k8s使用gpu

一、安装gpu容器运行时

官网地址:Installing the NVIDIA Container Toolkit — NVIDIA Container Toolkit

Ubuntu, Debian

curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg \
  && curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list | \
    sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | \
    sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list
sed -i -e '/experimental/ s/^#//g' /etc/apt/sources.list.d/nvidia-container-toolkit.list
sudo apt-get update
export NVIDIA_CONTAINER_TOOLKIT_VERSION=1.17.8-1
  sudo apt-get install -y \
      nvidia-container-toolkit=${NVIDIA_CONTAINER_TOOLKIT_VERSION} \
      nvidia-container-toolkit-base=${NVIDIA_CONTAINER_TOOLKIT_VERSION} \
      libnvidia-container-tools=${NVIDIA_CONTAINER_TOOLKIT_VERSION} \
      libnvidia-container1=${NVIDIA_CONTAINER_TOOLKIT_VERSION}

RHEL/CentOS, Fedora, Amazon Linux

curl -s -L https://nvidia.github.io/libnvidia-container/stable/rpm/nvidia-container-toolkit.repo | \
  sudo tee /etc/yum.repos.d/nvidia-container-toolkit.repo
sudo dnf-config-manager --enable nvidia-container-toolkit-experimental
export NVIDIA_CONTAINER_TOOLKIT_VERSION=1.17.8-1
  sudo dnf install -y \
      nvidia-container-toolkit-${NVIDIA_CONTAINER_TOOLKIT_VERSION} \
      nvidia-container-toolkit-base-${NVIDIA_CONTAINER_TOOLKIT_VERSION} \
      libnvidia-container-tools-${NVIDIA_CONTAINER_TOOLKIT_VERSION} \
      libnvidia-container1-${NVIDIA_CONTAINER_TOOLKIT_VERSION}

二、安装nvidia-device-plugin插件

官网地址:raw.githubusercontent.com/NVIDIA/k8s-device-plugin/v0.17.1/deployments/static/nvidia-device-plugin.yml

kubectl apply -f nvidia-device-plugin.yml

三、修改containerd配置文件使用gpu容器运行时,

完整config.toml

disabled_plugins = []
imports = []
oom_score = 0
plugin_dir = ""
required_plugins = []
root = "/var/lib/containerd"
state = "/run/containerd"
temp = ""
version = 2

[cgroup]
  path = ""

[debug]
  address = ""
  format = ""
  gid = 0
  level = ""
  uid = 0

[grpc]
  address = "/run/containerd/containerd.sock"
  gid = 0
  max_recv_message_size = 16777216
  max_send_message_size = 16777216
  tcp_address = ""
  tcp_tls_ca = ""
  tcp_tls_cert = ""
  tcp_tls_key = ""
  uid = 0

[metrics]
  address = ""
  grpc_histogram = false

[plugins]

  [plugins."io.containerd.gc.v1.scheduler"]
    deletion_threshold = 0
    mutation_threshold = 100
    pause_threshold = 0.02
    schedule_delay = "0s"
    startup_delay = "100ms"

  [plugins."io.containerd.grpc.v1.cri"]
    cdi_spec_dirs = ["/etc/cdi", "/var/run/cdi"]
    device_ownership_from_security_context = false
    disable_apparmor = false
    disable_cgroup = false
    disable_hugetlb_controller = true
    disable_proc_mount = false
    disable_tcp_service = true
    drain_exec_sync_io_timeout = "0s"
    enable_cdi = false
    enable_selinux = false
    enable_tls_streaming = false
    enable_unprivileged_icmp = false
    enable_unprivileged_ports = false
    ignore_deprecation_warnings = []
    ignore_image_defined_volumes = false
    image_pull_progress_timeout = "5m0s"
    image_pull_with_sync_fs = false
    max_concurrent_downloads = 3
    max_container_log_line_size = 16384
    netns_mounts_under_state_dir = false
    restrict_oom_score_adj = false
    sandbox_image = "registry.cn-hangzhou.aliyuncs.com/google_containers/pause:3.8"
    selinux_category_range = 1024
    stats_collect_period = 10
    stream_idle_timeout = "4h0m0s"
    stream_server_address = "127.0.0.1"
    stream_server_port = "0"
    systemd_cgroup = false
    tolerate_missing_hugetlb_controller = true
    unset_seccomp_profile = ""

