Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
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
96 changes: 96 additions & 0 deletions cmd/gpu-operator/cache.go
Original file line number Diff line number Diff line change
@@ -0,0 +1,96 @@
/**
# Copyright (c) NVIDIA CORPORATION. All rights reserved.
#
# 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 main

import (
"fmt"
"maps"

apiimagev1 "github.com/openshift/api/image/v1"
corev1 "k8s.io/api/core/v1"
resourcev1 "k8s.io/api/resource/v1"
apiextensionsv1 "k8s.io/apiextensions-apiserver/pkg/apis/apiextensions/v1"
"k8s.io/apimachinery/pkg/api/meta"
"k8s.io/apimachinery/pkg/fields"
"k8s.io/client-go/rest"
"sigs.k8s.io/controller-runtime/pkg/cache"
"sigs.k8s.io/controller-runtime/pkg/client"
"sigs.k8s.io/controller-runtime/pkg/client/apiutil"

"github.com/NVIDIA/gpu-operator/controllers"
"github.com/NVIDIA/gpu-operator/internal/consts"
)

func newOperatorCache(config *rest.Config, options cache.Options) (cache.Cache, error) {
// ByObject scopes are resolved eagerly, even if no informer is ever used.
// The manager supplies its shared scheme and discovery mapper before calling
// this factory, so optional APIs need not become startup requirements.
options.ByObject = maps.Clone(options.ByObject)
for object := range options.ByObject {
switch object.(type) {
case *apiimagev1.ImageStream, *resourcev1.ResourceClaim:
default:
continue
}
_, err := apiutil.IsObjectNamespaced(object, options.Scheme, options.Mapper)
if meta.IsNoMatchError(err) {
delete(options.ByObject, object)
} else if err != nil {
// An unavailable API server is not evidence that an API is absent.
return nil, fmt.Errorf("discover optional cache API %T: %w", object, err)
}
}
return cache.New(config, options)
}

func operatorCacheOptions(operatorNamespace string) cache.Options {
stripManagedFields := cache.TransformStripManagedFields()
// DRA teardown checks inspect Pods and their ResourceClaims across the existing
// cache namespaces. Preserve that scope independently of operand-only resources.
workloadNamespaces := map[string]cache.Config{
operatorNamespace: {},
consts.OpenshiftNamespace: {},
}
return cache.Options{
DefaultNamespaces: map[string]cache.Config{operatorNamespace: {}},
DefaultTransform: stripManagedFields,
ByObject: map[client.Object]cache.ByObject{
&corev1.Node{}: {
// Keep all nodes for GPU discovery and label cleanup, but omit the
// image inventory, which no operator consumer uses.
Transform: func(in any) (any, error) {
if node, ok := in.(*corev1.Node); ok {
node.Status.Images = nil
}
return stripManagedFields(in)
},
},
&corev1.Pod{}: {Namespaces: workloadNamespaces},
&resourcev1.ResourceClaim{}: {Namespaces: workloadNamespaces},
&apiextensionsv1.CustomResourceDefinition{}: {
// crdExists only checks ServiceMonitor availability. Apply the
// selector to LIST/WATCH so other CRD schemas never enter the cache.
Field: fields.OneTermEqualSelector("metadata.name", controllers.ServiceMonitorCRDName),
},
&apiimagev1.ImageStream{}: {
// Only the Driver Toolkit ImageStream is read from openshift.
Namespaces: map[string]cache.Config{consts.OpenshiftNamespace: {}},
Field: fields.OneTermEqualSelector("metadata.name", "driver-toolkit"),
},
},
}
}
Comment on lines +60 to +96

@coderabbitai coderabbitai Bot Sep 11, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

🩺 Stability & Availability | 🟠 Major | ⚡ Quick win

Cache Pods and ResourceClaims cluster-wide for DRA teardown

operatorCacheOptions caches both types only in the operator and OpenShift namespaces. During the DRA-to-device-plugin transition, nodeHasDRAClaimPods therefore misses claim-bearing Pods in other namespaces, removes gpu.deploy.dra-driver, and can leave those Pods stuck in Terminating when their claims cannot be unprepared. Configure both cache entries for cluster-wide coverage.

@kvalliyurnatt kvalliyurnatt Sep 11, 2026

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I noticed this as well and this seems to be a pre existing bug even before these changes, I am happy to fix it in this PR or carve out a separate PR for that. This will increase our memory footprint though, since we will end up caching all Pods and ResourceClaims in all namespaces. I can look to see there are ways to better than that

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@kvalliyurnatt, please include the cluster-wide Pod and ResourceClaim cache coverage in this PR.

A separate PR is appropriate only for unrelated cleanup or broader pre-existing DRA behavior. This change must prevent nodeHasDRAClaimPods from missing claim-bearing Pods outside the operator and OpenShift namespaces.

You are interacting with an AI system.

Loading
Loading