Fix validate-except syntax: trailing semicolon after last entry

named requires every entry in the list to be semicolon-terminated, including the last one before the closing brace; without it named fails config parse (missing ';' before '}') and crash-loops.
Exempt internal split-horizon zones from resolver DNSSEC validation
2026-07-12 22:21:22 +10:00 · 2026-07-12 22:13:50 +10:00 · 2026-07-12 21:43:03 +10:00 · 2026-07-12 19:12:39 +10:00 · 2026-07-12 18:41:08 +10:00 · 2026-07-12 18:39:13 +10:00
76 changed files with 879 additions and 365 deletions
@@ -79,7 +79,7 @@ spec:
      cpu: 500m
      memory: 512Mi
    requests:
-      cpu: 250m
+      cpu: 50m
      memory: 256Mi
  smartShutdownTimeout: 180
  startDelay: 3600
@@ -79,7 +79,7 @@ spec:
      cpu: 500m
      memory: 512Mi
    requests:
-      cpu: 250m
+      cpu: 50m
      memory: 256Mi
  smartShutdownTimeout: 180
  startDelay: 3600
@@ -31,7 +31,7 @@ spec:
      external-dns.alpha.kubernetes.io/hostname: bind-authoritative-primary.k8s.syd1.au.unkin.net
  resources:
    requests:
-      cpu: 100m
+      cpu: 20m
      memory: 128Mi
    limits:
      cpu: "1"
@@ -9,3 +9,16 @@ metadata:
 spec:
  clusterRef: bind-authoritative
  algorithm: hmac-sha256
+---
+# Client-update key: puppet clients (profiles::dns::updater) nsupdate their own
+# records to the authoritative zones with this key. Operator generates the
+# material into Secret client-update-tsig; the same value must reach puppet
+# eyaml (or the planned Vault-sync bridge) for clients to authenticate.
+apiVersion: bind.unkin.net/v1alpha1
+kind: BindTSIGKey
+metadata:
+  name: client-update
+  namespace: bind-internal
+spec:
+  clusterRef: bind-authoritative
+  algorithm: hmac-sha256
@@ -15,6 +15,8 @@ spec:
  zoneName: unkin.net
  type: primary
  defaultTTL: 600
+  dynamicUpdate: true
+  updateKeyRef: client-update
 ---
 apiVersion: bind.unkin.net/v1alpha1
 kind: BindZone
@@ -26,6 +28,8 @@ spec:
  zoneName: main.unkin.net
  type: primary
  defaultTTL: 600
+  dynamicUpdate: true
+  updateKeyRef: client-update
 ---
 apiVersion: bind.unkin.net/v1alpha1
 kind: BindZone
@@ -37,6 +41,8 @@ spec:
  zoneName: 13.18.198.in-addr.arpa
  type: primary
  defaultTTL: 600
+  dynamicUpdate: true
+  updateKeyRef: client-update
 ---
 apiVersion: bind.unkin.net/v1alpha1
 kind: BindZone
@@ -48,6 +54,8 @@ spec:
  zoneName: 14.18.198.in-addr.arpa
  type: primary
  defaultTTL: 600
+  dynamicUpdate: true
+  updateKeyRef: client-update
 ---
 apiVersion: bind.unkin.net/v1alpha1
 kind: BindZone
@@ -59,6 +67,8 @@ spec:
  zoneName: 15.18.198.in-addr.arpa
  type: primary
  defaultTTL: 600
+  dynamicUpdate: true
+  updateKeyRef: client-update
 ---
 apiVersion: bind.unkin.net/v1alpha1
 kind: BindZone
@@ -70,6 +80,8 @@ spec:
  zoneName: 16.18.198.in-addr.arpa
  type: primary
  defaultTTL: 600
+  dynamicUpdate: true
+  updateKeyRef: client-update
 ---
 apiVersion: bind.unkin.net/v1alpha1
 kind: BindZone
@@ -81,6 +93,8 @@ spec:
  zoneName: 17.18.198.in-addr.arpa
  type: primary
  defaultTTL: 600
+  dynamicUpdate: true
+  updateKeyRef: client-update
 ---
 apiVersion: bind.unkin.net/v1alpha1
 kind: BindZone
@@ -92,6 +106,8 @@ spec:
  zoneName: 19.18.198.in-addr.arpa
  type: primary
  defaultTTL: 600
+  dynamicUpdate: true
+  updateKeyRef: client-update
 ---
 apiVersion: bind.unkin.net/v1alpha1
 kind: BindZone
@@ -103,6 +119,8 @@ spec:
  zoneName: 20.18.198.in-addr.arpa
  type: primary
  defaultTTL: 600
+  dynamicUpdate: true
+  updateKeyRef: client-update
 ---
 apiVersion: bind.unkin.net/v1alpha1
 kind: BindZone
@@ -114,6 +132,8 @@ spec:
  zoneName: 21.18.198.in-addr.arpa
  type: primary
  defaultTTL: 600
+  dynamicUpdate: true
+  updateKeyRef: client-update
 ---
 apiVersion: bind.unkin.net/v1alpha1
 kind: BindZone
@@ -125,6 +145,8 @@ spec:
  zoneName: 22.18.198.in-addr.arpa
  type: primary
  defaultTTL: 600
+  dynamicUpdate: true
+  updateKeyRef: client-update
 ---
 apiVersion: bind.unkin.net/v1alpha1
 kind: BindZone
@@ -136,6 +158,8 @@ spec:
  zoneName: 23.18.198.in-addr.arpa
  type: primary
  defaultTTL: 600
+  dynamicUpdate: true
+  updateKeyRef: client-update
 ---
 apiVersion: bind.unkin.net/v1alpha1
 kind: BindZone
@@ -147,6 +171,8 @@ spec:
  zoneName: 24.18.198.in-addr.arpa
  type: primary
  defaultTTL: 600
+  dynamicUpdate: true
+  updateKeyRef: client-update
 ---
 apiVersion: bind.unkin.net/v1alpha1
 kind: BindZone
@@ -158,6 +184,8 @@ spec:
  zoneName: 25.18.198.in-addr.arpa
  type: primary
  defaultTTL: 600
+  dynamicUpdate: true
+  updateKeyRef: client-update
 ---
 apiVersion: bind.unkin.net/v1alpha1
 kind: BindZone
@@ -169,6 +197,8 @@ spec:
  zoneName: 26.18.198.in-addr.arpa
  type: primary
  defaultTTL: 600
+  dynamicUpdate: true
+  updateKeyRef: client-update
 ---
 apiVersion: bind.unkin.net/v1alpha1
 kind: BindZone
@@ -180,6 +210,8 @@ spec:
  zoneName: 27.18.198.in-addr.arpa
  type: primary
  defaultTTL: 600
+  dynamicUpdate: true
+  updateKeyRef: client-update
 ---
 apiVersion: bind.unkin.net/v1alpha1
 kind: BindZone
@@ -191,6 +223,8 @@ spec:
  zoneName: 28.18.198.in-addr.arpa
  type: primary
  defaultTTL: 600
+  dynamicUpdate: true
+  updateKeyRef: client-update
 ---
 apiVersion: bind.unkin.net/v1alpha1
 kind: BindZone
@@ -202,3 +236,5 @@ spec:
  zoneName: 29.18.198.in-addr.arpa
  type: primary
  defaultTTL: 600
+  dynamicUpdate: true
+  updateKeyRef: client-update
@@ -23,7 +23,7 @@ spec:
    type: ClusterIP
  resources:
    requests:
-      cpu: 100m
+      cpu: 20m
      memory: 128Mi
    limits:
      cpu: "1"
@@ -7,3 +7,4 @@ resources:
  - authoritative
  - resolvers
  - externaldns
+  - tsig-api
@@ -21,9 +21,18 @@ spec:
  forwarders:
    - 8.8.8.8
    - 1.1.1.1
+  # The internal split-horizon zones are served UNSIGNED by the in-cluster
+  # authoritative, but their public parents publish DS records (e.g. unkin.net
+  # is DNSSEC-signed on the Internet). With dnssec-validation on, the validator
+  # sees "parent indicates secure" but gets an insecure answer and returns
+  # SERVFAIL (broken trust chain). Treat the forwarded internal domains as
+  # insecure so they are not validated. unkin.net covers all *.unkin.net
+  # (incl. k8s.syd1.au.unkin.net); 18.198.in-addr.arpa covers every reverse zone.
