NFD worker POD CrashLoopBackoff on GPU node with SELinux enabled.

[RangaSamudrala]

NFD worker POD logs show log entry below:

failed to get self pod, cannot inherit ownerReference for NodeFeature. Get https://10.43.0.1:443/api/v1/namespaces/gpu-operator/pods/gpu-operator-node-feature-discovery-worker-xxxx. dial tcp 10.43.0.1:443 I/O timeout

The machine in which GPU operator is configured is an RHEL v9.5 with SELinux enabled but configured to be ```permissive``

• NFD version: v0.16.6
• GPU Operator Version: v25.3.0
• OS: RHEL 9.5
• Kernel Version: 5.14.0-503.35.1.el9_5.x86_64
• Container Runtime Version: v1.7.23-k3s2
• Kubernetes Distro and Version: Rancher v1.31.4 RKE2

[marquiz]

Looks like a problem in the cluster, not able to connect the kube apiserver

/cc @ArangoGutierrez