Merge pull request #62 from aslafy-z/feat/dashboard-labels

feat: allow deploying dashboard and alerts on existing instances

Author: dannykopping

README.md

@@ -22,7 +22,7 @@ Logs will be scraped from all pods in the Kubernetes cluster.
 
 ```bash
 helm repo add coder-observability https://helm.coder.com/observability
-helm upgrade --install coder-observability coder-observability/coder-observability --version 0.4.3 --namespace coder-observability --create-namespace
+helm upgrade --install coder-observability coder-observability/coder-observability --version 0.5.0 --namespace coder-observability --create-namespace
 ```
 
 ## Requirements
@@ -311,6 +311,8 @@ values which are defined [here](https://github.com/grafana/helm-charts/tree/main
 
 | Key | Type | Default | Description |
 |-----|------|---------|-------------|
+| global.alerts.enabled | bool | `true` | enable or disable alerting |
+| global.alerts.kind | string | `"configmap"` | the container resource kind in which alerts should be created; valid values are "prometheusrule" or "configmap" |
 | global.coder.alerts | object | `{"coderd":{"groups":{"CPU":{"delay":"10m","enabled":true,"period":"10m","thresholds":{"critical":0.9,"warning":0.8}},"IneligiblePrebuilds":{"delay":"10m","enabled":true,"thresholds":{"notify":1}},"Memory":{"delay":"10m","enabled":true,"thresholds":{"critical":0.9,"warning":0.8}},"Replicas":{"delay":"5m","enabled":true,"thresholds":{"critical":1,"notify":3,"warning":2}},"Restarts":{"delay":"1m","enabled":true,"period":"10m","thresholds":{"critical":3,"notify":1,"warning":2}},"UnprovisionedPrebuiltWorkspaces":{"delay":"10m","enabled":true,"thresholds":{"warn":1}},"WorkspaceBuildFailures":{"delay":"10m","enabled":true,"period":"10m","thresholds":{"critical":10,"notify":2,"warning":5}}}},"enterprise":{"groups":{"Licences":{"delay":"1m","enabled":true,"thresholds":{"critical":1,"warning":0.9}}}},"provisionerd":{"groups":{"Replicas":{"delay":"5m","enabled":true,"thresholds":{"critical":1,"notify":3,"warning":2}}}}}` | alerts for the various aspects of Coder |
 | global.coder.coderdSelector | string | `"pod=~`coder.*`, pod!~`.*provisioner.*`"` | series selector for Prometheus/Loki to locate provisioner pods. ensure this uses backticks for quotes! |
 | global.coder.controlPlaneNamespace | string | `"coder"` | the namespace into which the control plane has been deployed. |
@@ -319,7 +321,8 @@ values which are defined [here](https://github.com/grafana/helm-charts/tree/main
 | global.coder.provisionerdSelector | string | `"pod=~`coder-provisioner.*`"` | series selector for Prometheus/Loki to locate provisioner pods. https://coder.com/docs/v2/latest/admin/provisioners TODO: rename container label in provisioner helm chart to be "provisioner" not "coder" ensure this uses backticks for quotes! |
 | global.coder.scrapeMetrics | string | `nil` | use this to scrape metrics from a standalone (set of) coder deployment(s) if using kubernetes, rather add an annotation "prometheus.io/scrape=true" and coder will get automatically scraped; set this value to null and configure coderdSelector to target your coder pods |
 | global.coder.workspacesSelector | string | `"namespace=`coder-workspaces`"` | the namespace into which any external provisioners have been deployed. |
-| global.dashboards | object | `{"queryTimeout":900,"refresh":"30s","timerange":"12h"}` | settings for bundled dashboards |
+| global.dashboards.enabled | bool | `true` | enable or disable the creation of configmaps for dashboards |
+| global.dashboards.labels | string | `nil` | labels to apply to configmaps created for dashboards |
 | global.dashboards.queryTimeout | int | `900` | how long until a query in Grafana will timeout after |
 | global.dashboards.refresh | string | `"30s"` | how often dashboards should refresh |
 | global.dashboards.timerange | string | `"12h"` | how far back dashboards should look |
@@ -358,7 +361,7 @@ values which are defined [here](https://github.com/grafana/helm-charts/tree/main
 | grafana."grafana.ini"."auth.anonymous".org_name | string | `"Main Org."` |  |
 | grafana."grafana.ini"."auth.anonymous".org_role | string | `"Admin"` |  |
 | grafana."grafana.ini".analytics.reporting_enabled | bool | `false` |  |
-| grafana."grafana.ini".dashboards.default_home_dashboard_path | string | `"/var/lib/grafana/dashboards/coder/0/status.json"` |  |
+| grafana."grafana.ini".dashboards.default_home_dashboard_path | string | `"/var/lib/grafana/dashboards/coder/0/coder-status.json"` |  |
 | grafana."grafana.ini".dataproxy.timeout | string | `"{{ $.Values.global.dashboards.queryTimeout }}"` |  |
 | grafana."grafana.ini".feature_toggles.autoMigrateOldPanels | bool | `true` |  |
 | grafana."grafana.ini".users.allow_sign_up | bool | `false` |  |
@@ -442,29 +445,35 @@ values which are defined [here](https://github.com/grafana/helm-charts/tree/main
 | grafana.deploymentStrategy.type | string | `"Recreate"` |  |
 | grafana.enabled | bool | `true` |  |
 | grafana.env.GF_SECURITY_DISABLE_INITIAL_ADMIN_CREATION | bool | `true` |  |
-| grafana.extraConfigmapMounts[0].configMap | string | `"dashboards-status"` |  |
+| grafana.extraConfigmapMounts[0].configMap | string | `"coder-dashboard-status"` |  |
 | grafana.extraConfigmapMounts[0].mountPath | string | `"/var/lib/grafana/dashboards/coder/0"` |  |
-| grafana.extraConfigmapMounts[0].name | string | `"dashboards-status"` |  |
+| grafana.extraConfigmapMounts[0].name | string | `"coder-dashboard-status"` |  |
+| grafana.extraConfigmapMounts[0].optional | bool | `true` |  |
 | grafana.extraConfigmapMounts[0].readOnly | bool | `false` |  |