+  extraOptions:
+    - "validate-except { unkin.net; 18.198.in-addr.arpa; consul; }"
  resources:
    requests:
-      cpu: 100m
+      cpu: 20m
      memory: 128Mi
    limits:
      cpu: "1"
@@ -3,4 +3,4 @@ apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization

 resources:
-  - ../../../base/jellyfin
+  - tsig-api.yaml
@@ -0,0 +1,27 @@
+---
+# Companion TSIG API. The operator reconciles this into a Deployment, Service,
+# ConfigMap, master-token Secret and namespaced RBAC. vault-plugin-secrets-bind-tsig
+# calls it to create/rotate/delete TSIG keys, which it does by managing
+# BindTSIGKey resources in this namespace (the operator reconciles the material).
+#
+# The master access token Secret (bind-tsig-api-token) is generated by the
+# operator if absent; a VaultStaticSecret may later pre-seed/overwrite it so the
+# token is sourced from Vault rather than generated in-cluster.
+apiVersion: bind.unkin.net/v1alpha1
+kind: BindTSIGAPI
+metadata:
+  name: bind-tsig-api
+  namespace: bind-internal
+spec:
+  image: git.unkin.net/unkin/bind-tsig-api:v0.2.1
+  replicas: 1
+  port: 8443
+  # targetNamespace defaults to this resource's namespace (bind-internal), where
+  # the authoritative cluster and its keys live.
+  resources:
+    requests:
+      cpu: 25m
+      memory: 64Mi
+    limits:
+      cpu: 250m
+      memory: 128Mi
@@ -21,7 +21,7 @@ spec:
        runAsNonRoot: true
      containers:
        - name: operator
-          image: git.unkin.net/unkin/bind-operator:v0.1.5
+          image: git.unkin.net/unkin/bind-operator:v0.2.1
          args:
            - --metrics-bind-address=:8080
            - --health-probe-bind-address=:8081
@@ -6,6 +6,6 @@ resources:
  - namespace.yaml
  # CRDs are pulled from the bind-operator repo at the matching tag rather than
  # vendored here, so they never drift from the operator.
-  - https://git.unkin.net/unkin/bind-operator/raw/tag/v0.1.5/config/crd/install.yaml
+  - https://git.unkin.net/unkin/bind-operator/raw/tag/v0.2.1/config/crd/install.yaml
  - rbac.yaml
  - deployment.yaml
@@ -23,7 +23,15 @@ rules:
    resources: ["pods/exec"]
    verbs: ["create", "get"]
  - apiGroups: ["apps"]
-    resources: ["statefulsets"]
+    resources: ["statefulsets", "deployments"]
+    verbs: ["get", "list", "watch", "create", "update", "patch", "delete"]
+  # The BindTSIGAPI reconciler deploys the companion API: a ServiceAccount plus
+  # a namespaced Role/RoleBinding granting it access to BindTSIGKey + Secrets.
+  - apiGroups: [""]
+    resources: ["serviceaccounts"]
+    verbs: ["get", "list", "watch", "create", "update", "patch", "delete"]
+  - apiGroups: ["rbac.authorization.k8s.io"]
+    resources: ["roles", "rolebindings"]
    verbs: ["get", "list", "watch", "create", "update", "patch", "delete"]
  - apiGroups: [""]
    resources: ["events"]
@@ -7,3 +7,4 @@ resources:
  - serviceaccount.yaml
  - clusterrole.yaml
  - clusterrolebinding.yaml
+  - vmservicescrape.yaml
@@ -0,0 +1,17 @@
+---
+# Scrape cert-manager webhook + cainjector metrics endpoints.
+# Picked up by the observability VMAgent (selectAllByDefault).
+apiVersion: operator.victoriametrics.com/v1beta1
+kind: VMServiceScrape
+metadata:
+  name: cert-manager
+  namespace: cert-manager
+spec:
+  selector:
+    matchLabels:
+      app.kubernetes.io/instance: cert-manager
+  endpoints:
+    - port: metrics
+      path: /metrics
+    - port: http-metrics
+      path: /metrics
@@ -7,3 +7,4 @@ resources:
  - vaultauth.yaml
  - vaultstaticsecret.yaml
  - storageclass.yaml
+  - vmservicescrape.yaml
@@ -0,0 +1,15 @@
+---
+# Scrape the ceph-csi-cephfs nodeplugin + provisioner http-metrics endpoints.
+# Picked up by the observability VMAgent (selectAllByDefault).
+apiVersion: operator.victoriametrics.com/v1beta1
+kind: VMServiceScrape
+metadata:
+  name: ceph-csi-cephfs
+  namespace: csi-cephfs
+spec:
+  selector:
+    matchLabels:
+      app: ceph-csi-cephfs
+  endpoints:
+    - port: http-metrics
+      path: /metrics
@@ -7,3 +7,4 @@ resources:
  - vaultauth.yaml
  - vaultstaticsecret.yaml
  - storageclass.yaml
+  - vmservicescrape.yaml
@@ -0,0 +1,15 @@
+---
+# Scrape the ceph-csi-rbd nodeplugin + provisioner http-metrics endpoints.
+# Picked up by the observability VMAgent (selectAllByDefault).
+apiVersion: operator.victoriametrics.com/v1beta1
+kind: VMServiceScrape
+metadata:
+  name: ceph-csi-rbd
+  namespace: csi-cephrbd
+spec:
+  selector:
+    matchLabels:
+      app: ceph-csi-rbd
+  endpoints:
+    - port: http-metrics
+      path: /metrics
@@ -79,7 +79,7 @@ spec:
      cpu: 500m
      memory: 512Mi
    requests:
-      cpu: 250m
+      cpu: 50m
      memory: 256Mi
  smartShutdownTimeout: 180
  startDelay: 3600
@@ -0,0 +1,58 @@
+---
+apiVersion: postgresql.cnpg.io/v1
+kind: Cluster
+metadata:
+  name: postgres
+  namespace: grafana
+spec:
+  affinity:
+    podAntiAffinityType: preferred
+  bootstrap:
+    initdb:
+      database: grafana
+      encoding: UTF8
+      localeCType: C
+      localeCollate: C
+      owner: grafana
+      secret:
+        name: postgres-credentials
+  enablePDB: true
+  enableSuperuserAccess: false
+  failoverDelay: 0
+  imageName: ghcr.io/cloudnative-pg/postgresql:18.1-system-trixie
+  instances: 2
+  logLevel: info
+  monitoring:
+    customQueriesConfigMap:
+      - key: queries
+        name: cnpg-default-monitoring
+    disableDefaultQueries: false
+    enablePodMonitor: false
+  postgresql:
+    parameters:
+      max_connections: "200"
+      shared_buffers: 128MB
+  primaryUpdateMethod: restart
+  primaryUpdateStrategy: unsupervised
+  replicationSlots:
+    highAvailability:
+      enabled: true
+      slotPrefix: _cnpg_
+    synchronizeReplicas:
+      enabled: true
+    updateInterval: 30
+  resources:
+    limits:
+      cpu: 500m
+      memory: 512Mi
+    requests:
+      cpu: 50m
+      memory: 256Mi
+  smartShutdownTimeout: 180
+  startDelay: 3600
+  stopDelay: 1800
+  storage:
+    resizeInUseVolumes: true
+    size: 10Gi
+    storageClass: cephrbd-fast-delete
+  switchoverDelay: 3600
@@ -0,0 +1,33 @@
+---
+apiVersion: postgresql.cnpg.io/v1
+kind: Pooler
+metadata:
+  name: postgres-pooler-rw
+  namespace: grafana
+spec:
+  cluster:
+    name: postgres
+  instances: 2
+  pgbouncer:
+    parameters:
+      default_pool_size: "50"
+      max_client_conn: "200"
+    paused: false
+    poolMode: session
+  template:
+    metadata:
+      labels:
+        app: pooler-rw
+    spec:
+      affinity:
+        podAntiAffinity:
+          requiredDuringSchedulingIgnoredDuringExecution:
+            - labelSelector:
+                matchExpressions:
+                  - key: app
