Auto-update README with current k8s applications

Generated by CI/CD workflow on 2026-03-13 16:10:31

This PR updates the README.md file with the current list of applications found in the k8s/ directory structure.

.gitea/workflows/authentik-apps.yaml

@@ -25,7 +25,7 @@ jobs:
       uses: actions/checkout@v3
 
     - name: Setup Terraform
-      uses: hashicorp/setup-terraform@v2
+      uses: hashicorp/setup-terraform@v4.0.0
       with:
         cli_config_credentials_token: ${{ secrets.TF_API_TOKEN }}
 
@@ -45,7 +45,7 @@ jobs:
     - name: Terraform Apply
       env:
         TF_VAR_authentik_token: ${{ secrets.AUTHENTIK_TOKEN }}
-      run: terraform apply -var-file proxy-apps.tfvars -var-file oauth2-apps.tfvars -var-file terraform.tfvars -var-file groups.tfvars -input=false -auto-approve -parallelism=100
+      run: terraform apply -input=false -auto-approve -parallelism=100
       working-directory: ./terraform/authentik
 
     - name: Generate Wiki Content  

.gitea/workflows/k8s-wiki.yaml

@@ -22,12 +22,13 @@ jobs:
 
     - name: Install Python dependencies
       run: |
-        pip install pyyaml
+        python3 -m venv .venv
+        .venv/bin/pip install pyyaml
 
     - name: Generate K8s Services Wiki
       run: |
         echo "📋 Starting K8s wiki generation..."
-        python3 .gitea/scripts/generate-k8s-wiki.py k8s/ Kubernetes-Services.md
+        .venv/bin/python .gitea/scripts/generate-k8s-wiki.py k8s/ Kubernetes-Services.md
         
         if [ -f "Kubernetes-Services.md" ]; then
           echo "✅ Wiki content generated successfully"

.gitignore

@@ -13,6 +13,7 @@ crash.*.log
 *.tfvars
 *.tfvars.json
 !*terraform.tfvars
+!*.auto.tfvars
 
 # claude ai
 .claude/

README.md

@@ -16,8 +16,10 @@ ArgoCD homelab project
 | **authentik** | [![authentik](https://ag.hexor.cy/api/badge?name=authentik&revision=true)](https://ag.hexor.cy/applications/argocd/authentik) |
 | **cert-manager** | [![cert-manager](https://ag.hexor.cy/api/badge?name=cert-manager&revision=true)](https://ag.hexor.cy/applications/argocd/cert-manager) |
 | **external-secrets** | [![external-secrets](https://ag.hexor.cy/api/badge?name=external-secrets&revision=true)](https://ag.hexor.cy/applications/argocd/external-secrets) |
+| **gpu** | [![gpu](https://ag.hexor.cy/api/badge?name=gpu&revision=true)](https://ag.hexor.cy/applications/argocd/gpu) |
 | **kube-system-custom** | [![kube-system-custom](https://ag.hexor.cy/api/badge?name=kube-system-custom&revision=true)](https://ag.hexor.cy/applications/argocd/kube-system-custom) |
 | **kubernetes-dashboard** | [![kubernetes-dashboard](https://ag.hexor.cy/api/badge?name=kubernetes-dashboard&revision=true)](https://ag.hexor.cy/applications/argocd/kubernetes-dashboard) |
+| **longhorn** | [![longhorn](https://ag.hexor.cy/api/badge?name=longhorn&revision=true)](https://ag.hexor.cy/applications/argocd/longhorn) |
 | **postgresql** | [![postgresql](https://ag.hexor.cy/api/badge?name=postgresql&revision=true)](https://ag.hexor.cy/applications/argocd/postgresql) |
 | **prom-stack** | [![prom-stack](https://ag.hexor.cy/api/badge?name=prom-stack&revision=true)](https://ag.hexor.cy/applications/argocd/prom-stack) |
 | **system-upgrade** | [![system-upgrade](https://ag.hexor.cy/api/badge?name=system-upgrade&revision=true)](https://ag.hexor.cy/applications/argocd/system-upgrade) |
@@ -36,6 +38,8 @@ ArgoCD homelab project
 
 | Application | Status |
 | :--- | :---: |
+| **comfyui** | [![comfyui](https://ag.hexor.cy/api/badge?name=comfyui&revision=true)](https://ag.hexor.cy/applications/argocd/comfyui) |
+| **furumi-server** | [![furumi-server](https://ag.hexor.cy/api/badge?name=furumi-server&revision=true)](https://ag.hexor.cy/applications/argocd/furumi-server) |
 | **gitea** | [![gitea](https://ag.hexor.cy/api/badge?name=gitea&revision=true)](https://ag.hexor.cy/applications/argocd/gitea) |
 | **greece-notifier** | [![greece-notifier](https://ag.hexor.cy/api/badge?name=greece-notifier&revision=true)](https://ag.hexor.cy/applications/argocd/greece-notifier) |
 | **hexound** | [![hexound](https://ag.hexor.cy/api/badge?name=hexound&revision=true)](https://ag.hexor.cy/applications/argocd/hexound) |
@@ -44,6 +48,9 @@ ArgoCD homelab project
 | **jellyfin** | [![jellyfin](https://ag.hexor.cy/api/badge?name=jellyfin&revision=true)](https://ag.hexor.cy/applications/argocd/jellyfin) |
 | **k8s-secrets** | [![k8s-secrets](https://ag.hexor.cy/api/badge?name=k8s-secrets&revision=true)](https://ag.hexor.cy/applications/argocd/k8s-secrets) |
 | **khm** | [![khm](https://ag.hexor.cy/api/badge?name=khm&revision=true)](https://ag.hexor.cy/applications/argocd/khm) |
+| **lidarr** | [![lidarr](https://ag.hexor.cy/api/badge?name=lidarr&revision=true)](https://ag.hexor.cy/applications/argocd/lidarr) |
+| **mtproxy** | [![mtproxy](https://ag.hexor.cy/api/badge?name=mtproxy&revision=true)](https://ag.hexor.cy/applications/argocd/mtproxy) |
+| **n8n** | [![n8n](https://ag.hexor.cy/api/badge?name=n8n&revision=true)](https://ag.hexor.cy/applications/argocd/n8n) |
 | **ollama** | [![ollama](https://ag.hexor.cy/api/badge?name=ollama&revision=true)](https://ag.hexor.cy/applications/argocd/ollama) |
 | **paperless** | [![paperless](https://ag.hexor.cy/api/badge?name=paperless&revision=true)](https://ag.hexor.cy/applications/argocd/paperless) |
 | **pasarguard** | [![pasarguard](https://ag.hexor.cy/api/badge?name=pasarguard&revision=true)](https://ag.hexor.cy/applications/argocd/pasarguard) |
@@ -56,6 +63,7 @@ ArgoCD homelab project
 | **tg-bots** | [![tg-bots](https://ag.hexor.cy/api/badge?name=tg-bots&revision=true)](https://ag.hexor.cy/applications/argocd/tg-bots) |
 | **vaultwarden** | [![vaultwarden](https://ag.hexor.cy/api/badge?name=vaultwarden&revision=true)](https://ag.hexor.cy/applications/argocd/vaultwarden) |
 | **vpn** | [![vpn](https://ag.hexor.cy/api/badge?name=vpn&revision=true)](https://ag.hexor.cy/applications/argocd/vpn) |
+| **xandikos** | [![xandikos](https://ag.hexor.cy/api/badge?name=xandikos&revision=true)](https://ag.hexor.cy/applications/argocd/xandikos) |
 
 </td>
 </tr>

k8s/apps/comfyui/app.yaml

@@ -0,0 +1,20 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: comfyui
+  namespace: argocd
+spec:
+  project: apps
+  destination:
+    namespace: comfyui
+    server: https://kubernetes.default.svc
+  source:
+    repoURL: ssh://git@gt.hexor.cy:30022/ab/homelab.git
+    targetRevision: HEAD
+    path: k8s/apps/comfyui
+  syncPolicy:
+    automated:
+      selfHeal: true
+      prune: true
+    syncOptions:
+      - CreateNamespace=true

k8s/apps/comfyui/deployment.yaml

@@ -0,0 +1,57 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: comfyui
+  namespace: comfyui
+  labels:
+    app: comfyui
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: comfyui
+  template:
+    metadata:
+      labels:
+        app: comfyui
+    spec:
+      runtimeClassName: nvidia
+      tolerations:
+        - key: workload
+          operator: Equal
+          value: desktop
+          effect: NoSchedule
+      nodeSelector:
+        kubernetes.io/hostname: uk-desktop.tail2fe2d.ts.net
+      # Fix permissions mismatch usually happening when mapping host paths
+      securityContext:
+        runAsUser: 0
+      initContainers:
+        - name: create-data-dir
+          image: busybox
+          command: ["sh", "-c", "mkdir -p /host.data && chown -R 1000:1000 /host.data"]
+          volumeMounts:
+            - name: data
+              mountPath: /host.data
+      containers:
+        - name: comfyui
+          image: runpod/comfyui:latest-5090
+          imagePullPolicy: IfNotPresent
+          env:
+            - name: COMFYUI_PORT
+              value: "8188"
+          ports:
+            - containerPort: 8188
+              name: http
+              protocol: TCP
+          resources:
+            limits:
+              nvidia.com/gpu: 1
+          volumeMounts:
+            - name: data
+              # For ai-dock images, /workspace is the persistent user directory
+              mountPath: /workspace
+      volumes:
+        - name: data
+          persistentVolumeClaim:
+            claimName: comfyui-data-pvc

k8s/apps/comfyui/kustomization.yaml

@@ -0,0 +1,9 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+resources:
+  - namespace.yaml
+  - local-pv.yaml
+  - pvc.yaml
+  - deployment.yaml
+  - service.yaml

k8s/apps/comfyui/local-pv.yaml

@@ -0,0 +1,22 @@
+apiVersion: v1
+kind: PersistentVolume
+metadata:
+  name: comfyui-data-pv
+spec:
+  capacity:
+    storage: 200Gi
+  volumeMode: Filesystem
+  accessModes:
+  - ReadWriteOnce
+  persistentVolumeReclaimPolicy: Retain
+  storageClassName: local-path
+  local:
+    path: /data/comfyui
+  nodeAffinity:
+    required:
+      nodeSelectorTerms:
+      - matchExpressions:
+        - key: kubernetes.io/hostname
+          operator: In
+          values:
+          - uk-desktop.tail2fe2d.ts.net

k8s/apps/comfyui/namespace.yaml

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

k8s/apps/comfyui/pvc.yaml

@@ -0,0 +1,12 @@
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: comfyui-data-pvc
+  namespace: comfyui
+spec:
+  accessModes:
+    - ReadWriteOnce
+  storageClassName: local-path
+  resources:
+    requests:
+      storage: 200Gi

k8s/apps/comfyui/service.yaml

@@ -0,0 +1,15 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: comfyui
+  namespace: comfyui
+  labels:
+    app: comfyui
+spec:
+  ports:
+    - name: http
+      port: 8188
+      targetPort: 8188
+      protocol: TCP
+  selector:
+    app: comfyui

k8s/apps/furumi-server/app.yaml

@@ -0,0 +1,20 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: furumi-server
+  namespace: argocd
+spec:
+  project: apps
+  destination:
+    namespace: furumi-server
+    server: https://kubernetes.default.svc
+  source:
+    repoURL: ssh://git@gt.hexor.cy:30022/ab/homelab.git
+    targetRevision: HEAD
+    path: k8s/apps/furumi-server
+  syncPolicy:
+    automated:
+      selfHeal: true
+      prune: true
+    syncOptions:
+      - CreateNamespace=true

k8s/apps/furumi-server/deployment.yaml

@@ -0,0 +1,42 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: furumi-server
+  labels:
+    app: furumi-server
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: furumi-server
+  template:
+    metadata:
+      labels:
+        app: furumi-server
+    spec:
+      nodeSelector:
+        kubernetes.io/hostname: master.tail2fe2d.ts.net
+      containers:
+        - name: furumi-server
+          image: ultradesu/furumi-server:latest
+          imagePullPolicy: Always
+          env:
+            - name: FURUMI_TOKEN
+              value: "f38387266e75effe891b7953eb9c06b4"
+            - name: FURUMI_ROOT
+              value: "/media"
+          ports:
+            - name: grpc
+              containerPort: 50051
+              protocol: TCP
+            - name: metrics
+              containerPort: 9090
+              protocol: TCP
+          volumeMounts:
+            - name: music
+              mountPath: /media
+      volumes:
+        - name: music
+          hostPath:
+            path: /k8s/media/downloads/Lidarr_Music
+            type: DirectoryOrCreate

k8s/apps/furumi-server/kustomization.yaml

@@ -0,0 +1,8 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+resources:
+  - app.yaml
+  - deployment.yaml
+  - service.yaml
+  - servicemonitor.yaml

k8s/apps/furumi-server/service.yaml

@@ -0,0 +1,30 @@
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: furumi-server-grpc
+spec:
+  type: LoadBalancer
+  selector:
+    app: furumi-server
+  ports:
+    - name: grpc
+      protocol: TCP
+      port: 50051
+      targetPort: 50051
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: furumi-server-metrics
+  labels:
+    app: furumi-server
+spec:
+  type: ClusterIP
+  selector:
+    app: furumi-server
+  ports:
+    - name: metrics
+      protocol: TCP
+      port: 9090
+      targetPort: 9090

k8s/apps/furumi-server/servicemonitor.yaml

@@ -0,0 +1,21 @@
+---
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: furumi-server-metrics
+  labels:
+    app: furumi-server
+    release: prometheus
+spec:
+  selector:
+    matchLabels:
+      app: furumi-server
+  endpoints:
+    - port: metrics
+      path: /metrics
+      interval: 30s
+      scrapeTimeout: 10s
+      honorLabels: true
+  namespaceSelector:
+    matchNames:
+      - furumi-server

k8s/apps/gitea/deployment.yaml

@@ -77,8 +77,8 @@ spec:
       labels:
         app: gitea-runner
     spec:
-      nodeSelector:
-        kubernetes.io/hostname: home.homenet
+      #nodeSelector:
+      #  kubernetes.io/hostname: home.homenet
       volumes:
         - name: docker-sock
           hostPath:
@@ -90,27 +90,30 @@ spec:
       affinity:
         nodeAffinity:
           preferredDuringSchedulingIgnoredDuringExecution:
-          - weight: 3
-            preference:
-              matchExpressions:
-              - key: kubernetes.io/hostname
-                operator: In
-                values:
-                - home.homenet
           - weight: 1
             preference:
               matchExpressions:
               - key: kubernetes.io/hostname
                 operator: In
                 values:
-                - master.tail2fe2d.ts.net
+                - home.homenet
           - weight: 2
             preference:
               matchExpressions:
               - key: kubernetes.io/hostname
                 operator: In
                 values:
-                - nas.homenet
+                - master.tail2fe2d.ts.net
+          - weight: 3
+            preference:
+              matchExpressions:
+              - key: kubernetes.io/hostname
+                operator: In
+                values:
+                - it.tail2fe2d.ts.net
+                - ch.tail2fe2d.ts.net
+                - us.tail2fe2d.ts.net
+
           requiredDuringSchedulingIgnoredDuringExecution:
             nodeSelectorTerms:
             - matchExpressions:
@@ -118,7 +121,9 @@ spec:
                 operator: In
                 values:
                 - home.homenet
-                - nas.homenet
+                - it.tail2fe2d.ts.net
+                - ch.tail2fe2d.ts.net
+                - us.tail2fe2d.ts.net
                 - master.tail2fe2d.ts.net
       containers:
         - name: gitea-runner
@@ -149,3 +154,63 @@ spec:
               value: "k8s-runner"
             - name: GITEA_RUNNER_LABELS
               value: "ubuntu-latest:docker://ghcr.io/catthehacker/ubuntu:act-latest,ubuntu-22.04:docker://ghcr.io/catthehacker/ubuntu:act-22.04,ubuntu-20.04:docker://ghcr.io/catthehacker/ubuntu:act-20.04"
+
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: gitea-runner-desktop
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: gitea-runner-desktop
+  template:
+    metadata:
+      labels:
+        app: gitea-runner-desktop
+    spec:
+      nodeSelector:
+        kubernetes.io/hostname: uk-desktop.tail2fe2d.ts.net
+      tolerations:
+        - key: workload
+          operator: Equal
+          value: desktop
+          effect: NoSchedule
+      volumes:
+        - name: docker-sock
+          hostPath:
+            path: /var/run/docker.sock
+            type: Socket
+        - name: runner-data
+          emptyDir:
+            sizeLimit: 30Gi
+      containers:
+        - name: gitea-runner
+          image: gitea/act_runner:nightly
+          resources:
+            requests:
+              cpu: "100m"
+              memory: "256Mi"
+              ephemeral-storage: "1Gi"
+            limits:
+              cpu: "3000m"
+              memory: "4Gi"
+              ephemeral-storage: "28Gi"
+          volumeMounts:
+            - name: docker-sock
+              mountPath: /var/run/docker.sock
+            - name: runner-data
+              mountPath: /data
+          env:
+            - name: GITEA_INSTANCE_URL
+              value: "https://gt.hexor.cy"
+            - name: GITEA_RUNNER_REGISTRATION_TOKEN
+              valueFrom:
+                secretKeyRef:
+                  name: gitea-runner-act-runner-secrets
+                  key: token
+            - name: GITEA_RUNNER_NAME
+              value: "k8s-runner-desktop"
+            - name: GITEA_RUNNER_LABELS
+              value: "ubuntu-latest:docker://ghcr.io/catthehacker/ubuntu:act-latest,ubuntu-22.04:docker://ghcr.io/catthehacker/ubuntu:act-22.04,ubuntu-20.04:docker://ghcr.io/catthehacker/ubuntu:act-20.04"

