apiVersion: apps/v1
kind: StatefulSet
metadata:
  name: fancy-dns
  namespace: dns
  labels:
    app.kubernetes.io/name: fancy-dns
  annotations:
    k8s-helper.io/git-url: "https://git.k6n.net/mats/fancy-dns"
    k8s-helper.io/git-ssh: "git@git.k6n.net:mats/fancy-dns.git"
spec:
  serviceName: fancy-dns
  # A StatefulSet rather than a Deployment because each pod owns a PVC (the
  # cache snapshot and the query log are per-pod state worth keeping across a
  # reschedule). The flip side: the HPA does not work on a StatefulSet — the
  # controller and the autoscaler fight over the replica count — so scaling
  # means adding nodes and replicas here, not CPU targets.
  replicas: 2
  podManagementPolicy: Parallel
  selector:
    matchLabels:
      app.kubernetes.io/name: fancy-dns
  template:
    metadata:
      labels:
        app.kubernetes.io/name: fancy-dns
      annotations:
        k8s-helper.io/git-url: "https://git.k6n.net/mats/fancy-dns"
        k8s-helper.io/git-ssh: "git@git.k6n.net:mats/fancy-dns.git"
        # A config change is a SIGHUP, not a restart: the server re-reads the
        # file and hot-swaps every component. This annotation is for
        # stakater/reloader-class controllers; without one, `kubectl rollout
        # restart` is the manual equivalent.
        reloader.stakater.com/auto: "true"
    spec:
      serviceAccountName: fancy-dns
      imagePullSecrets:
        - name: reg-k6n
      # No hostNetwork. The server does not set SO_REUSEPORT, so a second
      # host-network pod would fail to bind :53 and crash-loop; the ports are
      # served by a LoadBalancer Service instead (see 20-service.yaml).
      dnsPolicy: ClusterFirst
      # The app drains in-flight queries for up to 15s on SIGTERM (see the
      # shutdown timeout in cmd/fancy-dns/main.go); give it room beyond that.
      terminationGracePeriodSeconds: 30
      securityContext:
        runAsNonRoot: true
        runAsUser: 65532
        runAsGroup: 65532
        fsGroup: 65532
        seccompProfile:
          type: RuntimeDefault
      topologySpreadConstraints:
        - maxSkew: 1
          topologyKey: kubernetes.io/hostname
          whenUnsatisfiable: ScheduleAnyway
          labelSelector:
            matchLabels:
              app.kubernetes.io/name: fancy-dns
      containers:
        - name: fancy-dns
          image: registry.k6n.net/fancydns
          imagePullPolicy: Always
          args:
            - -config
            - /etc/fancy-dns/config.yaml
          env:
            # Substituted into the config by the loader, so the admin API key
            # comes from the Secret and not from the ConfigMap.
            - name: FANCYDNS_API_KEY
              valueFrom:
                secretKeyRef:
                  name: fancy-dns-apikey
                  key: api-key
          ports:
            - name: dns-udp
              containerPort: 53
              protocol: UDP
            - name: dns-tcp
              containerPort: 53
              protocol: TCP
            - name: dot
              containerPort: 853
              protocol: TCP
            - name: doh
              containerPort: 443
              protocol: TCP
            - name: admin
              containerPort: 8080
              protocol: TCP
          securityContext:
            allowPrivilegeEscalation: false
            readOnlyRootFilesystem: true
            capabilities:
              drop: ["ALL"]
              # Only because of the low ports. The pod is not privileged and
              # has no other capability left; drop the Service and the
              # Capability together if you move the listeners off 53/443.
              add: ["NET_BIND_SERVICE"]
          # Liveness: the process is up. /api/healthz is unauthenticated on
          # purpose, because a probe cannot carry an API key.
          livenessProbe:
            httpGet:
              path: /api/healthz
              port: admin
            initialDelaySeconds: 5
            periodSeconds: 20
          # Readiness: the listener is actually bound, so the Service does not
          # send traffic to a pod that is still binding.
          readinessProbe:
            httpGet:
              path: /api/healthz
              port: admin
            initialDelaySeconds: 3
            periodSeconds: 5
            failureThreshold: 2
          # Startup: binding the listeners and fetching the first blocklist
          # can take a while on a cold node, so give it room before the
          # liveness probe starts killing it.
          startupProbe:
            httpGet:
              path: /api/healthz
              port: admin
            periodSeconds: 3
            failureThreshold: 30
          resources:
            requests:
              cpu: 250m
              memory: 256Mi
            limits:
              # No CPU limit on purpose: a DNS server that gets throttled
              # turns into dropped queries, which is worse than a noisy
              # neighbour. The memory limit is the one that matters, because
              # the cache is sized in entries.
              memory: 1Gi
          volumeMounts:
            - name: config
              mountPath: /etc/fancy-dns/config.yaml
              subPath: config.yaml
              readOnly: true
            - name: zones
              mountPath: /etc/fancy-dns/zones
              readOnly: true
            - name: tls
              mountPath: /etc/fancy-dns/tls
              readOnly: true
            - name: data
              mountPath: /var/lib/fancy-dns
            - name: tmp
              mountPath: /tmp
      volumes:
        - name: config
          configMap:
            name: fancy-dns-config
    # Local zones are ordinary master files; ship them in a ConfigMap or
    # edit them in the mounted volume. There is no zone API — the admin API
    # drives blocklists, the cache and the query log, not the zone files.
        # the data volume. Optional because the glob in the config matches
        # nothing cleanly.
        - name: zones
          configMap:
            name: fancy-dns-zones
            optional: true
        - name: tls
          secret:
            secretName: fancy-dns-tls
        - name: tmp
          emptyDir: {}
  volumeClaimTemplates:
    # Cache snapshot (cache.persist.path) and query log (qlog.path) live here,
    # along with downloaded blocklists. ReadWriteOnce is per-pod: a pod keeps
    # its own cache across a reschedule, which is the whole point of the
    # snapshot, but it cannot be shared between replicas.
    #
    # Sizing: cache.size is an entry count, not bytes, so disk usage has to be
    # estimated. A packed A/AAAA answer with a small authority section is
    # roughly 300-600 bytes on the wire and nearer 1 kB resident, so 500k
    # entries lands around 500 MB; qlog is the other consumer (see
    # qlog.max_entries). 4Gi leaves room for both plus a re-fetched list.
    - metadata:
        name: data
      spec:
        storageClassName: nfs-large
        accessModes: ["ReadWriteOnce"]
        resources:
          requests:
            storage: 4Gi