    [plugins."io.containerd.grpc.v1.cri".cni]
      bin_dir = "/opt/cni/bin"
      conf_dir = "/etc/cni/net.d"
      conf_template = ""
      ip_pref = ""
      max_conf_num = 1
      setup_serially = false

    [plugins."io.containerd.grpc.v1.cri".containerd]
      default_runtime_name = "nvidia"
      disable_snapshot_annotations = true
      discard_unpacked_layers = false
      ignore_blockio_not_enabled_errors = false
      ignore_rdt_not_enabled_errors = false
      no_pivot = false
      snapshotter = "overlayfs"

      [plugins."io.containerd.grpc.v1.cri".containerd.default_runtime]
        base_runtime_spec = ""
        cni_conf_dir = ""
        cni_max_conf_num = 0
        container_annotations = []
        pod_annotations = []
        privileged_without_host_devices = false
        privileged_without_host_devices_all_devices_allowed = false
        runtime_engine = ""
        runtime_path = ""
        runtime_root = ""
        runtime_type = ""
        sandbox_mode = ""
        snapshotter = ""

        [plugins."io.containerd.grpc.v1.cri".containerd.default_runtime.options]

      [plugins."io.containerd.grpc.v1.cri".containerd.runtimes]

        [plugins."io.containerd.grpc.v1.cri".containerd.runtimes.nvidia]
          base_runtime_spec = ""
          cni_conf_dir = ""
          cni_max_conf_num = 0
          container_annotations = []
          pod_annotations = []
          privileged_without_host_devices = false
          privileged_without_host_devices_all_devices_allowed = false
          runtime_engine = ""
          runtime_path = ""
          runtime_root = ""
          runtime_type = "io.containerd.runc.v2"
          sandbox_mode = "podsandbox"
          snapshotter = ""

          [plugins."io.containerd.grpc.v1.cri".containerd.runtimes.nvidia.options]
            BinaryName = "/usr/bin/nvidia-container-runtime"
            CriuImagePath = ""
            CriuPath = ""
            CriuWorkPath = ""
            IoGid = 0
            IoUid = 0
            NoNewKeyring = false
            NoPivotRoot = false
            Root = ""
            ShimCgroup = ""
            SystemdCgroup = true

        [plugins."io.containerd.grpc.v1.cri".containerd.runtimes.runc]
          base_runtime_spec = ""
          cni_conf_dir = ""
          cni_max_conf_num = 0
          container_annotations = []
          pod_annotations = []
          privileged_without_host_devices = false
          privileged_without_host_devices_all_devices_allowed = false
          runtime_engine = ""
          runtime_path = ""
          runtime_root = ""
          runtime_type = "io.containerd.runc.v2"
          sandbox_mode = "podsandbox"
          snapshotter = ""

          [plugins."io.containerd.grpc.v1.cri".containerd.runtimes.runc.options]
            BinaryName = ""
            CriuImagePath = ""
            CriuPath = ""
            CriuWorkPath = ""
            IoGid = 0
            IoUid = 0
            NoNewKeyring = false
            NoPivotRoot = false
            Root = ""
            ShimCgroup = ""
            SystemdCgroup = true

      [plugins."io.containerd.grpc.v1.cri".containerd.untrusted_workload_runtime]
        base_runtime_spec = ""
        cni_conf_dir = ""
        cni_max_conf_num = 0
        container_annotations = []
        pod_annotations = []
        privileged_without_host_devices = false
        privileged_without_host_devices_all_devices_allowed = false
        runtime_engine = ""
        runtime_path = ""
        runtime_root = ""
        runtime_type = ""
        sandbox_mode = ""
        snapshotter = ""

