feat: init cluster manager and node manager types (#6)

* feat: init cluster manager and node manager types

* fix: nested type and raw object issue

* fix: typing enhancement

* feat: fix webhook bug, create tfconn in pod controller (#7)

* chore(deps): bump golang.org/x/crypto from 0.24.0 to 0.31.0 (#9)

Bumps [golang.org/x/crypto](https://github.com/golang/crypto) from 0.24.0 to 0.31.0.
- [Commits](golang/crypto@v0.24.0...v0.31.0)

---
updated-dependencies:
- dependency-name: golang.org/x/crypto
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* fix: typing enhancement

* fix: go lint issues

---------

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: 0x5457 <0x5457@protonmail.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

.gitignore

@@ -25,3 +25,5 @@ go.work
 *.swp
 *.swo
 *~
+
+.DS_Store

PROJECT

@@ -63,4 +63,12 @@ resources:
   kind: GPUNodeClass
   path: github.com/NexusGPU/tensor-fusion-operator/api/v1
   version: v1
+- api:
+    crdVersion: v1
+    namespaced: true
+  controller: true
+  domain: tensor-fusion.ai
+  kind: SchedulingConfigTemplate
+  path: github.com/NexusGPU/tensor-fusion-operator/api/v1
+  version: v1
 version: "3"

README.md

@@ -12,6 +12,12 @@
 - kubectl version v1.11.3+.
 - Access to a Kubernetes v1.11.3+ cluster.
 
+### Add new API
+
+```bash
+kubebuilder create api --group "" --version v1 --kind SchedulingConfigTemplate --namespaced false
+```
+
 ### To Deploy on the cluster
 **Build and push your image to the location specified by `IMG`:**
 
@@ -112,3 +118,4 @@ 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.
 
+

api/v1/base_types.go

@@ -0,0 +1,6 @@
+package v1
+
+type NameNamespace struct {
+	Name      string `json:"name,omitempty"`
+	Namespace string `json:"namespace,omitempty"`
+}

api/v1/gpunode_types.go

@@ -25,21 +25,65 @@ import (
 
 // GPUNodeSpec defines the desired state of GPUNode.
 type GPUNodeSpec struct {
-	// INSERT ADDITIONAL SPEC FIELDS - desired state of cluster
-	// Important: Run "make" to regenerate code after modifying this file
+	ManageMode GPUNodeManageMode `json:"manageMode,omitempty"`
 
-	// Foo is an example field of GPUNode. Edit gpunode_types.go to remove/update
-	Foo string `json:"foo,omitempty"`
+	// if not all GPU cards should be used, specify the GPU card indices, default to empty,
+	// onboard all GPU cards to the pool
+	GPUCardIndices []int `json:"gpuCardIndices,omitempty"`
 }
 
+type GPUNodeManageMode string
+
+const (
+	GPUNodeManageModeNone   GPUNodeManageMode = "manual"
+	GPUNodeManageModeAuto   GPUNodeManageMode = "selected"
+	GPUNodeManageModeManual GPUNodeManageMode = "provisioned"
+)
+
 // GPUNodeStatus defines the observed state of GPUNode.
 type GPUNodeStatus struct {
-	// INSERT ADDITIONAL STATUS FIELD - define observed state of cluster
-	// Important: Run "make" to regenerate code after modifying this file
+	Phase TensorFusionClusterPhase `json:"phase,omitempty"`
+
+	Conditions []metav1.Condition `json:"conditions,omitempty"`
+
+	TotalTFlops int32  `json:"totalTFlops,omitempty"`
+	TotalVRAM   string `json:"totalVRAM,omitempty"`
+
+	AvailableTFlops int32  `json:"availableTFlops,omitempty"`
+	AvailableVRAM   string `json:"availableVRAM,omitempty"`
+
+	HypervisorStatus NodeHypervisorStatus `json:"hypervisorStatus,omitempty"`
+
+	NodeInfo GPUNodeInfo `json:"nodeInfo,omitempty"`
+
+	LoadedModels []string `json:"loadedModels,omitempty"`
+
+	TotalGPUs             int32    `json:"totalGPUs,omitempty"`
+	ManagedGPUs           int32    `json:"managedGPUs,omitempty"`
+	ManagedGPUResourceIDs []string `json:"managedGPUResourceIDs,omitempty"`
+}
+
+type GPUNodeInfo struct {
+	Hostname         string `json:"hostname,omitempty"`
+	IP               string `json:"ip,omitempty"`
+	KernalVersion    string `json:"kernalVersion,omitempty"`
+	OSImage          string `json:"osImage,omitempty"`
+	GPUDriverVersion string `json:"gpuDriverVersion,omitempty"`
+	GPUModel         string `json:"gpuModel,omitempty"`
+	GPUCount         int32  `json:"gpuCount,omitempty"`
+	OperatingSystem  string `json:"operatingSystem,omitempty"`
+	Architecture     string `json:"architecture,omitempty"`
+}
+
+type NodeHypervisorStatus struct {
+	HypervisorState   string      `json:"hypervisorState,omitempty"`
+	HypervisorVersion string      `json:"hypervisorVersion,omitempty"`
+	LastHeartbeatTime metav1.Time `json:"lastHeartbeatTime,omitempty"`
 }
 