+                    operator: In
+                    values:
+                      - pooler-rw
+              topologyKey: kubernetes.io/hostname
+      containers: []
+  type: rw
@@ -0,0 +1,13 @@
+---
+apiVersion: grafana.integreatly.org/v1beta1
+kind: GrafanaDashboard
+metadata:
+  name: bind9-exporter-dns
+  namespace: grafana
+spec:
+  instanceSelector:
+    matchLabels:
+      dashboards: "grafana"
+  resyncPeriod: 5m
+  allowCrossNamespaceImport: false
+  gzipJson: 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
@@ -0,0 +1,13 @@
+---
+apiVersion: grafana.integreatly.org/v1beta1
+kind: GrafanaDashboard
+metadata:
+  name: frr-ospf-route-metrics
+  namespace: grafana
+spec:
+  instanceSelector:
+    matchLabels:
+      dashboards: "grafana"
+  resyncPeriod: 5m
+  allowCrossNamespaceImport: false
+  gzipJson: H4sIAAycS2oC/+1ZbW/bNhD+KwJRFC0gF7brZkGAfXDcZgiQpkFcbNiawqCkk82FJjWScuIK/u+7o14sN0lXB0nRJfliS5TIe+655046sWBcKe24E1pZtlcwKaxje58KFuVCukPF9nohS7jjVucmBrrFLTP8Z1PDU644C1kuEjzvdILfyqGg02GrkIHikcQ7nckhZDORNMci1mqkpTY4zUwj/qIbBv1eD3/evAmD3ktcU/E5GRmu0QXPg6EE4yxerSAk3M4izU3CVp/JYCJc22QqbMzln8DN2HHj3mvlZmyvGxL0bPZRa+lE5gekUOfo/qfPIcu4Amk9BakAmYy0SsWU/E4g5bl0nqY5zzKhptUcNzNgZ1om5TVNnjIeWS1zBwjXOsjKJePK66kBUHhlwWWON3dX4fqagWR9ZbeLrqFvegHGIIXe4opcEMmJ9vbQp9chu2B7g5BdeneWfkVGYcHo6ayJrjfxvsRXGqjIqMaUVjT0d26dSJfVYAzKgcFhbQQe+miQf7nTOJiBoRtGM66mMGqtbx1XCcUmJI/yGD60cHAZkydMcpTb57CkGkdY7Tkep1xaQDeQ2YuTtpXqEvIOl66yVqHZPhLEdpv9ryLT88q6QOaP+FLnrtQWDmUynwr1Oxhb0tHrv+q96hIEbqbgSiPtxGHPWmco1suMzKXGTNC0hNhpM8mzojn59Yxpm6VnLBSKuIwBR57Vx2ds5YlNDyn3hpgAaFk4Ej/7MD45CEb1OgGK3+WtrMEFnHf5/6nvwYa+d7bSNzfAr+i7ks49qftYu+NcyrsU+f2q0eC6MHFYduUkFVHBU4HCE9ligFJcmJRUiH+30OXhyWIQnNLyNhAqODjcfzCi3N0Q5S9PovxRoty5A1HuPFBRlpXydSXKwZMo70+U91MlH1h5rJX45kmJP0KJd1kat1NipZpGdhmX4Bx0YiTXipiawxjDqed0D78Udl+bBMwY+WwopOGR7zwg+QuM3rzQiipxzcrhIx6BLGNFpyeSxzDHNdZhiLgZSjFV5WjXD/whEjc74PSujEOv8I0yMfxi7JaeBGwNiexUSPkh47FwKORe2UMmJL7Nzom63ANTOiZhCipZa6LuN6vzhfiylhKGA1tbEp1tbiDLh0RApmUtcRrj1IvRgQfO9vooJS2UG4sv4JOLul54i428EVFeTmy69mqBWr00j9StYOFbPIvt7yYKjHd8jmWF1piizjIvk7AOrfd71S43FXFN8HWaMqoWP1l52vXlqd9t9cw7VX3qb9SnOozrGoHwE2Ezyetq5D+aUEKv9RZpR/ouaT6qlqgSv1FC4fVC6l7zXVFhkSrpidDGNTzfbdWg9nKiQEzxI4qxxXfWipKPA23mnIAVhUjR7dV/tKPHtZkgWgZe1TRrXVacmAOmgMBoPaLikpX591V5+amqS+8OqkvFz6MuLr1BVV1eP6bqQi9vE2n5ROXzCEzx3WXlI73LBEfjYVAUtMjX9SW8JQxwF9qcbw3nuJx3E6D9WwPiNjJboxmO909vgjK6PTf2FnE6HiOMG6C83RYKocCCC0Zhmx/rnMrT90N5V80kOC0U764+jAjviJa3Tw+gpwfQQ3wA7Vx9APX71QNo95E8gGyMXxFgkuTGy2tiAbcdE1ts8WrbbMZ84/X24PS0vdnijQZvK6PX1xfaZjQgNV+nD65NkiGPu5SPNp7BnDc8DHrEgJcXGcQbqJDhH7XnpF8CBPOMMqlUc7ORG+fG+KAVPhFjmScwxI8bteVqp3WDxX9yMEsqD5jr4Gbgt48aiL3WBmwzyQu2MVXWLYwzEC9BTfNaxozS6htxvBloa60apqTKOCk/z7y42tmEjf2X17tRrnO9B1XlbyGvR27rADZY22DH278Nm7Kf1JWJ+BxMGWc6/0I5halq9IX1zX1bsf45+Lz8uhO8B6ylsW228hFGh2B0TP3xZ1ELsb/6F7MoRVUzIAAA
@@ -0,0 +1,13 @@
+---
+apiVersion: grafana.integreatly.org/v1beta1
+kind: GrafanaDashboard
+metadata:
+  name: gitea
+  namespace: grafana
+spec:
+  instanceSelector:
+    matchLabels:
+      dashboards: "grafana"
+  resyncPeriod: 5m
+  allowCrossNamespaceImport: false
+  gzipJson: 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
@@ -0,0 +1,13 @@
+---
+apiVersion: grafana.integreatly.org/v1beta1
+kind: GrafanaDashboard
+metadata:
+  name: nzbget
+  namespace: grafana
+spec:
+  instanceSelector:
+    matchLabels:
+      dashboards: "grafana"
+  resyncPeriod: 5m
+  allowCrossNamespaceImport: false
+  gzipJson: H4sIAAycS2oC/+1X227bRhD9FWIfCqegDcmNAtdAH2wHLgzErgEZDVpbMJbkiNx4uUvsDq0blG/vzHJFybHbpg3aIkBfJHEvczlz5gy1EtIYixKVNV4cr4RWHsXx7UpkrdJ4YcTxMBWFROlt63LgI7ho6FuUTk6lkSIVrSroeX8/+bFbSvb3xToVYGSm6SS6FlJRqaL/rXJrzqy2jq65MpN7gzQ5HA7pYzRKk+ErsmlkzU5OttEl3yQnGhx62o0hFNJXmZWuEOsJOywU7rqcKp9L/QtIN0bp8NIarMTxIOXQm+rGWo2qCQlqZR4o/dtJKhppQPsAwYtpN87WgBW0vs+8ADxcjEaFzF9/eMg59akCXZxZM1UlXy1gKluNAeC8y3slalsEe1IDIuznWnqvwu289WhrPiPnyp9aV4AbV3YmjqdSe0qMl8/AIDgofgVnn26wg8vOOMIcRbf8TmagaSk+XmuZQ002aEm2aGk5k+5Eq9J0q4Ow8F4VWJ3LHDnmwcEb4oKTszEuGGWGDQRnq/VPjcwVLjbwFoqMxCCMDaeYAOeuy0tDCabow8ZNKeLzo1rG34SGMp6qftVqrko8wI4vOP/G6sCOGIx0otsMcYfSNlYZHKslRTJKBRMC3hLHncra7mJf2WiAXHoC+5rveQ4fHoHNemLG0yg8yvxBmVDi0tm2YcLSyXonb7KGlQOyqAsfcetrb6dTsd7Q5VKZSznvjdeyach2ZOXWxs51mXmrW2RwPULTkTbyiwICMLTzKHVLhw1Fvk6328Sc7ebRIPRPaxTT4ZQs0ZOltB3VrDNbS8wrCMQNnM8WV9yhdKyJ2iFuqFN1clMREmXVtMhGqFsaqp6KVsLVLoTe+YrSn0Nx9kncMcewxyBtLofeOOBadWju2GE5IDfDQTocTDpaRpEgA5OQYkkZXdsAIh09SgU11eHrVMwDcZm+zLgiMKfPbMtXwk/qnHMR1K54ZQMvOVqQIWgVPqmM5L9QvtFysWnFoEyEyE7jOVVW3J/Mt3fRBUvXeqcl+mp7YkOw4K3Dnl58VLoS8Esli6LlCG9IMd6TPPY8ZFHt9STnL1qbN1wq5STCnllm5P7ewMzfU6cSa+6RmXCfLRD8qlv64eOdOPj2TqxvR/WE9X1KuF0CyjG1XF713pTJdVvAVdzldPqhYajfGLaNBgTAzq0jalIwq+hpvSbrTpqyHwMOphdFbM3Wwyk17VZ8mFh/H7SXwYGaiuy2CHZo+bbe+xzEAkKv7ozYzMwemj/M/1n3/Q4KpzQriTMKg4J3oSRv3yXjBqBIskVy7ewj+XXbMYuqBoqTm/jL4PoqxyIvj+0USZ83U/H/MfmfjMl/fSR+MgU/a4AcxQFy+CcD5NmACG/eT+dDZpEZ/xUNCP7X0GlHVL2odVwsWdzntjX4T6j/SY7qERLSFgN5h/pfmgLPJfFFiy8I4iSYZirSxjAUi16UavkzOB8a57vvuQI9a8NwwNgO8d8WE4tthpeh0PtUvNn+m4pd2u5JxDONosBZKePzkqtMwDs7851oP8mjLyjA4GFp1AezHJSDnIm+CZC6fwbwEP4jsRKufwNsYW6gFQ4AAA==
@@ -0,0 +1,13 @@
+---
+apiVersion: grafana.integreatly.org/v1beta1
+kind: GrafanaDashboard
+metadata:
+  name: puppet-report
+  namespace: grafana
+spec:
+  instanceSelector:
+    matchLabels:
+      dashboards: "grafana"
+  resyncPeriod: 5m
+  allowCrossNamespaceImport: false
+  gzipJson: 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
@@ -2,36 +2,38 @@
 apiVersion: gateway.networking.k8s.io/v1
 kind: Gateway
 metadata:
+  name: grafana
+  namespace: grafana
  labels:
+    app.kubernetes.io/name: grafana
+    app.kubernetes.io/instance: grafana
    traefik.io/instance: internal
  annotations:
    cert-manager.io/cluster-issuer: vault-issuer
-    cert-manager.io/common-name: jellyfin.k8s.syd1.au.unkin.net
+    cert-manager.io/common-name: grafana.k8s.syd1.au.unkin.net
    cert-manager.io/private-key-size: "4096"
-    external-dns.alpha.kubernetes.io/hostname: jellyfin.k8s.syd1.au.unkin.net
+    external-dns.alpha.kubernetes.io/hostname: grafana.k8s.syd1.au.unkin.net
    external-dns.alpha.kubernetes.io/target: 198.18.200.4
-  name: jellyfin
-  namespace: jellyfin
 spec:
  gatewayClassName: traefik-internal
  listeners:
-    - allowedRoutes:
-        namespaces:
-          from: Same
-      hostname: jellyfin.k8s.syd1.au.unkin.net
-      name: http
+    - name: http
      port: 80
      protocol: HTTP
-    - allowedRoutes:
+      hostname: grafana.k8s.syd1.au.unkin.net
+      allowedRoutes:
        namespaces:
          from: Same
-      hostname: jellyfin.k8s.syd1.au.unkin.net
-      name: https
+    - name: https
      port: 443
      protocol: HTTPS
