fix: readme and rbac issue (#78)

* fix: readme and rbac issue

* fix: bump chart version

Author: Code2Life

README.md

@@ -35,11 +35,22 @@ Tensor Fusion is a state-of-the-art **GPU virtualization and pooling solution**
 #### 🔄 Battle-tested GPU-over-IP Remote GPU Sharing 
 #### ⚖️ GPU-first Scheduling and Auto-scaling
 #### 📊 Computing Oversubscription and GPU VRAM Expansion
-#### 🛫 GPU Live Migration
+#### 🛫 GPU Pooling, Monitoring, Live Migration, AI Model Preloading and more
 
 ## 🎬 Demo
 
-WIP
+### Fractional vGPU & GPU-over-IP & Distributed Allocation
+
+![Fractional vGPU & GPU-over-IP & Distributed Allocation](https://cdn.tensor-fusion.ai//demo/overall-demo.gif)
+
+
+### AI Infra Console
+
+![AI Infra Console](https://cdn.tensor-fusion.ai//demo/ai-infra-console.gif)
+
+### GPU Live-migration [End-to-end feature WIP]
+
+![Live-migration PoC](https://cdn.tensor-fusion.ai//demo/gpu-migration-poc.gif)
 
 ## 🚀 Quick Start
 

charts/tensor-fusion/Chart.yaml

@@ -15,7 +15,7 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 1.2.9
+version: 1.2.10
 
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to

charts/tensor-fusion/templates/rbac.yaml

@@ -3,6 +3,17 @@ kind: ClusterRole
 metadata:
   name: {{ include "tensor-fusion.fullname" . }}-role
 rules:
+rules:
+- apiGroups:
+  - ""
+  resources:
+  - configmaps
+  - namespaces
+  - secrets
+  verbs:
+  - get
+  - list
+  - watch
 - apiGroups:
   - ""
   resources:
@@ -23,15 +34,6 @@ rules:
   - patch
   - update
   - watch
-- apiGroups:
-  - ""
-  resources:
-  - pods/exec
-  verbs:
-  - create
-  - get
-  - patch
-  - update
 - apiGroups:
   - ""
   resources:
@@ -51,19 +53,17 @@ rules:
 - apiGroups:
   - ""
   resources:
-  - secrets
+  - pods/exec
   verbs:
+  - create
   - get
-  - list
-  - watch
+  - patch
+  - update
 - apiGroups:
   - apps
   resources:
-  - configmaps
   - daemonsets
   - deployments
-  - namespaces
-  - secrets
   verbs:
   - create
   - delete
@@ -95,6 +95,7 @@ rules:
 - apiGroups:
   - tensor-fusion.ai
   resources:
+  - clientprofiles
   - gpunodeclasses
   - gpunodes
   - gpupools
@@ -103,7 +104,6 @@ rules:
   - tensorfusionclusters
   - tensorfusionconnections
   - tensorfusionworkloads
-  - clientprofiles
   verbs:
   - create
   - delete
@@ -115,18 +115,21 @@ rules:
 - apiGroups:
   - tensor-fusion.ai
   resources:
+  - clientprofiles/finalizers
   - gpunodeclasses/finalizers
   - gpunodes/finalizers
   - gpupools/finalizers
   - gpus/finalizers
   - schedulingconfigtemplates/finalizers
+  - tensorfusionclusters/finalizers
   - tensorfusionconnections/finalizers
   - tensorfusionworkloads/finalizers
   verbs:
   - update
 - apiGroups:
   - tensor-fusion.ai
   resources:
+  - clientprofiles/status
   - gpunodeclasses/status
   - gpunodes/status
   - gpupools/status
@@ -135,11 +138,11 @@ rules:
   - tensorfusionclusters/status
   - tensorfusionconnections/status
   - tensorfusionworkloads/status
-  - clientprofiles/status
   verbs:
   - get
   - patch
   - update
+
 ---
 apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRoleBinding
@@ -152,4 +155,4 @@ roleRef:
 subjects:
 - kind: ServiceAccount
   name: {{ include "tensor-fusion.serviceAccountName" . }}
-  namespace: {{ include "tensor-fusion.namespace" . }}
+  namespace: {{ include "tensor-fusion.namespace" . }}

