Skip to content

fix: comment out device allocation index assignment and logging in po… #446

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 1 commit into from
Nov 20, 2025
Merged

fix: comment out device allocation index assignment and logging in po… #446

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
7 changes: 3 additions & 4 deletions internal/webhook/v1/pod_webhook.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,6 @@
corev1 "k8s.io/api/core/v1"
"k8s.io/apimachinery/pkg/api/equality"
"k8s.io/apimachinery/pkg/api/errors"
"k8s.io/apimachinery/pkg/api/resource"
"k8s.io/apimachinery/pkg/util/strategicpatch"
ctrl "sigs.k8s.io/controller-runtime"
"sigs.k8s.io/controller-runtime/pkg/client"
Expand Down Expand Up @@ -273,7 +272,7 @@
}

func (m *TensorFusionPodMutator) patchTFClient(
ctx context.Context,

Check failure on line 275 in internal/webhook/v1/pod_webhook.go

View workflow job for this annotation

GitHub Actions / Run on Ubuntu 

(*TensorFusionPodMutator).patchTFClient - ctx is unused (unparam)
pod *corev1.Pod,
pool *tfv1.GPUPool,
isLocalGPU bool,
Expand All @@ -294,8 +293,8 @@
// Index must be assigned in webhook stage since scheduler cannot modify Pod
// This is a special index resource (1-512), not a real device resource
// Index is assigned in ascending order (1, 2, 3, ...) via distributed lock (leader election)
index := m.assignDeviceAllocationIndex(ctx, pod)
log.FromContext(ctx).Info("assigned device allocation index successfully", "index", index, "pod", pod.Name)
// index := m.assignDeviceAllocationIndex(ctx, pod)
// log.FromContext(ctx).Info("assigned device allocation index successfully", "index", index, "pod", pod.Name)

for _, containerIndex := range containerIndices {
container := &pod.Spec.Containers[containerIndex]
Expand Down Expand Up @@ -332,7 +331,7 @@
container.Resources.Limits = make(corev1.ResourceList)
}
// Limit is set to actual index value (1-512) for Device Plugin to match Pod
container.Resources.Limits[constants.PodIndexAnnotation] = resource.MustParse(strconv.Itoa(index))
// container.Resources.Limits[constants.PodIndexAnnotation] = resource.MustParse(strconv.Itoa(index))

if !isLocalGPU {
addConnectionForRemoteFixedReplicaVirtualGPU(pod, container, clientConfig)
Expand Down Expand Up @@ -378,7 +377,7 @@
return patches, nil
}

func (m *TensorFusionPodMutator) assignDeviceAllocationIndex(ctx context.Context, pod *corev1.Pod) int {

Check failure on line 380 in internal/webhook/v1/pod_webhook.go

View workflow job for this annotation

GitHub Actions / Run on Ubuntu 

func (*TensorFusionPodMutator).assignDeviceAllocationIndex is unused (unused)
var index int
var indexErr error
podIdentifier := pod.Name
Expand Down Expand Up @@ -599,7 +598,7 @@
return strconv.Atoi(string(body))
}

func (m *TensorFusionPodMutator) assignIndexFromLeader(ctx context.Context, pod *corev1.Pod) (int, error) {

Check failure on line 601 in internal/webhook/v1/pod_webhook.go

View workflow job for this annotation

GitHub Actions / Run on Ubuntu 

func (*TensorFusionPodMutator).assignIndexFromLeader is unused (unused)
leaderIP := utils.GetLeaderIP(m.Client)
if leaderIP == "" {
return 0, fmt.Errorf("operator leader IP not found")
Expand Down
Loading