feat: tensor-fusion workload Implementation (#59)

Author: 0x5457

.vscode/launch.json

@@ -50,12 +50,12 @@
             "program": "${workspaceFolder}/cmd/main.go",
         },
         {
-            "name": "Debug Test Code",
+            "name": "Run Unit Tests",
             "type": "go",
             "request": "launch",
-            "mode": "auto",
-            "console": "integratedTerminal",
-            "program": "${workspaceFolder}/cmd/tmp/main.go",
+            "mode": "test",
+            "program": "${workspaceFolder}",
+            "console": "integratedTerminal"
         }
     ]
 }

PROJECT

@@ -79,4 +79,12 @@ resources:
   kind: ClientProfile
   path: github.com/NexusGPU/tensor-fusion-operator/api/v1
   version: v1
+- api:
+    crdVersion: v1
+    namespaced: true
+  controller: true
+  domain: tensor-fusion.ai
+  kind: TensorFusionWorkload
+  path: github.com/NexusGPU/tensor-fusion-operator/api/v1
+  version: v1
 version: "3"

api/v1/tensorfusionconnection_types.go

@@ -33,29 +33,14 @@ type Resources struct {
 
 // TensorFusionConnectionSpec defines the desired state of TensorFusionConnection.
 type TensorFusionConnectionSpec struct {
-	PoolName  string    `json:"poolName"`
-	Resources Resources `json:"resources"`
-
-	// +optional
-	// localGpu mode will schedule the GPU in advance
-	GPUs []string `json:"gpu"`
+	WorkloadName string `json:"workloadName"`
 }
 
-type TensorFusionConnectionPhase string
-
-// These are the valid phases of a GpuConnection.
-const (
-	TensorFusionConnectionPending  TensorFusionConnectionPhase = "Pending"
-	TensorFusionConnectionStarting TensorFusionConnectionPhase = "Starting"
-	TensorFusionConnectionRunning  TensorFusionConnectionPhase = "Running"
-)
-
 // TensorFusionConnectionStatus defines the observed state of TensorFusionConnection.
 type TensorFusionConnectionStatus struct {
-	Phase         TensorFusionConnectionPhase `json:"phase"`
-	ConnectionURL string                      `json:"connectionURL"`
-	QoS           QoSLevel                    `json:"qos,omitempty"`
-	GPU           string                      `json:"gpu,omitempty"`
+	Phase         WorkerPhase `json:"phase"`
+	ConnectionURL string      `json:"connectionURL"`
+	WorkerName    string      `json:"workerName"`
 }
 
 // +kubebuilder:object:root=true

api/v1/tensorfusionworkload_types.go

@@ -0,0 +1,88 @@
+/*
+Copyright 2024.
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+*/
+
+package v1
+
+import (
+	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
+)
+
+// TensorFusionWorkloadSpec defines the desired state of TensorFusionWorkload.
+type TensorFusionWorkloadSpec struct {
+	Replicas *int32 `json:"replicas,omitempty"`
+	PoolName string `json:"poolName"`
+	// +optional
+	Resources Resources `json:"resources"`
+	// +optional
+	Qos QoSLevel `json:"qos,omitempty"`
+	// +optional
+	IsLocalGPU bool `json:"isLocalGPU,omitempty"`
+}
+
+type WorkerPhase string
+
+const (
+	WorkerPending WorkerPhase = "Pending"
+	WorkerRunning WorkerPhase = "Running"
+	WorkerFailed  WorkerPhase = "Failed"
+)
+
+type WorkerStatus struct {
+	WorkerPhase WorkerPhase `json:"workerPhase"`
+
+	WorkerName   string            `json:"workerName"`
+	NodeSelector map[string]string `json:"nodeSelector,omitempty"`
+	// +optional
+	WorkerIp string `json:"workerIp,omitempty"`
+	// +optional
+	WorkerPort int `json:"workerPort,omitempty"`
+}
+
+// TensorFusionWorkloadStatus defines the observed state of TensorFusionWorkload.
+type TensorFusionWorkloadStatus struct {
+	// replicas is the number of Pods created by the Workload controller.
+	Replicas int32 `json:"replicas"`
+
+	// readyReplicas is the number of pods created for this Workload with a Ready Condition.
+	ReadyReplicas int32 `json:"readyReplicas,omitempty"`
+
+	WorkerStatuses []WorkerStatus `json:"workerStatuses,omitempty"`
+}
+
+// +kubebuilder:object:root=true
+// +kubebuilder:subresource:status
+
+// TensorFusionWorkload is the Schema for the tensorfusionworkloads API.
+type TensorFusionWorkload struct {
+	metav1.TypeMeta   `json:",inline"`
+	metav1.ObjectMeta `json:"metadata,omitempty"`
+
+	Spec   TensorFusionWorkloadSpec   `json:"spec,omitempty"`
+	Status TensorFusionWorkloadStatus `json:"status,omitempty"`
+}
+
+// +kubebuilder:object:root=true
+
+// TensorFusionWorkloadList contains a list of TensorFusionWorkload.
+type TensorFusionWorkloadList struct {
+	metav1.TypeMeta `json:",inline"`
+	metav1.ListMeta `json:"metadata,omitempty"`
+	Items           []TensorFusionWorkload `json:"items"`
+}
+
+func init() {
+	SchemeBuilder.Register(&TensorFusionWorkload{}, &TensorFusionWorkloadList{})
+}

api/v1/zz_generated.deepcopy.go

@@ -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: 1.2.5
+version: 1.2.6
 
 # 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