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>
87 lines
2.5 KiB
YAML
87 lines
2.5 KiB
YAML
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: prometheus
|
|
namespace: observability
|
|
labels:
|
|
app.kubernetes.io/name: prometheus
|
|
app.kubernetes.io/component: metrics
|
|
app.kubernetes.io/part-of: observability
|
|
spec:
|
|
replicas: 1
|
|
strategy:
|
|
# ReadWriteOnce PVC: the old pod must release the volume first.
|
|
type: Recreate
|
|
selector:
|
|
matchLabels:
|
|
app: prometheus
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app: prometheus
|
|
app.kubernetes.io/name: prometheus
|
|
app.kubernetes.io/component: metrics
|
|
app.kubernetes.io/part-of: observability
|
|
annotations:
|
|
prometheus.io/scrape: "true"
|
|
prometheus.io/port: "9090"
|
|
spec:
|
|
serviceAccountName: prometheus
|
|
securityContext:
|
|
runAsUser: 65534
|
|
runAsGroup: 65534
|
|
fsGroup: 65534
|
|
containers:
|
|
- name: prometheus
|
|
image: prom/prometheus:v3.14.0
|
|
args:
|
|
- --config.file=/etc/prometheus/prometheus.yaml
|
|
- --storage.tsdb.path=/prometheus
|
|
- --storage.tsdb.retention.time=15d
|
|
- --storage.tsdb.retention.size=8GB
|
|
- --web.enable-lifecycle
|
|
# Receives remote_write from Tempo's metrics_generator (span metrics + service graphs).
|
|
- --web.enable-remote-write-receiver
|
|
- --web.external-url=https://prometheus.sttlab.local
|
|
- --web.route-prefix=/
|
|
ports:
|
|
- name: http
|
|
containerPort: 9090
|
|
resources:
|
|
requests:
|
|
cpu: 100m
|
|
memory: 512Mi
|
|
limits:
|
|
cpu: "2"
|
|
memory: 2Gi
|
|
readinessProbe:
|
|
httpGet:
|
|
path: /-/ready
|
|
port: http
|
|
initialDelaySeconds: 10
|
|
periodSeconds: 10
|
|
livenessProbe:
|
|
httpGet:
|
|
path: /-/healthy
|
|
port: http
|
|
initialDelaySeconds: 30
|
|
periodSeconds: 30
|
|
volumeMounts:
|
|
- name: config
|
|
mountPath: /etc/prometheus
|
|
- name: data
|
|
mountPath: /prometheus
|
|
- name: librechat-metrics
|
|
mountPath: /etc/prometheus/secrets/librechat
|
|
readOnly: true
|
|
volumes:
|
|
- name: config
|
|
configMap:
|
|
name: prometheus-config
|
|
- name: librechat-metrics
|
|
secret:
|
|
secretName: librechat-metrics
|
|
- name: data
|
|
persistentVolumeClaim:
|
|
claimName: prometheus-data
|