+      hostname: grafana.k8s.syd1.au.unkin.net
+      allowedRoutes:
+        namespaces:
+          from: Same
      tls:
+        mode: Terminate
        certificateRefs:
          - group: ""
            kind: Secret
-            name: jellyfin-tls
-        mode: Terminate
+            name: grafana-tls
@@ -0,0 +1,60 @@
+---
+apiVersion: grafana.integreatly.org/v1beta1
+kind: Grafana
+metadata:
+  name: grafana
+  namespace: grafana
+  labels:
+    dashboards: "grafana"
+spec:
+  deployment:
+    spec:
+      template:
+        spec:
+          containers:
+            - name: grafana
+              env:
+                # DB password + OAuth client secret injected from the
+                # Vault-synced secrets (GF_ env overrides grafana.ini).
+                - name: GF_DATABASE_PASSWORD
+                  valueFrom:
+                    secretKeyRef:
+                      name: postgres-credentials
+                      key: password
+                - name: GF_AUTH_GENERIC_OAUTH_CLIENT_SECRET
+                  valueFrom:
+                    secretKeyRef:
+                      name: oauth-credentials
+                      key: client_secret
+              resources:
+                requests:
+                  cpu: 100m
+                  memory: 256Mi
+                limits:
+                  cpu: "1"
+                  memory: 1Gi
+  config:
+    server:
+      root_url: "https://grafana.k8s.syd1.au.unkin.net"
+    database:
+      type: "postgres"
+      host: "postgres-pooler-rw.grafana.svc.cluster.local:5432"
+      name: "grafana"
+      user: "grafana"
+      ssl_mode: "require"
+    auth:
+      disable_login_form: "false"
+      oauth_auto_login: "false"
+    "auth.generic_oauth":
+      enabled: "true"
+      name: "Authentik"
+      allow_sign_up: "true"
+      use_pkce: "true"
+      client_id: "grafana"
+      scopes: "openid email profile"
+      auth_url: "https://identity.unkin.net/application/o/authorize/"
+      token_url: "https://identity.unkin.net/application/o/token/"
+      api_url: "https://identity.unkin.net/application/o/userinfo/"
+      # Authentik groups -> Grafana roles (adjust group name as needed).
+      role_attribute_path: "contains(groups[*], 'grafana-admins') && 'Admin' || 'Viewer'"
+      role_attribute_strict: "false"
@@ -0,0 +1,22 @@
+---
+apiVersion: grafana.integreatly.org/v1beta1
+kind: GrafanaDatasource
+metadata:
+  name: victoriametrics
+  namespace: grafana
+spec:
+  instanceSelector:
+    matchLabels:
+      dashboards: "grafana"
+  # uid matches the previous default datasource so the imported dashboards
+  # (which hardcode this uid or use the default) resolve without edits.
+  datasource:
+    name: "VictoriaMetrics"
+    type: "prometheus"
+    uid: "det2y55dac4jkc"
+    access: "proxy"
+    url: "http://vmselect-main.observability.svc.cluster.local:8481/select/0/prometheus"
+    isDefault: true
+    jsonData:
+      timeInterval: "15s"
+      httpMethod: "POST"
@@ -2,15 +2,18 @@
 apiVersion: gateway.networking.k8s.io/v1
 kind: HTTPRoute
 metadata:
-  name: http-redirect
-  namespace: jellyfin
+  name: grafana-http-redirect
+  namespace: grafana
+  labels:
+    app.kubernetes.io/name: grafana
+    app.kubernetes.io/instance: grafana
 spec:
  hostnames:
-    - jellyfin.k8s.syd1.au.unkin.net
+    - grafana.k8s.syd1.au.unkin.net
  parentRefs:
    - group: gateway.networking.k8s.io
      kind: Gateway
-      name: jellyfin
+      name: grafana
      sectionName: http
  rules:
    - filters:
@@ -26,22 +29,25 @@ spec:
 apiVersion: gateway.networking.k8s.io/v1
 kind: HTTPRoute
 metadata:
-  name: jellyfin-route
-  namespace: jellyfin
+  name: grafana
+  namespace: grafana
+  labels:
+    app.kubernetes.io/name: grafana
+    app.kubernetes.io/instance: grafana
 spec:
  hostnames:
-    - jellyfin.k8s.syd1.au.unkin.net
+    - grafana.k8s.syd1.au.unkin.net
  parentRefs:
    - group: gateway.networking.k8s.io
      kind: Gateway
-      name: jellyfin
+      name: grafana
      sectionName: https
  rules:
    - backendRefs:
        - group: ""
          kind: Service
-          name: jellyfin
-          port: 8096
+          name: grafana-service
+          port: 3000
          weight: 1
      matches:
        - path:
@@ -0,0 +1,28 @@
+---
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+resources:
+  - namespace.yaml
+  - cnpg_cluster.yaml
+  - cnpg_pooler.yaml
+  - vaultauth.yaml
+  - vaultstaticsecret.yaml
+  - grafana.yaml
+  - grafanadatasource.yaml
+  - gateway.yaml
+  - httproute.yaml
+  - dashboards/bind9-exporter-dns.yaml
+  - dashboards/ceph-cluster.yaml
+  - dashboards/frr-ospf-route-metrics.yaml
+  - dashboards/gitea.yaml
+  - dashboards/haproxy.yaml
+  - dashboards/media-dashboard.yaml
+  - dashboards/node-exporter-full.yaml
+  - dashboards/nzbget.yaml
+  - dashboards/postgresql-database.yaml
+  - dashboards/puppet-report.yaml
+  - dashboards/victorialogs-cluster.yaml
+  - dashboards/victoriametrics-cluster.yaml
+  - dashboards/victoriametrics-vmagent.yaml
+  - dashboards/cloudnativepg.yaml
@@ -0,0 +1,7 @@
+---
+apiVersion: v1
+kind: Namespace
+metadata:
+  labels:
+    app.kubernetes.io/name: grafana
+  name: grafana
@@ -0,0 +1,18 @@
+---
+apiVersion: secrets.hashicorp.com/v1beta1
+kind: VaultAuth
+metadata:
+  name: default
+  namespace: grafana
+spec:
+  allowedNamespaces:
+    - grafana
+  kubernetes:
+    audiences:
+      - vault
+    role: default
+    serviceAccount: default
+    tokenExpirationSeconds: 600
+  method: kubernetes
+  mount: k8s/au/syd1
+  vaultConnectionRef: vso-system/default
@@ -0,0 +1,34 @@
+---
+apiVersion: secrets.hashicorp.com/v1beta1
+kind: VaultStaticSecret
+metadata:
+  name: postgres-credentials
+  namespace: grafana
+spec:
+  destination:
+    create: true
+    name: postgres-credentials
+    overwrite: true
+  hmacSecretData: true
+  mount: kv
+  path: kubernetes/namespace/grafana/default/postgres-credentials
+  refreshAfter: 5m
+  type: kv-v2
+  vaultAuthRef: default
+---
+apiVersion: secrets.hashicorp.com/v1beta1
+kind: VaultStaticSecret
+metadata:
+  name: oauth-credentials
+  namespace: grafana
+spec:
+  destination:
+    create: true
+    name: oauth-credentials
+    overwrite: true
+  hmacSecretData: true
+  mount: kv
+  path: kubernetes/namespace/grafana/default/oauth-credentials
+  refreshAfter: 5m
+  type: kv-v2
+  vaultAuthRef: default
@@ -1,80 +0,0 @@
---
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: jellyfin
-  namespace: jellyfin
-spec:
-  # Start single-replica. Scaling to >1 (true HA) is a follow-up once the Redis
-  # transcode store and RWX transcode scratch are validated end-to-end.
