Skip to content

fix: allocation detail optimization, show detailed GPU pods in CR #433

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Nov 17, 2025
Merged

fix: allocation detail optimization, show detailed GPU pods in CR #433

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
db4094b
fix: index allocator, pod webhook priorityClass issue
Code2Life Nov 7, 2025
8b34f9e
fix: lint issue
Code2Life Nov 10, 2025
cfac49d
fix: add allocation detail in gpunode/gpu custom resource
Code2Life Nov 15, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 13 additions & 0 deletions api/v1/gpu_types.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,6 +79,19 @@ type RunningAppDetail struct {

// Worker count
Count int `json:"count"`

// Pod names that are running this workload
// +optional
Pods []*PodGPUInfo `json:"pods,omitempty"`
}

type PodGPUInfo struct {
Name string `json:"name,omitempty"`
Namespace string `json:"namespace,omitempty"`
UID string `json:"uid,omitempty"`
Requests Resource `json:"requests,omitempty"`
Limits Resource `json:"limits,omitempty"`
QoS QoSLevel `json:"qos,omitempty"`
}

// +kubebuilder:validation:Enum=Pending;Provisioning;Running;Unknown;Destroying;Migrating
Expand Down
2 changes: 1 addition & 1 deletion api/v1/gpunode_funcs.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ func (node *GPUNode) InitializeStatus(initTFlops, initVRAM resource.Quantity, in
TotalTFlops: initTFlops,
TotalVRAM: initVRAM,
TotalGPUs: initGPUs,
AllocationInfo: []*RunningAppDetail{},
AllocatedPods: make(map[string][]*PodGPUInfo),
LoadedModels: &[]string{},
ManagedGPUDeviceIDs: []string{},
ObservedGeneration: node.Generation,
Expand Down
5 changes: 4 additions & 1 deletion api/v1/gpunode_types.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,7 +96,10 @@ type GPUNodeStatus struct {
ObservedGeneration int64 `json:"observedGeneration,omitempty"`

// +optional
AllocationInfo []*RunningAppDetail `json:"allocationInfo,omitempty"`
TotalGPUPods int32 `json:"totalGPUPods,omitempty"`

// +optional
AllocatedPods map[string][]*PodGPUInfo `json:"allocatedPods,omitempty"`
}

// +kubebuilder:validation:Enum=Pending;Provisioning;Migrating;Running;Succeeded;Failed;Unknown;Destroying
Expand Down
57 changes: 48 additions & 9 deletions api/v1/zz_generated.deepcopy.go
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

90 changes: 75 additions & 15 deletions charts/tensor-fusion/crds/tensor-fusion.ai_gpunodes.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -86,21 +86,78 @@ spec:
status:
description: GPUNodeStatus defines the observed state of GPUNode.
properties:
allocationInfo:
items:
properties:
count:
description: Worker count
type: integer
name:
description: Workload name namespace
type: string
namespace:
type: string
required:
- count
type: object
type: array
allocatedPods:
additionalProperties:
items:
properties:
limits:
properties:
compute:
anyOf:
- type: integer
- type: string
description: 0-100 percentage, mutually exclusive with
TFLOPs
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
x-kubernetes-int-or-string: true
tflops:
anyOf:
- type: integer
- type: string
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
x-kubernetes-int-or-string: true
vram:
anyOf:
- type: integer
- type: string
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
x-kubernetes-int-or-string: true
required:
- tflops
- vram
type: object
name:
type: string
namespace:
type: string
qos:
enum:
- low
- medium
- high
- critical
type: string
requests:
properties:
compute:
anyOf:
- type: integer
- type: string
description: 0-100 percentage, mutually exclusive with
TFLOPs
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
x-kubernetes-int-or-string: true
tflops:
anyOf:
- type: integer
- type: string
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
x-kubernetes-int-or-string: true
vram:
anyOf:
- type: integer
- type: string
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
x-kubernetes-int-or-string: true
required:
- tflops
- vram
type: object
uid:
type: string
type: object
type: array
type: object
availableTFlops:
anyOf:
- type: integer
Expand Down Expand Up @@ -221,6 +278,9 @@ spec:
- Unknown
- Destroying
type: string
totalGPUPods:
format: int32
type: integer
totalGPUs:
format: int32
type: integer
Expand Down
71 changes: 71 additions & 0 deletions charts/tensor-fusion/crds/tensor-fusion.ai_gpus.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -159,6 +159,77 @@ spec:
type: string
namespace:
type: string
pods:
description: Pod names that are running this workload
items:
properties:
limits:
properties:
compute:
anyOf:
- type: integer
- type: string
description: 0-100 percentage, mutually exclusive
with TFLOPs
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
x-kubernetes-int-or-string: true
tflops:
anyOf:
- type: integer
- type: string
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
x-kubernetes-int-or-string: true
vram:
anyOf:
- type: integer
- type: string
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
x-kubernetes-int-or-string: true
required:
- tflops
- vram
type: object
name:
type: string
namespace:
type: string
qos:
enum:
- low
- medium
- high
- critical
type: string
requests:
properties:
compute:
anyOf:
- type: integer
- type: string
description: 0-100 percentage, mutually exclusive
with TFLOPs
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
x-kubernetes-int-or-string: true
tflops:
anyOf:
- type: integer
- type: string
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
x-kubernetes-int-or-string: true
vram:
anyOf:
- type: integer
- type: string
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
x-kubernetes-int-or-string: true
required:
- tflops
- vram
type: object
uid:
type: string
type: object
type: array
required:
- count
type: object
Expand Down
Loading
Loading