-| grafana.extraConfigmapMounts[1].configMap | string | `"dashboards-coderd"` |  |
+| grafana.extraConfigmapMounts[1].configMap | string | `"coder-dashboard-coderd"` |  |
 | grafana.extraConfigmapMounts[1].mountPath | string | `"/var/lib/grafana/dashboards/coder/1"` |  |
-| grafana.extraConfigmapMounts[1].name | string | `"dashboards-coderd"` |  |
+| grafana.extraConfigmapMounts[1].name | string | `"coder-dashboard-coderd"` |  |
+| grafana.extraConfigmapMounts[1].optional | bool | `true` |  |
 | grafana.extraConfigmapMounts[1].readOnly | bool | `false` |  |
-| grafana.extraConfigmapMounts[2].configMap | string | `"dashboards-provisionerd"` |  |
+| grafana.extraConfigmapMounts[2].configMap | string | `"coder-dashboard-provisionerd"` |  |
 | grafana.extraConfigmapMounts[2].mountPath | string | `"/var/lib/grafana/dashboards/coder/2"` |  |
-| grafana.extraConfigmapMounts[2].name | string | `"dashboards-provisionerd"` |  |
+| grafana.extraConfigmapMounts[2].name | string | `"coder-dashboard-provisionerd"` |  |
+| grafana.extraConfigmapMounts[2].optional | bool | `true` |  |
 | grafana.extraConfigmapMounts[2].readOnly | bool | `false` |  |
-| grafana.extraConfigmapMounts[3].configMap | string | `"dashboards-workspaces"` |  |
+| grafana.extraConfigmapMounts[3].configMap | string | `"coder-dashboard-workspaces"` |  |
 | grafana.extraConfigmapMounts[3].mountPath | string | `"/var/lib/grafana/dashboards/coder/3"` |  |
-| grafana.extraConfigmapMounts[3].name | string | `"dashboards-workspaces"` |  |
+| grafana.extraConfigmapMounts[3].name | string | `"coder-dashboard-workspaces"` |  |
+| grafana.extraConfigmapMounts[3].optional | bool | `true` |  |
 | grafana.extraConfigmapMounts[3].readOnly | bool | `false` |  |
-| grafana.extraConfigmapMounts[4].configMap | string | `"dashboards-workspace-detail"` |  |
+| grafana.extraConfigmapMounts[4].configMap | string | `"coder-dashboard-workspace-detail"` |  |
 | grafana.extraConfigmapMounts[4].mountPath | string | `"/var/lib/grafana/dashboards/coder/4"` |  |
-| grafana.extraConfigmapMounts[4].name | string | `"dashboards-workspace-detail"` |  |
+| grafana.extraConfigmapMounts[4].name | string | `"coder-dashboard-workspace-detail"` |  |
+| grafana.extraConfigmapMounts[4].optional | bool | `true` |  |
 | grafana.extraConfigmapMounts[4].readOnly | bool | `false` |  |
-| grafana.extraConfigmapMounts[5].configMap | string | `"dashboards-prebuilds"` |  |
+| grafana.extraConfigmapMounts[5].configMap | string | `"coder-dashboard-prebuilds"` |  |
 | grafana.extraConfigmapMounts[5].mountPath | string | `"/var/lib/grafana/dashboards/coder/5"` |  |
-| grafana.extraConfigmapMounts[5].name | string | `"dashboards-prebuilds"` |  |
+| grafana.extraConfigmapMounts[5].name | string | `"coder-dashboard-prebuilds"` |  |
+| grafana.extraConfigmapMounts[5].optional | bool | `true` |  |
 | grafana.extraConfigmapMounts[5].readOnly | bool | `false` |  |
 | grafana.fullnameOverride | string | `"grafana"` |  |
 | grafana.image.tag | string | `"10.4.19"` |  |
@@ -542,9 +551,10 @@ values which are defined [here](https://github.com/grafana/helm-charts/tree/main
 | prometheus.configmapReload.prometheus.containerPort | int | `9091` |  |
 | prometheus.configmapReload.prometheus.extraArgs.log-level | string | `"all"` |  |
 | prometheus.configmapReload.prometheus.extraArgs.watch-interval | string | `"15s"` |  |
-| prometheus.configmapReload.prometheus.extraConfigmapMounts[0].configMap | string | `"metrics-alerts"` |  |
+| prometheus.configmapReload.prometheus.extraConfigmapMounts[0].configMap | string | `"coder-metrics-alerts"` |  |
 | prometheus.configmapReload.prometheus.extraConfigmapMounts[0].mountPath | string | `"/etc/config/alerts"` |  |
 | prometheus.configmapReload.prometheus.extraConfigmapMounts[0].name | string | `"alerts"` |  |
+| prometheus.configmapReload.prometheus.extraConfigmapMounts[0].optional | bool | `true` |  |
 | prometheus.configmapReload.prometheus.extraConfigmapMounts[0].readonly | bool | `true` |  |
 | prometheus.enabled | bool | `true` |  |
 | prometheus.kube-state-metrics.enabled | bool | `true` |  |
@@ -555,9 +565,10 @@ values which are defined [here](https://github.com/grafana/helm-charts/tree/main
 | prometheus.prometheus-node-exporter.podAnnotations."prometheus.io/scrape" | string | `"true"` |  |
 | prometheus.prometheus-pushgateway.enabled | bool | `false` |  |
 | prometheus.server.extraArgs."log.level" | string | `"debug"` |  |
-| prometheus.server.extraConfigmapMounts[0].configMap | string | `"metrics-alerts"` |  |
+| prometheus.server.extraConfigmapMounts[0].configMap | string | `"coder-metrics-alerts"` |  |
 | prometheus.server.extraConfigmapMounts[0].mountPath | string | `"/etc/config/alerts"` |  |
 | prometheus.server.extraConfigmapMounts[0].name | string | `"alerts"` |  |
+| prometheus.server.extraConfigmapMounts[0].optional | bool | `true` |  |
 | prometheus.server.extraConfigmapMounts[0].readonly | bool | `true` |  |
 | prometheus.server.extraFlags[0] | string | `"web.enable-lifecycle"` |  |
 | prometheus.server.extraFlags[1] | string | `"enable-feature=remote-write-receiver"` |  |
@@ -582,6 +593,7 @@ values which are defined [here](https://github.com/grafana/helm-charts/tree/main
 | pyroscope.pyroscope.replicaCount | int | `1` |  |
 | pyroscope.pyroscope.service.port | int | `4040` |  |
 | pyroscope.pyroscope.service.type | string | `"ClusterIP"` |  |
+| runbookViewer.enabled | bool | `true` | enable or disable the runbook viewer |
 | runbookViewer.image | string | `"dannyben/madness"` |  |
 | sqlExporter.enabled | bool | `true` |  |
 | sqlExporter.image | string | `"burningalchemist/sql_exporter"` |  |