k8s/apps/immich/deployments.yaml

@@ -74,19 +74,14 @@ spec:
                 - nas.homenet
       volumes:
       - name: upload-storage
-        nfs:
-          server: nas.homenet
-          path: /mnt/storage/Storage/k8s/immich/library/
-          readOnly: false
+        persistentVolumeClaim:
+          claimName: immich-upload-pvc
       - name: gphoto-storage
-        nfs:
-          server: nas.homenet
-          path: /mnt/storage/Storage/k8s/immich/GPHOTO/
-          readOnly: false
+        persistentVolumeClaim:
+          claimName: immich-gphoto-pvc
       - name: camera
-        nfs:
-          server: nas.homenet
-          path: /mnt/storage/Storage/Syncthing-repos/PhoneCamera/
+        persistentVolumeClaim:
+          claimName: immich-camera-pvc
           readOnly: true
       - name: localtime
         hostPath:

k8s/apps/immich/volumes.yaml

@@ -1,79 +1,52 @@
 ---
 apiVersion: v1
-kind: PersistentVolume
-metadata:
-  name: immich-upload-pv
-spec:
-  capacity:
-    storage: 500Gi
-  accessModes:
-    - ReadWriteOnce
-  hostPath:
-    path: /mnt/storage/Storage/k8s/immich/library
----
-apiVersion: v1
 kind: PersistentVolumeClaim
 metadata:
   name: immich-upload-pvc
   namespace: immich
 spec:
-  storageClassName: ""
   accessModes:
-    - ReadWriteOnce
-  volumeName: immich-upload-pv
+    - ReadWriteMany
+  storageClassName: nfs-csi
   resources:
     requests:
       storage: 500Gi
 ---
 apiVersion: v1
-kind: PersistentVolume
-metadata:
-  name: immich-gphoto-pv
-spec:
-  capacity:
-    storage: 500Gi
-  accessModes:
-    - ReadWriteOnce
-  hostPath:
-    path: /mnt/storage/Storage/k8s/immich/GPHOTO
----
-apiVersion: v1
 kind: PersistentVolumeClaim
 metadata:
   name: immich-gphoto-pvc
   namespace: immich
 spec:
-  storageClassName: ""
   accessModes:
-    - ReadWriteOnce
-  volumeName: immich-gphoto-pv
+    - ReadWriteMany
+  storageClassName: nfs-csi
   resources:
     requests:
       storage: 500Gi
 ---
 apiVersion: v1
-kind: PersistentVolume
-metadata:
-  name: immich-db-pv
-spec:
-  capacity:
-    storage: 10Gi
-  accessModes:
-    - ReadWriteOnce
-  hostPath:
-    path: /mnt/storage/Storage/k8s/immich/db
----
-apiVersion: v1
 kind: PersistentVolumeClaim
 metadata:
   name: immich-db-pvc
   namespace: immich
 spec:
-  storageClassName: ""
   accessModes:
-    - ReadWriteOnce
-  volumeName: immich-db-pv
+    - ReadWriteMany
+  storageClassName: nfs-csi
   resources:
     requests:
       storage: 10Gi
-
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: immich-camera-pvc
+  namespace: immich
+spec:
+  accessModes:
+    - ReadOnlyMany
+  storageClassName: nfs-csi
+  resources:
+    requests:
+      storage: 100Gi

k8s/apps/k8s-secrets/deployment.yaml

@@ -19,7 +19,7 @@ spec:
         kubernetes.io/os: linux
       containers:
       - name: secret-reader
-        image: ultradesu/k8s-secrets:0.1.1
+        image: ultradesu/k8s-secrets:0.2.1
         imagePullPolicy: Always
         args:
           - "--secrets"
@@ -28,6 +28,7 @@ spec:
           - "k8s-secret"
           - "--port"
           - "3000"
+          - "--webhook"
         ports:
         - containerPort: 3000
           name: http

k8s/apps/lidarr/app.yaml

@@ -0,0 +1,20 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: lidarr
+  namespace: argocd
+spec:
+  project: apps
+  destination:
+    namespace: lidarr
+    server: https://kubernetes.default.svc
+  source:
+    repoURL: ssh://git@gt.hexor.cy:30022/ab/homelab.git
+    targetRevision: HEAD
+    path: k8s/apps/lidarr
+  syncPolicy:
+    automated:
+      selfHeal: true
+      prune: true
+    syncOptions:
+      - CreateNamespace=true

k8s/apps/lidarr/kustomization.yaml

@@ -0,0 +1,14 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+resources:
+  - app.yaml
+
+helmCharts:
+  - name: lidarr
+    repo: https://k8s-home-lab.github.io/helm-charts/
+    version: 15.3.0
+    releaseName: lidarr
+    namespace: lidarr
+    valuesFile: lidarr-values.yaml
+    includeCRDs: true

k8s/apps/lidarr/lidarr-values.yaml

@@ -0,0 +1,27 @@
+env:
+  TZ: Asia/Nicosia
+
+resources:
+  requests:
+    memory: "512Mi"
+    cpu: "200m"
+  limits:
+    memory: "2Gi"
+    cpu: "1500m"
+
+nodeSelector:
+  kubernetes.io/hostname: master.tail2fe2d.ts.net
+
+persistence:
+  config:
+    enabled: true
+    type: hostPath
+    hostPath: /k8s/lidarr
+    mountPath: /config
+
+  downloads:
+    enabled: true
+    type: hostPath
+    hostPath: /k8s/media/downloads
+    mountPath: /downloads
+    accessMode: ReadWriteOnce

k8s/apps/mtproxy/Dockerfile

@@ -0,0 +1,53 @@
+FROM --platform=$BUILDPLATFORM debian:bookworm-slim AS builder
+
+ARG TARGETARCH
+
+RUN apt-get update && apt-get install -y \
+    git curl make gcc libssl-dev zlib1g-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN if [ "$(dpkg --print-architecture)" != "$TARGETARCH" ]; then \
+      dpkg --add-architecture $TARGETARCH && \
+      apt-get update && \
+      case "$TARGETARCH" in \
+        arm64) apt-get install -y gcc-aarch64-linux-gnu libssl-dev:arm64 zlib1g-dev:arm64 ;; \
+        amd64) apt-get install -y gcc-x86-64-linux-gnu libssl-dev:amd64 zlib1g-dev:amd64 ;; \
+      esac && \
+      rm -rf /var/lib/apt/lists/*; \
+    fi
+
+RUN git clone https://github.com/TelegramMessenger/MTProxy.git /src
+WORKDIR /src
+
+RUN NATIVE=$(dpkg --print-architecture) && \
+    if [ "$NATIVE" != "$TARGETARCH" ]; then \
+      case "$TARGETARCH" in \
+        arm64) export CC=aarch64-linux-gnu-gcc ;; \
+        amd64) export CC=x86_64-linux-gnu-gcc ;; \
+      esac; \
+    fi && \
+    make -j$(nproc)
+
+FROM debian:bookworm-slim
+
+ENV PROXY_PORT=30443
+ENV STATS_PORT=8888
+ENV WORKERS=1
+ENV RUN_USER=nobody
+
+RUN apt-get update && apt-get install -y \
+    curl libssl3 zlib1g xxd \
+    && rm -rf /var/lib/apt/lists/*
+
+COPY --from=builder /src/objs/bin/mtproto-proxy /usr/local/bin/mtproto-proxy
+
+RUN curl -s https://core.telegram.org/getProxySecret -o /etc/mtproxy/proxy-secret --create-dirs && \
+    curl -s https://core.telegram.org/getProxyConfig -o /etc/mtproxy/proxy-multi.conf
+
+ENTRYPOINT mtproto-proxy \
+    -u ${RUN_USER} \
+    -p ${STATS_PORT} \
+    -H ${PROXY_PORT} \
+    -M ${WORKERS} \
+    --aes-pwd /etc/mtproxy/proxy-secret \
+    /etc/mtproxy/proxy-multi.conf

k8s/apps/mtproxy/app.yaml

@@ -0,0 +1,20 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: mtproxy
+  namespace: argocd
+spec:
+  project: apps
+  destination:
+    namespace: mtproxy
+    server: https://kubernetes.default.svc
+  source:
+    repoURL: ssh://git@gt.hexor.cy:30022/ab/homelab.git
+    targetRevision: HEAD
+    path: k8s/apps/mtproxy
+  syncPolicy:
+    automated:
+      selfHeal: true
+      prune: true
+    syncOptions:
+      - CreateNamespace=true

k8s/apps/mtproxy/daemonset.yaml

@@ -0,0 +1,117 @@
+---
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  name: mtproxy
+  labels:
+    app: mtproxy
+spec:
+  selector:
+    matchLabels:
+      app: mtproxy
+  updateStrategy:
+    type: RollingUpdate
+  template:
+    metadata:
+      labels:
+        app: mtproxy
+    spec:
+      affinity:
+        nodeAffinity:
+          requiredDuringSchedulingIgnoredDuringExecution:
+            nodeSelectorTerms:
+              - matchExpressions:
+                  - key: mtproxy
+                    operator: Exists
+      serviceAccountName: mtproxy
+      hostNetwork: true
+      dnsPolicy: ClusterFirstWithHostNet
+      initContainers:
+        - name: register-proxy
+          image: bitnami/kubectl:latest
+          env:
+            - name: NODE_NAME
+              valueFrom:
+                fieldRef:
+                  fieldPath: spec.nodeName
+            - name: SECRET
+              valueFrom:
+                secretKeyRef:
+                  name: tgproxy-secret
+                  key: SECRET
+            - name: PORT
+              valueFrom:
+                secretKeyRef:
+                  name: tgproxy-secret
+                  key: PORT
+          volumeMounts:
+            - name: data
+              mountPath: /data
+          command:
+            - /bin/bash
+            - -c
+            - |
+              set -e
+              curl -s https://core.telegram.org/getProxySecret -o /data/proxy-secret
+              curl -s https://core.telegram.org/getProxyConfig -o /data/proxy-multi.conf
+              NAMESPACE=$(cat /var/run/secrets/kubernetes.io/serviceaccount/namespace)
+              SERVER=$(kubectl get node "${NODE_NAME}" -o jsonpath='{.metadata.labels.mtproxy}')
+              if [ -z "${SERVER}" ]; then
+                echo "ERROR: node ${NODE_NAME} has no mtproxy label"
+                exit 1
+              fi
+              LINK="tg://proxy?server=${SERVER}&port=${PORT}&secret=${SECRET}"
+              echo "Registering: ${SERVER} -> ${LINK}"
+              if kubectl get secret mtproxy-links -n "${NAMESPACE}" &>/dev/null; then
+                kubectl patch secret mtproxy-links -n "${NAMESPACE}" \
+                  --type merge -p "{\"stringData\":{\"${SERVER}\":\"${LINK}\"}}"
+              else
+                kubectl create secret generic mtproxy-links -n "${NAMESPACE}" \
+                  --from-literal="${SERVER}=${LINK}"
+              fi
+              echo "Done"
+      containers:
+        - name: mtproxy
+          image: telegrammessenger/proxy:latest
+          # image: ultradesu/mtproxy:v0.02
+          imagePullPolicy: Always
+          ports:
+            - name: proxy
+              containerPort: 30443
+              protocol: TCP
+          command:
+            - /bin/sh
+            - -c
+            - >-
+              mtproto-proxy
+              -u nobody
+              -p 8888
+              -H $(PORT)
+              -M 1
+              -S $(SECRET)
+              --aes-pwd /data/proxy-secret
+              /data/proxy-multi.conf
+          env:
+            - name: SECRET
+              valueFrom:
+                secretKeyRef:
+                  name: tgproxy-secret
+                  key: SECRET
+            - name: PORT
+              valueFrom:
+                secretKeyRef:
+                  name: tgproxy-secret
+                  key: PORT
+          volumeMounts:
+            - name: data
+              mountPath: /data
+         #resources:
+         #  requests:
+         #    memory: "128Mi"
+         #    cpu: "100m"
+         #  limits:
+         #    memory: "256Mi"
+         #    cpu: "500m"
+      volumes:
+        - name: data
+          emptyDir: {}

k8s/apps/mtproxy/external-secrets.yaml

@@ -0,0 +1,25 @@
+---
+apiVersion: external-secrets.io/v1
+kind: ExternalSecret
+metadata:
+  name: tgproxy-secret
+spec:
+  target:
+    name: tgproxy-secret
+    deletionPolicy: Delete
+    template:
+      type: Opaque
+      data:
+        SECRET: |-
+          {{ .secret }}
+        PORT: "30443"
+  data:
+    - secretKey: secret
+      sourceRef:
+        storeRef:
+          name: vaultwarden-login
+          kind: ClusterSecretStore
+      remoteRef:
+        key: 58a37daf-72d8-430d-86bd-6152aa8f888d
+        property: fields[0].value
+

k8s/apps/mtproxy/kustomization.yaml

@@ -0,0 +1,11 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+resources:
+  - ./app.yaml
+  - ./rbac.yaml
+  - ./daemonset.yaml
+  - ./external-secrets.yaml
+  - ./service.yaml
+  - ./secret-reader.yaml
+# - ./storage.yaml

k8s/apps/mtproxy/rbac.yaml

@@ -0,0 +1,58 @@
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: mtproxy
+  labels:
+    app: mtproxy
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: mtproxy-node-reader
+  labels:
+    app: mtproxy
+rules:
+  - apiGroups: [""]
+    resources: ["nodes"]
+    verbs: ["get", "list"]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: mtproxy-node-reader
+  labels:
+    app: mtproxy
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: mtproxy-node-reader
+subjects:
+  - kind: ServiceAccount
+    name: mtproxy
+    namespace: mtproxy
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: Role
+metadata:
+  name: mtproxy-secret-manager
+  labels:
+    app: mtproxy
+rules:
+  - apiGroups: [""]
+    resources: ["secrets"]
+    verbs: ["get", "create", "patch"]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: RoleBinding
+metadata:
+  name: mtproxy-secret-manager
+  labels:
+    app: mtproxy
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: mtproxy-secret-manager
+subjects:
+  - kind: ServiceAccount
+    name: mtproxy

k8s/apps/mtproxy/secret-reader.yaml

@@ -0,0 +1,63 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: secret-reader
+  labels:
+    app: secret-reader
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: secret-reader
+  template:
+    metadata:
+      labels:
+        app: secret-reader
+    spec:
+      serviceAccountName: mtproxy
+      nodeSelector:
+        kubernetes.io/os: linux
+      containers:
+      - name: secret-reader
+        image: ultradesu/k8s-secrets:0.2.1
+        imagePullPolicy: Always
+        args:
+          - "--secrets"
+          - "mtproxy-links"
+          - "--namespace"
+          - "mtproxy"
+          - "--port"
+          - "3000"
+        ports:
+        - containerPort: 3000
+          name: http
+        env:
+        - name: RUST_LOG
+          value: "info"
+        resources:
+          requests:
+            memory: "64Mi"
+            cpu: "50m"
+          limits:
+            memory: "128Mi"
+            cpu: "150m"
+        livenessProbe:
+          httpGet:
+            path: /health
+            port: http
+          initialDelaySeconds: 10
+          periodSeconds: 10
+        readinessProbe:
+          httpGet:
+            path: /health
+            port: http
+          initialDelaySeconds: 5
+          periodSeconds: 5
+        securityContext:
+          runAsNonRoot: true
+          runAsUser: 1000
+          allowPrivilegeEscalation: false
+          readOnlyRootFilesystem: true
+          capabilities:
+            drop:
+            - ALL

k8s/apps/mtproxy/service.yaml

@@ -0,0 +1,16 @@
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: secret-reader
+  labels:
+    app: secret-reader
+spec:
+  type: ClusterIP
+  selector:
+    app: secret-reader
+  ports:
+  - port: 80
+    targetPort: 3000
+    protocol: TCP
+    name: http

k8s/apps/mtproxy/storage.yaml

@@ -0,0 +1,12 @@
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: mtproxy-data
+spec:
+  accessModes:
+    - ReadWriteOnce
+  storageClassName: longhorn
+  resources:
+    requests:
+      storage: 1Gi

k8s/apps/n8n/app.yaml

@@ -0,0 +1,21 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: n8n
+  namespace: argocd
+spec:
+  project: apps
+  destination:
+    namespace: n8n
+    server: https://kubernetes.default.svc
+  source:
+    repoURL: ssh://git@gt.hexor.cy:30022/ab/homelab.git
+    targetRevision: HEAD
+    path: k8s/apps/n8n
+  syncPolicy:
+    automated:
+      selfHeal: true
+      prune: true
+    syncOptions:
+      - CreateNamespace=true
+

