Add Trivy integration to noble cluster setup, including namespace and application configurations. Update README and playbook tags to reflect new security scanning capabilities. Enhance Longhorn and kube-prometheus-stack deployment reliability with increased timeout settings and retry mechanisms.

This commit is contained in:
Nikholas Pcenicni
2026-05-13 23:48:12 -04:00
parent 774b97894c
commit 663ebc5001
16 changed files with 223 additions and 13 deletions

View File

@@ -4,6 +4,14 @@ noble_platform_kubectl_request_timeout: 120s
noble_platform_kustomize_retries: 5
noble_platform_kustomize_delay: 20
# kube-prometheus-stack: operator Deployment uses Kubernetes default progressDeadlineSeconds (600s).
# First install (images + cert-manager webhook TLS) can exceed that; patch + optional rollout restart, then Helm --wait.
noble_platform_kube_prometheus_operator_progress_deadline_seconds: 1800
noble_platform_kube_prometheus_operator_wait_retries: 60
noble_platform_kube_prometheus_operator_wait_delay: 5
# Longhorn PVCs + full stack often need 45-60m; node-exporter DaemonSet can be last at 3/4 until one node catches up.
noble_platform_kube_prometheus_helm_wait_timeout: 60m
# Decrypt **clusters/noble/secrets/*.yaml** with SOPS and kubectl apply (requires **sops**, **age**, and **age-key.txt**).
noble_apply_sops_secrets: true
noble_sops_age_key_file: "{{ noble_repo_root }}/age-key.txt"