Implement TURN server (coturn) for WebRTC video calls

Add coturn Deployment with hostNetwork mode and init container for secret substitution. Include SOPS-encrypted shared secret, TLS certificate for turn.axion1337.chat, and Synapse TURN configuration with proper relay URIs and credentials.

Resolves DTLS timeout issues in RTC video calls by providing media relay for clients behind NAT/Firewall.

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>

apps/monitoring/alloy-config.yaml

@@ -0,0 +1,135 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: alloy-config
+  namespace: monitoring
+data:
+  config.alloy: |
+    // Kubernetes pod discovery
+    discovery.kubernetes "k8s_pods" {
+      role = "pod"
+    }
+
+    // Relabel for Prometheus scrape
+    discovery.relabel "prometheus_pods" {
+      targets = discovery.kubernetes.k8s_pods.targets
+      rule {
+        source_labels = ["__meta_kubernetes_pod_annotation_prometheus_io_scrape"]
+        action = "keep"
+        regex = "true"
+      }
+      rule {
+        source_labels = ["__meta_kubernetes_pod_annotation_prometheus_io_path"]
+        action = "replace"
+        target_label = "__metrics_path__"
+        regex = "(.+)"
+      }
+      rule {
+        source_labels = ["__address__", "__meta_kubernetes_pod_annotation_prometheus_io_port"]
+        action = "replace"
+        regex = "([^:]+)(?::\\d+)?;(\\d+)"
+        replacement = "$1:$2"
+        target_label = "__address__"
+      }
+      rule {
+        source_labels = ["__meta_kubernetes_namespace"]
+        action = "replace"
+        target_label = "namespace"
+      }
+      rule {
+        source_labels = ["__meta_kubernetes_pod_name"]
+        action = "replace"
+        target_label = "pod"
+      }
+    }
+
+    // Scrape Flux controllers (flux-system namespace, port 8080)
+    discovery.kubernetes "flux_pods" {
+      role = "pod"
+      namespaces {
+        names = ["flux-system"]
+      }
+    }
+
+    discovery.relabel "flux_scrape" {
+      targets = discovery.kubernetes.flux_pods.targets
+      rule {
+        source_labels = ["__meta_kubernetes_pod_container_port_number"]
+        action = "keep"
+        regex = "8080"
+      }
+      rule {
+        source_labels = ["__meta_kubernetes_namespace"]
+        action = "replace"
+        target_label = "namespace"
+      }
+      rule {
+        source_labels = ["__meta_kubernetes_pod_name"]
+        action = "replace"
+        target_label = "pod"
+      }
+    }
+
+    // Scrape kube-state-metrics
+    prometheus.scrape "kube_state_metrics" {
+      targets = [{
+        __address__ = "kube-state-metrics.monitoring.svc.cluster.local:8080",
+      }]
+      forward_to = [prometheus.remote_write.selendis.receiver]
+      scrape_interval = "30s"
+      scrape_timeout = "10s"
+    }
+
+    // Scrape Flux controllers
+    prometheus.scrape "flux" {
+      targets = discovery.relabel.flux_scrape.output
+      forward_to = [prometheus.remote_write.selendis.receiver]
+      scrape_interval = "30s"
+      scrape_timeout = "10s"
+      job_name = "flux"
+    }
+
+    // Scrape node-exporter DaemonSet
+    prometheus.scrape "node_exporter" {
+      targets = [{
+        __address__ = "prometheus-node-exporter.monitoring.svc.cluster.local:9100",
+      }]
+      forward_to = [prometheus.remote_write.selendis.receiver]
+      scrape_interval = "30s"
+      scrape_timeout = "10s"
+    }
+
+    // Scrape Synapse metrics
+    prometheus.scrape "synapse" {
+      targets = [{
+        __address__ = "matrix-stack-synapse-main.matrix.svc.cluster.local:9000",
+      }]
+      forward_to = [prometheus.remote_write.selendis.receiver]
+      scrape_interval = "30s"
+      scrape_timeout = "10s"
+    }
+
+    // Kubernetes pod logs to Loki
+    loki.source.kubernetes "k8s_logs" {
+      targets = discovery.kubernetes.k8s_pods.targets
+      forward_to = [loki.write.selendis.receiver]
+    }
+
+    // Remote write to Selendis Prometheus
+    prometheus.remote_write "selendis" {
+      endpoint {
+        url = "http://10.0.0.3:9090/api/v1/write"
+        write_relabel_config {
+          source_labels = ["__name__"]
+          regex = "go_.*|process_.*"
+          action = "drop"
+        }
+      }
+    }
+
+    // Remote write logs to Selendis Loki
+    loki.write "selendis" {
+      endpoint {
+        url = "http://10.0.0.3:3100/loki/api/v1/push"
+      }
+    }