config/rbac/role.yaml

@@ -4,6 +4,16 @@ kind: ClusterRole
 metadata:
   name: manager-role
 rules:
+- apiGroups:
+  - ""
+  resources:
+  - configmaps
+  - namespaces
+  - secrets
+  verbs:
+  - get
+  - list
+  - watch
 - apiGroups:
   - ""
   resources:
@@ -49,22 +59,11 @@ rules:
   - get
   - patch
   - update
-- apiGroups:
-  - ""
-  resources:
-  - secrets
-  verbs:
-  - get
-  - list
-  - watch
 - apiGroups:
   - apps
   resources:
-  - configmaps
   - daemonsets
   - deployments
-  - namespaces
-  - secrets
   verbs:
   - create
   - delete
@@ -104,6 +103,7 @@ rules:
   - schedulingconfigtemplates
   - tensorfusionclusters
   - tensorfusionconnections
+  - tensorfusionworkloads
   verbs:
   - create
   - delete
@@ -123,6 +123,7 @@ rules:
   - schedulingconfigtemplates/finalizers
   - tensorfusionclusters/finalizers
   - tensorfusionconnections/finalizers
+  - tensorfusionworkloads/finalizers
   verbs:
   - update
 - apiGroups:
@@ -136,6 +137,7 @@ rules:
   - schedulingconfigtemplates/status
   - tensorfusionclusters/status
   - tensorfusionconnections/status
+  - tensorfusionworkloads/status
   verbs:
   - get
   - patch

internal/controller/tensorfusioncluster_controller.go

@@ -56,10 +56,10 @@ type TensorFusionClusterReconciler struct {
 // +kubebuilder:rbac:groups=tensor-fusion.ai,resources=tensorfusionclusters/status,verbs=get;update;patch
 // +kubebuilder:rbac:groups=tensor-fusion.ai,resources=tensorfusionclusters/finalizers,verbs=update
 // +kubebuilder:rbac:groups=core,resources=events,verbs=create;patch
-// +kubebuilder:rbac:groups=apps,resources=deployments;namespaces;configmaps;secrets,verbs=get;list;watch;create;update;patch;delete
+// +kubebuilder:rbac:groups=apps,resources=deployments,verbs=get;list;watch;create;update;patch;delete
 // +kubebuilder:rbac:groups=batch,resources=jobs,verbs=get;list;watch;create;update;patch;delete
 // +kubebuilder:rbac:groups=batch,resources=cronjobs,verbs=get;list;watch
-// +kubebuilder:rbac:groups="",resources=secrets,verbs=get;list;watch
+// +kubebuilder:rbac:groups="",resources=secrets;namespaces;configmaps,verbs=get;list;watch
 // +kubebuilder:rbac:groups=apps,resources=daemonsets,verbs=get;list;watch;create;update;patch;delete
 
 // Reconcile a TensorFusionCluster object, create and monitor GPU Pool, managing cluster level component versions

internal/controller/tensorfusionworkload_controller.go

@@ -54,6 +54,8 @@ type TensorFusionWorkloadReconciler struct {
 // +kubebuilder:rbac:groups=tensor-fusion.ai,resources=tensorfusionworkloads,verbs=get;list;watch;create;update;patch;delete
 // +kubebuilder:rbac:groups=tensor-fusion.ai,resources=tensorfusionworkloads/status,verbs=get;update;patch
 // +kubebuilder:rbac:groups=tensor-fusion.ai,resources=tensorfusionworkloads/finalizers,verbs=update
+
+// TensorFusionWorkload Reconciler
 func (r *TensorFusionWorkloadReconciler) Reconcile(ctx context.Context, req ctrl.Request) (ctrl.Result, error) {
 	log := log.FromContext(ctx)
 	log.Info("Reconciling TensorFusionWorkload", "request", req)