Stéphane Tailland
3937b4f366
Deploys the whole stack into the observability namespace of the local cluster with Kustomize alone — no helm install, no dashboard created by hand in the UI. The Makefile carries every command: deploy, dashboards, diagnostics, PVC flush, teardown. Dashboards are files, never UI objects. Each carries a stable uid, which is what keeps URLs, cross-links and alerts alive across redeployments, and references datasources by stable uid rather than by name. The dashboard ConfigMap is generated without a name-suffix hash so applying it updates it in place and Grafana reloads without a restart, while the provisioning ConfigMaps keep their hash precisely so that a change there does force one. Prometheus scrapes the kubelet /metrics/resource endpoint rather than /metrics/cadvisor: on this cluster cadvisor exposes machine_* series only and no container_* at all, which would leave every CPU and memory panel empty. Alloy ships every pod's logs to Loki through the Kubernetes API, so no /var/log mount is needed. Tempo's metrics_generator feeds span metrics and the service graph back into Prometheus, and the datasources are wired so a log line's trace_id opens the matching trace. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
113 lines
3.6 KiB
YAML
113 lines
3.6 KiB
YAML
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: grafana
|
|
namespace: observability
|
|
labels:
|
|
app.kubernetes.io/name: grafana
|
|
app.kubernetes.io/component: ui
|
|
app.kubernetes.io/part-of: observability
|
|
spec:
|
|
replicas: 1
|
|
strategy:
|
|
type: Recreate
|
|
selector:
|
|
matchLabels:
|
|
app: grafana
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app: grafana
|
|
app.kubernetes.io/name: grafana
|
|
app.kubernetes.io/component: ui
|
|
app.kubernetes.io/part-of: observability
|
|
annotations:
|
|
prometheus.io/scrape: "true"
|
|
prometheus.io/port: "3000"
|
|
prometheus.io/path: "/metrics"
|
|
spec:
|
|
securityContext:
|
|
runAsUser: 472
|
|
runAsGroup: 472
|
|
fsGroup: 472
|
|
containers:
|
|
- name: grafana
|
|
image: grafana/grafana:13.2.0
|
|
ports:
|
|
- name: http
|
|
containerPort: 3000
|
|
env:
|
|
- name: GF_SECURITY_ADMIN_USER
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: observability-secrets
|
|
key: GF_SECURITY_ADMIN_USER
|
|
- name: GF_SECURITY_ADMIN_PASSWORD
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: observability-secrets
|
|
key: GF_SECURITY_ADMIN_PASSWORD
|
|
- name: GF_SERVER_ROOT_URL
|
|
value: https://grafana.sttlab.local
|
|
- name: GF_PATHS_PROVISIONING
|
|
value: /etc/grafana/provisioning
|
|
# Everything is driven by the provisioning files, so creating
|
|
# dashboards or datasources from the UI is disabled.
|
|
- name: GF_USERS_ALLOW_SIGN_UP
|
|
value: "false"
|
|
- name: GF_ANALYTICS_REPORTING_ENABLED
|
|
value: "false"
|
|
- name: GF_ANALYTICS_CHECK_FOR_UPDATES
|
|
value: "false"
|
|
- name: GF_ANALYTICS_CHECK_FOR_PLUGIN_UPDATES
|
|
value: "false"
|
|
- name: GF_NEWS_NEWS_FEED_ENABLED
|
|
value: "false"
|
|
- name: GF_LOG_LEVEL
|
|
value: info
|
|
- name: GF_FEATURE_TOGGLES_ENABLE
|
|
value: traceqlEditor,traceQLStreaming,correlations,lokiLogsDataplane
|
|
resources:
|
|
requests:
|
|
cpu: 100m
|
|
memory: 256Mi
|
|
limits:
|
|
cpu: "1"
|
|
memory: 1Gi
|
|
readinessProbe:
|
|
httpGet:
|
|
path: /api/health
|
|
port: http
|
|
initialDelaySeconds: 15
|
|
periodSeconds: 10
|
|
livenessProbe:
|
|
httpGet:
|
|
path: /api/health
|
|
port: http
|
|
initialDelaySeconds: 60
|
|
periodSeconds: 30
|
|
volumeMounts:
|
|
- name: data
|
|
mountPath: /var/lib/grafana
|
|
- name: provisioning-datasources
|
|
mountPath: /etc/grafana/provisioning/datasources
|
|
- name: provisioning-dashboards
|
|
mountPath: /etc/grafana/provisioning/dashboards
|
|
- name: dashboards
|
|
mountPath: /var/lib/grafana/dashboards
|
|
volumes:
|
|
- name: data
|
|
persistentVolumeClaim:
|
|
claimName: grafana-data
|
|
- name: provisioning-datasources
|
|
configMap:
|
|
name: grafana-datasources
|
|
- name: provisioning-dashboards
|
|
configMap:
|
|
name: grafana-dashboard-providers
|
|
- name: dashboards
|
|
# Stable-named ConfigMap: updated in place by `make dashboards` and
|
|
# re-read by Grafana without a restart (~70s: kubelet sync + 10s poll).
|
|
configMap:
|
|
name: grafana-dashboards
|