apps/monitoring/alloy.yaml

@@ -0,0 +1,33 @@
+apiVersion: helm.toolkit.fluxcd.io/v2
+kind: HelmRelease
+metadata:
+  name: alloy
+  namespace: monitoring
+spec:
+  interval: 1h
+  chart:
+    spec:
+      chart: alloy
+      version: "0.x"
+      sourceRef:
+        kind: HelmRepository
+        name: grafana
+        namespace: flux-system
+  values:
+    alloy:
+      configMap:
+        name: alloy-config
+    replicaCount: 1
+    serviceAccount:
+      create: true
+      name: alloy
+    rbac:
+      create: true
+    podAnnotations:
+      prometheus.io/scrape: "false"
+    resources:
+      limits:
+        memory: 512Mi
+      requests:
+        cpu: 100m
+        memory: 256Mi

apps/monitoring/helm-repos.yaml

@@ -0,0 +1,18 @@
+apiVersion: source.toolkit.fluxcd.io/v1
+kind: HelmRepository
+metadata:
+  name: prometheus-community
+  namespace: flux-system
+spec:
+  interval: 1h
+  url: https://prometheus-community.github.io/helm-charts
+
+---
+apiVersion: source.toolkit.fluxcd.io/v1
+kind: HelmRepository
+metadata:
+  name: grafana
+  namespace: flux-system
+spec:
+  interval: 1h
+  url: https://grafana.github.io/helm-charts

apps/monitoring/kube-state-metrics.yaml

@@ -0,0 +1,22 @@
+apiVersion: helm.toolkit.fluxcd.io/v2
+kind: HelmRelease
+metadata:
+  name: kube-state-metrics
+  namespace: monitoring
+spec:
+  interval: 1h
+  chart:
+    spec:
+      chart: kube-state-metrics
+      version: "5.x"
+      sourceRef:
+        kind: HelmRepository
+        name: prometheus-community
+        namespace: flux-system
+  values:
+    replicas: 1
+    service:
+      port: 8080
+    prometheus:
+      monitor:
+        enabled: false

apps/monitoring/kustomization.yaml

@@ -0,0 +1,9 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  - namespace.yaml
+  - helm-repos.yaml
+  - kube-state-metrics.yaml
+  - node-exporter.yaml
+  - alloy-config.yaml
+  - alloy.yaml

apps/monitoring/namespace.yaml

@@ -0,0 +1,4 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: monitoring

apps/monitoring/node-exporter.yaml

@@ -0,0 +1,29 @@
+apiVersion: helm.toolkit.fluxcd.io/v2
+kind: HelmRelease
+metadata:
+  name: prometheus-node-exporter
+  namespace: monitoring
+spec:
+  interval: 1h
+  chart:
+    spec:
+      chart: prometheus-node-exporter
+      version: "4.x"
+      sourceRef:
+        kind: HelmRepository
+        name: prometheus-community
+        namespace: flux-system
+  values:
+    hostNetwork: true
+    hostPID: true
+    hostRootFsMount:
+      enabled: true
+    service:
+      port: 9100
+      targetPort: 9100
+    prometheus:
+      monitor:
+        enabled: false
+    tolerations:
+      - effect: NoSchedule
+        operator: Exists

