mirror of
https://github.com/mulgadc/spinifex.git
synced 2026-10-21 19:56:33 +00:00
Josh Siviour
76 lines
2.5 KiB
YAML
76 lines
2.5 KiB
YAML
# nvidia-device-plugin 0.17.4 — CDI-mode DaemonSet exposing nvidia.com/gpu
|
|
# allocatable on GPU-tainted nodes. Gated to GPU nodes via nodeSelector on the
|
|
# node-label nvidia.com/gpu.present=true (written by mulga-eks-provider-id from
|
|
# the SPINIFEX_GPU_NODE agent.env signal); inert
|
|
# elsewhere. --device-list-strategy=cdi-cri makes the plugin generate a CDI spec
|
|
# for GPU workloads (containerd 2.x resolves the CRI-passed CDI devices; no
|
|
# enable_cdi drop-in needed on k3s v1.32.5). The plugin's OWN container needs
|
|
# NVML + the driver tree to run nvml.Init and generate that spec, so it runs
|
|
# under the k3s-auto-configured "nvidia" runtimeClass with the host root mounted
|
|
# at /driver-root and the host /var/run/cdi mounted writable so the generated
|
|
# spec is visible to containerd. GPU workloads themselves need only
|
|
# resources.limits nvidia.com/gpu — no runtimeClass.
|
|
---
|
|
kind: DaemonSet
|
|
apiVersion: apps/v1
|
|
metadata:
|
|
name: nvidia-device-plugin-daemonset
|
|
namespace: kube-system
|
|
labels:
|
|
app.kubernetes.io/name: nvidia-device-plugin
|
|
spec:
|
|
selector:
|
|
matchLabels:
|
|
name: nvidia-device-plugin-ds
|
|
updateStrategy:
|
|
type: RollingUpdate
|
|
template:
|
|
metadata:
|
|
labels:
|
|
name: nvidia-device-plugin-ds
|
|
spec:
|
|
nodeSelector:
|
|
nvidia.com/gpu.present: "true"
|
|
tolerations:
|
|
- key: nvidia.com/gpu
|
|
operator: Exists
|
|
effect: NoSchedule
|
|
priorityClassName: "system-node-critical"
|
|
runtimeClassName: nvidia
|
|
containers:
|
|
- image: nvcr.io/nvidia/k8s-device-plugin:v0.17.4
|
|
name: nvidia-device-plugin-ctr
|
|
args:
|
|
- --device-list-strategy=cdi-cri
|
|
env:
|
|
- name: FAIL_ON_INIT_ERROR
|
|
value: "false"
|
|
- name: NVIDIA_VISIBLE_DEVICES
|
|
value: all
|
|
- name: NVIDIA_DRIVER_CAPABILITIES
|
|
value: all
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
capabilities:
|
|
drop: ["ALL"]
|
|
volumeMounts:
|
|
- name: kubelet-device-plugins-dir
|
|
mountPath: /var/lib/kubelet/device-plugins
|
|
- name: driver-root
|
|
mountPath: /driver-root
|
|
readOnly: true
|
|
- name: cdi-root
|
|
mountPath: /var/run/cdi
|
|
volumes:
|
|
- name: kubelet-device-plugins-dir
|
|
hostPath:
|
|
path: /var/lib/kubelet/device-plugins
|
|
type: Directory
|
|
- name: driver-root
|
|
hostPath:
|
|
path: /
|
|
- name: cdi-root
|
|
hostPath:
|
|
path: /var/run/cdi
|
|
type: DirectoryOrCreate
|