-  replicas: 1
-  strategy:
-    # Config PVC is RWO; a Recreate rollout avoids two pods contending for it.
-    type: Recreate
-  selector:
-    matchLabels:
-      app: jellyfin
-  template:
-    metadata:
-      labels:
-        app: jellyfin
-    spec:
-      containers:
-        - name: jellyfin
-          image: git.unkin.net/unkin/jellyfin-ha:v0.1.0
-          imagePullPolicy: IfNotPresent
-          ports:
-            - name: http
-              containerPort: 8096
-              protocol: TCP
-          env:
-            # Distributed transcode session store (jellyfin-ha additions).
-            - name: Jellyfin__TranscodeStore__RedisConnectionString
-              value: "redis:6379,abortConnect=false"
-            - name: Jellyfin__TranscodeStore__LeaseDurationSeconds
-              value: "30"
-          livenessProbe:
-            httpGet:
-              path: /health
-              port: http
-            initialDelaySeconds: 30
-            periodSeconds: 30
-            timeoutSeconds: 5
-            failureThreshold: 3
-          readinessProbe:
-            httpGet:
-              path: /health
-              port: http
-            initialDelaySeconds: 10
-            periodSeconds: 10
-            timeoutSeconds: 5
-            failureThreshold: 3
-          resources:
-            requests:
-              cpu: "1"
-              memory: 1Gi
-            limits:
-              cpu: "4"
-              memory: 6Gi
-          volumeMounts:
-            - name: config
-              mountPath: /config
-            - name: cache
-              mountPath: /cache
-            - name: transcode
-              mountPath: /transcode
-            - name: media
-              mountPath: /media
-              readOnly: true
-      volumes:
-        - name: config
-          persistentVolumeClaim:
-            claimName: jellyfin-config
-        - name: cache
-          emptyDir: {}
-        - name: transcode
-          persistentVolumeClaim:
-            claimName: jellyfin-transcode
-        - name: media
-          persistentVolumeClaim:
-            claimName: jellyfin-media
@@ -1,16 +0,0 @@
---
-apiVersion: kustomize.config.k8s.io/v1beta1
-kind: Kustomization
-
-resources:
-  - namespace.yaml
-  - pvc-config.yaml
-  - pvc-transcode.yaml
-  - pvc-media.yaml
-  - deployment.yaml
-  - service.yaml
-  - redis-deployment.yaml
-  - redis-pvc.yaml
-  - redis-service.yaml
-  - gateway.yaml
-  - httproute.yaml
@@ -1,5 +0,0 @@
---
-apiVersion: v1
-kind: Namespace
-metadata:
-  name: jellyfin
@@ -1,15 +0,0 @@
---
-# Jellyfin config + SQLite library database. Single-writer, block storage.
-apiVersion: v1
-kind: PersistentVolumeClaim
-metadata:
-  name: jellyfin-config
-  namespace: jellyfin
-spec:
-  accessModes:
-    - ReadWriteOnce
-  resources:
-    requests:
-      storage: 20Gi
-  storageClassName: cephrbd-fast-retain
-  volumeMode: Filesystem
@@ -1,17 +0,0 @@
---
-# Media library, shared read-many across replicas. Retain — this holds the
-# actual media and must survive PVC deletion. Empty on first deploy; populating
-# it is out of scope for this app.
-apiVersion: v1
-kind: PersistentVolumeClaim
-metadata:
-  name: jellyfin-media
-  namespace: jellyfin
-spec:
-  accessModes:
-    - ReadWriteMany
-  resources:
-    requests:
-      storage: 1Ti
-  storageClassName: cephfs-raid6-retain
-  volumeMode: Filesystem
@@ -1,17 +0,0 @@
---
-# Shared transcode scratch. ReadWriteMany is the hard requirement for the HA
-# fork: a taking-over pod must read the in-flight HLS segments written by the
-# pod it replaces. Scratch data, so delete reclaim policy.
-apiVersion: v1
-kind: PersistentVolumeClaim
-metadata:
-  name: jellyfin-transcode
-  namespace: jellyfin
-spec:
-  accessModes:
-    - ReadWriteMany
-  resources:
-    requests:
-      storage: 100Gi
-  storageClassName: cephfs-raid6-delete
-  volumeMode: Filesystem
@@ -1,66 +0,0 @@
---
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: redis
-  namespace: jellyfin
-spec:
-  replicas: 1
-  selector:
-    matchLabels:
-      app: redis
-  strategy:
-    type: Recreate
-  template:
-    metadata:
-      labels:
-        app: redis
-    spec:
-      containers:
-        - name: redis
-          image: redis:7-alpine
-          imagePullPolicy: IfNotPresent
-          command:
-            - redis-server
-            - --save
-            - "20"
-            - "1"
-          ports:
-            - containerPort: 6379
-              name: redis
-              protocol: TCP
-          livenessProbe:
-            exec:
-              command:
-                - redis-cli
-                - ping
-            failureThreshold: 3
-            initialDelaySeconds: 30
-            periodSeconds: 30
-            successThreshold: 1
-            timeoutSeconds: 5
-          readinessProbe:
-            exec:
-              command:
-                - redis-cli
-                - ping
-            failureThreshold: 3
-            initialDelaySeconds: 5
-            periodSeconds: 10
-            successThreshold: 1
-            timeoutSeconds: 5
-          resources:
-            limits:
-              cpu: 500m
-              memory: 512Mi
-            requests:
-              cpu: 50m
-              memory: 128Mi
-          volumeMounts:
-            - mountPath: /data
-              name: data
-      restartPolicy: Always
-      volumes:
-        - name: data
-          persistentVolumeClaim:
-            claimName: jellyfin-redis-data
@@ -1,14 +0,0 @@
---
-apiVersion: v1
-kind: PersistentVolumeClaim
-metadata:
-  name: jellyfin-redis-data
-  namespace: jellyfin
-spec:
-  accessModes:
-    - ReadWriteOnce
-  resources:
-    requests:
-      storage: 5Gi
-  storageClassName: cephrbd-fast-delete
-  volumeMode: Filesystem
@@ -1,17 +0,0 @@
---
-apiVersion: v1
-kind: Service
-metadata:
-  name: redis
-  namespace: jellyfin
-spec:
-  internalTrafficPolicy: Cluster
-  ports:
-    - name: redis
-      port: 6379
-      protocol: TCP
-      targetPort: redis
-  selector:
-    app: redis
-  sessionAffinity: None
-  type: ClusterIP
@@ -1,17 +0,0 @@
---
-apiVersion: v1
-kind: Service
-metadata:
-  name: jellyfin
-  namespace: jellyfin
-spec:
-  internalTrafficPolicy: Cluster
-  ports:
-    - name: http
-      port: 8096
-      protocol: TCP
-      targetPort: http
-  selector:
-    app: jellyfin
-  sessionAffinity: None
-  type: ClusterIP
@@ -79,7 +79,7 @@ spec:
      cpu: "1"
      memory: 1Gi
    requests:
-      cpu: 250m
+      cpu: 50m
      memory: 512Mi
  smartShutdownTimeout: 180
  startDelay: 3600
@@ -8,3 +8,4 @@ resources:
  - vmagent.yaml
  - gateway.yaml
  - httproute.yaml
+  - vmpodscrape-cnpg.yaml
@@ -16,7 +16,7 @@ spec:
    - url: http://vminsert-main.observability.svc.cluster.local:8480/insert/0/prometheus/
  resources:
    requests:
-      cpu: 500m
+      cpu: 250m
      memory: 512Mi
    limits:
      cpu: "1"
@@ -99,6 +99,10 @@ spec:
      consul_sd_configs:
        - server: consul.service.consul:443
          scheme: https
+          # Set datacenter explicitly so VM does not call /v1/agent/self
+          # (which needs agent:read that the anonymous token lacks); catalog
+          # and health reads work anonymously.
