actions: "enqueue, allocate, backfill"
tiers:
- plugins:
- name: priority
- name: gang
- name: conformance
- name: usage  # usage based scheduling plugin
arguments:
thresholds:
CPUUsageAvg.5m: 90 # The node whose average usage in 5 minute is higher than 90% will be filtered in predicating stage
MEMUsageAvg.5m: 80 # The node whose average usage in 5 minute is higher than 80% will be filtered in predicating stage
- plugins:
- name: overcommit
- name: drf
- name: predicates
- name: proportion
- name: nodeorder
- name: binpack
metrics:                    # metrics server related configuration
address: http://192.168.0.10:9090 # mandatory, The Prometheus server address
interval: 30s                    # Optional, The scheduler pull metrics from Prometheus with this interval, 5s by default

## Configuration Option actions: "enqueue, allocate, backfill, shuffle"  ## add 'shuffle' at the end of the actionstiers:
  - plugins:
      - name: priority
      - name: gang
      - name: conformance
      - name: rescheduling       ## rescheduling plugin
        arguments:
          interval: 5m           ## optional, the strategies will be called in this duration periodcally. 5 minuters by default.
          strategies:            ## required, strategies working in order
            - name: offlineOnly
            - name: lowPriorityFirst
            - name: lowNodeUtilization
              params:
                thresholds:
                  "cpu" : 20
                  "memory": 20
                  "pods": 20
                targetThresholds:
                  "cpu" : 50
                  "memory": 50
                  "pods": 50
          queueSelector:         ## optional, select workloads in specified queues as potential evictees. All queues by default.
            - default
            - test-queue
          labelSelector:         ## optional, select workloads with specified labels as potential evictees. All labels by default.
            business: offline
            team: test
  - plugins:
      - name: overcommit
      - name: drf
      - name: predicates
      - name: proportion
      - name: nodeorder
      - name: binpack

apiVersion: batch.volcano.sh/v1alpha1
kind: Job
metadata:
 name: lm-mpi-job
spec:
 minAvailable: 1
 schedulerName: volcano
 plugins:
   mpi: ["--master=mpimaster","--worker=mpiworker","--port=22"]  ## MPI plugin register
 tasks:
   - replicas: 1
     name: mpimaster
     policies:
       - event: TaskCompleted
         action: CompleteJob
     template:
       spec:
         containers:
           - command:
               - /bin/sh
               - -c
               - |
                 mkdir -p /var/run/sshd; /usr/sbin/sshd;
                 mpiexec --allow-run-as-root --host ${MPI_HOST} -np 2 mpi_hello_world;
             image: volcanosh/example-mpi:0.0.1
             name: mpimaster
             workingDir: /home
         restartPolicy: OnFailure
   - replicas: 2
     name: mpiworker
     template:
       spec:
         containers:
           - command:
               - /bin/sh
               - -c
               - |
                 mkdir -p /var/run/sshd; /usr/sbin/sshd -D;
             image: volcanosh/example-mpi:0.0.1
             name: mpiworker
             workingDir: /home
            
         restartPolicy: OnFailure