koordlet: support heterogeneous GPU device reporting (koordinator-sh#2501)

Signed-off-by: ZhuZhezz <[email protected]>

Author: ZhuZhezz

apis/scheduling/v1alpha1/device_types.go

@@ -53,6 +53,8 @@ type DeviceInfo struct {
 	Topology *DeviceTopology `json:"topology,omitempty"`
 	// VFGroups represents the virtual function devices
 	VFGroups []VirtualFunctionGroup `json:"vfGroups,omitempty"`
+	// Conditions represents current conditions of device
+	Conditions []metav1.Condition `json:"conditions,omitempty"`
 }
 
 type DeviceTopology struct {
@@ -80,6 +82,12 @@ type VirtualFunction struct {
 	BusID string `json:"busID,omitempty"`
 }
 
+type DeviceConditionType string
+
+const (
+	DeviceConditionHealthy DeviceConditionType = "Healthy"
+)
+
 type DeviceStatus struct {
 	Allocations []DeviceAllocation `json:"allocations,omitempty"`
 }

apis/scheduling/v1alpha1/zz_generated.deepcopy.go

@@ -40,6 +40,79 @@ spec:
               devices:
                 items:
                   properties:
+                    conditions:
+                      description: Conditions represents current conditions of device
+                      items:
+                        description: "Condition contains details for one aspect of
+                          the current state of this API Resource.\n---\nThis struct
+                          is intended for direct use as an array at the field path
+                          .status.conditions.  For example,\n\n\n\ttype FooStatus
+                          struct{\n\t    // Represents the observations of a foo's
+                          current state.\n\t    // Known .status.conditions.type are:
+                          \"Available\", \"Progressing\", and \"Degraded\"\n\t    //
+                          +patchMergeKey=type\n\t    // +patchStrategy=merge\n\t    //
+                          +listType=map\n\t    // +listMapKey=type\n\t    Conditions
+                          []metav1.Condition `json:\"conditions,omitempty\" patchStrategy:\"merge\"
+                          patchMergeKey:\"type\" protobuf:\"bytes,1,rep,name=conditions\"`\n\n\n\t
+                          \   // other fields\n\t}"
+                        properties:
+                          lastTransitionTime:
+                            description: |-
+                              lastTransitionTime is the last time the condition transitioned from one status to another.
+                              This should be when the underlying condition changed.  If that is not known, then using the time when the API field changed is acceptable.
+                            format: date-time
+                            type: string
+                          message:
+                            description: |-
+                              message is a human readable message indicating details about the transition.
+                              This may be an empty string.
+                            maxLength: 32768
+                            type: string
+                          observedGeneration:
+                            description: |-
+                              observedGeneration represents the .metadata.generation that the condition was set based upon.
+                              For instance, if .metadata.generation is currently 12, but the .status.conditions[x].observedGeneration is 9, the condition is out of date
+                              with respect to the current state of the instance.
+                            format: int64
+                            minimum: 0
+                            type: integer
+                          reason:
+                            description: |-
+                              reason contains a programmatic identifier indicating the reason for the condition's last transition.
+                              Producers of specific condition types may define expected values and meanings for this field,
+                              and whether the values are considered a guaranteed API.
+                              The value should be a CamelCase string.
+                              This field may not be empty.
+                            maxLength: 1024
+                            minLength: 1
+                            pattern: ^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$
+                            type: string
+                          status:
+                            description: status of the condition, one of True, False,
+                              Unknown.
+                            enum:
+                            - "True"
+                            - "False"
+                            - Unknown
+                            type: string
+                          type:
+                            description: |-
+                              type of condition in CamelCase or in foo.example.com/CamelCase.
+                              ---
+                              Many .condition.type values are consistent across resources like Available, but because arbitrary conditions can be
+                              useful (see .node.status.conditions), the ability to deconflict is important.
+                              The regex it matches is (dns1123SubdomainFmt/)?(qualifiedNameFmt)
+                            maxLength: 316
+                            pattern: ^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$
+                            type: string
+                        required:
+                        - lastTransitionTime
+                        - message
+                        - reason
+                        - status
+                        - type
+                        type: object
+                      type: array
                     health:
                       default: false
                       description: Health indicates whether the device is normal