k8s/apps/n8n/deployment-main.yaml

@@ -0,0 +1,165 @@
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: n8n-main
+  labels:
+    app: n8n
+    component: main
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: n8n
+      component: main
+  template:
+    metadata:
+      labels:
+        app: n8n
+        component: main
+    spec:
+      serviceAccountName: n8n
+      initContainers:
+      - name: install-tools
+        image: alpine:3.22
+        command:
+        - /bin/sh
+        - -c
+        - |
+          set -e
+          if [ -x /tools/kubectl ]; then
+            echo "kubectl already exists, skipping download"
+            /tools/kubectl version --client
+            exit 0
+          fi
+          echo "Downloading kubectl..."
+          ARCH=$(uname -m)
+          case $ARCH in
+            x86_64) ARCH="amd64" ;;
+            aarch64) ARCH="arm64" ;;
+          esac
+          wget -O /tools/kubectl "https://dl.k8s.io/release/$(wget -qO- https://dl.k8s.io/release/stable.txt)/bin/linux/${ARCH}/kubectl"
+          chmod +x /tools/kubectl
+          /tools/kubectl version --client
+        volumeMounts:
+        - name: tools
+          mountPath: /tools
+        securityContext:
+          runAsUser: 1000
+          runAsGroup: 1000
+          runAsNonRoot: true
+      containers:
+      - name: n8n
+        image: n8nio/n8n:latest
+        ports:
+        - containerPort: 5678
+          name: http
+        - containerPort: 5679
+          name: task-broker
+        env:
+        - name: PATH
+          value: "/opt/tools:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin"
+        - name: HOME
+          value: "/home/node"
+        - name: N8N_ENFORCE_SETTINGS_FILE_PERMISSIONS
+          value: "true"
+        - name: NODES_EXCLUDE
+          value: "[]"
+        - name: N8N_HOST
+          value: "n8n.hexor.cy"
+        - name: N8N_PORT
+          value: "5678"
+        - name: N8N_PROTOCOL
+          value: "https"
+        - name: N8N_RUNNERS_ENABLED
+          value: "true"
+        - name: N8N_RUNNERS_MODE
+          value: "external"
+        - name: N8N_RUNNERS_BROKER_LISTEN_ADDRESS
+          value: "0.0.0.0"
+        - name: N8N_LISTEN_ADDRESS
+          value: "0.0.0.0"
+        - name: N8N_RUNNERS_BROKER_PORT
+          value: "5679"
+        - name: EXECUTIONS_MODE
+          value: "queue"
+        - name: QUEUE_BULL_REDIS_HOST
+          value: "n8n-redis"
+        - name: QUEUE_BULL_REDIS_PORT
+          value: "6379"
+        - name: NODE_ENV
+          value: "production"
+        - name: WEBHOOK_URL
+          value: "https://n8n.hexor.cy/"
+        - name: N8N_PROXY_HOPS
+          value: "1"
+        - name: GENERIC_TIMEZONE
+          value: "Europe/Moscow"
+        - name: TZ
+          value: "Europe/Moscow"
+        - name: DB_TYPE
+          value: "postgresdb"
+        - name: DB_POSTGRESDB_HOST
+          value: "psql.psql.svc"
+        - name: DB_POSTGRESDB_DATABASE
+          value: "n8n"
+        - name: DB_POSTGRESDB_USER
+          valueFrom:
+            secretKeyRef:
+              name: credentials
+              key: username
+        - name: DB_POSTGRESDB_PASSWORD
+          valueFrom:
+            secretKeyRef:
+              name: credentials
+              key: password
+        - name: N8N_ENCRYPTION_KEY
+          valueFrom:
+            secretKeyRef:
+              name: credentials
+              key: encryptionkey
+        - name: N8N_RUNNERS_AUTH_TOKEN
+          valueFrom:
+            secretKeyRef:
+              name: credentials
+              key: runnertoken
+        volumeMounts:
+        - name: n8n-data
+          mountPath: /home/node/.n8n
+        - name: tools
+          mountPath: /opt/tools
+        resources:
+          requests:
+            cpu: 2000m
+            memory: 512Mi
+          limits:
+            cpu: 4000m
+            memory: 2048Mi
+        livenessProbe:
+          httpGet:
+            path: /healthz
+            port: http
+          initialDelaySeconds: 240
+          periodSeconds: 30
+          timeoutSeconds: 20
+          failureThreshold: 10
+        readinessProbe:
+          httpGet:
+            path: /healthz/readiness
+            port: http
+          initialDelaySeconds: 120
+          periodSeconds: 10
+          timeoutSeconds: 5
+          failureThreshold: 15
+      volumes:
+      - name: n8n-data
+        persistentVolumeClaim:
+          claimName: n8n-data
+      - name: tools
+        persistentVolumeClaim:
+          claimName: n8n-tools
+      securityContext:
+        runAsUser: 1000
+        runAsGroup: 1000
+        runAsNonRoot: true
+        fsGroup: 1000

k8s/apps/n8n/deployment-runner.yaml

@@ -0,0 +1,87 @@
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: n8n-runner
+  labels:
+    app: n8n
+    component: runner
+spec:
+  replicas: 2
+  selector:
+    matchLabels:
+      app: n8n
+      component: runner
+  template:
+    metadata:
+      labels:
+        app: n8n
+        component: runner
+    spec:
+      serviceAccountName: n8n
+      containers:
+      - name: n8n-runner
+        image: n8nio/runners:latest
+        ports:
+        - containerPort: 5680
+          name: health
+        env:
+        - name: PATH
+          value: "/opt/tools:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin"
+        - name: HOME
+          value: "/home/node"
+        - name: N8N_RUNNERS_TASK_BROKER_URI
+          value: "http://n8n:5679"
+        - name: N8N_RUNNERS_LAUNCHER_LOG_LEVEL
+          value: "info"
+        - name: N8N_RUNNERS_MAX_CONCURRENCY
+          value: "10"
+        - name: GENERIC_TIMEZONE
+          value: "Europe/Moscow"
+        - name: TZ
+          value: "Europe/Moscow"
+        - name: N8N_RUNNERS_AUTH_TOKEN
+          valueFrom:
+            secretKeyRef:
+              name: credentials
+              key: runnertoken
+        volumeMounts:
+        - name: n8n-data
+          mountPath: /home/node/.n8n
+        - name: tools
+          mountPath: /opt/tools
+        resources:
+          requests:
+            cpu: 500m
+            memory: 512Mi
+          limits:
+            cpu: 2000m
+            memory: 2048Mi
+        livenessProbe:
+          httpGet:
+            path: /healthz
+            port: 5680
+          initialDelaySeconds: 30
+          periodSeconds: 30
+          timeoutSeconds: 5
+          failureThreshold: 3
+        readinessProbe:
+          httpGet:
+            path: /healthz
+            port: 5680
+          initialDelaySeconds: 15
+          periodSeconds: 10
+          timeoutSeconds: 5
+          failureThreshold: 3
+      volumes:
+      - name: n8n-data
+        persistentVolumeClaim:
+          claimName: n8n-data
+      - name: tools
+        persistentVolumeClaim:
+          claimName: n8n-tools
+      securityContext:
+        runAsUser: 1000
+        runAsGroup: 1000
+        runAsNonRoot: true
+        fsGroup: 1000

k8s/apps/n8n/deployment-worker.yaml

@@ -0,0 +1,84 @@
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: n8n-worker
+  labels:
+    app: n8n
+    component: worker
+spec:
+  replicas: 2
+  selector:
+    matchLabels:
+      app: n8n
+      component: worker
+  template:
+    metadata:
+      labels:
+        app: n8n
+        component: worker
+    spec:
+      serviceAccountName: n8n
+      containers:
+      - name: n8n-worker
+        image: n8nio/n8n:latest
+        command:
+        - n8n
+        - worker
+        env:
+        - name: HOME
+          value: "/home/node"
+        - name: N8N_ENFORCE_SETTINGS_FILE_PERMISSIONS
+          value: "true"
+        - name: EXECUTIONS_MODE
+          value: "queue"
+        - name: QUEUE_BULL_REDIS_HOST
+          value: "n8n-redis"
+        - name: QUEUE_BULL_REDIS_PORT
+          value: "6379"
+        - name: NODE_ENV
+          value: "production"
+        - name: GENERIC_TIMEZONE
+          value: "Europe/Moscow"
+        - name: TZ
+          value: "Europe/Moscow"
+        - name: DB_TYPE
+          value: "postgresdb"
+        - name: DB_POSTGRESDB_HOST
+          value: "psql.psql.svc"
+        - name: DB_POSTGRESDB_DATABASE
+          value: "n8n"
+        - name: DB_POSTGRESDB_USER
+          valueFrom:
+            secretKeyRef:
+              name: credentials
+              key: username
+        - name: DB_POSTGRESDB_PASSWORD
+          valueFrom:
+            secretKeyRef:
+              name: credentials
+              key: password
+        - name: N8N_ENCRYPTION_KEY
+          valueFrom:
+            secretKeyRef:
+              name: credentials
+              key: encryptionkey
+        volumeMounts:
+        - name: n8n-data
+          mountPath: /home/node/.n8n
+        resources:
+          requests:
+            cpu: 500m
+            memory: 512Mi
+          limits:
+            cpu: 2000m
+            memory: 2048Mi
+      volumes:
+      - name: n8n-data
+        persistentVolumeClaim:
+          claimName: n8n-data
+      securityContext:
+        runAsUser: 1000
+        runAsGroup: 1000
+        runAsNonRoot: true
+        fsGroup: 1000

k8s/apps/n8n/external-secrets.yaml

@@ -0,0 +1,50 @@
+---
+apiVersion: external-secrets.io/v1
+kind: ExternalSecret
+metadata:
+  name: credentials
+spec:
+  target:
+    name: credentials
+    deletionPolicy: Delete
+    template:
+      type: Opaque
+      data:
+        password: "{{ .psql | trim }}"
+        username: "n8n"
+        encryptionkey: "{{ .enc_pass | trim }}"
+        runnertoken: "{{ .runner_token | trim }}"
+  data:
+    - secretKey: psql
+      sourceRef:
+        storeRef:
+          name: vaultwarden-login
+          kind: ClusterSecretStore
+      remoteRef:
+        conversionStrategy: Default
+        decodingStrategy: None
+        metadataPolicy: None
+        key: 2a9deb39-ef22-433e-a1be-df1555625e22
+        property: fields[13].value
+    - secretKey: enc_pass
+      sourceRef:
+        storeRef:
+          name: vaultwarden-login
+          kind: ClusterSecretStore
+      remoteRef:
+        conversionStrategy: Default
+        decodingStrategy: None
+        metadataPolicy: None
+        key: 18c92d73-9637-4419-8642-7f7b308460cb
+        property: fields[0].value
+    - secretKey: runner_token
+      sourceRef:
+        storeRef:
+          name: vaultwarden-login
+          kind: ClusterSecretStore
+      remoteRef:
+        conversionStrategy: Default
+        decodingStrategy: None
+        metadataPolicy: None
+        key: 18c92d73-9637-4419-8642-7f7b308460cb
+        property: fields[1].value

k8s/apps/n8n/ingress.yaml

@@ -0,0 +1,28 @@
+---
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: n8n
+  labels:
+    app: n8n
+  annotations:
+    cert-manager.io/cluster-issuer: letsencrypt
+    traefik.ingress.kubernetes.io/router.middlewares: kube-system-https-redirect@kubernetescrd
+    traefik.ingress.kubernetes.io/router.tls: "true"
+spec:
+  ingressClassName: traefik
+  tls:
+  - hosts:
+    - n8n.hexor.cy
+    secretName: n8n-tls
+  rules:
+  - host: n8n.hexor.cy
+    http:
+      paths:
+      - path: /
+        pathType: Prefix
+        backend:
+          service:
+            name: n8n
+            port:
+              number: 80

k8s/apps/n8n/kustomization.yaml

@@ -0,0 +1,28 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+resources:
+  - external-secrets.yaml
+  - storage.yaml
+  - rbac.yaml
+  - redis-deployment.yaml
+  - redis-service.yaml
+  - paddleocr-deployment.yaml
+  - paddleocr-service.yaml
+  - deployment-main.yaml
+  - deployment-worker.yaml
+  - deployment-runner.yaml
+  - service.yaml
+  - ingress.yaml
+
+helmCharts:
+  - name: yacy
+    repo: https://gt.hexor.cy/api/packages/ab/helm
+    version: 0.1.2
+    releaseName: yacy
+    namespace: n8n
+    valuesFile: values-yacy.yaml
+    includeCRDs: true
+
+commonLabels:
+  app.kubernetes.io/name: n8n

k8s/apps/n8n/paddleocr-deployment.yaml

@@ -0,0 +1,43 @@
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: paddleocr
+  labels:
+    app: paddleocr
+    component: n8n
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: paddleocr
+      component: n8n
+  template:
+    metadata:
+      labels:
+        app: paddleocr
+        component: n8n
+    spec:
+      containers:
+      - name: paddleocr
+        image: c403/paddleocr
+        ports:
+        - containerPort: 5000
+          name: http
+        resources:
+          requests:
+            cpu: 200m
+            memory: 512Mi
+          limits:
+            cpu: 1000m
+            memory: 2Gi
+        livenessProbe:
+          tcpSocket:
+            port: 5000
+          initialDelaySeconds: 60
+          periodSeconds: 30
+        readinessProbe:
+          tcpSocket:
+            port: 5000
+          initialDelaySeconds: 30
+          periodSeconds: 10

k8s/apps/n8n/paddleocr-service.yaml

@@ -0,0 +1,18 @@
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: paddleocr
+  labels:
+    app: paddleocr
+    component: n8n
+spec:
+  selector:
+    app: paddleocr
+    component: n8n
+  ports:
+  - name: http
+    port: 80
+    targetPort: 5000
+    protocol: TCP
+  type: ClusterIP

k8s/apps/n8n/rbac.yaml

@@ -0,0 +1,45 @@
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: n8n
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: n8n-clusterrole
+rules:
+  # Core API group ("")
+  - apiGroups: [""]
+    resources: ["*"]
+    verbs: ["get", "list", "watch"]
+
+  # Common built-in API groups
+  - apiGroups: ["apps", "batch", "autoscaling", "extensions", "policy"]
+    resources: ["*"]
+    verbs: ["get", "list", "watch"]
+
+  - apiGroups: ["networking.k8s.io", "rbac.authorization.k8s.io", "apiextensions.k8s.io"]
+    resources: ["*"]
+    verbs: ["get", "list", "watch"]
+
+  - apiGroups: ["coordination.k8s.io", "discovery.k8s.io", "events.k8s.io"]
+    resources: ["*"]
+    verbs: ["get", "list", "watch"]
+
+  - apiGroups: ["storage.k8s.io", "admissionregistration.k8s.io", "authentication.k8s.io", "authorization.k8s.io"]
+    resources: ["*"]
+    verbs: ["get", "list", "watch"]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: n8n-clusterrolebinding
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: n8n-clusterrole
+subjects:
+- kind: ServiceAccount
+  name: n8n
+  namespace: n8n

k8s/apps/n8n/redis-deployment.yaml

@@ -0,0 +1,57 @@
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: n8n-redis
+  labels:
+    app: redis
+    component: n8n
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: redis
+      component: n8n
+  template:
+    metadata:
+      labels:
+        app: redis
+        component: n8n
+    spec:
+      containers:
+      - name: redis
+        image: redis:7-alpine
+        ports:
+        - containerPort: 6379
+          name: redis
+        command:
+        - redis-server
+        - --appendonly
+        - "yes"
+        - --save
+        - "900 1"
+        volumeMounts:
+        - name: redis-data
+          mountPath: /data
+        resources:
+          requests:
+            cpu: 50m
+            memory: 64Mi
+          limits:
+            cpu: 200m
+            memory: 256Mi
+        livenessProbe:
+          tcpSocket:
+            port: 6379
+          initialDelaySeconds: 30
+          periodSeconds: 10
+        readinessProbe:
+          exec:
+            command:
+            - redis-cli
+            - ping
+          initialDelaySeconds: 5
+          periodSeconds: 5
+      volumes:
+      - name: redis-data
+        emptyDir: {}

k8s/apps/n8n/redis-service.yaml

@@ -0,0 +1,18 @@
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: n8n-redis
+  labels:
+    app: redis
+    component: n8n
+spec:
+  selector:
+    app: redis
+    component: n8n
+  ports:
+  - name: redis
+    port: 6379
+    targetPort: 6379
+    protocol: TCP
+  type: ClusterIP

k8s/apps/n8n/service.yaml

@@ -0,0 +1,21 @@
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: n8n
+  labels:
+    app: n8n
+spec:
+  selector:
+    app: n8n
+    component: main
+  ports:
+  - name: http
+    port: 80
+    targetPort: 5678
+    protocol: TCP
+  - name: task-broker
+    port: 5679
+    targetPort: 5679
+    protocol: TCP
+  type: ClusterIP

k8s/apps/n8n/storage.yaml

@@ -0,0 +1,24 @@
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: n8n-data
+spec:
+  accessModes:
+    - ReadWriteMany
+  storageClassName: longhorn
+  resources:
+    requests:
+      storage: 10Gi
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: n8n-tools
+spec:
+  accessModes:
+    - ReadWriteMany
+  storageClassName: longhorn
+  resources:
+    requests:
+      storage: 20Gi

k8s/apps/n8n/values-yacy.yaml

@@ -0,0 +1,24 @@
+nodeSelector:
+  kubernetes.io/hostname: master.tail2fe2d.ts.net
+
+resources:
+  limits:
+    memory: 2Gi
+  requests:
+    memory: 1Gi
+
+persistence:
+  enabled: true
+  size: 10Gi
+
+yacy:
+  network:
+    mode: "intranet"
+  config:
+    network.unit.bootstrap.seedlist: ""
+    network.unit.remotecrawl: "false"
+    network.unit.dhtredundancy.junior: "1"
+    network.unit.dhtredundancy.senior: "1"
+    index.receive.allow: "false"
+    index.distribute.allow: "false"
+    crawl.response.timeout: "10000"