apps/production/coturn-secret.yaml

@@ -0,0 +1,22 @@
+apiVersion: v1
+kind: Secret
+metadata:
+    name: coturn-secret
+    namespace: matrix
+stringData:
+    TURN_SECRET: ENC[AES256_GCM,data:SILIqMB+fmAMFITAL7lG1hOgICec6BJf1mOcK0gdmnCHWYqRuJv7jgjfGylG25xzQKi+zE7Qual9PnkZG2KiOA==,iv:+GZqLGusE4Q0x2jEEtFxj06rryyQmQhXdkTy4eE8ZHw=,tag:OpSZkinPTAi1ZKWyo8OX3A==,type:str]
+sops:
+    age:
+        - recipient: age14l0hwfqylwpemz5y2ghh2yxk0phszlnj3qlejhue0fw0kz3tmfgqdsjzdh
+          enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSAyRk1mK3NWc1l4T0JCOFpF
+            S0RuQ3ViZmo3QTNVL2JvZ0hzMy91R2l0TEhzCk01a1VGdk1sdVg4aWswTzRibXI4
+            ZlJtNFF5MjBONEZOaWVpeU5taHl2bkEKLS0tIGxpUHY3NUFLWFBaWm1QSlZiVFkx
+            MEJleHFnd3oyT3VPL2dsYkpMUlRkOWMKcKUIgsQ/ff49pGGXMnYwJmwqPVC7woAR
+            IEzvhcNX97xx746SnrxZe5t2YadsYMkYIl0nvqBPJhSlvqMNafpQbQ==
+            -----END AGE ENCRYPTED FILE-----
+    lastmodified: "2026-04-29T21:06:21Z"
+    mac: ENC[AES256_GCM,data:UhyR5m1HYWrZHwNLW5sg2PxbpaydWbP5cekghGlzSpQg7CYEcvZw3tJ/qB8zA19xZSM7tdSHOXdD+QytRq6qW59M1unqMaumA43B6JxQg1C1NdXAW0mkSc2WiNchvgpVii9P/TVlzSSIRwC3YGCQUsfa3SSfNzI4Z6fMuBnhYLE=,iv:4HYxbrYSRJLe1KcQ6q8bpee8/Lx1m3pPmisb/L2Mu64=,tag:l7n3u+Pg6533OzwtNUZvNw==,type:str]
+    encrypted_regex: ^(data|stringData)$
+    version: 3.12.2

apps/production/coturn.yaml

@@ -0,0 +1,162 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: coturn-config
+  namespace: matrix
+data:
+  turnserver.conf: |
+    # TURN Server configuration
+    realm=axion1337.chat
+
+    # Listen ports
+    listening-port=3478
+    listening-ip=0.0.0.0
+    alt-listening-port=5349
+    alt-listening-ip=0.0.0.0
+
+    # External IPs (for clients behind NAT)
+    relay-ip=49.13.132.245
+    external-ip=49.13.132.245
+
+    # Relay port range
+    min-bps=0
+    bps-capacity=0
+
+    # Authentication
+    use-auth-secret
+    static-auth-secret=$TURN_SECRET
+
+    # HTTPS/TLS
+    cert=/etc/coturn/tls/tls.crt
+    pkey=/etc/coturn/tls/tls.key
+
+    # Performance tuning
+    max-bps=0
+    bps-capacity=0
+    log-file=stdout
+
+    # Logging
+    verbose
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: coturn
+  namespace: matrix
+spec:
+  type: ClusterIP
+  ports:
+    - name: stun-udp
+      port: 3478
+      protocol: UDP
+    - name: stun-tcp
+      port: 3478
+      protocol: TCP
+    - name: turns-tcp
+      port: 5349
+      protocol: TCP
+  selector:
+    app: coturn
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: coturn
+  namespace: matrix
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: coturn
+  template:
+    metadata:
+      labels:
+        app: coturn
+      annotations:
+        prometheus.io/scrape: "false"
+    spec:
+      hostNetwork: true
+      dnsPolicy: ClusterFirstWithHostNet
+      initContainers:
+      - name: init-config
+        image: busybox:1.28
+        command:
+        - sh
+        - -c
+        - |
+          TURN_SECRET=$(cat /etc/coturn-secret/TURN_SECRET)
+          sed "s|\$TURN_SECRET|$TURN_SECRET|g" /etc/coturn-template/turnserver.conf > /etc/coturn/turnserver.conf
+          chmod 644 /etc/coturn/turnserver.conf
+        resources:
+          limits:
+            cpu: 100m
+            memory: 64Mi
+          requests:
+            cpu: 50m
+            memory: 32Mi
+        volumeMounts:
+        - name: config-template
+          mountPath: /etc/coturn-template
+        - name: config
+          mountPath: /etc/coturn
+        - name: secret
+          mountPath: /etc/coturn-secret
+          readOnly: true
+      containers:
+      - name: coturn
+        image: coturn/coturn:latest
+        imagePullPolicy: IfNotPresent
+        ports:
+        - name: stun-udp
+          containerPort: 3478
+          protocol: UDP
+        - name: stun-tcp
+          containerPort: 3478
+          protocol: TCP
+        - name: turns-tcp
+          containerPort: 5349
+          protocol: TCP
+        volumeMounts:
+        - name: config
+          mountPath: /etc/coturn
+        - name: tls
+          mountPath: /etc/coturn/tls
+          readOnly: true
+        resources:
+          limits:
+            cpu: 500m
+            memory: 256Mi
+          requests:
+            cpu: 100m
+            memory: 128Mi
+        livenessProbe:
+          exec:
+            command:
+            - /bin/sh
+            - -c
+            - "netstat -uln | grep 3478 || exit 1"
+          initialDelaySeconds: 30
+          periodSeconds: 10
+      volumes:
+      - name: config
+        emptyDir: {}
+      - name: config-template
+        configMap:
+          name: coturn-config
+      - name: secret
+        secret:
+          secretName: coturn-secret
+          defaultMode: 0400
+      - name: tls
+        secret:
+          secretName: turn-axion1337-chat-tls
+      affinity:
+        nodeAffinity:
+          preferredDuringSchedulingIgnoredDuringExecution:
+          - weight: 100
+            preference:
+              matchExpressions:
+              - key: kubernetes.io/hostname
+                operator: In
+                values:
+                - matrix

