Erich Blume
483db74a3c
Adds smartctl_exporter alongside the existing node_exporter on sifaka, routed through Caddy L4 TCP proxy at nas.ops.eblu.me, with a Grafana dashboard for disk health visibility. Introduces the first Ansible playbook for sifaka (mise run provision-sifaka) and shared exporter port variables in group_vars/all.yml. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
46 lines
1.3 KiB
YAML
46 lines
1.3 KiB
YAML
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: prometheus-config
|
|
namespace: monitoring
|
|
data:
|
|
prometheus.yml: |
|
|
global:
|
|
scrape_interval: 15s
|
|
evaluation_interval: 15s
|
|
|
|
# Indri system metrics are pushed via Alloy remote_write
|
|
# K8s services are scraped directly
|
|
|
|
scrape_configs:
|
|
# Sifaka NAS exporters (via Caddy L4 TCP proxy on indri)
|
|
- job_name: "node-exporter-sifaka"
|
|
static_configs:
|
|
- targets: ["nas.ops.eblu.me:9100"]
|
|
|
|
- job_name: "smartctl-sifaka"
|
|
scrape_interval: 60s
|
|
static_configs:
|
|
- targets: ["nas.ops.eblu.me:9633"]
|
|
|
|
# CNPG PostgreSQL metrics (k8s internal)
|
|
- job_name: "cnpg-postgres"
|
|
static_configs:
|
|
- targets: ["blumeops-pg-metrics-tailscale.databases.svc.cluster.local:9187"]
|
|
labels:
|
|
instance: "blumeops-pg"
|
|
|
|
# Prometheus self-monitoring
|
|
- job_name: "prometheus"
|
|
static_configs:
|
|
- targets: ["localhost:9090"]
|
|
|
|
# Loki metrics
|
|
- job_name: "loki"
|
|
static_configs:
|
|
- targets: ["loki.monitoring.svc.cluster.local:3100"]
|
|
|
|
# Kubernetes state metrics (pods, deployments, resource usage, etc.)
|
|
- job_name: "kube-state-metrics"
|
|
static_configs:
|
|
- targets: ["kube-state-metrics.monitoring.svc.cluster.local:8080"]
|