gpudirect-tcpx/nccl-test.yaml

apiVersion: v1
kind: Service
metadata:
  name: nccl-host-1
spec:
  selector:
    name: nccl-host-1
  clusterIP: None
---
apiVersion: v1
kind: Service
metadata:
  name: nccl-host-2
spec:
  selector:
    name: nccl-host-2
  clusterIP: None
---
apiVersion: v1
kind: Pod
metadata:
  name: nccl-test-host-1
  labels:
    name: nccl-host-1
spec:
  hostNetwork: true
  dnsPolicy: ClusterFirstWithHostNet
  containers:
    - name: tcpx-daemon
      image: us-docker.pkg.dev/gce-ai-infra/gpudirect-tcpx/tcpgpudmarxd-dev:v2.0.9
      imagePullPolicy: Always
      command:
        - /tcpgpudmarxd/build/app/tcpgpudmarxd
        - --gpu_nic_preset
        - a3vm
        - --gpu_shmem_type
        - fd
        - --uds_path
        - /run/tcpx
        - --setup_param
        - \"--verbose 128 2 0 \"
      securityContext:
        privileged: true
      volumeMounts:
        - name: libraries
          mountPath: /usr/local/nvidia/lib64
          readOnly: true
        - name: tcpx-socket
          mountPath: /run/tcpx
      env:
        - name: LD_LIBRARY_PATH
          value: /usr/local/nvidia/lib64
    - name: nccl-test
      image: us-docker.pkg.dev/gce-ai-infra/gpudirect-tcpx/nccl-plugin-gpudirecttcpx-dev:v3.1.9
      imagePullPolicy: Always
      command:
        - /bin/sh
        - -c
        - |
          service ssh restart;
          sleep infinity;
      env:
        - name: LD_LIBRARY_PATH
          value: /usr/local/nvidia/lib64
      securityContext:
        capabilities:
          add:
            - IPC_LOCK
      volumeMounts:
        - name: tcpx-socket
          mountPath: /tmp
        - name: config-volume
          mountPath: /configs
      resources:
        limits:
          nvidia.com/gpu: 8
  volumes:
    - name: config-volume
      configMap:
        name: nccl-configmap
        defaultMode: 0777
    - name: libraries
      hostPath:
        path: /home/kubernetes/bin/nvidia/lib64
    - name: tcpx-socket
      emptyDir:

---
apiVersion: v1
kind: Pod
metadata:
  name: nccl-test-host-2
  labels:
    name: nccl-host-2
spec:
  hostNetwork: true
  dnsPolicy: ClusterFirstWithHostNet
  containers:
    - name: tcpx-daemon
      image: us-docker.pkg.dev/gce-ai-infra/gpudirect-tcpx/tcpgpudmarxd-dev:v2.0.9
      imagePullPolicy: Always
      command:
        - /tcpgpudmarxd/build/app/tcpgpudmarxd
        - --gpu_nic_preset
        - a3vm
        - --gpu_shmem_type
        - fd
        - --uds_path
        - /run/tcpx
        - --setup_param
        - \"--verbose 128 2 0 \"
      securityContext:
        privileged: true
      volumeMounts:
        - name: libraries
          mountPath: /usr/local/nvidia/lib64
          readOnly: true
        - name: tcpx-socket
          mountPath: /run/tcpx
      env:
        - name: LD_LIBRARY_PATH
          value: /usr/local/nvidia/lib64
    - name: nccl-test
      image: us-docker.pkg.dev/gce-ai-infra/gpudirect-tcpx/nccl-plugin-gpudirecttcpx-dev:v3.1.9
      imagePullPolicy: Always
      command:
        - /bin/sh
        - -c
        - |
          service ssh restart;
          sleep infinity;
      env:
        - name: LD_LIBRARY_PATH
          value: /usr/local/nvidia/lib64
      securityContext:
        capabilities:
          add:
            - IPC_LOCK
      volumeMounts:
        - name: tcpx-socket
          mountPath: /tmp
        - name: config-volume
          mountPath: /configs
      resources:
        limits:
          nvidia.com/gpu: 8
  volumes:
    - name: config-volume
      configMap:
        name: nccl-configmap
        defaultMode: 0777
    - name: libraries
      hostPath:
        path: /home/kubernetes/bin/nvidia/lib64
    - name: tcpx-socket
      emptyDir: