example/MindSpore-example/mindspore_gpu/mindspore-gpu.yaml

apiVersion: batch.volcano.sh/v1alpha1
kind: Job
metadata:
  name: mindspore-gpu
spec:
  minAvailable: 3
  schedulerName: volcano
  plugins:
    ssh: []
    svc: []
  tasks:
    - replicas: 1
      name: mpimaster
      template:
        spec:
          containers:
            - command:
                - /bin/bash
                - -c
                - |
                  mkdir -p /var/run/sshd; /usr/sbin/sshd;
                  MPI_HOST=`cat /etc/volcano/mpiworker.host | tr "\n" ","`;
                  sleep 10;
                  mpiexec --allow-run-as-root --host ${MPI_HOST} -np 2 --prefix /usr/local/openmpi-3.1.5 python /tmp/gpu-test.py;
                  sleep 3600;
              image: lyd911/mindspore-gpu-example:0.2.0
              name: mpimaster
              ports:
                - containerPort: 22
                  name: mpijob-port
              workingDir: /home
          restartPolicy: OnFailure
    - replicas: 2
      name: mpiworker
      template:
        spec:
          containers:
            - command:
                - /bin/bash
                - -c
                - |
                  mkdir -p /var/run/sshd; /usr/sbin/sshd -D; 
              image: lyd911/mindspore-gpu-example:0.2.0
              name: mpiworker
              resources:
                limits:
                  nvidia.com/gpu: "1"
              ports:
                - containerPort: 22
                  name: mpijob-port
              workingDir: /home
          restartPolicy: OnFailure
 
---