimit: 400
+    # -- Ping latency you want alerts to be triggered in ms
+    pingLimit: 10
+    # -- Jitter latency you want alerts to be triggered in ms
+    jitterLimit: 30
+    labels: {}
+    # -- Configure additionial rules for the chart under this key.
+    # @default -- See prometheusrules.yaml
+    rules: []
+      # - alert: SpeedtestSlowInternetDownload
+      #   annotations:
+      #     description: Internet download speed is averaging {{ humanize $value }} Mbps.
+      #     summary: SpeedTest slow internet download.
+      #   expr: |
+      #     avg_over_time(speedtest_download[4h])
+      #       < 420
+      #   for: 0m
+      #   labels:
+      #     severity: warning