apps/production/custom-configs/synapse-values.yaml

@@ -22,4 +22,48 @@ data:
             - '::1/128'
             - 'fe80::/10'
             - 'fc00::/7'
-            max_spider_size: 10M
+            max_spider_size: 10M
+        retention:
+          config: |
+            retention:
+              enabled: true
+              default_policy:
+                min_lifetime: 1d
+                max_lifetime: 1y
+              allowed_lifetime_min: 1d
+              allowed_lifetime_max: 2y
+              purge_jobs:
+                - longest_max_lifetime: 3d
+                  interval: 12h
+                - shortest_max_lifetime: 3d
+                  longest_max_lifetime: 1w
+                  interval: 1d
+                - shortest_max_lifetime: 1w
+                  interval: 2d
+
+            media_retention:
+              local_media_lifetime: 365d
+              remote_media_lifetime: 90d
+
+            redaction_retention_period: 7d
+            forgotten_room_retention_period: 28d
+            user_ips_max_age: 90d
+        auto_join:
+          config: |
+            auto_join_rooms:
+              - "!NkFTshKWJMgdTqTbTh:axion1337.chat"
+            auto_join_rooms_for_guests: false
+        room_publish:
+          config: |
+            room_list_publication_rules:
+              - user_id: "*"
+                action: allow
+        turn:
+          config: |
+            turn_uris:
+              - "turn:turn.axion1337.chat?transport=udp"
+              - "turn:turn.axion1337.chat?transport=tcp"
+              - "turns:turn.axion1337.chat?transport=tcp"
+            turn_shared_secret: "cab3c8408363515d9b4cdc3384a1f76ca17a973242fdfdc72b67ac4d86158527"
+            turn_user_lifetime: 86400000
+            turn_allow_guests: false

apps/production/kustomization.yaml

@@ -3,12 +3,16 @@ kind: Kustomization
 resources:
   - matrix-postgres-auth.yaml
   - cert-issuer.yaml
+  - matrix-certificates.yaml
   # Neue Dateien:
   - custom-configs/synapse-values.yaml
   - custom-configs/element-values.yaml
   - custom-configs/mas-secret.yaml
   - element-web-docs-configmap.yaml
   - element-web-docs-server.yaml
+  # TURN Server für WebRTC
+  - coturn-secret.yaml
+  - coturn.yaml
   # HelmRelease (muss ganz unten stehen, damit die ConfigMaps vorher da sind!)
   - element-server-suite.yaml
   # Custom Apex Ingress für Element Web + Well-Known auf axion1337.chat

apps/production/matrix-certificates.yaml

@@ -62,3 +62,16 @@ spec:
     kind: ClusterIssuer
   dnsNames:
     - admin.axion1337.chat
+---
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: turn-axion1337-chat-cert
+  namespace: matrix
+spec:
+  secretName: turn-axion1337-chat-tls
+  issuerRef:
+    name: letsencrypt-prod
+    kind: ClusterIssuer
+  dnsNames:
+    - turn.axion1337.chat

clusters/matrix/flux-system/kustomization.yaml

@@ -4,4 +4,5 @@ resources:
   - gotk-components.yaml
   - gotk-sync.yaml
   - infra-sync.yaml
+  - monitoring-sync.yaml
   - production-sync.yaml

clusters/matrix/flux-system/monitoring-sync.yaml

@@ -0,0 +1,14 @@
+apiVersion: kustomize.toolkit.fluxcd.io/v1
+kind: Kustomization
+metadata:
+  name: monitoring-apps
+  namespace: flux-system
+spec:
+  interval: 10m
+  path: ./apps/monitoring
+  prune: true
+  sourceRef:
+    kind: GitRepository
+    name: flux-system
+  dependsOn:
+    - name: infra-apps