k8s/apps/ollama/kustomization.yaml

@@ -3,19 +3,23 @@ kind: Kustomization
 
 resources:
   - external-secrets.yaml
+  - local-pv.yaml
   
 helmCharts:
   - name: ollama
     repo: https://otwld.github.io/ollama-helm/
-    version: 0.4.0
+    version: 1.49.0
     releaseName: ollama
     namespace: ollama
     valuesFile: ollama-values.yaml
     includeCRDs: true
   - name: open-webui
     repo: https://helm.openwebui.com/
-    version: 8.14.0
+    version: 12.8.1
     releaseName: openweb-ui
     namespace: ollama
     valuesFile: openweb-ui-values.yaml
-    includeCRDs: true
+    includeCRDs: true
+
+patches:
+  - path: patch-runtimeclass.yaml

k8s/apps/ollama/local-pv.yaml

@@ -0,0 +1,22 @@
+apiVersion: v1
+kind: PersistentVolume
+metadata:
+  name: ollama-local-pv
+spec:
+  capacity:
+    storage: 100Gi
+  volumeMode: Filesystem
+  accessModes:
+  - ReadWriteOnce
+  persistentVolumeReclaimPolicy: Retain
+  storageClassName: local-path
+  local:
+    path: /var/lib/ollama
+  nodeAffinity:
+    required:
+      nodeSelectorTerms:
+      - matchExpressions:
+        - key: kubernetes.io/hostname
+          operator: In
+          values:
+          - uk-desktop.tail2fe2d.ts.net

k8s/apps/ollama/ollama-values.yaml

@@ -3,6 +3,20 @@ image:
   pullPolicy: Always
   tag: "latest"
 nodeSelector:
-  kubernetes.io/hostname: master.tail2fe2d.ts.net
+  kubernetes.io/hostname: uk-desktop.tail2fe2d.ts.net
+tolerations:
+  - key: workload
+    operator: Equal
+    value: desktop
+    effect: NoSchedule
 ingress:
     enabled: false
+ollama:
+  gpu:
+    enabled: true
+    type: 'nvidia'
+    number: 1
+persistentVolume:
+  enabled: true
+  size: 100Gi
+  storageClass: "local-path"

k8s/apps/ollama/openweb-ui-values.yaml

@@ -1,4 +1,4 @@
-clusterDomain: ai.hexor.cy
+clusterDomain: cluster.local
 
 extraEnvVars:
   GLOBAL_LOG_LEVEL: debug
@@ -32,12 +32,22 @@ ollama:
         
 pipelines:
   enabled: true
+  nodeSelector:
+    kubernetes.io/hostname: master.tail2fe2d.ts.net
   
 tika:
   enabled: true
+  nodeSelector:
+    kubernetes.io/hostname: master.tail2fe2d.ts.net
   
 websocket:
   enabled: true
+  nodeSelector:
+    kubernetes.io/hostname: master.tail2fe2d.ts.net
+  redis:
+    master:
+      nodeSelector:
+        kubernetes.io/hostname: master.tail2fe2d.ts.net
 
 ingress:
     enabled: true
@@ -46,7 +56,5 @@ ingress:
       cert-manager.io/cluster-issuer: letsencrypt
       traefik.ingress.kubernetes.io/router.middlewares: kube-system-https-redirect@kubernetescrd
     host: "ai.hexor.cy"
-    tls:
-      - hosts:
-          - '*.hexor.cy'
-        secretName: ollama-tls
+    tls: true
+    existingSecret: ollama-tls

k8s/apps/ollama/patch-runtimeclass.yaml

@@ -0,0 +1,9 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: ollama
+  namespace: ollama
+spec:
+  template:
+    spec:
+      runtimeClassName: nvidia

k8s/apps/paperless/kustomization.yaml

@@ -4,6 +4,7 @@ kind: Kustomization
 resources:
   - app.yaml
   - external-secrets.yaml
+  - paperless-ai.yaml
 
 helmCharts:
   - name: paperless-ngx

k8s/apps/paperless/paperless-ai.yaml

@@ -0,0 +1,101 @@
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: paperless-ai
+  labels:
+    app: paperless-ai
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: paperless-ai
+  template:
+    metadata:
+      labels:
+        app: paperless-ai
+    spec:
+      nodeSelector:
+        kubernetes.io/hostname: nas.homenet
+      containers:
+        - name: paperless-ai
+          image: clusterzx/paperless-ai:latest
+          imagePullPolicy: Always
+          ports:
+            - containerPort: 3000
+              name: http
+          env:
+            - name: NODE_ENV
+              value: production
+            - name: PAPERLESS_AI_PORT
+              value: "3000"
+          resources:
+            requests:
+              memory: 512Mi
+              cpu: 500m
+            limits:
+              memory: 1024Mi
+              cpu: 2000m
+         #livenessProbe:
+         #  httpGet:
+         #    path: /
+         #    port: 8000
+         #  initialDelaySeconds: 30
+         #  periodSeconds: 10
+         #readinessProbe:
+         #  httpGet:
+         #    path: /
+         #    port: 8000
+         #  initialDelaySeconds: 5
+         #  periodSeconds: 5
+          volumeMounts:
+            - name: data
+              mountPath: /app/data
+      volumes:
+        - name: data
+          hostPath:
+            path: /mnt/storage/Storage/k8s/paperless/ai-data
+            type: DirectoryOrCreate
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: paperless-ai
+  namespace: paperless
+  labels:
+    app: paperless-ai
+spec:
+  type: ClusterIP
+  ports:
+    - port: 3000
+      targetPort: 3000
+      protocol: TCP
+      name: http
+  selector:
+    app: paperless-ai
+---
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: paperless-ai-ingress
+  annotations:
+    ingressClassName: traefik
+    cert-manager.io/cluster-issuer: letsencrypt
+    traefik.ingress.kubernetes.io/router.middlewares: kube-system-https-redirect@kubernetescrd
+    acme.cert-manager.io/http01-edit-in-place: "true"
+spec:
+  rules:
+    - host: ai-docs.hexor.cy
+      http:
+        paths:
+          - path: /
+            pathType: Prefix
+            backend:
+              service:
+                name: paperless-ai
+                port:
+                  number: 3000
+  tls:
+    - secretName: docs-tls
+      hosts:
+        - '*.hexor.cy'

k8s/apps/paperless/paperless-values.yaml

@@ -1,5 +1,5 @@
 image:
-  tag: 2.19.3
+  tag: latest
 resources:
   requests:
     memory: "1Gi"
@@ -9,7 +9,7 @@ resources:
     cpu: "3000m"
 initContainers:
   install-tesseract-langs:
-    image: ghcr.io/paperless-ngx/paperless-ngx:2.18.2
+    image: ghcr.io/paperless-ngx/paperless-ngx:latest
     resources:
       requests:
         memory: "256Mi"

k8s/apps/pasarguard/configmap-scripts-ingress.yaml

@@ -1,212 +0,0 @@
----
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: pasarguard-scripts-ingress
-  labels:
-    app: pasarguard-node-ingress
-data:
-  init-uuid-ingress.sh: |
-    #!/bin/bash
-    set -e
-    echo "Started"
-    # NODE_NAME is already set via environment variable
-    NAMESPACE=$(cat /var/run/secrets/kubernetes.io/serviceaccount/namespace)
-
-    # Get DNS name from node label xray-public-address
-    DNS_NAME=$(kubectl get node "${NODE_NAME}" -o jsonpath='{.metadata.labels.xray-public-address}')
-
-    if [ -z "${DNS_NAME}" ]; then
-      echo "ERROR: Node ${NODE_NAME} does not have label 'xray-public-address'"
-      exit 1
-    fi
-
-    echo "Node: ${NODE_NAME}"
-    echo "DNS Name from label: ${DNS_NAME}"
-
-    # Use DNS name for ConfigMap name to ensure uniqueness
-    CONFIGMAP_NAME="node-uuid-ingress-${DNS_NAME//./-}"
-
-    echo "Checking ConfigMap: ${CONFIGMAP_NAME}"
-
-    # Check if ConfigMap exists and get UUID
-    if kubectl get configmap "${CONFIGMAP_NAME}" -n "${NAMESPACE}" &>/dev/null; then
-      echo "ConfigMap exists, reading UUID..."
-      API_KEY=$(kubectl get configmap "${CONFIGMAP_NAME}" -n "${NAMESPACE}" -o jsonpath='{.data.API_KEY}')
-
-      if [ -z "${API_KEY}" ]; then
-        echo "UUID not found in ConfigMap, generating new one..."
-        API_KEY=$(cat /proc/sys/kernel/random/uuid)
-        kubectl patch configmap "${CONFIGMAP_NAME}" -n "${NAMESPACE}" --type merge -p "{\"data\":{\"API_KEY\":\"${API_KEY}\"}}"
-      else
-        echo "Using existing UUID from ConfigMap"
-      fi
-    else
-      echo "ConfigMap does not exist, creating new one..."
-      API_KEY=$(cat /proc/sys/kernel/random/uuid)
-      kubectl create configmap "${CONFIGMAP_NAME}" -n "${NAMESPACE}" \
-        --from-literal=API_KEY="${API_KEY}" \
-        --from-literal=NODE_NAME="${NODE_NAME}"
-    fi
-
-    # Save UUID and node info to shared volume for the main container
-    echo -n "${API_KEY}" > /shared/api-key
-    echo -n "${NODE_NAME}" > /shared/node-name
-    echo -n "${CONFIGMAP_NAME}" > /shared/configmap-name
-    echo "UUID initialized: ${API_KEY}"
-    echo "Node name: ${NODE_NAME}"
-    echo "ConfigMap: ${CONFIGMAP_NAME}"
-
-    # Create Certificate for this node using DNS name from label
-    CERT_NAME="pasarguard-node-ingress-${DNS_NAME//./-}"
-
-    echo "Creating Certificate: ${CERT_NAME} for ${DNS_NAME}"
-
-    # Check if Certificate already exists
-    if ! kubectl get certificate "${CERT_NAME}" -n "${NAMESPACE}" &>/dev/null; then
-      echo "Certificate does not exist, creating..."
-      cat <<EOF | kubectl apply -f -
-    apiVersion: cert-manager.io/v1
-    kind: Certificate
-    metadata:
-      name: ${CERT_NAME}
-      namespace: ${NAMESPACE}
-    spec:
-      secretName: ${CERT_NAME}-tls
-      issuerRef:
-        name: letsencrypt
-        kind: ClusterIssuer
-      dnsNames:
-        - ${DNS_NAME}
-    EOF
-    else
-      echo "Certificate already exists"
-    fi
-
-    # Wait for certificate to be ready
-    
-    echo "Waiting for certificate to be ready..."
-    for i in {1..600}; do
-      if kubectl get secret "${CERT_NAME}-tls" -n "${NAMESPACE}" &>/dev/null; then
-        echo "Certificate secret is ready!"
-        break
-      fi
-      echo "Waiting for certificate... ($i/600)"
-      sleep 1
-    done
-
-    if ! kubectl get secret "${CERT_NAME}-tls" -n "${NAMESPACE}" &>/dev/null; then
-      echo "WARNING: Certificate secret not ready after 600 seconds"
-    else
-      # Extract certificate and key from secret to shared volume
-      echo "Extracting certificate and key..."
-      kubectl get secret "${CERT_NAME}-tls" -n "${NAMESPACE}" -o jsonpath='{.data.tls\.crt}' | base64 -d > /shared/tls.crt
-      kubectl get secret "${CERT_NAME}-tls" -n "${NAMESPACE}" -o jsonpath='{.data.tls\.key}' | base64 -d > /shared/tls.key
-      echo "Certificate and key extracted successfully."
-      cat /shared/tls.crt
-    fi
-
-    # Create ClusterIP Service for this node (pod selector based)
-    NODE_SHORT_NAME="${NODE_NAME%%.*}"
-    SERVICE_NAME="${NODE_SHORT_NAME}-ingress"
-
-    echo "Creating Service: ${SERVICE_NAME} for node ${NODE_NAME} (short: ${NODE_SHORT_NAME})"
-
-    # Create Service with pod selector including node name
-    cat <<EOF | kubectl apply -f -
-    apiVersion: v1
-    kind: Service
-    metadata:
-      name: ${SERVICE_NAME}
-      namespace: ${NAMESPACE}
-      labels:
-        app: pasarguard-node-ingress
-        node: ${NODE_NAME}
-    spec:
-      type: ClusterIP
-      selector:
-        app: pasarguard-node-ingress
-        node-name: ${NODE_SHORT_NAME}
-      ports:
-        - name: proxy
-          port: 443
-          protocol: TCP
-          targetPort: 443
-        - name: api
-          port: 62050
-          protocol: TCP
-          targetPort: 62050
-    EOF
-
-    echo "Service created: ${SERVICE_NAME}.${NAMESPACE}.svc.cluster.local"
-
-    # Create IngressRouteTCP for this DNS name with TLS passthrough
-    INGRESS_NAME="pasarguard-tcp-${DNS_NAME//./-}"
-
-    echo "Creating IngressRouteTCP: ${INGRESS_NAME} for ${DNS_NAME}"
-
-    cat <<EOF | kubectl apply -f -
-    apiVersion: traefik.io/v1alpha1
-    kind: IngressRouteTCP
-    metadata:
-      name: ${INGRESS_NAME}
-      namespace: ${NAMESPACE}
-      labels:
-        app: pasarguard-node-ingress
-        node: ${NODE_NAME}
-    spec:
-      entryPoints:
-        - websecure
-      routes:
-        - match: HostSNI(\`${DNS_NAME}\`)
-          services:
-            - name: ${SERVICE_NAME}
-              port: 443
-      tls:
-        passthrough: true
-    EOF
-
-    echo "IngressRouteTCP created: ${INGRESS_NAME}"
-    echo "Traffic to ${DNS_NAME}:443 will be routed to ${SERVICE_NAME}:443"
-
-    # Create second IngressRouteTCP for API port 62051
-    INGRESS_API_NAME="pasarguard-api-${DNS_NAME//./-}"
-
-    echo "Creating IngressRouteTCP for API: ${INGRESS_API_NAME} for ${DNS_NAME}:62051"
-
-    cat <<EOF | kubectl apply -f -
-    apiVersion: traefik.io/v1alpha1
-    kind: IngressRouteTCP
-    metadata:
-      name: ${INGRESS_API_NAME}
-      namespace: ${NAMESPACE}
-      labels:
-        app: pasarguard-node-ingress
-        node: ${NODE_NAME}
-    spec:
-      entryPoints:
-        - pasarguard-api
-      routes:
-        - match: HostSNI(\`${DNS_NAME}\`)
-          services:
-            - name: ${SERVICE_NAME}
-              port: 62050
-      tls:
-        passthrough: true
-    EOF
-
-    echo "IngressRouteTCP API created: ${INGRESS_API_NAME}"
-    echo "Traffic to ${DNS_NAME}:62051 will be routed to ${SERVICE_NAME}:62050"
-
-  pasarguard-start.sh: |
-    #!/bin/sh
-    # Read API_KEY from shared volume created by init container
-    if [ -f /shared/api-key ]; then
-      export API_KEY=$(cat /shared/api-key)
-      echo "Loaded API_KEY from shared volume"
-    else
-      echo "WARNING: API_KEY file not found, using default"
-    fi
-
-    cd /app
-    exec ./main

