KubeZero/charts/kubezero-addons/templates/device-plugins/aws-neuron-ds.yaml

70 lines
2.1 KiB
YAML
Raw Normal View History

{{- if .Values.awsNeuron.enabled }}
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: neuron-device-plugin
namespace: kube-system
spec:
selector:
matchLabels:
name: neuron-device-plugin-ds
updateStrategy:
type: RollingUpdate
template:
metadata:
labels:
name: neuron-device-plugin-ds
spec:
serviceAccount: neuron-device-plugin
tolerations:
- key: CriticalAddonsOnly
operator: Exists
- key: aws.amazon.com/neuron
operator: Exists
effect: NoSchedule
# Mark this pod as a critical add-on; when enabled, the critical add-on
# scheduler reserves resources for critical add-on pods so that they can
# be rescheduled after a failure.
# See https://kubernetes.io/docs/tasks/administer-cluster/guaranteed-scheduling-critical-addon-pods/
priorityClassName: "system-node-critical"
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
nodeSelectorTerms:
- matchExpressions:
- key: "node.kubernetes.io/instance-type"
operator: In
values:
- inf1.xlarge
- inf1.2xlarge
- inf1.6xlarge
- inf1.24xlarge
containers:
- image: "{{ .Values.awsNeuron.image.name }}:{{ .Values.awsNeuron.image.tag }}"
imagePullPolicy: IfNotPresent
name: neuron-device-plugin
env:
- name: KUBECONFIG
value: /etc/kubernetes/kubelet.conf
- name: NODE_NAME
valueFrom:
fieldRef:
fieldPath: spec.nodeName
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop: ["ALL"]
volumeMounts:
- name: device-plugin
mountPath: /var/lib/kubelet/device-plugins
- name: infa-map
mountPath: /run
volumes:
- name: device-plugin
hostPath:
path: /var/lib/kubelet/device-plugins
- name: infa-map
hostPath:
path: /run
{{- end }}