infrastructure

# 1. Create the namespace + secret
kubectl create namespace monitoring
kubectl create secret generic grafana-cloud-secret \
  -n monitoring --from-literal=api-key=<your-api-key>
 
# 2. Install — values.yaml in references/k8s-monitoring-values.md
helm repo add grafana https://grafana.github.io/helm-charts && helm repo update
helm install k8s-monitoring grafana/k8s-monitoring \
  --version 4.1.4 -n monitoring -f values.yaml
 
# 3. Verify every pod is Running
kubectl get pods -n monitoring
# Expect alloy-*, kube-state-metrics-*, node-exporter-*, etc. all Ready.
 
# 4. Verify no error logs in the metrics/logs/traces Alloys
kubectl -n monitoring logs deploy/k8s-monitoring-alloy-metrics --tail=50 | grep -iE 'error|level=err' || echo "clean"
 
# 5. Verify telemetry landed in Grafana Cloud
#    PromQL on the metrics datasource (should be > 0):
#      sum(up{cluster="production-us-east"})
#    LogQL on Loki:
#      sum(count_over_time({cluster="production-us-east"}[5m]))

# 1. /etc/alloy/config.alloy — see references/clouds-and-hosts.md for the full block
prometheus.exporter.unix "host"  { rootfs_path = "/" }
prometheus.scrape         "node" { targets = prometheus.exporter.unix.host.targets
                                   forward_to = [prometheus.remote_write.cloud.receiver] }

# 2. Reload Alloy and verify the unix exporter is up
systemctl reload alloy
curl -s http://localhost:12345/api/v0/web/components | jq '.[] | select(.id|contains("prometheus.exporter.unix"))'
 
# 3. Verify in Grafana Cloud — open the "Node Exporter Full" dashboard (ID 1860)
#    and pick your host from the `instance` dropdown.

# 1. After provisioning, restart Grafana to pick up the file
# 2. Verify the datasource — Grafana → Connections → Data sources → "Test"
#    Expect "Successfully queried the CloudWatch metrics API" (or equivalent).
# 3. Confirm a query — Explore → datasource → metric e.g.
#    CloudWatch namespace AWS/EC2 metric CPUUtilization, last 1h.