        [plugins."io.containerd.grpc.v1.cri".containerd.untrusted_workload_runtime.options]

    [plugins."io.containerd.grpc.v1.cri".image_decryption]
      key_model = "node"

    [plugins."io.containerd.grpc.v1.cri".registry]
      config_path = "/etc/containerd/certs.d"

      [plugins."io.containerd.grpc.v1.cri".registry.auths]

      [plugins."io.containerd.grpc.v1.cri".registry.configs]

      [plugins."io.containerd.grpc.v1.cri".registry.headers]

      [plugins."io.containerd.grpc.v1.cri".registry.mirrors]

    [plugins."io.containerd.grpc.v1.cri".x509_key_pair_streaming]
      tls_cert_file = ""
      tls_key_file = ""

  [plugins."io.containerd.internal.v1.opt"]
    path = "/opt/containerd"

  [plugins."io.containerd.internal.v1.restart"]
    interval = "10s"

  [plugins."io.containerd.internal.v1.tracing"]

  [plugins."io.containerd.metadata.v1.bolt"]
    content_sharing_policy = "shared"

  [plugins."io.containerd.monitor.v1.cgroups"]
    no_prometheus = false

  [plugins."io.containerd.nri.v1.nri"]
    disable = true
    disable_connections = false
    plugin_config_path = "/etc/containerd/certs.d"
    plugin_path = "/opt/nri/plugins"
    plugin_registration_timeout = "5s"
    plugin_request_timeout = "2s"
    socket_path = "/var/run/nri/nri.sock"

  [plugins."io.containerd.runtime.v1.linux"]
    no_shim = false
    runtime = "runc"
    runtime_root = ""
    shim = "containerd-shim"
    shim_debug = false

  [plugins."io.containerd.runtime.v2.task"]
    platforms = ["linux/amd64"]
    sched_core = false

  [plugins."io.containerd.service.v1.diff-service"]
    default = ["walking"]
    sync_fs = false

  [plugins."io.containerd.service.v1.tasks-service"]
    blockio_config_file = ""
    rdt_config_file = ""

  [plugins."io.containerd.snapshotter.v1.aufs"]
    root_path = ""

  [plugins."io.containerd.snapshotter.v1.blockfile"]
    fs_type = ""
    mount_options = []
    root_path = ""
    scratch_file = ""

  [plugins."io.containerd.snapshotter.v1.devmapper"]
    async_remove = false
    base_image_size = ""
    discard_blocks = false
    fs_options = ""
    fs_type = ""
    pool_name = ""
    root_path = ""

  [plugins."io.containerd.snapshotter.v1.native"]
    root_path = ""

  [plugins."io.containerd.snapshotter.v1.overlayfs"]
    mount_options = []
    root_path = ""
    sync_remove = false
    upperdir_label = false

  [plugins."io.containerd.snapshotter.v1.zfs"]
    root_path = ""

  [plugins."io.containerd.tracing.processor.v1.otlp"]

  [plugins."io.containerd.transfer.v1.local"]
    config_path = "/etc/containerd/certs.d"
    max_concurrent_downloads = 3
    max_concurrent_uploaded_layers = 3

    [[plugins."io.containerd.transfer.v1.local".unpack_config]]
      differ = ""
      platform = "linux/amd64"
      snapshotter = "overlayfs"

[proxy_plugins]

[stream_processors]

  [stream_processors."io.containerd.ocicrypt.decoder.v1.tar"]
    accepts = ["application/vnd.oci.image.layer.v1.tar+encrypted"]
    args = ["--decryption-keys-path", "/etc/containerd/ocicrypt/keys"]
    env = ["OCICRYPT_KEYPROVIDER_CONFIG=/etc/containerd/ocicrypt/ocicrypt_keyprovider.conf"]
    path = "ctd-decoder"
    returns = "application/vnd.oci.image.layer.v1.tar"