k8s/apps/pasarguard/daemonset-ingress.yaml

@@ -1,211 +0,0 @@
----
-apiVersion: v1
-kind: ServiceAccount
-metadata:
-  name: pasarguard-node-ingress
-  labels:
-    app: pasarguard-node-ingress
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: Role
-metadata:
-  name: pasarguard-node-ingress-configmap
-  labels:
-    app: pasarguard-node-ingress
-rules:
-  - apiGroups: [""]
-    resources: ["configmaps"]
-    verbs: ["get", "list", "create", "update", "patch"]
-  - apiGroups: ["cert-manager.io"]
-    resources: ["certificates"]
-    verbs: ["get", "list", "create", "update", "patch", "delete"]
-  - apiGroups: [""]
-    resources: ["secrets"]
-    verbs: ["get", "list"]
-  - apiGroups: [""]
-    resources: ["services", "endpoints"]
-    verbs: ["get", "list", "create", "update", "patch", "delete"]
-  - apiGroups: ["traefik.io", "traefik.containo.us"]
-    resources: ["ingressroutetcps"]
-    verbs: ["get", "list", "create", "update", "patch", "delete"]
-  - apiGroups: [""]
-    resources: ["pods"]
-    verbs: ["get", "list", "patch", "update"]
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: RoleBinding
-metadata:
-  name: pasarguard-node-ingress-configmap
-  labels:
-    app: pasarguard-node-ingress
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: Role
-  name: pasarguard-node-ingress-configmap
-subjects:
-  - kind: ServiceAccount
-    name: pasarguard-node-ingress
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRole
-metadata:
-  name: pasarguard-node-ingress-reader
-  labels:
-    app: pasarguard-node-ingress
-rules:
-  - apiGroups: [""]
-    resources: ["nodes"]
-    verbs: ["get", "list"]
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRoleBinding
-metadata:
-  name: pasarguard-node-ingress-reader
-  labels:
-    app: pasarguard-node-ingress
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: ClusterRole
-  name: pasarguard-node-ingress-reader
-subjects:
-  - kind: ServiceAccount
-    name: pasarguard-node-ingress
-    namespace: pasarguard
----
-apiVersion: apps/v1
-kind: DaemonSet
-metadata:
-  name: pasarguard-node-ingress
-  labels:
-    app: pasarguard-node-ingress
-spec:
-  selector:
-    matchLabels:
-      app: pasarguard-node-ingress
-  revisionHistoryLimit: 3
-  updateStrategy:
-    type: RollingUpdate
-  template:
-    metadata:
-      labels:
-        app: pasarguard-node-ingress
-    spec:
-      serviceAccountName: pasarguard-node-ingress
-      affinity:
-        nodeAffinity:
-          requiredDuringSchedulingIgnoredDuringExecution:
-            nodeSelectorTerms:
-            - matchExpressions:
-              - key: xray-public-address
-                operator: Exists
-      initContainers:
-        - name: label-pod
-          image: bitnami/kubectl:latest
-          env:
-            - name: POD_NAME
-              valueFrom:
-                fieldRef:
-                  fieldPath: metadata.name
-            - name: POD_NAMESPACE
-              valueFrom:
-                fieldRef:
-                  fieldPath: metadata.namespace
-            - name: NODE_NAME
-              valueFrom:
-                fieldRef:
-                  fieldPath: spec.nodeName
-          command:
-            - /bin/bash
-            - -c
-            - |
-              # Add node label to pod
-              NODE_SHORT=$(echo ${NODE_NAME} | cut -d. -f1)
-              kubectl label pod ${POD_NAME} -n ${POD_NAMESPACE} node-name=${NODE_SHORT} --overwrite
-        - name: init-uuid
-          image: bitnami/kubectl:latest
-          env:
-            - name: GODEBUG
-              value: "x509sha1=1"
-            - name: NODE_NAME
-              valueFrom:
-                fieldRef:
-                  fieldPath: spec.nodeName
-          command:
-            - /bin/bash
-            - /scripts/init-uuid-ingress.sh
-          volumeMounts:
-            - name: shared-data
-              mountPath: /shared
-            - name: scripts
-              mountPath: /scripts
-      containers:
-        - name: pasarguard-node
-          image: 'pasarguard/node:v0.1.3'
-          imagePullPolicy: Always
-          command:
-            - /bin/sh
-            - /scripts/pasarguard-start.sh
-          ports:
-            - name: api
-              containerPort: 62050
-              protocol: TCP
-            - name: proxy
-              containerPort: 443
-              protocol: TCP
-          env:
-            - name: NODE_NAME
-              valueFrom:
-                fieldRef:
-                  fieldPath: spec.nodeName
-            - name: NODE_HOST
-              value: "0.0.0.0"
-            - name: SERVICE_PORT
-              value: "62050"
-            - name: SERVICE_PROTOCOL
-              value: "grpc"
-            - name: DEBUG
-              value: "true"
-            - name: SSL_CERT_FILE
-              value: "/shared/tls.crt"
-            - name: SSL_KEY_FILE
-              value: "/shared/tls.key"
-            - name: XRAY_EXECUTABLE_PATH
-              value: "/usr/local/bin/xray"
-            - name: XRAY_ASSETS_PATH
-              value: "/usr/local/share/xray"
-            - name: API_KEY
-              value: "change-this-to-a-secure-uuid"
-          livenessProbe:
-            tcpSocket:
-              port: 62050
-            initialDelaySeconds: 30
-            periodSeconds: 10
-            timeoutSeconds: 5
-            failureThreshold: 3
-          readinessProbe:
-            tcpSocket:
-              port: 62050
-            initialDelaySeconds: 10
-            periodSeconds: 5
-            timeoutSeconds: 3
-            failureThreshold: 3
-          resources:
-            requests:
-              memory: "128Mi"
-              cpu: "100m"
-            limits:
-              memory: "512Mi"
-              cpu: "750m"
-          volumeMounts:
-            - name: shared-data
-              mountPath: /shared
-              readOnly: false
-            - name: scripts
-              mountPath: /scripts
-      volumes:
-        - name: shared-data
-          emptyDir: {}
-        - name: scripts
-          configMap:
-            name: pasarguard-scripts-ingress
-            defaultMode: 0755

k8s/apps/pasarguard/daemonset.yaml

@@ -113,7 +113,7 @@ spec:
               mountPath: /scripts
       containers:
         - name: pasarguard-node
-          image: 'pasarguard/node:v0.1.3'
+          image: 'pasarguard/node:v0.2.1'
           imagePullPolicy: Always
           command:
             - /bin/sh
@@ -162,10 +162,10 @@ spec:
           resources:
             requests:
               memory: "128Mi"
-              cpu: "100m"
+              #cpu: "500m"
             limits:
               memory: "512Mi"
-              cpu: "750m"
+              #cpu: "1200m"
           volumeMounts:
             - name: shared-data
               mountPath: /shared
@@ -205,7 +205,7 @@ spec:
               cpu: "50m"
             limits:
               memory: "128Mi"
-              cpu: "150m"
+              cpu: "500m"
           volumeMounts:
             - name: shared-data
               mountPath: /shared

k8s/apps/pasarguard/kustomization.yaml

@@ -9,6 +9,3 @@ resources:
   - ./certificate.yaml
   - ./configmap-scripts.yaml
   - ./servicemonitor.yaml
-  - ./configmap-scripts-ingress.yaml
-# - ./daemonset-ingress.yaml
-# - ./traefik-pasarguard-entrypoint.yaml

k8s/apps/pasarguard/traefik-pasarguard-entrypoint.yaml

@@ -1,66 +0,0 @@
----
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: traefik
-  namespace: kube-system
-spec:
-  template:
-    spec:
-      containers:
-      - name: traefik
-        args:
-        - --entryPoints.metrics.address=:9100/tcp
-        - --entryPoints.traefik.address=:8080/tcp
-        - --entryPoints.web.address=:8000/tcp
-        - --entryPoints.websecure.address=:8443/tcp
-        - --entryPoints.pasarguard-api.address=:62051/tcp
-        - --api.dashboard=true
-        - --ping=true
-        - --metrics.prometheus=true
-        - --metrics.prometheus.entrypoint=metrics
-        - --providers.kubernetescrd
-        - --providers.kubernetescrd.allowEmptyServices=true
-        - --providers.kubernetesingress
-        - --providers.kubernetesingress.allowEmptyServices=true
-        - --providers.kubernetesingress.ingressendpoint.publishedservice=kube-system/traefik
-        - --entryPoints.websecure.http.tls=true
-        - --log.level=INFO
-        - --entryPoints.web.transport.respondingTimeouts.readTimeout=0s
-        - --entryPoints.websecure.transport.respondingTimeouts.readTimeout=0s
-        ports:
-        - containerPort: 9100
-          name: metrics
-          protocol: TCP
-        - containerPort: 8080
-          name: traefik
-          protocol: TCP
-        - containerPort: 8000
-          name: web
-          protocol: TCP
-        - containerPort: 8443
-          name: websecure
-          protocol: TCP
-        - containerPort: 62051
-          name: pasarguard-api
-          protocol: TCP
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: traefik
-  namespace: kube-system
-spec:
-  ports:
-  - name: web
-    port: 80
-    protocol: TCP
-    targetPort: web
-  - name: websecure
-    port: 443
-    protocol: TCP
-    targetPort: websecure
-  - name: pasarguard-api
-    port: 62051
-    protocol: TCP
-    targetPort: pasarguard-api

k8s/apps/syncthing/kustomization.yaml

@@ -16,18 +16,18 @@ helmCharts:
     valuesFile: syncthing-master.yaml
     includeCRDs: true
 
-  - name: syncthing
-    repo: https://k8s-home-lab.github.io/helm-charts
-    version: 4.0.0
-    releaseName: syncthing-khv
-    namespace: syncthing
-    valuesFile: syncthing-khv.yaml
-    includeCRDs: true
-
   - name: syncthing
     repo: https://k8s-home-lab.github.io/helm-charts
     version: 4.0.0
     releaseName: syncthing-nas
     namespace: syncthing
     valuesFile: syncthing-nas.yaml
-    includeCRDs: true
+    includeCRDs: true
+
+#  - name: syncthing
+#    repo: https://k8s-home-lab.github.io/helm-charts
+#    version: 4.0.0
+#    releaseName: syncthing-khv
+#    namespace: syncthing
+#    valuesFile: syncthing-khv.yaml
+#    includeCRDs: true

k8s/apps/tg-bots/desubot.yaml

@@ -1,4 +1,3 @@
----
 apiVersion: apps/v1
 kind: Deployment
 metadata:
@@ -23,7 +22,7 @@ spec:
         kubernetes.io/hostname: home.homenet
       containers:
         - name: desubot
-          image: 'ultradesu/desubot:latest'
+          image: "ultradesu/desubot:latest"
           imagePullPolicy: Always
           envFrom:
             - secretRef:
@@ -32,11 +31,11 @@ spec:
             - name: RUST_LOG
               value: "info"
           volumeMounts:
-          - mountPath: /storage
-            name: storage
+            - mountPath: /storage
+              name: storage
       volumes:
         - name: storage
-          nfs:
-            server: nas.homenet
-            path: /mnt/storage/Storage/k8s/desubot/
-            readOnly: false
+          persistentVolumeClaim:
+            claimName: desubot-storage
+            readOnly: false
+

k8s/apps/tg-bots/kustomization.yaml

@@ -8,3 +8,5 @@ resources:
   - external-secrets.yaml
   - desubot.yaml
   - restart-job.yaml
+  - storage.yaml
+

k8s/apps/tg-bots/storage.yaml

@@ -0,0 +1,12 @@
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: desubot-storage
+spec:
+  accessModes:
+    - ReadWriteMany
+  storageClassName: nfs-csi
+  resources:
+    requests:
+      storage: 200Gi

k8s/apps/xandikos/deployment.yaml

@@ -49,14 +49,14 @@ spec:
               cpu: "1000m"
           livenessProbe:
             httpGet:
-              path: /health
+              path: /
               port: 8081
             initialDelaySeconds: 30
             periodSeconds: 10
             timeoutSeconds: 5
           readinessProbe:
             httpGet:
-              path: /health
+              path: /
               port: 8081
             initialDelaySeconds: 10
             periodSeconds: 5

k8s/apps/xandikos/external-secrets.yaml

@@ -0,0 +1,31 @@
+---
+apiVersion: external-secrets.io/v1
+kind: ExternalSecret
+metadata:
+  name: mmdl-secrets
+spec:
+  target:
+    name: mmdl-secrets
+    deletionPolicy: Delete
+    template:
+      type: Opaque
+      data:
+        DB_DIALECT: 'postgres'
+        DB_HOST: psql.psql.svc
+        DB_USER: mmdl
+        DB_NAME: mmdl
+        DB_PORT: "5432"
+        DB_PASS: |-
+          {{ .pg_pass }}
+        AES_PASSWORD: |-
+          {{ .pg_pass }}
+
+  data:
+    - secretKey: pg_pass
+      sourceRef:
+        storeRef:
+          name: vaultwarden-login
+          kind: ClusterSecretStore
+      remoteRef:
+        key: 2a9deb39-ef22-433e-a1be-df1555625e22
+        property: fields[12].value

k8s/apps/xandikos/ingress.yaml

@@ -13,6 +13,13 @@ spec:
     - host: cal.hexor.cy
       http:
         paths:
+          - path: /
+            pathType: Prefix
+            backend:
+              service:
+                name: mmdl
+                port:
+                  number: 3000
           - path: /dav
             pathType: Prefix
             backend:

k8s/apps/xandikos/kustomization.yaml

@@ -2,9 +2,10 @@ apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 
 resources:
-  - app.yaml
   - deployment.yaml
   - service.yaml
+  - mmdl-deployment.yaml
+  - mmdl-service.yaml
   - ingress.yaml
-
+  - external-secrets.yaml
 

k8s/apps/xandikos/mmdl-deployment.yaml

@@ -0,0 +1,61 @@
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: mmdl
+  labels:
+    app: mmdl
+spec:
+  selector:
+    matchLabels:
+      app: mmdl
+  replicas: 1
+  strategy:
+    type: RollingUpdate
+    rollingUpdate:
+      maxSurge: 1
+      maxUnavailable: 0
+  template:
+    metadata:
+      labels:
+        app: mmdl
+    spec:
+      nodeSelector:
+        kubernetes.io/hostname: master.tail2fe2d.ts.net
+      containers:
+        - name: mmdl
+          image: intriin/mmdl:latest
+          imagePullPolicy: Always
+          envFrom:
+            - secretRef:
+                name: mmdl-secrets
+          env:
+            - name: NEXTAUTH_URL
+              value: "https://cal.hexor.cy"
+            - name: CALDAV_SERVER_URL
+              value: "https://cal.hexor.cy/dav"
+          resources:
+            requests:
+              memory: "128Mi"
+              cpu: "100m"
+            limits:
+              memory: "512Mi"
+              cpu: "1000m"
+          livenessProbe:
+            httpGet:
+              path: /
+              port: 3000
+            initialDelaySeconds: 30
+            periodSeconds: 10
+            timeoutSeconds: 5
+          readinessProbe:
+            httpGet:
+              path: /
+              port: 3000
+            initialDelaySeconds: 10
+            periodSeconds: 5
+            timeoutSeconds: 3
+          ports:
+            - name: http
+              containerPort: 3000
+              protocol: TCP

k8s/apps/xandikos/mmdl-service.yaml

@@ -0,0 +1,14 @@
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: mmdl
+spec:
+  selector:
+    app: mmdl
+  type: ClusterIP
+  ports:
+    - name: http
+      port: 3000
+      protocol: TCP
+      targetPort: 3000

k8s/core/argocd/app.yaml

@@ -18,4 +18,5 @@ spec:
       prune: true
     syncOptions:
       - CreateNamespace=true
+      - ServerSideApply=true
 

k8s/core/argocd/appprojects.yaml

@@ -47,3 +47,20 @@ spec:
     server: https://kubernetes.default.svc
   sourceRepos:
   - ssh://git@gt.hexor.cy:30022/ab/homelab.git
+
+---
+apiVersion: argoproj.io/v1alpha1
+kind: AppProject
+metadata:
+  name: desktop
+  namespace: argocd
+spec:
+  clusterResourceWhitelist:
+  - group: '*'
+    kind: '*'
+  description: Hexor Home Lab Desktop Apps
+  destinations:
+  - namespace: '*'
+    server: https://kubernetes.default.svc
+  sourceRepos:
+  - ssh://git@gt.hexor.cy:30022/ab/homelab.git

k8s/core/argocd/external-secrets.yaml

@@ -23,6 +23,9 @@ spec:
           name: vaultwarden-login
           kind: ClusterSecretStore
       remoteRef:
+        conversionStrategy: Default
+        decodingStrategy: None
+        metadataPolicy: None
         key: 1062e5b4-5380-49f1-97c3-340f26f3487e
         property: fields[0].value
     - secretKey: client_secret
@@ -31,6 +34,9 @@ spec:
           name: vaultwarden-login
           kind: ClusterSecretStore
       remoteRef:
+        conversionStrategy: Default
+        decodingStrategy: None
+        metadataPolicy: None
         key: 1062e5b4-5380-49f1-97c3-340f26f3487e
         property: fields[1].value
 

k8s/core/argocd/kustomization.yaml

@@ -10,7 +10,7 @@ resources:
 helmCharts:
   - name: argo-cd
     repo: https://argoproj.github.io/argo-helm
-    version: 9.1.4
+    version: 9.4.10
     releaseName: argocd
     namespace: argocd
     valuesFile: values.yaml

k8s/core/argocd/values.yaml

@@ -2,7 +2,7 @@
 
 global:
   domain: ag.hexor.cy
-  nodeSelector:
+  nodeSelector: &nodeSelector
     kubernetes.io/hostname: master.tail2fe2d.ts.net
   logging:
     format: text
@@ -28,8 +28,9 @@ configs:
       issuer: https://idm.hexor.cy/application/o/argocd/
       clientID: $oidc-creds:id
       clientSecret: $oidc-creds:secret
-      requestedScopes: ["openid", "profile", "email", "groups"]
+      requestedScopes: ["openid", "profile", "email", "groups", "offline_access"]
       requestedIDTokenClaims: {"groups": {"essential": true}}
+      refreshTokenThreshold: 2m
   rbac:
     create: true
     policy.default: ""
@@ -55,15 +56,15 @@ configs:
 
 controller:
   replicas: 1
-  nodeSelector:
-    kubernetes.io/hostname: master.tail2fe2d.ts.net
+  nodeSelector: 
+    <<: *nodeSelector
   # Add resources (requests/limits), PDB etc. if needed
 
 # Dex OIDC provider
 dex:
   replicas: 1
   nodeSelector:
-    kubernetes.io/hostname: master.tail2fe2d.ts.net
+    <<: *nodeSelector
   enabled: false
 
 # Standard Redis disabled because Redis HA is enabled
@@ -86,7 +87,7 @@ redis-ha:
 server:
   replicas: 1
   nodeSelector:
-    kubernetes.io/hostname: master.tail2fe2d.ts.net
+    <<: *nodeSelector
   ingress:
     enabled: false
 
