Merge fix/split-horizon-dns: in-cluster split-horizon DNS (R-DNS-01/03) — unblocks SSO

2026-08-24 22:29:59 -05:00
commit 3b97f5f058
@@ -0,0 +1,88 @@
+# =============================================================================
+# L2 BEHAVIORAL — split-horizon INTERNAL resolution  (R-DNS-01 / R-DNS-03)   [RUNNABLE]
+# Catalog: docs/14 "DNS/exposure (R-DNS-*)"
+# Spec:    docs/09 "Split-horizon resolution (R-DNS-03)" — internal clients resolve
+#          <svc>.home.keithjackson.dev to the INTERNAL Gateway VIP, not the public hairpin.
+# Impl:    platform/coredns/coredns-custom.yaml (k3s CoreDNS `import *.server`; template plugin
+#          answers the whole home.keithjackson.dev zone with ${GATEWAY_VIP}).
+#
+# GIVEN the split-horizon coredns-custom ConfigMap is reconciled into k3s CoreDNS,
+# WHEN  an in-cluster pod resolves a platform hostname over its PUBLIC name
+#       (keycloak.home.keithjackson.dev) using the default cluster resolver (CoreDNS 10.43.0.10),
+# THEN  the answer is the in-cluster Gateway VIP (the L2-announced LB range 10.73.0.24x) — NOT a
+#       public/off-cluster IP. This is what lets pod->public-hostname traffic hairpin through the
+#       Gateway with the correct SNI (*.home.keithjackson.dev) so the wildcard cert validates
+#       (R-DNS-01 "services reachable at <svc>.home..."; R-DNS-03 split-horizon).
+#
+# Complements dns-exposure (R-DNS-02, the EXTERNAL/public-record side). Together they cover the
+# split-horizon pair: external answer = public record (R-DNS-02); internal answer = Gateway VIP
+# (R-DNS-01/03).
+#
+# CLEANUP: chainsaw deletes the per-test namespace (Job included) at teardown. Read-only otherwise.
+# chainsaw v0.2.12: Job + status assert; no test-level finally.
+# =============================================================================
+apiVersion: chainsaw.kyverno.io/v1alpha1
+kind: Test
+metadata:
+  name: dns-internal-resolution
+  labels:
+    conformance.home.k3s/R-DNS-01: "true"
+    conformance.home.k3s/R-DNS-03: "true"
+  annotations:
+    conformance.home.k3s/requirements: "R-DNS-01,R-DNS-03"
+    conformance.home.k3s/layer: "L2"
+    conformance.home.k3s/safety-critical: "false"
+    conformance.home.k3s/executable: "true"
+    conformance.home.k3s/intent: >-
+      An in-cluster pod resolving keycloak.home.keithjackson.dev via cluster DNS gets the internal
+      Gateway VIP (10.73.0.24x), not the public hairpin — split-horizon in-cluster resolution.
+spec:
+  timeouts:
+    apply: 60s
+    assert: 2m
+    exec: 2m
+  steps:
+    - name: then-cluster-dns-answers-with-the-internal-gateway-vip
+      try:
+        - apply:
+            resource:
+              apiVersion: batch/v1
+              kind: Job
+              metadata:
+                name: dns-internal-probe
+              spec:
+                backoffLimit: 2
+                activeDeadlineSeconds: 100
+                template:
+                  spec:
+                    restartPolicy: Never
+                    containers:
+                      - name: probe
+                        image: busybox:1.36.1
+                        command:
+                          - sh
+                          - -c
+                          - |
+                            set -u
+                            host="keycloak.home.keithjackson.dev"
+                            # Resolve via the DEFAULT cluster resolver (CoreDNS, /etc/resolv.conf ->
+                            # 10.43.0.10). Split-horizon must answer with the in-cluster Gateway VIP
+                            # (L2 pool 10.73.0.24x), proving pods hairpin through the Gateway.
+                            out="$(nslookup "$host" 2>/dev/null)"
+                            echo "$out"
+                            ip="$(echo "$out" | awk '/^Address: /{print $2}' | grep -E '^10\.73\.0\.24[0-9]$' | head -1)"
+                            if [ -n "$ip" ]; then
+                              echo "INTERNAL_RESOLUTION_OK $host -> $ip (in-cluster Gateway VIP)"
+                              exit 0
+                            fi
+                            echo "FAIL: $host did not resolve to the in-cluster Gateway VIP (10.73.0.24x);"
+                            echo "      split-horizon coredns-custom not in effect (got a public/off-cluster answer)."
+                            exit 1
+        - assert:
+            resource:
+              apiVersion: batch/v1
+              kind: Job
+              metadata:
+                name: dns-internal-probe
+              status:
+                succeeded: 1