Auto-update README with current k8s applications

Generated by CI/CD workflow on 2026-03-12 10:28:35

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

README.md

@@ -16,6 +16,7 @@ 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) |
@@ -37,6 +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) |
@@ -45,6 +48,8 @@ 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) |

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/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/n8n/deployment-main.yaml

@@ -85,6 +85,8 @@ spec:
           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
@@ -132,7 +134,7 @@ spec:
             memory: 512Mi
           limits:
             cpu: 4000m
-            memory: 2048Gi
+            memory: 2048Mi
         livenessProbe:
           httpGet:
             path: /healthz

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/kustomization.yaml

@@ -10,7 +10,7 @@ resources:
   - paddleocr-deployment.yaml
   - paddleocr-service.yaml
   - deployment-main.yaml
-# - deployment-worker.yaml
+  - deployment-worker.yaml
   - deployment-runner.yaml
   - service.yaml
   - ingress.yaml

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

@@ -4,6 +4,11 @@ image:
   tag: "latest"
 nodeSelector:
   kubernetes.io/hostname: uk-desktop.tail2fe2d.ts.net
+tolerations:
+  - key: workload
+    operator: Equal
+    value: desktop
+    effect: NoSchedule
 ingress:
     enabled: false
 ollama:
@@ -11,3 +16,7 @@ ollama:
     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:
+    tls: true
-      - hosts:
+    existingSecret: ollama-tls
-          - '*.hexor.cy'
-        secretName: 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/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/authentik/app.yaml

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

k8s/core/authentik/kustomization.yaml

@@ -10,7 +10,7 @@ resources:
 helmCharts:
   - name: authentik
     repo: https://charts.goauthentik.io
-    version: 2026.2.0
+    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"
+    tag: "2026.2.1"
-  nodeSelector:
-    kubernetes.io/hostname: master.tail2fe2d.ts.net
 
 authentik:
     error_reporting:
@@ -15,14 +13,35 @@ worker:
   envFrom:
     - secretRef:
         name: authentik-creds
-  volumes:
+# volumes:
-    - name: dshm
+#   - name: dshm
-      emptyDir:
+#     emptyDir:
-        medium: Memory
+#       medium: Memory
-        sizeLimit: 512Mi
+#       sizeLimit: 512Mi
-  volumeMounts:
+# volumeMounts:
-    - name: dshm
+#   - name: dshm
-      mountPath: /dev/shm
+#     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/gpu/values.yaml

@@ -1,21 +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:
-  name: "nvidia-plugin-config"
+  default: any
   map:
-    # use device driver mode instead of dev/nvmem
+    any: |-
-    default: |-
       version: v1
-      flags:
+      sharing:
-        migStrategy: none
+        timeSlicing:
-        failOnInitError: true
+          resources:
-        nvidiaDriverRoot: "/"
+          - name: nvidia.com/gpu
-        plugin:
+            replicas: 4
-          passDeviceSpecs: false
-          deviceListStrategy: envvar
-          deviceIDStrategy: uuid

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": "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": 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/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

@@ -20,7 +20,7 @@ data:
                 relativeTimeRange:
                   from: 600
                   to: 0
-                datasourceUid: P76F38748CEC837F0
+                datasourceUid: prometheus
                 model:
                   expr: 'rate(container_cpu_cfs_throttled_periods_total{container="pasarguard-node"}[5m])'
                   refId: A
@@ -73,7 +73,7 @@ data:
                 relativeTimeRange:
                   from: 600
                   to: 0
-                datasourceUid: P76F38748CEC837F0
+                datasourceUid: prometheus
                 model:
                   expr: 'kube_node_status_condition{condition="Ready",status="false"}'
                   refId: A
@@ -119,7 +119,7 @@ data:
                 relativeTimeRange:
                   from: 300
                   to: 0
-                datasourceUid: P76F38748CEC837F0
+                datasourceUid: prometheus
                 model:
                   expr: '(1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100'
                   refId: A
@@ -165,7 +165,7 @@ data:
                 relativeTimeRange:
                   from: 300
                   to: 0
-                datasourceUid: P76F38748CEC837F0
+                datasourceUid: prometheus
                 model:
                   expr: '100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100)'
                   refId: A
@@ -211,7 +211,7 @@ data:
                 relativeTimeRange:
                   from: 300
                   to: 0
-                datasourceUid: P76F38748CEC837F0
+                datasourceUid: prometheus
                 model:
                   expr: '(1 - (node_filesystem_avail_bytes{fstype=~"ext[234]|xfs|zfs|btrfs"} / node_filesystem_size_bytes)) * 100'
                   refId: A
@@ -258,9 +258,9 @@ data:
                 relativeTimeRange:
                   from: 300
                   to: 0
-                datasourceUid: P76F38748CEC837F0
+                datasourceUid: prometheus
                 model:
-                  expr: 'node_load5 / on(instance) group_left count by(instance)(node_cpu_seconds_total{mode="idle"})'
+                  expr: 'node_load15 / on(instance) group_left count by(instance)(node_cpu_seconds_total{mode="idle"})'
                   refId: A
                   intervalMs: 1000
                   maxDataPoints: 43200
@@ -273,7 +273,7 @@ data:
                   conditions:
                     - evaluator:
                         params:
-                          - 0.8
+                          - 2
                         type: gt
                       operator:
                         type: and
@@ -283,16 +283,16 @@ data:
                     type: __expr__
                     uid: __expr__
                   expression: A
-                  reducer: max
+                  reducer: last
                   refId: B
                   type: reduce
             noDataState: NoData
             execErrState: Alerting
-            for: 5m
+            for: 15m
             annotations:
               node: '{{ $labels.instance }}'
               load_average: '{{ printf "%.2f" $values.A }}'
-              summary: 'Node load average is high relative to CPU count'
+              summary: 'Node load average is critically high relative to CPU count'
             labels:
               severity: warning
 
