Skip to content

mofed‐ubuntu22.04‐f5c9c944d‐ds‐wlnhj.yaml

Anson Qian edited this page Aug 12, 2025 · 2 revisions
apiVersion: v1
kind: Pod
metadata:
  creationTimestamp: "2025-08-12T20:39:30Z"
  generateName: mofed-ubuntu22.04-f5c9c944d-ds-
  labels:
    app: mofed-ubuntu22.04-f5c9c944d
    controller-revision-hash: 777957b7c7
    kernel: 5.15.0-1091-azure
    nvidia.com/ofed-driver: ""
    pod-template-generation: "1"
  name: mofed-ubuntu22.04-f5c9c944d-ds-wlnhj
  namespace: network-operator
  ownerReferences:
  - apiVersion: apps/v1
    blockOwnerDeletion: true
    controller: true
    kind: DaemonSet
    name: mofed-ubuntu22.04-f5c9c944d-ds
    uid: c173aec5-75ef-4662-bb96-0953085037c3
  resourceVersion: "404484"
  uid: fb1d762f-a71a-45d5-99c6-e615bfd3d698
spec:
  affinity:
    nodeAffinity:
      requiredDuringSchedulingIgnoredDuringExecution:
        nodeSelectorTerms:
        - matchFields:
          - key: metadata.name
            operator: In
            values:
            - aks-user-12248297-vmss000000
    podAntiAffinity:
      requiredDuringSchedulingIgnoredDuringExecution:
      - labelSelector:
          matchExpressions:
          - key: nvidia.com/ofed-driver
            operator: Exists
        topologyKey: kubernetes.io/hostname
  containers:
  - env:
    - name: CREATE_IFNAMES_UDEV
      value: "true"
    - name: NVIDIA_NIC_DRIVERS_INVENTORY_PATH
      value: /mnt/drivers-inventory
    image: nvcr.io/nvidia/mellanox/doca-driver:25.04-0.6.1.0-2-ubuntu22.04-amd64
    imagePullPolicy: IfNotPresent
    livenessProbe:
      exec:
        command:
        - sh
        - -c
        - lsmod | grep mlx5_core
      failureThreshold: 1
      initialDelaySeconds: 30
      periodSeconds: 30
      successThreshold: 1
      timeoutSeconds: 10
    name: mofed-container
    readinessProbe:
      exec:
        command:
        - sh
        - -c
        - lsmod | grep mlx5_core
      failureThreshold: 1
      initialDelaySeconds: 10
      periodSeconds: 30
      successThreshold: 1
      timeoutSeconds: 10
    resources: {}
    securityContext:
      privileged: true
      seLinuxOptions:
        level: s0
    startupProbe:
      exec:
        command:
        - sh
        - -c
        - ls /run/mellanox/drivers/.driver-ready
      failureThreshold: 60
      initialDelaySeconds: 10
      periodSeconds: 20
      successThreshold: 1
      timeoutSeconds: 10
    terminationMessagePath: /dev/termination-log
    terminationMessagePolicy: File
    volumeMounts:
    - mountPath: /run/mellanox/drivers
      mountPropagation: Bidirectional
      name: run-mlnx-ofed
    - mountPath: /etc/network
      name: etc-network
    - mountPath: /host/etc
      name: host-etc
    - mountPath: /host/usr
      name: host-usr
    - mountPath: /host/lib/udev
      name: host-udev
    - mountPath: /run/udev
      name: host-run-udev
      readOnly: true
    - mountPath: /host/lib/modules
      name: host-lib-modules
    - mountPath: /mnt/drivers-inventory
      name: drivers-inventory
    - mountPath: /etc/modprobe.d/ib_core.conf
      name: host-ib-core
    - mountPath: /var/run/secrets/kubernetes.io/serviceaccount
      name: kube-api-access-cpn7p
      readOnly: true
  dnsPolicy: ClusterFirst
  enableServiceLinks: true
  hostNetwork: true
  initContainers:
  - args:
    - --node-name
    - $(NODE_NAME)
    - --configmap-name
    - ofed-init-container-config
    - --configmap-namespace
    - network-operator
    - --configmap-key
    - config.json
    env:
    - name: NODE_NAME
      valueFrom:
        fieldRef:
          apiVersion: v1
          fieldPath: spec.nodeName
    image: ghcr.io/mellanox/network-operator-init-container:v0.0.3
    imagePullPolicy: IfNotPresent
    name: network-operator-init-container
    resources: {}
    terminationMessagePath: /dev/termination-log
    terminationMessagePolicy: File
    volumeMounts:
    - mountPath: /var/run/secrets/kubernetes.io/serviceaccount
      name: kube-api-access-cpn7p
      readOnly: true
  nodeName: aks-user-12248297-vmss000000
  nodeSelector:
    feature.node.kubernetes.io/kernel-version.full: 5.15.0-1091-azure
    feature.node.kubernetes.io/pci-15b3.present: "true"
    feature.node.kubernetes.io/system-os_release.ID: ubuntu
    feature.node.kubernetes.io/system-os_release.VERSION_ID: "22.04"
  preemptionPolicy: PreemptLowerPriority
  priority: 2000001000
  priorityClassName: system-node-critical
  restartPolicy: Always
  schedulerName: default-scheduler
  securityContext: {}
  serviceAccount: ofed-driver
  serviceAccountName: ofed-driver
  terminationGracePeriodSeconds: 300
  tolerations:
  - effect: NoSchedule
    key: nvidia.com/gpu
    operator: Exists
