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
66 lines
1.5 KiB
YAML
66 lines
1.5 KiB
YAML
apiVersion: apps/v1
|
|
kind: StatefulSet
|
|
metadata:
|
|
name: loki
|
|
namespace: monitoring
|
|
spec:
|
|
serviceName: loki
|
|
replicas: 1
|
|
selector:
|
|
matchLabels:
|
|
app: loki
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app: loki
|
|
spec:
|
|
securityContext:
|
|
fsGroup: 10001
|
|
runAsNonRoot: true
|
|
runAsUser: 10001
|
|
containers:
|
|
- name: loki
|
|
image: grafana/loki:3.3.2
|
|
args:
|
|
- -config.file=/etc/loki/loki-config.yaml
|
|
ports:
|
|
- name: http
|
|
containerPort: 3100
|
|
- name: grpc
|
|
containerPort: 9096
|
|
volumeMounts:
|
|
- name: config
|
|
mountPath: /etc/loki
|
|
- name: data
|
|
mountPath: /loki
|
|
resources:
|
|
requests:
|
|
memory: "256Mi"
|
|
cpu: "100m"
|
|
limits:
|
|
memory: "1Gi"
|
|
cpu: "500m"
|
|
livenessProbe:
|
|
httpGet:
|
|
path: /ready
|
|
port: 3100
|
|
initialDelaySeconds: 45
|
|
periodSeconds: 10
|
|
readinessProbe:
|
|
httpGet:
|
|
path: /ready
|
|
port: 3100
|
|
initialDelaySeconds: 10
|
|
periodSeconds: 5
|
|
volumes:
|
|
- name: config
|
|
configMap:
|
|
name: loki-config
|
|
volumeClaimTemplates:
|
|
- metadata:
|
|
name: data
|
|
spec:
|
|
accessModes: ["ReadWriteOnce"]
|
|
resources:
|
|
requests:
|
|
storage: 20Gi
|