+          datacenter: au-syd1
          tls_config:
            ca_file: /etc/vmagent-tls/ca.crt
      relabel_configs:
@@ -23,7 +23,7 @@ spec:
              storage: 200Gi
    resources:
      requests:
-        cpu: "1"
+        cpu: 250m
        memory: 2Gi
      limits:
        cpu: "2"
@@ -0,0 +1,17 @@
+---
+# Scrape metrics (:9187) from every CloudNativePG postgres instance pod in any
+# namespace. Picked up by the observability VMAgent (selectAllByDefault).
+apiVersion: operator.victoriametrics.com/v1beta1
+kind: VMPodScrape
+metadata:
+  name: cnpg-clusters
+  namespace: observability
+spec:
+  namespaceSelector:
+    any: true
+  selector:
+    matchLabels:
+      cnpg.io/podRole: instance
+  podMetricsEndpoints:
+    - port: metrics
+      path: /metrics
@@ -79,7 +79,7 @@ spec:
      cpu: 500m
      memory: 512Mi
    requests:
-      cpu: 250m
+      cpu: 50m
      memory: 256Mi
  smartShutdownTimeout: 180
  startDelay: 3600
@@ -100,7 +100,7 @@ spec:
      cpu: 500m
      memory: 512Mi
    requests:
-      cpu: 250m
+      cpu: 50m
      memory: 256Mi
  smartShutdownTimeout: 180
  startDelay: 3600
@@ -47,7 +47,7 @@ spec:
                  cpu: 300m
                  memory: 1Gi
                requests:
-                  cpu: 200m
+                  cpu: 50m
                  memory: 512Mi
              securityContext:
                runAsUser: 0
@@ -148,7 +148,7 @@ spec:
          resources:
            requests:
              memory: 350Mi
-              cpu: 100m
+              cpu: 50m
            limits:
              memory: 1024Mi
              cpu: 500m
@@ -38,8 +38,8 @@ spec:
              cpu: 1
              memory: 1536Mi
            requests:
-              cpu: 250m
-              memory: 512Mi
+              cpu: 50m
+              memory: 768Mi
          ports:
            - containerPort: 8080
              name: pdb-http
@@ -34,7 +34,7 @@ spec:
            cpu: 2
            memory: 3072Mi
          requests:
-            cpu: 500m
+            cpu: 200m
            memory: 1024Mi
        ports:
        - containerPort: 8140
@@ -38,7 +38,7 @@ spec:
              cpu: 2
              memory: 3500Mi
            requests:
-              cpu: 250m
+              cpu: 100m
              memory: 1024Mi
          ports:
            - containerPort: 8140
@@ -83,7 +83,7 @@ server:
      cpu: "2"
      memory: 2Gi
    requests:
-      cpu: 250m
+      cpu: 50m
      memory: 512Mi

 worker:
@@ -95,7 +95,7 @@ worker:
      cpu: "2"
      memory: 2Gi
    requests:
-      cpu: 250m
+      cpu: 100m
      memory: 512Mi

 postgresql:
@@ -2,5 +2,7 @@
 apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization

+namespace: grafana
+
 resources:
-  - ../../../base/paperclip
+  - ../../../base/grafana
@@ -15,7 +15,7 @@ agent:
    reloader.stakater.com/auto: "true"
  resources:
    requests:
-      cpu: 100m
+      cpu: 50m
    limits:
      memory: 128Mi

@@ -4,7 +4,6 @@ kind: Kustomization

 resources:
  - aitooling.yaml
-  - media.yaml
  - observability.yaml
  - platform.yaml
  - storage.yaml
@@ -1,31 +0,0 @@
---
-apiVersion: argoproj.io/v1alpha1
-kind: ApplicationSet
-metadata:
-  name: media-apps
-  namespace: argocd
-spec:
-  generators:
-  - git:
-      repoURL: https://git.unkin.net/unkin/argocd-apps
-      revision: HEAD
-      directories:
-      - path: apps/overlays/*/jellyfin
-  template:
-    metadata:
-      name: 'media-{{path[3]}}'
-    spec:
-      project: media
-      source:
-        repoURL: https://git.unkin.net/unkin/argocd-apps
-        targetRevision: HEAD
-        path: '{{path}}'
-      destination:
-        server: https://kubernetes.default.svc
-        namespace: '{{path[3]}}'
-      syncPolicy:
-        automated:
-          prune: true
-          selfHeal: true
-        syncOptions:
-        - ServerSideApply=true
@@ -11,6 +11,7 @@ spec:
      revision: HEAD
      directories:
      - path: apps/overlays/*/observability
+      - path: apps/overlays/*/grafana
  template:
    metadata:
      name: 'observability-{{path[3]}}'
@@ -4,7 +4,6 @@ kind: Kustomization

 resources:
  - aitooling.yaml
-  - media.yaml
  - observability.yaml
  - platform.yaml
  - storage.yaml
@@ -1,19 +0,0 @@
---
-apiVersion: argoproj.io/v1alpha1
-kind: AppProject
-metadata:
-  name: media
-  namespace: argocd
-spec:
-  description: Media services
-  sourceRepos:
-    - https://git.unkin.net/unkin/argocd-apps
-  destinations:
-    - namespace: 'jellyfin'
-      server: https://kubernetes.default.svc
-  clusterResourceWhitelist:
-    - group: ''
-      kind: Namespace
-  namespaceResourceWhitelist:
-    - group: '*'
-      kind: '*'
@@ -11,6 +11,8 @@ spec:
  destinations:
    - namespace: 'observability'
      server: https://kubernetes.default.svc
+    - namespace: 'grafana'
+      server: https://kubernetes.default.svc
  clusterResourceWhitelist:
    - group: ''
      kind: Namespace
@@ -0,0 +1,207 @@
+{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "properties": {
+    "apiVersion": {
+      "type": "string"
+    },
+    "kind": {
+      "type": "string"
+    },
+    "metadata": {
+      "type": "object"
+    },
+    "spec": {
+      "properties": {
+        "env": {
+          "additionalProperties": {
+            "type": "string"
+          },
+          "type": "object"
+        },
+        "image": {
+          "default": "git.unkin.net/unkin/bind-tsig-api:latest",
+          "type": "string"
+        },
+        "imagePullPolicy": {
+          "type": "string"
+        },
+        "port": {
+          "default": 8443,
+          "format": "int32",
+          "type": "integer"
+        },
+        "replicas": {
+          "default": 1,
+          "format": "int32",
+          "type": "integer"
+        },
+        "resources": {
+          "properties": {
+            "claims": {
+              "items": {
+                "properties": {
+                  "name": {
+                    "type": "string"
+                  },
+                  "request": {
+                    "type": "string"
+                  }
+                },
+                "required": [
+                  "name"
+                ],
+                "type": "object"
+              },
+              "type": "array",
+              "x-kubernetes-list-map-keys": [
+                "name"
+              ],
+              "x-kubernetes-list-type": "map"
+            },
+            "limits": {
+              "additionalProperties": {
+                "anyOf": [
+                  {
+                    "type": "integer"
+                  },
+                  {
+                    "type": "string"
+                  }
+                ],
+                "pattern": "^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$",
+                "x-kubernetes-int-or-string": true
+              },
+              "type": "object"
+            },
+            "requests": {
+              "additionalProperties": {
+                "anyOf": [
+                  {
+                    "type": "integer"
+                  },
+                  {
+                    "type": "string"
+                  }
+                ],
+                "pattern": "^(\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\\+|-)?(([0-9]+(\\.[0-9]*)?)|(\\.[0-9]+))))?$",
+                "x-kubernetes-int-or-string": true
+              },
+              "type": "object"
+            }
+          },
+          "type": "object"
+        },
+        "service": {
+          "properties": {
+            "annotations": {
+              "additionalProperties": {
+                "type": "string"
+              },
+              "type": "object"
+            },
+            "externalTrafficPolicy": {
+              "enum": [
+                "Cluster",
+                "Local"
+              ],
+              "type": "string"
+            },
+            "loadBalancerIP": {
+              "type": "string"
+            },
+            "type": {
+              "enum": [
+                "ClusterIP",
+                "LoadBalancer",
+                "NodePort"
+              ],