@@ -99,8 +100,11 @@ server:
 # Repository Server
 repoServer:
   replicas: 1
+  livenessProbe:
+    timeoutSeconds: 10
+    periodSeconds: 60
   nodeSelector:
-    kubernetes.io/hostname: master.tail2fe2d.ts.net
+    <<: *nodeSelector
   # Add resources (requests/limits), PDB etc. if needed
 
 # ApplicationSet Controller
@@ -108,7 +112,7 @@ applicationSet:
   enabled: true # Enabled by default
   replicas: 1
   nodeSelector:
-    kubernetes.io/hostname: master.tail2fe2d.ts.net
+    <<: *nodeSelector
   # Add resources (requests/limits), PDB etc. if needed
 
 # Notifications Controller
@@ -116,5 +120,5 @@ notifications:
   enabled: true # Enabled by default
   replicas: 1
   nodeSelector:
-    kubernetes.io/hostname: master.tail2fe2d.ts.net
+    <<: *nodeSelector
   # Add notifiers, triggers, templates configurations if needed

k8s/core/authentik/app.yaml

@@ -18,4 +18,4 @@ spec:
       prune: true
     syncOptions:
       - CreateNamespace=true
-
+      - ServerSideApply=true

k8s/core/authentik/external-secrets.yaml

@@ -19,6 +19,14 @@ spec:
           {{ .password }}
         AUTHENTIK_SECRET_KEY: |-
           {{ .secret_key }}
+        POSTGRES_PASSWORD: |-
+          {{ .password }}
+        POSTGRES_USER: |-
+          {{ .username }}
+        username: |-
+          {{ .password }}
+        password: |-
+          {{ .username }}
   data:
     - secretKey: password
       sourceRef:
@@ -26,6 +34,9 @@ spec:
           name: vaultwarden-login
           kind: ClusterSecretStore
       remoteRef:
+        conversionStrategy: Default
+        decodingStrategy: None
+        metadataPolicy: None
         key: 279c2c1f-c147-4b6b-a511-36c3cd764f9d
         property: login.password
     - secretKey: username
@@ -34,6 +45,9 @@ spec:
           name: vaultwarden-login
           kind: ClusterSecretStore
       remoteRef:
+        conversionStrategy: Default
+        decodingStrategy: None
+        metadataPolicy: None
         key: 279c2c1f-c147-4b6b-a511-36c3cd764f9d
         property: login.username
     - secretKey: secret_key
@@ -42,6 +56,9 @@ spec:
           name: vaultwarden-login
           kind: ClusterSecretStore
       remoteRef:
+        conversionStrategy: Default
+        decodingStrategy: None
+        metadataPolicy: None
         key: 279c2c1f-c147-4b6b-a511-36c3cd764f9d
         property: fields[0].value
 

k8s/core/authentik/kustomization.yaml

@@ -5,12 +5,12 @@ resources:
   - app.yaml
   - external-secrets.yaml
   - https-middleware.yaml
-  - worker-restart.yaml
+# - worker-restart.yaml
 
 helmCharts:
   - name: authentik
     repo: https://charts.goauthentik.io
-    version: 2025.10.1
+    version: 2026.2.1
     releaseName: authentik
     namespace: authentik
     valuesFile: values.yaml

k8s/core/authentik/values.yaml

@@ -1,8 +1,6 @@
 global:
   image:
-    tag: "2025.10.1"
-  nodeSelector:
-    kubernetes.io/hostname: master.tail2fe2d.ts.net
+    tag: "2026.2.1"
 
 authentik:
     error_reporting:
@@ -15,14 +13,35 @@ worker:
   envFrom:
     - secretRef:
         name: authentik-creds
-  volumes:
-    - name: dshm
-      emptyDir:
-        medium: Memory
-        sizeLimit: 512Mi
-  volumeMounts:
-    - name: dshm
-      mountPath: /dev/shm
+# volumes:
+#   - name: dshm
+#     emptyDir:
+#       medium: Memory
+#       sizeLimit: 512Mi
+# volumeMounts:
+#   - name: dshm
+#     mountPath: /dev/shm
+# livenessProbe:
+#   exec:
+#     command: ["/bin/sh", "-c", "kill -0 1"]
+#   initialDelaySeconds: 5
+#   periodSeconds: 10
+#   failureThreshold: 3
+#   timeoutSeconds: 3
+# readinessProbe:
+#   exec:
+#     command: ["/bin/sh", "-c", "kill -0 1"]
+#   initialDelaySeconds: 5
+#   periodSeconds: 10
+#   failureThreshold: 3
+#   timeoutSeconds: 3
+# startupProbe:
+#   exec:
+#     command: ["/bin/sh", "-c", "kill -0 1"]
+#   initialDelaySeconds: 30
+#   periodSeconds: 10
+#   failureThreshold: 60
+#   timeoutSeconds: 3
 server:
   envFrom:
     - secretRef:
@@ -53,5 +72,5 @@ server:
           hosts:
             - '*.hexor.cy'
 redis:
-    enabled: true
+    enabled: false
 

k8s/core/cert-manager/issuer.yaml

@@ -35,5 +35,6 @@ spec:
               key: secretKey
         selector:
           dnsZones:
+            - "ps.hexor.cy"
             - "of.hexor.cy"
 

k8s/core/external-secrets/Dockerfile-bitwarden-cli

@@ -1,6 +1,6 @@
 FROM debian:sid
 
-ENV BW_CLI_VERSION=2025.5.0
+ENV BW_CLI_VERSION=2025.12.1
 
 RUN apt update && \
     apt install -y wget unzip && \

k8s/core/external-secrets/bitwarden-store.yaml

@@ -37,15 +37,15 @@ spec:
         kubernetes.io/hostname: master.tail2fe2d.ts.net
       containers:
         - name: bitwarden-cli
-          image: ultradesu/bitwarden-client:2025.5.0
+          image: ultradesu/bitwarden-client:2025.12.1
           imagePullPolicy: Always
           resources:
             requests:
               memory: "128Mi"
-              cpu: "100m"
+              cpu: "300m"
             limits:
               memory: "512Mi"
-              cpu: "500m"
+              cpu: "1000m"
           env:
             - name: BW_HOST
               valueFrom:

k8s/core/gpu/app.yaml

@@ -0,0 +1,20 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: gpu-system
+  namespace: argocd
+spec:
+  project: core
+  destination:
+    namespace: gpu-system
+    server: https://kubernetes.default.svc
+  source:
+    repoURL: ssh://git@gt.hexor.cy:30022/ab/homelab.git
+    targetRevision: HEAD
+    path: k8s/core/gpu
+  syncPolicy:
+    automated:
+      selfHeal: true
+      prune: true
+    syncOptions:
+      - CreateNamespace=true

k8s/core/gpu/kustomization.yaml

@@ -0,0 +1,15 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+resources:
+  - app.yaml
+  - runtime-class.yaml
+
+helmCharts:
+  - name: nvidia-device-plugin
+    repo: https://nvidia.github.io/k8s-device-plugin
+    version: 0.17.0
+    releaseName: nvidia-device-plugin
+    namespace: gpu-system
+    valuesFile: values.yaml
+    includeCRDs: true

k8s/core/gpu/runtime-class.yaml

@@ -0,0 +1,5 @@
+apiVersion: node.k8s.io/v1
+kind: RuntimeClass
+metadata:
+  name: nvidia
+handler: nvidia

k8s/core/gpu/values.yaml

@@ -0,0 +1,23 @@
+nodeSelector:
+  kubernetes.io/hostname: uk-desktop.tail2fe2d.ts.net
+
+tolerations:
+  - key: workload
+    operator: Equal
+    value: desktop
+    effect: NoSchedule
+
+runtimeClassName: nvidia
+
+setAsDefault: false
+
+config:
+  default: any
+  map:
+    any: |-
+      version: v1
+      sharing:
+        timeSlicing:
+          resources:
+          - name: nvidia.com/gpu
+            replicas: 4

k8s/core/kube-system-custom/kustomization.yaml

@@ -3,5 +3,15 @@ kind: Kustomization
 
 resources:
   - app.yaml
+  - nfs-storage.yaml
   - coredns-internal-resolve.yaml
 
+helmCharts:
+  - name: csi-driver-nfs
+    repo: https://raw.githubusercontent.com/kubernetes-csi/csi-driver-nfs/master/charts
+    version: 4.12.0
+    releaseName: csi-driver-nfs
+    namespace: kube-system
+    #valuesFile: values.yaml
+    includeCRDs: true
+

k8s/core/kube-system-custom/nfs-storage.yaml

@@ -0,0 +1,20 @@
+---
+apiVersion: storage.k8s.io/v1
+kind: StorageClass
+metadata:
+  name: nfs-csi
+provisioner: nfs.csi.k8s.io
+parameters:
+  server: nas.homenet
+  share: /mnt/storage/Storage/PVC
+reclaimPolicy: Retain
+volumeBindingMode: Immediate
+mountOptions:
+  - nfsvers=4.1
+  - rsize=1048576
+  - wsize=1048576
+  - timeo=14
+  - intr
+  - bg
+  - soft
+  - noatime

k8s/core/longhorn/app.yaml

@@ -0,0 +1,21 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: longhorn
+  namespace: argocd
+spec:
+  project: core
+  destination:
+    namespace: longhorn
+    server: https://kubernetes.default.svc
+  source:
+    repoURL: ssh://git@gt.hexor.cy:30022/ab/homelab.git
+    targetRevision: HEAD
+    path: k8s/core/longhorn
+  syncPolicy:
+    automated:
+      selfHeal: true
+      prune: true
+    syncOptions:
+      - CreateNamespace=true
+

k8s/core/longhorn/kustomization.yaml

@@ -0,0 +1,15 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+#resources:
+#  - app.yaml
+
+helmCharts:
+  - name: longhorn
+    repo: https://charts.longhorn.io
+    version: 1.11.0
+    releaseName: longhorn
+    namespace: longhorn
+    valuesFile: values.yaml
+    includeCRDs: true
+

k8s/core/longhorn/values.yaml

@@ -0,0 +1,4 @@
+longhornUI:
+  replicas: 1
+persistence:
+  reclaimPolicy: "Retain"

k8s/core/postgresql/external-secrets.yaml

@@ -123,6 +123,10 @@ spec:
           {{ .remnawave }}
         USER_umami: |-
           {{ .umami }}
+        USER_mmdl: |-
+          {{ .mmdl }}
+        USER_n8n: |-
+          {{ .n8n }}
   data:
     - secretKey: authentik
       sourceRef:
@@ -245,3 +249,26 @@ spec:
         metadataPolicy: None
         key: 2a9deb39-ef22-433e-a1be-df1555625e22
         property: fields[11].value
+    - secretKey: mmdl
+      sourceRef:
+        storeRef:
+          name: vaultwarden-login
+          kind: ClusterSecretStore
+      remoteRef:
+        conversionStrategy: Default
+        decodingStrategy: None
+        metadataPolicy: None
+        key: 2a9deb39-ef22-433e-a1be-df1555625e22
+        property: fields[12].value
+    - secretKey: n8n
+      sourceRef:
+        storeRef:
+          name: vaultwarden-login
+          kind: ClusterSecretStore
+      remoteRef:
+        conversionStrategy: Default
+        decodingStrategy: None
+        metadataPolicy: None
+        key: 2a9deb39-ef22-433e-a1be-df1555625e22
+        property: fields[13].value
+

k8s/core/prom-stack/alertmanager-config.yaml

@@ -0,0 +1,46 @@
+apiVersion: monitoring.coreos.com/v1alpha1
+kind: AlertmanagerConfig
+metadata:
+  name: telegram-notifications
+  namespace: prometheus
+  labels:
+    app: kube-prometheus-stack-alertmanager
+    release: prometheus
+spec:
+  route:
+    groupBy: ['alertname', 'cluster', 'service']
+    groupWait: 10s
+    groupInterval: 5m
+    repeatInterval: 12h
+    receiver: telegram
+    routes:
+    - matchers:
+      - name: alertname
+        value: Watchdog
+        matchType: "="
+      receiver: 'null'
+  receivers:
+  - name: telegram
+    telegramConfigs:
+    - botToken:
+        name: alertmanager-telegram-secret
+        key: TELEGRAM_BOT_TOKEN
+      chatID: 124317807
+      parseMode: HTML
+      sendResolved: true
+      disableNotifications: false
+      message: |
+        {{ if eq .Status "firing" }}🔥 FIRING{{ else }}✅ RESOLVED{{ end }}
+        
+        {{ range .Alerts }}
+        📊 <b>{{ .Labels.alertname }}</b>
+        {{ .Annotations.summary }}
+        
+        {{ if .Annotations.node }}🖥 <b>Node:</b> <code>{{ .Annotations.node }}</code>{{ end }}
+        {{ if .Annotations.pod }}📦 <b>Pod:</b> <code>{{ .Annotations.pod }}</code>{{ end }}
+        {{ if .Annotations.namespace }}📁 <b>Namespace:</b> <code>{{ .Annotations.namespace }}</code>{{ end }}
+        {{ if .Annotations.throttle_rate }}⚠️ <b>Throttling rate:</b> {{ .Annotations.throttle_rate }}{{ end }}
+        
+        🔗 <a href="{{ .GeneratorURL }}">View in Grafana</a>
+        {{ end }}
+  - name: 'null'

k8s/core/prom-stack/app.yaml

@@ -13,9 +13,6 @@ spec:
     targetRevision: HEAD
     path: k8s/core/prom-stack
   syncPolicy:
-    automated:
-      selfHeal: true
-      prune: true
     syncOptions:
       - CreateNamespace=true
       - ServerSideApply=true

k8s/core/prom-stack/dashboards/furumi-server.json

@@ -0,0 +1,647 @@
+{
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": {
+          "type": "grafana",
+          "uid": "-- Grafana --"
+        },
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 0,
+  "id": null,
+  "links": [],
+  "liveNow": false,
+  "panels": [
+    {
+      "gridPos": {
+        "h": 4,
+        "w": 6,
+        "x": 0,
+        "y": 0
+      },
+      "id": 1,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calc": "lastNotNull",
+          "fields": "",
+          "values": false
+        },
+        "textMode": "auto"
+      },
+      "pluginVersion": "10.0.0",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${datasource}"
+          },
+          "expr": "furumi_active_streams",
+          "refId": "A"
+        }
+      ],
+      "title": "Active Streams",
+      "type": "stat"
+    },
+    {
+      "gridPos": {
+        "h": 4,
+        "w": 6,
+        "x": 6,
+        "y": 0
+      },
+      "id": 2,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calc": "rate",
+          "fields": "",
+          "values": false
+        },
+        "textMode": "auto"
+      },
+      "pluginVersion": "10.0.0",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${datasource}"
+          },
+          "expr": "rate(furumi_bytes_read_total[$__rate_interval])",
+          "refId": "A"
+        }
+      ],
+      "title": "Bytes Read / Sec",
+      "type": "stat",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              }
+            ]
+          },
+          "unit": "Bps"
+        },
+        "overrides": []
+      }
+    },
+    {
+      "gridPos": {
+        "h": 4,
+        "w": 6,
+        "x": 12,
+        "y": 0
+      },
+      "id": 3,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calc": "lastNotNull",
+          "fields": "",
+          "values": false
+        },
+        "textMode": "auto"
+      },
+      "pluginVersion": "10.0.0",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${datasource}"
+          },
+          "expr": "sum(increase(furumi_file_open_errors_total[$__rate_interval]))",
+          "refId": "A"
+        }
+      ],
+      "title": "File Open Errors (Rate)",
+      "type": "stat",
+       "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "mappings": [],
+          "thresholds": {
+             "mode": "absolute",
+             "steps": [
+               { "color": "green", "value": null },
+               { "color": "red", "value": 1 }
+             ]
+           }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "gridPos": {
+        "h": 4,
+        "w": 6,
+        "x": 18,
+        "y": 0
+      },
+      "id": 4,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calc": "lastNotNull",
+          "fields": "",
+          "values": false
+        },
+        "textMode": "auto"
+      },
+      "pluginVersion": "10.0.0",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${datasource}"
+          },
+          "expr": "sum(increase(furumi_auth_failures_total[$__rate_interval]))",
+          "refId": "A"
+        }
+      ],
+      "title": "Auth Failures (Rate)",
+      "type": "stat",
+       "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "mappings": [],
+          "thresholds": {
+             "mode": "absolute",
+             "steps": [
+               { "color": "green", "value": null },
+               { "color": "red", "value": 1 }
+             ]
+           }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 4
+      },
+      "id": 5,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "pluginVersion": "10.0.0",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${datasource}"
+          },
+          "expr": "sum by (method, status) (rate(furumi_grpc_requests_total[$__rate_interval]))",
+          "legendFormat": "{{method}} - {{status}}",
+          "refId": "A"
+        }
+      ],
+      "title": "gRPC Request Rate by Method & Status",
+      "type": "timeseries",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 10,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              }
+            ]
+          },
+          "unit": "reqps"
+        },
+        "overrides": []
+      }
+    },
+    {
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 4
+      },
+      "id": 6,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "pluginVersion": "10.0.0",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${datasource}"
+          },
+          "expr": "histogram_quantile(0.95, sum(rate(furumi_grpc_request_duration_seconds_bucket[$__rate_interval])) by (le, method))",
+          "legendFormat": "p95 {{method}}",
+          "refId": "A"
+        },
+         {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${datasource}"
+          },
+          "expr": "histogram_quantile(0.99, sum(rate(furumi_grpc_request_duration_seconds_bucket[$__rate_interval])) by (le, method))",
+          "legendFormat": "p99 {{method}}",
+          "refId": "B"
+        }
+      ],
+      "title": "gRPC Request Duration (p95, p99)",
+      "type": "timeseries",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              }
+            ]
+          },
+          "unit": "s"
+        },
+        "overrides": []
+      }
+    },
+    {
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 12
+      },
+      "id": 7,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "pluginVersion": "10.0.0",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${datasource}"
+          },
+          "expr": "sum(process_resident_memory_bytes) / 1024 / 1024",
+          "legendFormat": "Resident Memory",
+          "refId": "A"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${datasource}"
+          },
+          "expr": "sum(process_virtual_memory_bytes) / 1024 / 1024",
+          "legendFormat": "Virtual Memory",
+          "refId": "B"
+        }
+      ],
+      "title": "Process Memory Usage",
+      "type": "timeseries",
+       "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 15,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+             "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+               { "color": "green", "value": null }
+            ]
+          },
+          "unit": "megbytes"
+        },
+        "overrides": []
+      }
+    },
+    {
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 12
+      },
+      "id": 8,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "pluginVersion": "10.0.0",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${datasource}"
+          },
+          "expr": "process_open_fds",
+          "legendFormat": "Open FDs",
+          "refId": "A"
+        },
+        {
+           "datasource": {
+            "type": "prometheus",
+            "uid": "${datasource}"
+          },
+          "expr": "process_max_fds",
+          "legendFormat": "Max FDs",
+          "refId": "B"
+        }
+      ],
+      "title": "Process File Descriptors",
+      "type": "timeseries",
+       "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+             "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 10,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+            "pointSize": 5,
+            "scaleDistribution": {
+               "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+             "thresholdsStyle": {
+              "mode": "off"
+             }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+               { "color": "green", "value": null }
+            ]
+          },
+          "unit": "short"
+        },
+        "overrides": []
+      }
+    }
+  ],
+  "refresh": "10s",
+  "schemaVersion": 38,
+  "style": "dark",
+  "tags": [
+    "furumi-server",
+    "grpc"
+  ],
+  "templating": {
+    "list": [
+      {
+        "current": {
+          "selected": false,
+          "text": "Prometheus",
+          "value": "Prometheus"
+        },
+        "hide": 0,
+        "includeAll": false,
+        "multi": false,
+        "name": "datasource",
+        "options": [],
+        "query": "prometheus",
+        "refresh": 1,
+        "regex": "",
+        "skipUrlSync": false,
+        "type": "datasource"
+      }
+    ]
+  },
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "timepicker": {},
+  "timezone": "",
+  "title": "Furumi Server Metrics",
+  "uid": "furumi-metrics",
+  "version": 1
+}