coder-observability/Chart.yaml

@@ -2,7 +2,7 @@ apiVersion: v2
 name: coder-observability
 description: Gain insights into your Coder deployment
 type: application
-version: 0.4.3
+version: 0.5.0
 dependencies:
   - name: pyroscope
     condition: pyroscope.enabled

coder-observability/templates/_helpers.tpl

@@ -99,9 +99,13 @@ envFrom:
 {{/* Build a runbook URL */}}
 {{- define "runbook-url" -}}
 {{ $outer := . }}
+{{- if .Values.runbookViewer.enabled -}}
 {{- with .Values.global -}}
   {{- .externalScheme }}://runbook-viewer.{{ $outer.Release.Namespace }}.{{ .externalZone }}/{{- $outer.service }}#{{- $outer.alert | lower }}
 {{- end }}
+{{- else -}}
+https://github.com/coder/observability/blob/main/coder-observability/runbooks/{{- $outer.service }}.md#{{- $outer.alert | lower }}
+{{- end }}
 {{- end }}
 
 {{- define "coderd-selector" -}} {{- printf "%s, namespace=`%s`" .Values.global.coder.coderdSelector .Values.global.coder.controlPlaneNamespace -}} {{- end }}
@@ -121,4 +125,4 @@ envFrom:
 {{- define "grafana-agent-job" -}} {{- printf "%s/%s/%s" .Release.Namespace (index .Values "grafana-agent").fullnameOverride "grafana-agent" -}} {{- end }}
 
 {{- define "dashboard-range" -}} {{ .Values.global.dashboards.timerange }} {{- end }}
-{{- define "dashboard-refresh" -}} {{ .Values.global.dashboards.refresh }} {{- end }}
+{{- define "dashboard-refresh" -}} {{ .Values.global.dashboards.refresh }} {{- end }}