+              "type": "string"
+            }
+          },
+          "type": "object"
+        },
+        "targetNamespace": {
+          "type": "string"
+        },
+        "tokenSecretName": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "status": {
+      "properties": {
+        "conditions": {
+          "items": {
+            "properties": {
+              "lastTransitionTime": {
+                "format": "date-time",
+                "type": "string"
+              },
+              "message": {
+                "maxLength": 32768,
+                "type": "string"
+              },
+              "observedGeneration": {
+                "format": "int64",
+                "minimum": 0,
+                "type": "integer"
+              },
+              "reason": {
+                "maxLength": 1024,
+                "minLength": 1,
+                "pattern": "^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$",
+                "type": "string"
+              },
+              "status": {
+                "enum": [
+                  "True",
+                  "False",
+                  "Unknown"
+                ],
+                "type": "string"
+              },
+              "type": {
+                "maxLength": 316,
+                "pattern": "^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$",
+                "type": "string"
+              }
+            },
+            "required": [
+              "lastTransitionTime",
+              "message",
+              "reason",
+              "status",
+              "type"
+            ],
+            "type": "object"
+          },
+          "type": "array",
+          "x-kubernetes-list-map-keys": [
+            "type"
+          ],
+          "x-kubernetes-list-type": "map"
+        },
+        "endpoint": {
+          "type": "string"
+        },
+        "observedGeneration": {
+          "format": "int64",
+          "type": "integer"
+        },
+        "phase": {
+          "type": "string"
+        },
+        "readyReplicas": {
+          "format": "int32",
+          "type": "integer"
+        },
+        "tokenSecret": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    }
+  },
+  "type": "object"
+}
Author	SHA1	Message	Date
unkinben	0f8c816235	Fix validate-except syntax: trailing semicolon after last entry named requires every entry in the list to be semicolon-terminated, including the last one before the closing brace; without it named fails config parse (missing ';' before '}') and crash-loops.	2026-07-12 22:21:22 +10:00
unkinben	2706632f54	Exempt internal split-horizon zones from resolver DNSSEC validation ci/woodpecker/pr/pre-commit Pipeline was successful Details ci/woodpecker/pr/kubeconform Pipeline was successful Details Resolver queries for unkin.net records returned SERVFAIL (broken trust chain): the in-cluster authoritative serves unkin.net UNSIGNED, but the public parent publishes a DS record (unkin.net is DNSSEC-signed on the Internet), so the validating resolver rejects the insecure answer. Add validate-except for the forwarded internal domains so the resolver treats them as insecure and does not validate them. unkin.net covers all *.unkin.net (incl. k8s.syd1.au.unkin.net); 18.198.in-addr.arpa covers every NN.18.198.in-addr.arpa reverse zone; consul covers the consul TLD.	2026-07-12 22:13:50 +10:00
unkinben	65f18a6380	Bump bind-operator to v0.2.1 (secondary replication fix) (#250 ) ## Why v0.2.1 fixes authoritative secondary replication, which never actually worked — the master REFUSED the catalog AXFR. Root causes (bind-operator #9): secondaries presented no TSIG key, member zones had no `allow-transfer`, and secondaries pointed at the primary's ephemeral pod IP. ## Changes - Bump the operator image (`bind-system/deployment.yaml`) and the pulled CRD bundle URL (`bind-system/kustomization.yaml`) to `v0.2.1`. - Bump the `bind-tsig-api` image (`bind-internal/tsig-api/tsig-api.yaml`) to `v0.2.1`. CRDs are unchanged from v0.2.0, so the generated kubeconform schemas need no update. ## Validation - `bind-system` renders with the v0.2.1 CRD bundle; `bind-internal` passes `kubeconform` (56/56); pre-commit clean. ## Deploy note Existing member zones pick up `allow-transfer` via `modzone`, and secondaries re-point at the stable primary Service ClusterIP with the transfer key, restoring replication without manual BIND surgery. A from-scratch namespace recreate also comes up clean (OrderedReady startup means secondaries snapshot a ClusterIP-correct config). Caveat for a full recreate: the operator regenerates the `client-update` TSIG key, so its new material must be re-synced into puppet eyaml before clients can nsupdate. Reviewed-on: #250 Co-authored-by: Ben Vincent <ben@unkin.net> Co-committed-by: Ben Vincent <ben@unkin.net>	2026-07-12 21:43:03 +10:00
unkinben	38ef6c4a09	Bump bind-operator to v0.2.0 and deploy companion TSIG API (#249 ) ## Why bind-operator v0.2.0 adds the `BindTSIGAPI` CRD and a companion API that `vault-plugin-secrets-bind-tsig` calls to create, rotate and delete TSIG keys (it does so by managing `BindTSIGKey` resources, which the operator reconciles into key material). This rolls the operator forward and deploys an API instance so Vault never talks to the Kubernetes API directly. ## Changes - Bump the operator image (`bind-system/deployment.yaml`) and the pulled CRD bundle URL (`bind-system/kustomization.yaml`) to `v0.2.0`. - Broaden the operator ClusterRole (`bind-system/rbac.yaml`) with `deployments`, `serviceaccounts` and `roles`/`rolebindings`, so the `BindTSIGAPI` reconciler can create the API Deployment and its namespaced Role/RoleBinding. - Add a `BindTSIGAPI` (`bind-tsig-api`) in `bind-internal`; the operator reconciles it into a Deployment, Service, ConfigMap, master-token Secret and RBAC. Keys are created in `bind-internal`, alongside the authoritative cluster and its existing keys. - Add the generated kubeconform schema for `BindTSIGAPI`. ## Notes - The master access token Secret (`bind-tsig-api-token`) is generated by the operator when absent; the operator does not own it, so a `VaultStaticSecret` can later pre-seed/overwrite it to source the token from Vault. - Validated: both overlays render (`kubectl kustomize`) and pass `kubeconform` (bind-internal 56/56 valid); pre-commit clean. ## Follow-up - Point `vault-plugin-secrets-bind-tsig` config at `http://bind-tsig-api.bind-internal.svc:8443`. Reviewed-on: #249 Co-authored-by: Ben Vincent <ben@unkin.net> Co-committed-by: Ben Vincent <ben@unkin.net>	2026-07-12 19:12:39 +10:00
unkinben	2409a4d3a0	reduce CPU requests across observability, authentik, bind, woodpecker (#248 ) Reduce reserved-but-unused CPU requests across several workloads (limits unchanged). \| Workload \| CPU request \| \|---\|---\| \| vmstorage (vmcluster) \| 1 → 250m \| \| vmagent \| 500m → 250m \| \| authentik server \| 250m → 50m \| \| authentik worker \| 250m → 100m \| \| bind authoritative \| 100m → 20m \| \| bind externaldns \| 100m → 20m \| \| bind resolvers \| 100m → 20m \| \| woodpecker agent \| 100m → 50m \| Reviewed-on: #248 Co-authored-by: Ben Vincent <ben@unkin.net> Co-committed-by: Ben Vincent <ben@unkin.net>	2026-07-12 18:41:08 +10:00
unkinben	e0e0873ccb	cnpg: reduce cluster CPU requests to 50m (#247 ) Reduce CloudNativePG cluster CPU requests to `50m` across the platform to cut reserved-but-unused CPU. Updated (memory and limits unchanged): - artifactapi, authentik, encapi, paperclip (250m → 50m) - grafana (100m → 50m) - litellm (250m → 50m) Excluded: woodpecker (already 50m), puppet (handled separately). Reviewed-on: #247 Co-authored-by: Ben Vincent <ben@unkin.net> Co-committed-by: Ben Vincent <ben@unkin.net>	2026-07-12 18:39:13 +10:00
benvin	3320c823b3	chore: remove paperclip (#245 ) no longer using paperclip, remove it from au-syd1 cluster --------- Co-authored-by: Ben Vincent <ben@unkin.net> Reviewed-on: #245	2026-07-12 18:05:54 +10:00
benvin	646d76da16	chore: reduce resource requirements of puppet (#246 ) - lower reserved CPU for puppet related services --------- Co-authored-by: Ben Vincent <ben@unkin.net> Reviewed-on: #246	2026-07-12 18:04:50 +10:00