k8s/core/prom-stack/external-secrets.yaml

@@ -79,3 +79,83 @@ spec:
         key: 2a9deb39-ef22-433e-a1be-df1555625e22
         property: fields[2].value
 
+---
+apiVersion: external-secrets.io/v1
+kind: ExternalSecret
+metadata:
+  name: alertmanager-telegram
+spec:
+  target:
+    name: alertmanager-telegram-secret
+    deletionPolicy: Delete
+    template:
+      type: Opaque
+      data:
+        TELEGRAM_BOT_TOKEN: |-
+          {{ .bot_token }}
+        TELEGRAM_CHAT_ID: |-
+          {{ .chat_id }}
+  data:
+    - secretKey: bot_token
+      sourceRef:
+        storeRef:
+          name: vaultwarden-login
+          kind: ClusterSecretStore
+      remoteRef:
+        conversionStrategy: Default
+        decodingStrategy: None
+        metadataPolicy: None
+        key: eca0fb0b-3939-40a8-890a-6294863e5a65
+        property: fields[0].value
+    - secretKey: chat_id
+      sourceRef:
+        storeRef:
+          name: vaultwarden-login
+          kind: ClusterSecretStore
+      remoteRef:
+        conversionStrategy: Default
+        decodingStrategy: None
+        metadataPolicy: None
+        key: eca0fb0b-3939-40a8-890a-6294863e5a65
+        property: fields[1].value
+
+---
+apiVersion: external-secrets.io/v1
+kind: ExternalSecret
+metadata:
+  name: grafana-telegram
+spec:
+  target:
+    name: grafana-telegram
+    deletionPolicy: Delete
+    template:
+      type: Opaque
+      data:
+        bot-token: |-
+          {{ .bot_token }}
+        chat-id: |-
+          {{ .chat_id }}
+  data:
+    - secretKey: bot_token
+      sourceRef:
+        storeRef:
+          name: vaultwarden-login
+          kind: ClusterSecretStore
+      remoteRef:
+        conversionStrategy: Default
+        decodingStrategy: None
+        metadataPolicy: None
+        key: eca0fb0b-3939-40a8-890a-6294863e5a65
+        property: fields[0].value
+    - secretKey: chat_id
+      sourceRef:
+        storeRef:
+          name: vaultwarden-login
+          kind: ClusterSecretStore
+      remoteRef:
+        conversionStrategy: Default
+        decodingStrategy: None
+        metadataPolicy: None
+        key: eca0fb0b-3939-40a8-890a-6294863e5a65
+        property: fields[1].value
+

k8s/core/prom-stack/furumi-dashboard-cm.yaml

@@ -0,0 +1,669 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: furumi-server-dashboard
+  labels:
+    grafana_dashboard: "1"
+data:
+  furumi-server.json: |-
+    {
+      "annotations": {
+        "list": [
+          {
+            "builtIn": 1,
+            "datasource": {
+              "type": "grafana",
+              "uid": "-- Grafana --"
+            },
+            "enable": true,
+            "hide": true,
+            "iconColor": "rgba(0, 211, 255, 1)",
+            "name": "Annotations & Alerts",
+            "type": "dashboard"
+          }
+        ]
+      },
+      "editable": true,
+      "fiscalYearStartMonth": 0,
+      "graphTooltip": 0,
+      "id": null,
+      "links": [],
+      "liveNow": false,
+      "panels": [
+        {
+          "gridPos": {
+            "h": 4,
+            "w": 6,
+            "x": 0,
+            "y": 0
+          },
+          "id": 1,
+          "options": {
+            "colorMode": "value",
+            "graphMode": "area",
+            "justifyMode": "auto",
+            "orientation": "auto",
+            "reduceOptions": {
+              "calc": "lastNotNull",
+              "fields": "",
+              "values": false
+            },
+            "textMode": "auto"
+          },
+          "pluginVersion": "10.0.0",
+          "targets": [
+            {
+              "datasource": {
+                "type": "prometheus",
+                "uid": "${datasource}"
+              },
+              "expr": "sum(furumi_active_streams)",
+              "refId": "A"
+            }
+          ],
+          "title": "Active Streams",
+          "type": "stat"
+        },
+        {
+          "gridPos": {
+            "h": 4,
+            "w": 6,
+            "x": 6,
+            "y": 0
+          },
+          "id": 2,
+          "options": {
+            "colorMode": "value",
+            "graphMode": "area",
+            "justifyMode": "auto",
+            "orientation": "auto",
+            "reduceOptions": {
+              "calc": "rate",
+              "fields": "",
+              "values": false
+            },
+            "textMode": "auto"
+          },
+          "pluginVersion": "10.0.0",
+          "targets": [
+            {
+              "datasource": {
+                "type": "prometheus",
+                "uid": "${datasource}"
+              },
+              "expr": "sum(rate(furumi_bytes_read_total[$__rate_interval]))",
+              "refId": "A"
+            }
+          ],
+          "title": "Bytes Read / Sec",
+          "type": "stat",
+          "fieldConfig": {
+            "defaults": {
+              "color": {
+                "mode": "palette-classic"
+              },
+              "custom": {
+                "axisBorderShow": false,
+                "axisCenteredZero": false,
+                "axisColorMode": "text",
+                "axisLabel": "",
+                "axisPlacement": "auto",
+                "barAlignment": 0,
+                "drawStyle": "line",
+                "fillOpacity": 0,
+                "gradientMode": "none",
+                "hideFrom": {
+                  "legend": false,
+                  "tooltip": false,
+                  "viz": false
+                },
+                "insertNulls": false,
+                "lineInterpolation": "linear",
+                "lineWidth": 1,
+                "pointSize": 5,
+                "scaleDistribution": {
+                  "type": "linear"
+                },
+                "showPoints": "auto",
+                "spanNulls": false,
+                "stacking": {
+                  "group": "A",
+                  "mode": "none"
+                },
+                "thresholdsStyle": {
+                  "mode": "off"
+                }
+              },
+              "mappings": [],
+              "thresholds": {
+                "mode": "absolute",
+                "steps": [
+                  {
+                    "color": "green",
+                    "value": null
+                  }
+                ]
+              },
+              "unit": "Bps"
+            },
+            "overrides": []
+          }
+        },
+        {
+          "gridPos": {
+            "h": 4,
+            "w": 6,
+            "x": 12,
+            "y": 0
+          },
+          "id": 3,
+          "options": {
+            "colorMode": "value",
+            "graphMode": "area",
+            "justifyMode": "auto",
+            "orientation": "auto",
+            "reduceOptions": {
+              "calc": "lastNotNull",
+              "fields": "",
+              "values": false
+            },
+            "textMode": "auto"
+          },
+          "pluginVersion": "10.0.0",
+          "targets": [
+            {
+              "datasource": {
+                "type": "prometheus",
+                "uid": "${datasource}"
+              },
+              "expr": "sum(increase(furumi_file_open_errors_total[$__rate_interval]))",
+              "refId": "A"
+            }
+          ],
+          "title": "File Open Errors (Rate)",
+          "type": "stat",
+           "fieldConfig": {
+            "defaults": {
+              "color": {
+                "mode": "thresholds"
+              },
+              "mappings": [],
+              "thresholds": {
+                 "mode": "absolute",
+                 "steps": [
+                   { "color": "green", "value": null },
+                   { "color": "red", "value": 1 }
+                 ]
+               }
+            },
+            "overrides": []
+          }
+        },
+        {
+          "gridPos": {
+            "h": 4,
+            "w": 6,
+            "x": 18,
+            "y": 0
+          },
+          "id": 4,
+          "options": {
+            "colorMode": "value",
+            "graphMode": "area",
+            "justifyMode": "auto",
+            "orientation": "auto",
+            "reduceOptions": {
+              "calc": "lastNotNull",
+              "fields": "",
+              "values": false
+            },
+            "textMode": "auto"
+          },
+          "pluginVersion": "10.0.0",
+          "targets": [
+            {
+              "datasource": {
+                "type": "prometheus",
+                "uid": "${datasource}"
+              },
+              "expr": "sum(increase(furumi_auth_failures_total[$__rate_interval]))",
+              "refId": "A"
+            }
+          ],
+          "title": "Auth Failures (Rate)",
+          "type": "stat",
+           "fieldConfig": {
+            "defaults": {
+              "color": {
+                "mode": "thresholds"
+              },
+              "mappings": [],
+              "thresholds": {
+                 "mode": "absolute",
+                 "steps": [
+                   { "color": "green", "value": null },
+                   { "color": "red", "value": 1 }
+                 ]
+               }
+            },
+            "overrides": []
+          }
+        },
+        {
+          "gridPos": {
+            "h": 8,
+            "w": 12,
+            "x": 0,
+            "y": 4
+          },
+          "id": 5,
+          "options": {
+            "legend": {
+              "calcs": [],
+              "displayMode": "list",
+              "placement": "bottom",
+              "showLegend": true
+            },
+            "tooltip": {
+              "mode": "single",
+              "sort": "none"
+            }
+          },
+          "pluginVersion": "10.0.0",
+          "targets": [
+            {
+              "datasource": {
+                "type": "prometheus",
+                "uid": "${datasource}"
+              },
+              "expr": "sum by (method, status) (rate(furumi_grpc_requests_total[$__rate_interval]))",
+              "legendFormat": "{{method}} - {{status}}",
+              "refId": "A"
+            }
+          ],
+          "title": "gRPC Request Rate by Method & Status",
+          "type": "timeseries",
+          "fieldConfig": {
+            "defaults": {
+              "color": {
+                "mode": "palette-classic"
+              },
+              "custom": {
+                "axisBorderShow": false,
+                "axisCenteredZero": false,
+                "axisColorMode": "text",
+                "axisLabel": "",
+                "axisPlacement": "auto",
+                "barAlignment": 0,
+                "drawStyle": "line",
+                "fillOpacity": 10,
+                "gradientMode": "none",
+                "hideFrom": {
+                  "legend": false,
+                  "tooltip": false,
+                  "viz": false
+                },
+                "insertNulls": false,
+                "lineInterpolation": "linear",
+                "lineWidth": 2,
+                "pointSize": 5,
+                "scaleDistribution": {
+                  "type": "linear"
+                },
+                "showPoints": "auto",
+                "spanNulls": false,
+                "stacking": {
+                  "group": "A",
+                  "mode": "none"
+                },
+                "thresholdsStyle": {
+                  "mode": "off"
+                }
+              },
+              "mappings": [],
+              "thresholds": {
+                "mode": "absolute",
+                "steps": [
+                  {
+                    "color": "green",
+                    "value": null
+                  }
+                ]
+              },
+              "unit": "reqps"
+            },
+            "overrides": []
+          }
+        },
+        {
+          "gridPos": {
+            "h": 8,
+            "w": 12,
+            "x": 12,
+            "y": 4
+          },
+          "id": 6,
+          "options": {
+            "legend": {
+              "calcs": [],
+              "displayMode": "list",
+              "placement": "bottom",
+              "showLegend": true
+            },
+            "tooltip": {
+              "mode": "single",
+              "sort": "none"
+            }
+          },
+          "pluginVersion": "10.0.0",
+          "targets": [
+            {
+              "datasource": {
+                "type": "prometheus",
+                "uid": "${datasource}"
+              },
+              "expr": "histogram_quantile(0.95, sum(rate(furumi_grpc_request_duration_seconds_bucket[$__rate_interval])) by (le, method))",
+              "legendFormat": "p95 {{method}}",
+              "refId": "A"
+            },
+             {
+              "datasource": {
+                "type": "prometheus",
+                "uid": "${datasource}"
+              },
+              "expr": "histogram_quantile(0.99, sum(rate(furumi_grpc_request_duration_seconds_bucket[$__rate_interval])) by (le, method))",
+              "legendFormat": "p99 {{method}}",
+              "refId": "B"
+            }
+          ],
+          "title": "gRPC Request Duration (p95, p99)",
+          "type": "timeseries",
+          "fieldConfig": {
+            "defaults": {
+              "color": {
+                "mode": "palette-classic"
+              },
+              "custom": {
+                "axisBorderShow": false,
+                "axisCenteredZero": false,
+                "axisColorMode": "text",
+                "axisLabel": "",
+                "axisPlacement": "auto",
+                "barAlignment": 0,
+                "drawStyle": "line",
+                "fillOpacity": 0,
+                "gradientMode": "none",
+                "hideFrom": {
+                  "legend": false,
+                  "tooltip": false,
+                  "viz": false
+                },
+                "insertNulls": false,
+                "lineInterpolation": "linear",
+                "lineWidth": 2,
+                "pointSize": 5,
+                "scaleDistribution": {
+                  "type": "linear"
+                },
+                "showPoints": "auto",
+                "spanNulls": false,
+                "stacking": {
+                  "group": "A",
+                  "mode": "none"
+                },
+                "thresholdsStyle": {
+                  "mode": "off"
+                }
+              },
+              "mappings": [],
+              "thresholds": {
+                "mode": "absolute",
+                "steps": [
+                  {
+                    "color": "green",
+                    "value": null
+                  }
+                ]
+              },
+              "unit": "s"
+            },
+            "overrides": []
+          }
+        },
+        {
+          "collapsed": true,
+          "gridPos": {
+            "h": 1,
+            "w": 24,
+            "x": 0,
+            "y": 12
+          },
+          "id": 99,
+          "panels": [
+            {
+              "gridPos": {
+                "h": 8,
+                "w": 12,
+                "x": 0,
+                "y": 13
+              },
+              "id": 7,
+              "options": {
+                "legend": {
+                  "calcs": [],
+                  "displayMode": "list",
+                  "placement": "bottom",
+                  "showLegend": true
+                },
+                "tooltip": {
+                  "mode": "single",
+                  "sort": "none"
+                }
+              },
+              "pluginVersion": "10.0.0",
+              "targets": [
+                {
+                  "datasource": {
+                    "type": "prometheus",
+                    "uid": "${datasource}"
+                  },
+                  "expr": "process_resident_memory_bytes / 1024 / 1024",
+                  "legendFormat": "Resident Memory",
+                  "refId": "A"
+                },
+                {
+                  "datasource": {
+                    "type": "prometheus",
+                    "uid": "${datasource}"
+                  },
+                  "expr": "process_virtual_memory_bytes / 1024 / 1024",
+                  "legendFormat": "Virtual Memory",
+                  "refId": "B"
+                }
+              ],
+              "title": "Process Memory Usage",
+              "type": "timeseries",
+               "fieldConfig": {
+                "defaults": {
+                  "color": {
+                    "mode": "palette-classic"
+                  },
+                  "custom": {
+                    "axisBorderShow": false,
+                    "axisCenteredZero": false,
+                    "axisColorMode": "text",
+                    "axisLabel": "",
+                    "axisPlacement": "auto",
+                    "barAlignment": 0,
+                    "drawStyle": "line",
+                    "fillOpacity": 15,
+                    "gradientMode": "none",
+                    "hideFrom": {
+                      "legend": false,
+                      "tooltip": false,
+                      "viz": false
+                    },
+                    "insertNulls": false,
+                    "lineInterpolation": "linear",
+                    "lineWidth": 2,
+                     "pointSize": 5,
+                    "scaleDistribution": {
+                      "type": "linear"
+                    },
+                    "showPoints": "auto",
+                    "spanNulls": false,
+                    "stacking": {
+                      "group": "A",
+                      "mode": "none"
+                    },
+                    "thresholdsStyle": {
+                      "mode": "off"
+                    }
+                  },
+                  "mappings": [],
+                  "thresholds": {
+                    "mode": "absolute",
+                    "steps": [
+                       { "color": "green", "value": null }
+                    ]
+                  },
+                  "unit": "megbytes"
+                },
+                "overrides": []
+              }
+            },
+            {
+              "gridPos": {
+                "h": 8,
+                "w": 12,
+                "x": 12,
+                "y": 13
+              },
+              "id": 8,
+              "options": {
+                "legend": {
+                  "calcs": [],
+                  "displayMode": "list",
+                  "placement": "bottom",
+                  "showLegend": true
+                },
+                "tooltip": {
+                  "mode": "single",
+                  "sort": "none"
+                }
+              },
+              "pluginVersion": "10.0.0",
+              "targets": [
+                {
+                  "datasource": {
+                    "type": "prometheus",
+                    "uid": "${datasource}"
+                  },
+                  "expr": "process_open_fds",
+                  "legendFormat": "Open FDs",
+                  "refId": "A"
+                },
+                {
+                   "datasource": {
+                    "type": "prometheus",
+                    "uid": "${datasource}"
+                  },
+                  "expr": "process_max_fds",
+                  "legendFormat": "Max FDs",
+                  "refId": "B"
+                }
+              ],
+              "title": "Process File Descriptors",
+              "type": "timeseries",
+               "fieldConfig": {
+                "defaults": {
+                  "color": {
+                    "mode": "palette-classic"
+                  },
+                  "custom": {
+                     "axisBorderShow": false,
+                    "axisCenteredZero": false,
+                    "axisColorMode": "text",
+                    "axisLabel": "",
+                    "axisPlacement": "auto",
+                    "barAlignment": 0,
+                    "drawStyle": "line",
+                    "fillOpacity": 10,
+                    "gradientMode": "none",
+                    "hideFrom": {
+                      "legend": false,
+                      "tooltip": false,
+                      "viz": false
+                    },
+                    "insertNulls": false,
+                    "lineInterpolation": "linear",
+                    "lineWidth": 2,
+                    "pointSize": 5,
+                    "scaleDistribution": {
+                       "type": "linear"
+                    },
+                    "showPoints": "auto",
+                    "spanNulls": false,
+                    "stacking": {
+                      "group": "A",
+                      "mode": "none"
+                    },
+                     "thresholdsStyle": {
+                      "mode": "off"
+                     }
+                  },
+                  "mappings": [],
+                  "thresholds": {
+                    "mode": "absolute",
+                    "steps": [
+                       { "color": "green", "value": null }
+                    ]
+                  },
+                  "unit": "short"
+                },
+                "overrides": []
+              }
+            }
+          ],
+          "title": "Process Metrics (Memory, FDs)",
+          "type": "row"
+        }
+      ],
+      "refresh": "10s",
+      "schemaVersion": 38,
+      "style": "dark",
+      "tags": [
+        "furumi-server",
+        "grpc"
+      ],
+      "templating": {
+        "list": [
+          {
+            "current": {
+              "selected": false,
+              "text": "Prometheus",
+              "value": "Prometheus"
+            },
+            "hide": 0,
+            "includeAll": false,
+            "multi": false,
+            "name": "datasource",
+            "options": [],
+            "query": "prometheus",
+            "refresh": 1,
+            "regex": "",
+            "skipUrlSync": false,
+            "type": "datasource"
+          }
+        ]
+      },
+      "time": {
+        "from": "now-1h",
+        "to": "now"
+      },
+      "timepicker": {},
+      "timezone": "",
+      "title": "Furumi Server Metrics",
+      "uid": "furumi-metrics",
+      "version": 1
+    }