 // +kubebuilder:object:root=true
 // +kubebuilder:subresource:status
+// +kubebuilder:resource:scope=Cluster
 
 // GPUNode is the Schema for the gpunodes API.
 type GPUNode struct {

api/v1/gpunodeclass_types.go

@@ -25,21 +25,60 @@ import (
 
 // GPUNodeClassSpec defines the desired state of GPUNodeClass.
 type GPUNodeClassSpec struct {
-	// INSERT ADDITIONAL SPEC FIELDS - desired state of cluster
-	// Important: Run "make" to regenerate code after modifying this file
+	OSImageFamily string `json:"osImageFamily,omitempty"` // The AMI family to use
 
-	// Foo is an example field of GPUNodeClass. Edit gpunodeclass_types.go to remove/update
-	Foo string `json:"foo,omitempty"`
+	OSImageSelectorTerms []NodeClassOSImageSelectorTerms `json:"osImageSelectorTerms,omitempty"`
+
+	BlockDeviceMappings []NodeClassBlockDeviceMappings `json:"blockDeviceMappings,omitempty"` // Block device mappings for the instance
+
+	InstanceProfile string `json:"instanceProfile,omitempty"` // The instance profile to use
+
+	MetadataOptions NodeClassMetadataOptions `json:"metadataOptions,omitempty"`
+
+	SecurityGroupSelectorTerms []NodeClassItemIDSelectorTerms `json:"securityGroupSelectorTerms,omitempty"`
+
+	SubnetSelectorTerms []NodeClassItemIDSelectorTerms `json:"subnetSelectorTerms,omitempty"` // Terms to select subnets
+
+	Tags map[string]string `json:"tags,omitempty"` // Tags associated with the resource
+
+	UserData string `json:"userData,omitempty"` // User data script for the instance
+}
+
+type NodeClassItemIDSelectorTerms struct {
+	ID string `json:"id,omitempty"` // The ID of the security group
+}
+
+type NodeClassMetadataOptions struct {
+	HttpEndpoint            string `json:"httpEndpoint,omitempty"`            // Whether the HTTP metadata endpoint is enabled
+	HttpProtocolIPv6        string `json:"httpProtocolIPv6,omitempty"`        // Whether IPv6 is enabled for the HTTP metadata endpoint
+	HttpPutResponseHopLimit int    `json:"httpPutResponseHopLimit,omitempty"` // The hop limit for HTTP PUT responses
+	HttpTokens              string `json:"httpTokens,omitempty"`              // The HTTP tokens required for metadata access
+}
+
+type NodeClassOSImageSelectorTerms struct {
+	Name  string `json:"name,omitempty"`
+	Owner string `json:"owner,omitempty"`
+}
+
+type NodeClassBlockDeviceMappings struct {
+	DeviceName string               `json:"deviceName,omitempty"` // The device name for the block device
+	Ebs        NodeClassEbsSettings `json:"ebs,omitempty"`
+}
+
+type NodeClassEbsSettings struct {
+	DeleteOnTermination bool   `json:"deleteOnTermination,omitempty"` // Whether to delete the EBS volume on termination
+	Encrypted           bool   `json:"encrypted,omitempty"`           // Whether the EBS volume is encrypted
+	VolumeSize          string `json:"volumeSize,omitempty"`          // The size of the EBS volume
+	VolumeType          string `json:"volumeType,omitempty"`          // The type of the EBS volume
 }
 
 // GPUNodeClassStatus defines the observed state of GPUNodeClass.
 type GPUNodeClassStatus struct {
-	// INSERT ADDITIONAL STATUS FIELD - define observed state of cluster
-	// Important: Run "make" to regenerate code after modifying this file
 }
 
 // +kubebuilder:object:root=true
 // +kubebuilder:subresource:status
+// +kubebuilder:resource:scope=Cluster
 
 // GPUNodeClass is the Schema for the gpunodeclasses API.
 type GPUNodeClass struct {