Container Service for Kubernetes:ACK クラスターでの eRDMA を使用したコンテナネットワークの高速化

# Debian または Ubuntu の場合: sources.list の OS 名とバージョンが使用するバージョンと一致していることを確認してください。
wget -qO - https://mirrors.aliyun.com/erdma/GPGKEY | apt-key add - && echo "deb [ arch=amd64 ] https://mirrors.aliyun.com/erdma/apt/{OS|ubuntu} {Version|focal}/erdma main" | tee /etc/apt/sources.list.d/erdma.list && apt update && apt install -y libibverbs1 ibverbs-providers ibverbs-utils librdmacm1

# Alibaba Cloud Linux または RHEL の場合: ご利用の OS に対応するリポジトリディレクトリを見つけて、yum.repos.d ディレクトリに構成してください。
cat > /etc/yum.repos.d/erdma.repo <<EOF
[erdma]
name = ERDMA Repository
baseurl = http://mirrors.aliyun.com/erdma/yum/redhat/7/erdma/x86_64/
gpgcheck = 0
enabled = 1
EOF
yum install --disablerepo=*  --enablerepo erdma -y libibverbs ibverbs-providers ibverbs-utils librdmacm

apiVersion: apps/v1
kind: StatefulSet
metadata:
  name: nccltest
spec:
  selector:
    matchLabels:
      app: nccltest
  serviceName: "nccltest"
  replicas: 2
  template:
    metadata:
      labels:
        app: nccltest
    spec:
      hostNetwork: true 
      dnsPolicy: ClusterFirstWithHostNet
      containers:
      - env:
        - name: NCCL_SOCKET_IFNAME
          value: "eth0"
        - name: NCCL_DEBUG
          value: "INFO"
        - name: NCCL_IB_GID_INDEX
          value: "1"
        image: <nccl-test-image-with-erdma>
        imagePullPolicy: Always
        name: nccltest
        securityContext:
          privileged: true
        resources:
          limits:
            nvidia.com/gpu: "8"
            aliyun/erdma: "1"
          requests:
            nvidia.com/gpu: "8"
            aliyun/erdma: "1"

apiVersion: apps/v1
kind: Deployment
metadata:
  labels:
    app: app-with-erdma
  name: app-with-erdma
spec:
  replicas: 2
  selector:
    matchLabels:
      app: app-with-erdma
  template:
    metadata:
      labels:
        app: app-with-erdma
      annotations:
        network.alibabacloud.com/erdma-smcr: "true"
    spec:
      containers:
      - image: <application image>
        imagePullPolicy: Always
        name: app-with-erdma
        resources:
          limits:
            aliyun/erdma: 1