114 lines
3.3 KiB
YAML
114 lines
3.3 KiB
YAML
apiVersion: apps/v1
|
|
kind: DaemonSet
|
|
metadata:
|
|
annotations:
|
|
deprecated.daemonset.template.generation: "12"
|
|
nvidia.com/last-applied-hash: "973427659"
|
|
openshift.io/scc: nvidia-dcgm-exporter
|
|
labels:
|
|
app: nvidia-dcgm-exporter
|
|
app.kubernetes.io/managed-by: gpu-operator
|
|
helm.sh/chart: gpu-operator-v25.3.1
|
|
name: nvidia-dcgm-exporter-custom
|
|
namespace: dcgm-exporter
|
|
spec:
|
|
revisionHistoryLimit: 10
|
|
selector:
|
|
matchLabels:
|
|
app: nvidia-dcgm-exporter
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app: nvidia-dcgm-exporter
|
|
app.kubernetes.io/managed-by: gpu-operator
|
|
helm.sh/chart: gpu-operator-v25.3.1
|
|
spec:
|
|
containers:
|
|
- env:
|
|
- name: DCGM_EXPORTER_LISTEN
|
|
value: :9400
|
|
- name: DCGM_EXPORTER_KUBERNETES
|
|
value: "true"
|
|
- name: DCGM_EXPORTER_COLLECTORS
|
|
value: /etc/dcgm-exporter/dcgm-metrics.csv
|
|
- name: NODE_NAME
|
|
valueFrom:
|
|
fieldRef:
|
|
apiVersion: v1
|
|
fieldPath: spec.nodeName
|
|
image: nvcr.io/nvidia/k8s/dcgm-exporter:4.1.1-4.0.4-ubuntu22.04
|
|
imagePullPolicy: IfNotPresent
|
|
name: nvidia-dcgm-exporter
|
|
ports:
|
|
- containerPort: 9400
|
|
name: metrics
|
|
protocol: TCP
|
|
resources: {}
|
|
securityContext:
|
|
privileged: true
|
|
terminationMessagePath: /dev/termination-log
|
|
terminationMessagePolicy: File
|
|
volumeMounts:
|
|
- mountPath: /var/lib/kubelet/pod-resources
|
|
name: pod-gpu-resources
|
|
readOnly: true
|
|
- mountPath: /etc/dcgm-exporter/dcgm-metrics.csv
|
|
name: metrics-config
|
|
readOnly: true
|
|
subPath: dcgm-metrics.csv
|
|
dnsPolicy: ClusterFirst
|
|
initContainers:
|
|
- args:
|
|
- until [ -f /run/nvidia/validations/toolkit-ready ]; do echo waiting for
|
|
nvidia container stack to be setup; sleep 5; done
|
|
command:
|
|
- sh
|
|
- -c
|
|
image: nvcr.io/nvidia/cloud-native/gpu-operator-validator:v25.3.1
|
|
imagePullPolicy: IfNotPresent
|
|
name: toolkit-validation
|
|
resources: {}
|
|
securityContext:
|
|
privileged: true
|
|
terminationMessagePath: /dev/termination-log
|
|
terminationMessagePolicy: File
|
|
volumeMounts:
|
|
- mountPath: /run/nvidia
|
|
mountPropagation: HostToContainer
|
|
name: run-nvidia
|
|
nodeSelector:
|
|
nvidia.com/gpu.deploy.dcgm-exporter: "true"
|
|
priorityClassName: system-node-critical
|
|
restartPolicy: Always
|
|
runtimeClassName: nvidia
|
|
schedulerName: default-scheduler
|
|
securityContext: {}
|
|
serviceAccount: nvidia-dcgm-exporter
|
|
serviceAccountName: nvidia-dcgm-exporter
|
|
terminationGracePeriodSeconds: 30
|
|
tolerations:
|
|
- effect: NoSchedule
|
|
key: nvidia.com/gpu
|
|
operator: Exists
|
|
volumes:
|
|
- hostPath:
|
|
path: /mnt/vdb/kubelet/pod-resources
|
|
type: ""
|
|
name: pod-gpu-resources
|
|
- hostPath:
|
|
path: /run/nvidia
|
|
type: ""
|
|
name: run-nvidia
|
|
- configMap:
|
|
defaultMode: 420
|
|
items:
|
|
- key: dcgm-metrics.csv
|
|
path: dcgm-metrics.csv
|
|
name: custom-dcgm-metric
|
|
name: metrics-config
|
|
updateStrategy:
|
|
rollingUpdate:
|
|
maxSurge: 0
|
|
maxUnavailable: 1
|
|
type: RollingUpdate
|