  [stream_processors."io.containerd.ocicrypt.decoder.v1.tar.gzip"]
    accepts = ["application/vnd.oci.image.layer.v1.tar+gzip+encrypted"]
    args = ["--decryption-keys-path", "/etc/containerd/ocicrypt/keys"]
    env = ["OCICRYPT_KEYPROVIDER_CONFIG=/etc/containerd/ocicrypt/ocicrypt_keyprovider.conf"]
    path = "ctd-decoder"
    returns = "application/vnd.oci.image.layer.v1.tar+gzip"

[timeouts]
  "io.containerd.timeout.bolt.open" = "0s"
  "io.containerd.timeout.metrics.shimstats" = "2s"
  "io.containerd.timeout.shim.cleanup" = "5s"
  "io.containerd.timeout.shim.load" = "5s"
  "io.containerd.timeout.shim.shutdown" = "3s"
  "io.containerd.timeout.task.state" = "2s"

[ttrpc]
  address = ""
  gid = 0
  uid = 0
#重点修改
[plugins."io.containerd.grpc.v1.cri".containerd.runtimes.nvidia]
  runtime_type = "io.containerd.runc.v2"
  privileged_without_host_devices = false
  [plugins."io.containerd.grpc.v1.cri".containerd.runtimes.nvidia.options]
    BinaryName = "/usr/bin/nvidia-container-runtime"


[plugins."io.containerd.grpc.v1.cri".containerd]
  default_runtime_name = "nvidia"
四、验证
kubectl -n kube-system get pods -o wide | grep nvidia
kubectl -n kube-system logs <nvidia-device-plugin-pod-name>
kubectl describe node k8s-master | grep -A10 Allocatable
Allocatable:
  cpu:                24
  ephemeral-storage:  67585336823
  hugepages-1Gi:      0
  hugepages-2Mi:      0
  memory:             65501672Ki
  nvidia.com/gpu:     1                  #gpu资源
  pods:               110
System Info:
  Machine ID:                 cd77e17dd95449379844098d8e0f43c1
  System UUID:                03000200-0400-0500-0006-000700080009

五、测试

部署一个简易测试含gpu的pod

apiVersion: v1
kind: Pod
metadata:
  name: gpu-test-pod
spec:
  containers:
  - name: cuda-container
    image: registry.cn-shanghai.aliyuncs.com/sucloud/nvidia:11.3.1-cudnn8-devel-ubuntu20.0.4
    command: ["/bin/sh", "-c", "nvidia-smi && sleep 3600"]
    resources:
      limits:
        nvidia.com/gpu: 1
  restartPolicy: Never
kubectl apply -f gpu-test.yaml
#kubectl get pods
NAME           READY   STATUS    RESTARTS   AGE
gpu-test-pod   1/1     Running   0          12s
#kubectl exec -it gpu-test-pod sh
kubectl exec [POD] [COMMAND] is DEPRECATED and will be removed in a future version. Use kubectl exec [POD] -- [COMMAND] instead.
# nvidia-smi
Wed Aug  6 02:53:28 2025       
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 570.172.08             Driver Version: 570.172.08     CUDA Version: 12.8     |
|-----------------------------------------+------------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |
|                                         |                        |               MIG M. |
|=========================================+========================+======================|
|   0  NVIDIA GeForce RTX 3080        Off |   00000000:01:00.0 Off |                  N/A |
| 30%   31C    P8             24W /  320W |     257MiB /  10240MiB |      0%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+
                                                                                         
+-----------------------------------------------------------------------------------------+
| Processes:                                                                              |
|  GPU   GI   CI              PID   Type   Process name                        GPU Memory |
|        ID   ID                                                               Usage      |
|=========================================================================================|
+-----------------------------------------------------------------------------------------+
Logo

分享最新的 NVIDIA AI Software 资源以及活动/会议信息,精选收录AI相关技术内容,欢迎大家加入社区并参与讨论。

更多推荐