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>
89 lines
2.2 KiB
YAML
89 lines
2.2 KiB
YAML
apiVersion: networking.k8s.io/v1
|
|
kind: Ingress
|
|
metadata:
|
|
name: grafana
|
|
namespace: observability
|
|
labels:
|
|
app.kubernetes.io/name: grafana
|
|
app.kubernetes.io/part-of: observability
|
|
annotations:
|
|
nginx.ingress.kubernetes.io/proxy-body-size: "20m"
|
|
nginx.ingress.kubernetes.io/proxy-read-timeout: "600"
|
|
nginx.ingress.kubernetes.io/proxy-send-timeout: "600"
|
|
nginx.ingress.kubernetes.io/proxy-http-version: "1.1"
|
|
# Required for TraceQL streaming and Loki live tail.
|
|
nginx.ingress.kubernetes.io/proxy-buffering: "off"
|
|
spec:
|
|
ingressClassName: nginx
|
|
tls:
|
|
- hosts:
|
|
- grafana.sttlab.local
|
|
secretName: observability-tls
|
|
rules:
|
|
- host: grafana.sttlab.local
|
|
http:
|
|
paths:
|
|
- path: /
|
|
pathType: Prefix
|
|
backend:
|
|
service:
|
|
name: grafana
|
|
port:
|
|
number: 3000
|
|
---
|
|
# Exposed for diagnostics (targets, TSDB status, expression browser).
|
|
apiVersion: networking.k8s.io/v1
|
|
kind: Ingress
|
|
metadata:
|
|
name: prometheus
|
|
namespace: observability
|
|
labels:
|
|
app.kubernetes.io/name: prometheus
|
|
app.kubernetes.io/part-of: observability
|
|
annotations:
|
|
nginx.ingress.kubernetes.io/proxy-read-timeout: "600"
|
|
spec:
|
|
ingressClassName: nginx
|
|
tls:
|
|
- hosts:
|
|
- prometheus.sttlab.local
|
|
secretName: observability-tls
|
|
rules:
|
|
- host: prometheus.sttlab.local
|
|
http:
|
|
paths:
|
|
- path: /
|
|
pathType: Prefix
|
|
backend:
|
|
service:
|
|
name: prometheus
|
|
port:
|
|
number: 9090
|
|
---
|
|
# Alloy UI: state of the log collection pipeline components.
|
|
apiVersion: networking.k8s.io/v1
|
|
kind: Ingress
|
|
metadata:
|
|
name: alloy
|
|
namespace: observability
|
|
labels:
|
|
app.kubernetes.io/name: alloy
|
|
app.kubernetes.io/part-of: observability
|
|
spec:
|
|
ingressClassName: nginx
|
|
tls:
|
|
- hosts:
|
|
- alloy.sttlab.local
|
|
secretName: observability-tls
|
|
rules:
|
|
- host: alloy.sttlab.local
|
|
http:
|
|
paths:
|
|
- path: /
|
|
pathType: Prefix
|
|
backend:
|
|
service:
|
|
name: alloy
|
|
port:
|
|
number: 12345
|