k8s/core/prom-stack/grafana-alerting-configmap.yaml

@@ -0,0 +1,382 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: grafana-alerting
+  namespace: prometheus
+data:
+  rules.yaml: |
+    apiVersion: 1
+    groups:
+      - orgId: 1
+        name: pasarguard_alerts
+        folder: Kubernetes
+        interval: 1m
+        rules:
+          - uid: pasarguard_cpu_throttling
+            title: VPN CPU Throttle
+            condition: B
+            data:
+              - refId: A
+                relativeTimeRange:
+                  from: 600
+                  to: 0
+                datasourceUid: prometheus
+                model:
+                  expr: 'rate(container_cpu_cfs_throttled_periods_total{container="pasarguard-node"}[5m])'
+                  refId: A
+                  intervalMs: 1000
+                  maxDataPoints: 43200
+              - refId: B
+                relativeTimeRange:
+                  from: 600
+                  to: 0
+                datasourceUid: __expr__
+                model:
+                  conditions:
+                    - evaluator:
+                        params:
+                          - 0.1
+                        type: gt
+                      operator:
+                        type: and
+                      query:
+                        params: []
+                  datasource:
+                    type: __expr__
+                    uid: __expr__
+                  expression: A
+                  reducer: min
+                  refId: B
+                  type: reduce
+            noDataState: NoData
+            execErrState: Alerting
+            for: 5m
+            annotations:
+              pod: '{{ $labels.pod }}'
+              node: '{{ $labels.node }}'
+              namespace: '{{ $labels.namespace }}'
+              throttle_rate: '{{ printf "%.2f" $values.A }}'
+              summary: 'VPN node throttling CPU'
+            labels:
+              severity: warning
+      
+      - orgId: 1
+        name: kubernetes_alerts
+        folder: Kubernetes
+        interval: 2m
+        rules:
+          - uid: node_not_ready
+            title: Kubernetes Node Not Ready
+            condition: B
+            data:
+              - refId: A
+                relativeTimeRange:
+                  from: 600
+                  to: 0
+                datasourceUid: prometheus
+                model:
+                  expr: 'kube_node_status_condition{condition="Ready",status="false"}'
+                  refId: A
+                  intervalMs: 1000
+                  maxDataPoints: 43200
+              - refId: B
+                relativeTimeRange:
+                  from: 600
+                  to: 0
+                datasourceUid: __expr__
+                model:
+                  conditions:
+                    - evaluator:
+                        params:
+                          - 0
+                        type: gt
+                      operator:
+                        type: and
+                      query:
+                        params: []
+                  datasource:
+                    type: __expr__
+                    uid: __expr__
+                  expression: A
+                  reducer: min
+                  refId: B
+                  type: reduce
+            noDataState: NoData
+            execErrState: Alerting
+            for: 10m
+            annotations:
+              node: '{{ $labels.node }}'
+              condition: '{{ $labels.condition }}'
+              summary: 'Kubernetes node is not ready'
+            labels:
+              severity: critical
+
+          - uid: node_high_memory_usage
+            title: High Node Memory Usage
+            condition: B
+            data:
+              - refId: A
+                relativeTimeRange:
+                  from: 300
+                  to: 0
+                datasourceUid: prometheus
+                model:
+                  expr: '(1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100'
+                  refId: A
+                  intervalMs: 1000
+                  maxDataPoints: 43200
+              - refId: B
+                relativeTimeRange:
+                  from: 300
+                  to: 0
+                datasourceUid: __expr__
+                model:
+                  conditions:
+                    - evaluator:
+                        params:
+                          - 80
+                        type: gt
+                      operator:
+                        type: and
+                      query:
+                        params: []
+                  datasource:
+                    type: __expr__
+                    uid: __expr__
+                  expression: A
+                  reducer: max
+                  refId: B
+                  type: reduce
+            noDataState: NoData
+            execErrState: Alerting
+            for: 5m
+            annotations:
+              node: '{{ $labels.instance }}'
+              memory_usage: '{{ printf "%.1f%%" $values.A }}'
+              summary: 'Node memory usage is critically high'
+            labels:
+              severity: warning
+
+          - uid: node_high_cpu_usage
+            title: High Node CPU Usage
+            condition: B
+            data:
+              - refId: A
+                relativeTimeRange:
+                  from: 300
+                  to: 0
+                datasourceUid: prometheus
+                model:
+                  expr: '100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100)'
+                  refId: A
+                  intervalMs: 1000
+                  maxDataPoints: 43200
+              - refId: B
+                relativeTimeRange:
+                  from: 300
+                  to: 0
+                datasourceUid: __expr__
+                model:
+                  conditions:
+                    - evaluator:
+                        params:
+                          - 80
+                        type: gt
+                      operator:
+                        type: and
+                      query:
+                        params: []
+                  datasource:
+                    type: __expr__
+                    uid: __expr__
+                  expression: A
+                  reducer: max
+                  refId: B
+                  type: reduce
+            noDataState: NoData
+            execErrState: Alerting
+            for: 10m
+            annotations:
+              node: '{{ $labels.instance }}'
+              cpu_usage: '{{ printf "%.1f%%" $values.A }}'
+              summary: 'Node CPU usage is critically high'
+            labels:
+              severity: warning
+
+          - uid: node_high_disk_usage
+            title: High Node Disk Usage
+            condition: B
+            data:
+              - refId: A
+                relativeTimeRange:
+                  from: 300
+                  to: 0
+                datasourceUid: prometheus
+                model:
+                  expr: '(1 - (node_filesystem_avail_bytes{fstype=~"ext[234]|xfs|zfs|btrfs"} / node_filesystem_size_bytes)) * 100'
+                  refId: A
+                  intervalMs: 1000
+                  maxDataPoints: 43200
+              - refId: B
+                relativeTimeRange:
+                  from: 300
+                  to: 0
+                datasourceUid: __expr__
+                model:
+                  conditions:
+                    - evaluator:
+                        params:
+                          - 85
+                        type: gt
+                      operator:
+                        type: and
+                      query:
+                        params: []
+                  datasource:
+                    type: __expr__
+                    uid: __expr__
+                  expression: A
+                  reducer: max
+                  refId: B
+                  type: reduce
+            noDataState: NoData
+            execErrState: Alerting
+            for: 5m
+            annotations:
+              node: '{{ $labels.instance }}'
+              filesystem: '{{ $labels.mountpoint }}'
+              disk_usage: '{{ printf "%.1f%%" $values.A }}'
+              summary: 'Node disk usage is critically high'
+            labels:
+              severity: critical
+
+          - uid: node_load_average_high
+            title: High Node Load Average
+            condition: B
+            data:
+              - refId: A
+                relativeTimeRange:
+                  from: 300
+                  to: 0
+                datasourceUid: prometheus
+                model:
+                  expr: 'node_load15 / on(instance) group_left count by(instance)(node_cpu_seconds_total{mode="idle"})'
+                  refId: A
+                  intervalMs: 1000
+                  maxDataPoints: 43200
+              - refId: B
+                relativeTimeRange:
+                  from: 300
+                  to: 0
+                datasourceUid: __expr__
+                model:
+                  conditions:
+                    - evaluator:
+                        params:
+                          - 2
+                        type: gt
+                      operator:
+                        type: and
+                      query:
+                        params: []
+                  datasource:
+                    type: __expr__
+                    uid: __expr__
+                  expression: A
+                  reducer: last
+                  refId: B
+                  type: reduce
+            noDataState: NoData
+            execErrState: Alerting
+            for: 15m
+            annotations:
+              node: '{{ $labels.instance }}'
+              load_average: '{{ printf "%.2f" $values.A }}'
+              summary: 'Node load average is critically high relative to CPU count'
+            labels:
+              severity: warning
+
+          - uid: node_exporter_down
+            title: Node Exporter Down
+            condition: B
+            data:
+              - refId: A
+                relativeTimeRange:
+                  from: 300
+                  to: 0
+                datasourceUid: prometheus
+                model:
+                  expr: 'up{job="node-exporter"}'
+                  refId: A
+                  intervalMs: 1000
+                  maxDataPoints: 43200
+              - refId: B
+                relativeTimeRange:
+                  from: 300
+                  to: 0
+                datasourceUid: __expr__
+                model:
+                  conditions:
+                    - evaluator:
+                        params:
+                          - 1
+                        type: lt
+                      operator:
+                        type: and
+                      query:
+                        params: []
+                  datasource:
+                    type: __expr__
+                    uid: __expr__
+                  expression: A
+                  reducer: min
+                  refId: B
+                  type: reduce
+            noDataState: NoData
+            execErrState: Alerting
+            for: 2m
+            annotations:
+              node: '{{ $labels.instance }}'
+              summary: 'Node exporter is down - unable to collect metrics'
+            labels:
+              severity: critical
+  
+  contactpoints.yaml: |
+    apiVersion: 1
+    contactPoints:
+      - orgId: 1
+        name: telegram
+        receivers:
+          - uid: telegram_default
+            type: telegram
+            disableResolveMessage: false
+            settings:
+              bottoken: $TELEGRAM_BOT_TOKEN
+              chatid: "124317807"
+              message: |
+                {{ if eq .Status "firing" }}🔥 FIRING{{ else }}✅ RESOLVED{{ end }}
+                
+                {{ range .Alerts }}
+                📊 <b>{{ .Labels.alertname }}</b>
+                {{ .Annotations.summary }}
+                
+                {{ if .Annotations.node }}🖥 <b>Node:</b> <code>{{ .Annotations.node }}</code>{{ end }}
+                {{ if .Annotations.pod }}📦 <b>Pod:</b> <code>{{ .Annotations.pod }}</code>{{ end }}
+                {{ if .Annotations.namespace }}📁 <b>Namespace:</b> <code>{{ .Annotations.namespace }}</code>{{ end }}
+                {{ if .Annotations.throttle_rate }}⚠️ <b>Throttling rate:</b> {{ .Annotations.throttle_rate }}{{ end }}
+                
+                🔗 <a href="{{ .GeneratorURL }}">View in Grafana</a>
+                {{ end }}
+              parse_mode: HTML
+  
+  policies.yaml: |
+    apiVersion: 1
+    policies:
+      - orgId: 1
+        receiver: telegram
+        group_by:
+          - grafana_folder
+          - alertname
+        group_wait: 10s
+        group_interval: 5m
+        repeat_interval: 12h

k8s/core/prom-stack/grafana-values.yaml

@@ -1,54 +0,0 @@
-envFromSecret: grafana-admin
-nodeSelector:
-  kubernetes.io/hostname: master.tail2fe2d.ts.net
-
-admin:
-  existingSecret: grafana-admin
-  userKey: username
-  passwordKey: password
-
-grafana.ini:
-  auth:
-    signout_redirect_url: https://idm.hexor.cy/application/o/grafana/end-session/
-    # oauth_auto_login: true
-  auth.generic_oauth:
-    name: authentik
-    enabled: true
-    scopes: "openid profile email"
-    auth_url: https://idm.hexor.cy/application/o/authorize/
-    token_url: https://idm.hexor.cy/application/o/token/
-    api_url: https://idm.hexor.cy/application/o/userinfo/
-    role_attribute_path: >-
-      contains(groups, 'Grafana Admin') && 'Admin' ||
-      contains(groups, 'Grafana Editors') && 'Editor' ||
-      contains(groups, 'Grafana Viewer') && 'Viewer'
-  database:
-    type: postgres
-    host: psql.psql.svc:5432
-    name: grafana
-    user: grafana
-    ssl_mode: disable
-
-datasources:
-  datasources.yaml:
-    apiVersion: 1
-    datasources:
-      - name: Prometheus Local
-        type: prometheus
-        url: http://prometheus-kube-prometheus-prometheus.prometheus.svc:9090
-        access: proxy
-        isDefault: true
-
-ingress:
-  enabled: true
-  ingressClassName: traefik
-  annotations:
-    cert-manager.io/cluster-issuer: letsencrypt
-    traefik.ingress.kubernetes.io/router.middlewares: kube-system-https-redirect@kubernetescrd
-  hosts:
-    - gf.hexor.cy
-  tls:
-    - secretName: grafana-tls
-      hosts:
-        - '*.hexor.cy'
-

k8s/core/prom-stack/kustomization.yaml

@@ -2,9 +2,11 @@ apiVersion: kustomize.config.k8s.io/v1beta1
 kind: Kustomization
 
 resources:
-  - app.yaml
   - persistentVolume.yaml
   - external-secrets.yaml
+  - grafana-alerting-configmap.yaml
+  - alertmanager-config.yaml
+  - furumi-dashboard-cm.yaml
 
 helmCharts:
   - name: kube-prometheus-stack
@@ -15,11 +17,18 @@ helmCharts:
     valuesFile: prom-values.yaml
     includeCRDs: true
 
-  - name: grafana
+  - name: loki
     repo: https://grafana.github.io/helm-charts
-    version: 10.2.0
-    releaseName: grafana
+    version: 6.29.0
+    releaseName: loki
     namespace: prometheus
-    valuesFile: grafana-values.yaml
+    valuesFile: loki-values.yaml
     includeCRDs: true
 
+  - name: promtail
+    repo: https://grafana.github.io/helm-charts
+    version: 6.16.6
+    releaseName: promtail
+    namespace: prometheus
+    valuesFile: promtail-values.yaml
+