mrcharles
18c590ba2a
k8s now in the O&M lane (Charles 09-04). Verification: capacity/ allocatable nvidia.com/gpu=1 on wnode-tsys3; CUDA pod scheduled and nvidia-smi clean in-container. Q2 sweep: zero node_exporters on all PVE hosts (Beszel owns host metrics). https://projects.knownelement.com/issues/763
35 lines
1.1 KiB
YAML
35 lines
1.1 KiB
YAML
# nvidia GPU device-plugin DaemonSet — pfv-k8s-wnode-tsys3 (Quadro M2000M 4G)
|
|
# GPU verified end-to-end 2026-09-04 (#763/#769): pod with nvidia.com/gpu:1
|
|
# schedules + nvidia-smi works in-container (driver 550.163.01, CUDA 12.4).
|
|
# Prereq on the node: nvidia driver + nvidia-container-runtime (k3s).
|
|
apiVersion: apps/v1
|
|
kind: DaemonSet
|
|
metadata:
|
|
name: nvidia-device-plugin-daemonset
|
|
namespace: kube-system
|
|
spec:
|
|
selector:
|
|
matchLabels:
|
|
name: nvidia-device-plugin-ds
|
|
template:
|
|
metadata:
|
|
labels:
|
|
name: nvidia-device-plugin-ds
|
|
spec:
|
|
nodeSelector:
|
|
kubernetes.io/hostname: pfv-k8s-wnode-tsys3
|
|
tolerations:
|
|
- key: CriticalAddonsOnly
|
|
operator: Exists
|
|
containers:
|
|
- name: nvidia-device-plugin-ctr
|
|
image: nvcr.io/nvidia/k8s-device-plugin:v0.17.0
|
|
args: ["--fail-on-init-error=false"]
|
|
volumeMounts:
|
|
- name: device-plugin
|
|
mountPath: /var/lib/kubelet/device-plugins
|
|
volumes:
|
|
- name: device-plugin
|
|
hostPath:
|
|
path: /var/lib/kubelet/device-plugins
|