Erich Blume
17023085cb
Note: the name of this branch was chosen before the scope widened to encompass the entire observability stack. Summary - Fix Grafana data source URLs (docker driver uses host.minikube.internal, not host.containers.internal) - Migrate Prometheus and Loki from indri to Kubernetes with Tailscale Ingresses - Expose CNPG PostgreSQL metrics via Tailscale and update dashboard to use cnpg_* metrics - Update Alloy to push metrics/logs to k8s endpoints (prometheus.tail8d86e.ts.net, loki.tail8d86e.ts.net) - Add ACL rule for port 9187 (CNPG metrics) - Delete obsolete ansible roles for prometheus and loki Changes - argocd/manifests/prometheus/ - New Prometheus StatefulSet with 20Gi PVC and Tailscale Ingress - argocd/manifests/loki/ - New Loki StatefulSet with 20Gi PVC and Tailscale Ingress - argocd/apps/prometheus.yaml, argocd/apps/loki.yaml - ArgoCD Applications - argocd/manifests/grafana/values.yaml - Data sources now use k8s internal DNS - argocd/manifests/databases/service-metrics-tailscale.yaml - CNPG metrics endpoint - argocd/manifests/grafana-config/dashboards/configmap-postgresql.yaml - Updated to cnpg_* metrics - ansible/roles/alloy/defaults/main.yml - Push to k8s Tailscale endpoints - pulumi/policy.hujson - ACL for port 9187 - Deleted ansible/roles/prometheus/ and ansible/roles/loki/ Deployment and Testing - Stop prometheus and loki on indri - Sync ArgoCD apps (apps, prometheus, loki, grafana) - Run mise run provision-indri -- --tags alloy - Verify Grafana dashboards show data 🤖 Generated with https://claude.ai/claude-code Reviewed-on: https://forge.tail8d86e.ts.net/eblume/blumeops/pulls/42
70 lines
1.6 KiB
YAML
70 lines
1.6 KiB
YAML
# Grafana Helm values for blumeops
|
|
# Chart: https://github.com/grafana/helm-charts/tree/main/charts/grafana
|
|
|
|
# Admin credentials from pre-created secret
|
|
# Secret must exist before deploying - see grafana-config/README.md
|
|
admin:
|
|
existingSecret: grafana-admin
|
|
userKey: admin-user
|
|
passwordKey: admin-password
|
|
|
|
# Persistence with PVC for SQLite database
|
|
persistence:
|
|
enabled: true
|
|
type: pvc
|
|
size: 1Gi
|
|
accessModes:
|
|
- ReadWriteOnce
|
|
|
|
# Grafana configuration via grafana.ini
|
|
grafana.ini:
|
|
server:
|
|
root_url: https://grafana.tail8d86e.ts.net
|
|
analytics:
|
|
check_for_updates: false
|
|
reporting_enabled: false
|
|
|
|
# Datasources - point to k8s-internal services
|
|
datasources:
|
|
datasources.yaml:
|
|
apiVersion: 1
|
|
datasources:
|
|
- name: Prometheus
|
|
type: prometheus
|
|
access: proxy
|
|
orgId: 1
|
|
uid: prometheus
|
|
url: http://prometheus.monitoring.svc.cluster.local:9090
|
|
isDefault: true
|
|
editable: false
|
|
- name: Loki
|
|
type: loki
|
|
access: proxy
|
|
orgId: 1
|
|
uid: loki
|
|
url: http://loki.monitoring.svc.cluster.local:3100
|
|
editable: false
|
|
|
|
# Dashboard provisioning - sidecar watches for ConfigMaps with label
|
|
sidecar:
|
|
dashboards:
|
|
enabled: true
|
|
label: grafana_dashboard
|
|
labelValue: "1"
|
|
folderAnnotation: grafana_folder
|
|
provider:
|
|
foldersFromFilesStructure: false
|
|
|
|
# Service configuration (Ingress will handle external access)
|
|
service:
|
|
type: ClusterIP
|
|
port: 80
|
|
|
|
# Resource limits for minikube
|
|
resources:
|
|
requests:
|
|
memory: "128Mi"
|
|
cpu: "100m"
|
|
limits:
|
|
memory: "512Mi"
|
|
cpu: "500m"
|