refactor(k8s): consolidate to infra/+apps/ single-source tree, dedicated per-app CNPG (authentik-db/temporal-db), wire monitoring-config, forgejo→cicd ns, drop orphan/stale (data-schemas, ollama, story-crater, sqs/argocd, key-rotation)

2026-08-18 15:08:03 -07:00
parent 54fa540b33
commit 41f5b05395
241 changed files with 467 additions and 10416 deletions
@@ -0,0 +1,58 @@
+# k8s/portainer/portainer-values.yaml
+# Portainer — web UI for browsing cluster workloads, exec-ing into pods,
+# and viewing logs without kubectl. Operator-only access (ClusterIP + port-forward).
+#
+# Node failure behaviour:
+#   Portainer is a Deployment (not StatefulSet), so K8s auto-evicts and
+#   reschedules it ~5 min after a node becomes unreachable. Longhorn
+#   reattaches the PVC on the new node in ~1-2 min. Worst case: ~7-10 min.
+#
+#   To cut that down: in Longhorn UI → Settings set
+#     nodeDownPodDeletionPolicy = delete-deployment-pod
+#   Longhorn will force-delete the stuck pod immediately when the node is
+#   fenced rather than waiting for Kubernetes' eviction timeout.
+
+# ── Service ───────────────────────────────────────────────────────────────────
+# ClusterIP — no external exposure. Access via:
+#   kubectl -n dashboard port-forward svc/portainer 9000:9000
+# Portainer holds cluster-admin credentials; never expose as LoadBalancer.
+service:
+  type: ClusterIP
+
+# ── TLS ───────────────────────────────────────────────────────────────────────
+# Portainer by default redirects HTTP → HTTPS using a self-signed cert.
+# force: false disables the redirect so plain HTTP over port-forward works
+# without browser cert warnings. TLS is terminated at the ingress layer
+# if/when an ingress rule is added.
+tls:
+  force: false
+
+# ── Persistence ───────────────────────────────────────────────────────────────
+# Stores Portainer's own config: environment registrations, user accounts,
+# stack definitions, and access control settings. Longhorn provides the
+# RWO block volume. 10Gi is generous for config data but cheap on Longhorn.
+persistence:
+  enabled: true
+  storageClass: "longhorn-wffc"
+  size: 10Gi
+
+resources:
+  requests:
+    cpu: 100m
+    memory: 128Mi
+  limits:
+    cpu: 500m
+    memory: 512Mi
+
+# ── Scheduling ────────────────────────────────────────────────────────────────
+# Allow scheduling on talos-cp-1 (carries NoSchedule taint) so Portainer
+# keeps running even when the worker node is down.
+tolerations:
+  - key: node-role.kubernetes.io/control-plane
+    operator: Exists
+    effect: NoSchedule
+
+# Pin to az-a (talos-cp-1) — sole Longhorn storage node. Its RWO PVC can only
+# attach there; without this the pod may land on cp-2/cp-3 and fail to mount.
+nodeSelector:
+  topology.kubernetes.io/zone: az-a