  - effect: NoExecute
    key: node.kubernetes.io/not-ready
    operator: Exists
  - effect: NoExecute
    key: node.kubernetes.io/unreachable
    operator: Exists
  - effect: NoSchedule
    key: node.kubernetes.io/disk-pressure
    operator: Exists
  - effect: NoSchedule
    key: node.kubernetes.io/memory-pressure
    operator: Exists
  - effect: NoSchedule
    key: node.kubernetes.io/pid-pressure
    operator: Exists
  - effect: NoSchedule
    key: node.kubernetes.io/unschedulable
    operator: Exists
  - effect: NoSchedule
    key: node.kubernetes.io/network-unavailable
    operator: Exists
  volumes:
  - hostPath:
      path: /run/mellanox/drivers
      type: ""
    name: run-mlnx-ofed
  - hostPath:
      path: /etc/network
      type: ""
    name: etc-network
  - hostPath:
      path: /etc
      type: ""
    name: host-etc
  - hostPath:
      path: /usr
      type: ""
    name: host-usr
  - hostPath:
      path: /lib/udev
      type: ""
    name: host-udev
  - hostPath:
      path: /run/udev
      type: ""
    name: host-run-udev
  - hostPath:
      path: /lib/modules
      type: ""
    name: host-lib-modules
  - hostPath:
      path: /var/opt/mofed-container/inventory
      type: DirectoryOrCreate
    name: drivers-inventory
  - hostPath:
      path: /etc/modprobe.d/ib_core.conf
      type: FileOrCreate
    name: host-ib-core
  - name: kube-api-access-cpn7p
    projected:
      defaultMode: 420
      sources:
      - serviceAccountToken:
          expirationSeconds: 3607
          path: token
      - configMap:
          items:
          - key: ca.crt
            path: ca.crt
          name: kube-root-ca.crt
      - downwardAPI:
          items:
          - fieldRef:
              apiVersion: v1
              fieldPath: metadata.namespace
            path: namespace
status:
  conditions:
  - lastProbeTime: null
    lastTransitionTime: "2025-08-12T20:39:32Z"
    status: "True"
    type: PodReadyToStartContainers
  - lastProbeTime: null
    lastTransitionTime: "2025-08-12T20:39:32Z"
    status: "True"
    type: Initialized
  - lastProbeTime: null
    lastTransitionTime: "2025-08-12T20:44:30Z"
    status: "True"
    type: Ready
  - lastProbeTime: null
    lastTransitionTime: "2025-08-12T20:44:30Z"
    status: "True"
    type: ContainersReady
  - lastProbeTime: null
    lastTransitionTime: "2025-08-12T20:39:30Z"
    status: "True"
    type: PodScheduled
  containerStatuses:
  - containerID: containerd://7ecc86c10e21683703e7a79e27b349ef7f68bc071de610b4f230f59fe8abaf86
    image: nvcr.io/nvidia/mellanox/doca-driver:25.04-0.6.1.0-2-ubuntu22.04-amd64
    imageID: nvcr.io/nvidia/mellanox/doca-driver@sha256:cb436254179a539a33c31b97c3eb84f78011e5eba3b7a49780245fed233076cf
    lastState: {}
    name: mofed-container
    ready: true
    restartCount: 0
    started: true
    state:
      running:
        startedAt: "2025-08-12T20:39:45Z"
    volumeMounts:
    - mountPath: /run/mellanox/drivers
      name: run-mlnx-ofed
    - mountPath: /etc/network
      name: etc-network
    - mountPath: /host/etc
      name: host-etc
    - mountPath: /host/usr
      name: host-usr
    - mountPath: /host/lib/udev
      name: host-udev
    - mountPath: /run/udev
      name: host-run-udev
      readOnly: true
      recursiveReadOnly: Disabled
    - mountPath: /host/lib/modules
      name: host-lib-modules
    - mountPath: /mnt/drivers-inventory
      name: drivers-inventory
    - mountPath: /etc/modprobe.d/ib_core.conf
      name: host-ib-core
    - mountPath: /var/run/secrets/kubernetes.io/serviceaccount
      name: kube-api-access-cpn7p
      readOnly: true
      recursiveReadOnly: Disabled
  hostIP: 10.224.0.6
  hostIPs:
  - ip: 10.224.0.6
  initContainerStatuses:
  - containerID: containerd://255a4b17b361f82844a6a205a2d3ebbd2d412b20936901f50124bc068b49c78d
    image: ghcr.io/mellanox/network-operator-init-container:v0.0.3
    imageID: ghcr.io/mellanox/network-operator-init-container@sha256:67e93ccf3ecb61f17597567faf0f72e1b8ddcf73c5d7440baeadcc1cb6bb811b
    lastState: {}
    name: network-operator-init-container
    ready: true
    restartCount: 0
    started: false
    state:
      terminated:
        containerID: containerd://255a4b17b361f82844a6a205a2d3ebbd2d412b20936901f50124bc068b49c78d
        exitCode: 0
        finishedAt: "2025-08-12T20:39:31Z"
        reason: Completed
        startedAt: "2025-08-12T20:39:31Z"
    volumeMounts:
    - mountPath: /var/run/secrets/kubernetes.io/serviceaccount
      name: kube-api-access-cpn7p
      readOnly: true
      recursiveReadOnly: Disabled
  phase: Running
  podIP: 10.224.0.6
  podIPs:
  - ip: 10.224.0.6
  qosClass: BestEffort
  startTime: "2025-08-12T20:39:30Z"

Clone this wiki locally