unkinben	05d2c83258	Authoritative zones: accept puppet client dynamic updates (#244 ) Enables per-host RFC2136 updates from puppet (puppet-prod #475 profiles::dns::updater) to the bind-authoritative zones, via the .9 write endpoint. ## Changes - add client-update BindTSIGKey (clusterRef bind-authoritative; operator generates the material into Secret client-update-tsig) - set `dynamicUpdate: true` + `updateKeyRef: client-update` on all 18 authoritative zones → the operator renders `allow-update { key "client-update"; }` ## Key bridge (manual, per the TSIG plan) The operator generates the client-update key value; it must reach puppet eyaml (`profiles::dns::updater::key_secret`) for clients to authenticate — until the planned Vault-sync/secret-reflection operator features exist. Get it with: `kubectl -n bind-internal get secret client-update-tsig -o jsonpath='{.data.secret}' \| base64 -d` ## Validated kustomize build + kubeconform. Reviewed-on: #244 Co-authored-by: Ben Vincent <ben@unkin.net> Co-committed-by: Ben Vincent <ben@unkin.net>	2026-07-11 00:57:52 +10:00
unkinben	38ab7199b3	grafana: add CloudNativePG dashboard (follow-up to #239 ) (#243 ) Follow-up to #239, pairing with the CNPG VMPodScrape (#242). Imports the CloudNativePG dashboard (grafana.com 20417) as a `GrafanaDashboard` (gzipJson, datasources resolved to the in-cluster VictoriaMetrics uid). Now that #242 collects the postgres metrics, this dashboard renders real data for all CNPG clusters. Reviewed-on: #243 Co-authored-by: Ben Vincent <ben@unkin.net> Co-committed-by: Ben Vincent <ben@unkin.net>	2026-07-07 00:10:36 +10:00
unkinben	be6d07cf77	observability: scrape CloudNativePG postgres metrics (follow-up to #239 ) (#242 ) Follow-up to #239. Every CNPG instance pod already exposes Prometheus metrics on `:9187` (`metrics` port), but nothing scraped them. Adds a single namespace-wide `VMPodScrape` (`namespaceSelector.any`, `selector cnpg.io/podRole=instance`) so the observability VMAgent collects postgres metrics for all ~23 CNPG clusters across the estate (authentik, grafana, woodpecker, artifactapi, puppet, litellm, …). No chart changes. Pairs well with the CNPG grafana.com dashboard (20417) as a further follow-up. Reviewed-on: #242 Co-authored-by: Ben Vincent <ben@unkin.net> Co-committed-by: Ben Vincent <ben@unkin.net>	2026-07-07 00:08:32 +10:00
unkinben	8c9eb9befc	cert-manager: scrape metrics (follow-up to #239 ) (#241 ) Follow-up to #239. Adds a `VMServiceScrape` for cert-manager's existing webhook (`metrics` :9402) and cainjector (`http-metrics` :9402) services so the observability VMAgent collects them. No chart change needed. (The controller's own metrics need `prometheus.enabled` in the chart to expose a metrics service — separate follow-up.) Reviewed-on: #241 Co-authored-by: Ben Vincent <ben@unkin.net> Co-committed-by: Ben Vincent <ben@unkin.net>	2026-07-07 00:08:06 +10:00
unkinben	55e41897ef	vmagent: set consul datacenter (fix 0 discovered targets) (#240 ) ## Why The Consul SD job discovered 0 targets. vmagent logs showed it reaching the puppet Consul fine (TLS/connectivity OK) but getting `403` on `GET /v1/agent/self`: the anonymous token `lacks permission 'agent:read'`. VictoriaMetrics calls `/v1/agent/self` only to auto-detect the datacenter; catalog/health reads (what SD actually needs) work anonymously. ## Fix Set `datacenter: au-syd1` on the consul_sd_config so VM skips the `agent/self` call. No consul token needed. ## Verify after sync vmagent `/targets` → `consul` job shows the puppet targets (haproxy/ceph/gitea/node/…) up. Reviewed-on: #240 Co-authored-by: Ben Vincent <ben@unkin.net> Co-committed-by: Ben Vincent <ben@unkin.net>	2026-07-07 00:05:30 +10:00
unkinben	9a56612ae6	observability: scrape existing app metrics (audit + ceph-csi batch) (#239 ) ## Why Audit of existing helm deployments for (a) metrics collection and (b) bundled Grafana dashboards, per request. This PR enables the first, cleanest batch (ceph-csi) and documents the rest for follow-up review. ## Key constraint The cluster has no Prometheus-Operator CRDs (`servicemonitors.monitoring.coreos.com` absent) — only the VM-native `VMServiceScrape`/`VMPodScrape`. So flipping charts' `serviceMonitor: true` toggles would fail. The correct mechanism here is native VMServiceScrape CRs, which the observability VMAgent picks up (`selectAllByDefault`, added in #234). Bundled chart dashboards ship as ConfigMaps that grafana-operator v5 ignores (it uses CRs), so "enabling" them means adding `GrafanaDashboard` CRs. ## This PR - `VMServiceScrape` for csi-cephfs and csi-cephrbd (their `-http-metrics` services already exist). ## Audit — metrics (apps already exposing a metrics service; enable via VMServiceScrape) \| App \| Metrics service / port \| Note \| \|-----\|------------------------\|------\| \| csi-cephfs / csi-cephrbd \| `-http-metrics` :8080 \| done here \| \| cert-manager \| webhook :9402 `metrics`, cainjector :9402 `http-metrics` \| multi-port; easy follow-up \| \| argocd \| `argocd--metrics` :8082/8083/8084/9001 \| many components \| \| media-apps \| `prowlarr/radarr/sonarr-metrics` :9707 (exportarr) \| follow-up \| \| vm-system / grafana-operator \| operator metrics \| low value \| ## Audit — charts with metrics toggles* (need endpoint enabled + VMServiceScrape) authentik, vault, purelb, externaldns, cnpg-system (`enablePodMonitor`), reloader, traefik. These expose `serviceMonitor`/`podMonitor` toggles that assume Prometheus CRDs — recommend enabling the metrics endpoint + a VMServiceScrape rather than the toggle. ## Audit — bundled Grafana dashboards - CNPG: ships a dashboard (grafana.com id 20417) — add as `GrafanaDashboard` (grafanaCom). - traefik: `dashboard: true` option + community dashboards — add as `GrafanaDashboard`. - Others: none bundled. ## Review ask Confirm the VMServiceScrape approach; I'll extend to the remaining apps (cert-manager/argocd/media-apps + CNPG/traefik dashboards) in follow-up batches. Reviewed-on: #239 Co-authored-by: Ben Vincent <ben@unkin.net> Co-committed-by: Ben Vincent <ben@unkin.net>	2026-07-06 23:57:54 +10:00
unkinben	95c5d71222	grafana: deploy Grafana instance, datasource and dashboards (#238 ) ## Why Deploys Grafana in-cluster (observability project) via the grafana-operator, mirroring the puppet Grafana but modernised — CNPG for state, Authentik OIDC for auth — and ports the live datasource + dashboards in as CRs. Depends on: grafana-operator (#235, merged), grafana schemas (#236, merged), Authentik OIDC (terraform-authentik #2), Vault seeds (done), and `^grafana/` image proxy (terraform-artifactapi #5). ## Changes (`apps/base/grafana`) - CNPG postgres Cluster + rw Pooler (db `grafana`); VaultAuth + VaultStaticSecrets pulling `postgres`/`oauth` credentials from `kv/kubernetes/namespace/grafana/default/`. - Grafana CR: postgres backend via the pooler; Authentik `generic_oauth` (client id/secret from the Vault-synced secret, openid/email/profile scopes, group→role mapping); `root_url` grafana.k8s.syd1.au.unkin.net. - 1 GrafanaDatasource* — k8s VictoriaMetrics via the operator `vmselect-main` service; reuses the previous default datasource uid so the imported dashboards resolve unedited. - 13 GrafanaDashboards (gzipJson) exported from the current grafana. - Gateway API (traefik-internal) + HTTPRoute for grafana.k8s.syd1.au.unkin.net. - Registered in the observability ApplicationSet + project. ## Review notes - OAuth `role_attribute_path` maps Authentik group `grafana-admins` → Admin, else Viewer — confirm the group name. - `database.ssl_mode: require` against the CNPG pooler — adjust if the pooler isn't serving TLS. - The `VictoriaLogs - cluster` dashboard has no in-cluster logs datasource yet (no VictoriaLogs in k8s) — included for completeness, will be empty until one exists. - `make kubeconform` clean (24 resources, validated against the strict grafana schemas). Reviewed-on: #238 Co-authored-by: Ben Vincent <ben@unkin.net> Co-committed-by: Ben Vincent <ben@unkin.net>	2026-07-06 23:54:51 +10:00