@@ -304,7 +304,7 @@ data:
                 relativeTimeRange:
                   from: 300
                   to: 0
-                datasourceUid: P76F38748CEC837F0
+                datasourceUid: prometheus
                 model:
                   expr: 'up{job="node-exporter"}'
                   refId: A

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

@@ -1,85 +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
-      - name: Loki
-        type: loki
-        url: http://loki-gateway.prometheus.svc:80
-        access: proxy
-
-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'
-
-extraConfigmapMounts:
-  - name: grafana-alerting-rules
-    mountPath: /etc/grafana/provisioning/alerting/rules.yaml
-    configMap: grafana-alerting
-    subPath: rules.yaml
-    readOnly: true
-  - name: grafana-alerting-contactpoints
-    mountPath: /etc/grafana/provisioning/alerting/contactpoints.yaml
-    configMap: grafana-alerting
-    subPath: contactpoints.yaml
-    readOnly: true
-  - name: grafana-alerting-policies
-    mountPath: /etc/grafana/provisioning/alerting/policies.yaml
-    configMap: grafana-alerting
-    subPath: policies.yaml
-    readOnly: true
-
-envValueFrom:
-  TELEGRAM_BOT_TOKEN:
-    secretKeyRef:
-      name: grafana-telegram
-      key: bot-token
-  TELEGRAM_CHAT_ID:
-    secretKeyRef:
-      name: grafana-telegram
-      key: chat-id
-

k8s/core/prom-stack/kustomization.yaml

@@ -6,6 +6,7 @@ resources:
   - external-secrets.yaml
   - grafana-alerting-configmap.yaml
   - alertmanager-config.yaml
+  - furumi-dashboard-cm.yaml
 
 helmCharts:
   - name: kube-prometheus-stack
@@ -16,14 +17,6 @@ helmCharts:
     valuesFile: prom-values.yaml
     includeCRDs: true
 
-  - name: grafana
-    repo: https://grafana.github.io/helm-charts
-    version: 10.2.0
-    releaseName: grafana
-    namespace: prometheus
-    valuesFile: grafana-values.yaml
-    includeCRDs: true
-
   - name: loki
     repo: https://grafana.github.io/helm-charts
     version: 6.29.0

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

@@ -1,5 +1,4 @@
-grafana:
+
-  enabled: false
 
 alertmanager:
   config:
@@ -92,3 +91,88 @@ prometheus:
             requests:
               storage: 400Gi
 
+grafana:
+  enabled: true
+  
+  serviceAccount:
+    create: true
+    name: "prom-grafana-sa"
+
+  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/
+    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
+
+  # The Loki datasource config needs to be preserved, 
+  # but instead of "datasources.datasources.yaml", we define it like this for the prometheus-stack chart:
+  additionalDataSources:
+    - name: Loki
+      type: loki
+      url: http://loki-gateway.prometheus.svc:80
+      access: proxy
+      orgId: 1
+
+  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'
+
+  extraConfigmapMounts:
+    - name: grafana-alerting-rules
+      mountPath: /etc/grafana/provisioning/alerting/rules.yaml
+      configMap: grafana-alerting
+      subPath: rules.yaml
+      readOnly: true
+    - name: grafana-alerting-contactpoints
+      mountPath: /etc/grafana/provisioning/alerting/contactpoints.yaml
+      configMap: grafana-alerting
+      subPath: contactpoints.yaml
+      readOnly: true
+    - name: grafana-alerting-policies
+      mountPath: /etc/grafana/provisioning/alerting/policies.yaml
+      configMap: grafana-alerting
+      subPath: policies.yaml
+      readOnly: true
+
+  envValueFrom:
+    TELEGRAM_BOT_TOKEN:
+      secretKeyRef:
+        name: grafana-telegram
+        key: bot-token
+    TELEGRAM_CHAT_ID:
+      secretKeyRef:
+        name: grafana-telegram
+        key: chat-id