deploy-IB-on-AKS.sh

git clone https://github.com/surajssd/llm-k8s
cd llm-k8s
git checkout 4b4dd8e8521346aa3473175eb0c45b4c7e6e6883

source .env
export GPU_NODE_COUNT=2
export VM_SIZE="Standard_HB120-16rs_v3"

./scripts/deploy-aks.sh deploy_aks
./scripts/deploy-aks.sh download_aks_credentials
./scripts/deploy-aks.sh add_nodepool
./scripts/deploy-aks.sh install_network_operator

# See how to create a k8s service and expose an app with the new CNI IP

cat <<EOF | kubectl apply -f -
apiVersion: apps/v1
kind: Deployment
metadata:
  name: ibtest
  namespace: default
spec:
  replicas: 2
  selector:
    matchLabels:
      app: ibtest
  template:
    metadata:
      labels:
        app: ibtest
      annotations:
        # This name should match the IPoIBNetwork object we created earlier.
        k8s.v1.cni.cncf.io/networks: aks-infiniband
    spec:
      containers:
      - name: ibtest
        image: ghcr.io/surajssd/doca-ofed:2.10.0
        securityContext:
          capabilities:
            add: [ "IPC_LOCK" ]
          privileged: true
        resources:
          requests:
            rdma/rdma_shared_device_a: 1
          limits:
            rdma/rdma_shared_device_a: 1
        command: ["/bin/bash", "-c"]
        args:
        - sleep inf
        ports:
        - containerPort: 19090
      affinity:
        podAntiAffinity:
          requiredDuringSchedulingIgnoredDuringExecution:
          - labelSelector:
              matchExpressions:
              - key: app
                operator: In
                values:
                - ibtest
            topologyKey: "kubernetes.io/hostname"
        nodeAffinity:
          requiredDuringSchedulingIgnoredDuringExecution:
            nodeSelectorTerms:
            - matchExpressions:
              - key: beta.kubernetes.io/instance-type
                operator: In
                values:
                - Standard_HB120-16rs_v3
                - Standard_HB120rs_v3
                - Standard_ND96asr_v4
EOF

kubectl get pods -A -o json | jq '
  .items[]
  # 1. Only consider Pods whose annotation "k8s.v1.cni.cncf.io/networks" == "ipoibnetwork-test"
  | select(.metadata.annotations["k8s.v1.cni.cncf.io/networks"] == "ipoibnetwork-test")

  # 2. Build a small JSON object where the key is the pod name, and the value is
  #    the IP from the "network-status" JSON for interface "net1".
  | {
      (.metadata.name):
        (
          .metadata.annotations["k8s.v1.cni.cncf.io/network-status"]
          | fromjson                            # parse the JSON string into an array
          | map(select(.interface == "net1"))   # only the interface == "net1"
          | .[]
          | .ips[]
        )
    }
' | jq -s add # ^^ 3. Since this emits multiple one-key objects (one per Pod),  we use jq again to merge them into a single map