# jetson nano install k3s、檢測GPU

## 1. 系統參數、RAM調整

nvidia@tegra-ubuntu:~$ git clone https://github.com/JetsonHacksNano/resizeSwapMemory

nvidia@tegra-ubuntu:~$ cd resizeSwapMemory/

nvidia@tegra-ubuntu:~/resizeSwapMemory$ sudo ./setSwapMemorySize.sh -g 8
Please reboot for changes to take effect.

nvidia@tegra-ubuntu:~/resizeSwapMemory$ cd 
nvidia@tegra-ubuntu:~$

nvidia@tegra-ubuntu:~$ sudo sysctl -w net.ipv6.conf.all.disable_ipv6=1
net.ipv6.conf.all.disable_ipv6 = 1

nvidia@tegra-ubuntu:~$ sudo sysctl -w net.ipv6.conf.default.disable_ipv6=1
net.ipv6.conf.default.disable_ipv6 = 1

nvidia@tegra-ubuntu:~$ sudo sysctl -w net.ipv6.conf.lo.disable_ipv6=1
net.ipv6.conf.lo.disable_ipv6 = 1

nvidia@tegra-ubuntu:~$ sudo nvpmodel -m 0

## 2. 安裝nvidia-container-tools

**安裝相關套件**

nvidia@tegra-ubuntu:~$ sudo apt update

nvidia@tegra-ubuntu:~$ sudo apt install curl -y

nvidia@tegra-ubuntu:~$ 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

deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://nvidia.github.io/libnvidia-container/stable/deb/$(ARCH) /
#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://nvidia.github.io/libnvidia-container/experimental/deb/$(ARCH) /

nvidia@tegra-ubuntu:~$ sudo sed -i -e '/experimental/ s/^#//g' /etc/apt/sources.list.d/nvidia-container-toolkit.list

nvidia@tegra-ubuntu:~$ sudo apt-get update

nvidia@tegra-ubuntu:~$ sudo apt-get install -y nvidia-container-toolkit

nvidia@tegra-ubuntu:~$ sudo nvidia-ctk runtime configure --runtime=containerd
INFO[0000] Config file does not exist; using empty config
INFO[0000] Wrote updated config to /etc/containerd/config.toml
INFO[0000] It is recommended that containerd daemon be restarted.

nvidia@tegra-ubuntu:~$ sudo systemctl daemon-reload

sudo reboot

**確認跟nvidia有關的套件清單**

nvidia@tegra-ubuntu:~$ sudo dpkg --get-selections | grep nvidia
[sudo] password for nvidia:
libnvidia-container-tools			install
libnvidia-container1:arm64			install
nvidia-container-toolkit			install
nvidia-container-toolkit-base			install
nvidia-l4t-3d-core				install
nvidia-l4t-apt-source				install
nvidia-l4t-bootloader				install
nvidia-l4t-camera				install
nvidia-l4t-configs				install
nvidia-l4t-core					install
nvidia-l4t-cuda					install
nvidia-l4t-display-kernel			install
nvidia-l4t-firmware				install
nvidia-l4t-gbm					install
nvidia-l4t-graphics-demos			install
nvidia-l4t-gstreamer				install
nvidia-l4t-init					install
nvidia-l4t-initrd				install
nvidia-l4t-jetson-io				install
nvidia-l4t-jetsonpower-gui-tools		install
nvidia-l4t-kernel				install
nvidia-l4t-kernel-dtbs				install
nvidia-l4t-kernel-headers			install
nvidia-l4t-libvulkan				install
nvidia-l4t-multimedia				install
nvidia-l4t-multimedia-utils			install
nvidia-l4t-nvfancontrol				install
nvidia-l4t-nvpmodel				install
nvidia-l4t-nvpmodel-gui-tools			install
nvidia-l4t-nvsci				install
nvidia-l4t-oem-config				install
nvidia-l4t-openwfd				install
nvidia-l4t-optee				install
nvidia-l4t-pva					install
nvidia-l4t-tools				install
nvidia-l4t-vulkan-sc				install
nvidia-l4t-vulkan-sc-dev			install
nvidia-l4t-vulkan-sc-samples			install
nvidia-l4t-vulkan-sc-sdk			install
nvidia-l4t-wayland				install
nvidia-l4t-weston				install
nvidia-l4t-x11					install
nvidia-l4t-xusb-firmware			install

## 3. 安裝K3S

nvidia@tegra-ubuntu:~$ export INSTALL_K3S_VERSION=v1.28.10+k3s1
nvidia@tegra-ubuntu:~$ curl -sfL https://get.k3s.io | sh -s - --write-kubeconfig-mode 644 --write-kubeconfig $HOME/.kube/config
[INFO]  Using v1.28.10+k3s1 as release
[INFO]  Downloading hash https://github.com/k3s-io/k3s/releases/download/v1.28.10+k3s1/sha256sum-arm64.txt
[INFO]  Downloading binary https://github.com/k3s-io/k3s/releases/download/v1.28.10+k3s1/k3s-arm64
[INFO]  Verifying binary download
[INFO]  Installing k3s to /usr/local/bin/k3s
[INFO]  Skipping installation of SELinux RPM
[INFO]  Creating /usr/local/bin/kubectl symlink to k3s
[INFO]  Creating /usr/local/bin/crictl symlink to k3s
[INFO]  Creating /usr/local/bin/ctr symlink to k3s
[INFO]  Creating killall script /usr/local/bin/k3s-killall.sh
[INFO]  Creating uninstall script /usr/local/bin/k3s-uninstall.sh
[INFO]  env: Creating environment file /etc/systemd/system/k3s.service.env
[INFO]  systemd: Creating service file /etc/systemd/system/k3s.service
[INFO]  systemd: Enabling k3s unit
Created symlink /etc/systemd/system/multi-user.target.wants/k3s.service → /etc/systemd/system/k3s.service.
[INFO]  systemd: Starting k3s

**檢查K3S中的組態是否有正確設定nvidia container runtime**

nvidia@tegra-ubuntu:~$ sudo grep nvidia /var/lib/rancher/k3s/agent/etc/containerd/config.toml
[plugins."io.containerd.grpc.v1.cri".containerd.runtimes."nvidia"]
[plugins."io.containerd.grpc.v1.cri".containerd.runtimes."nvidia".options]
  BinaryName = "/usr/bin/nvidia-container-runtime"

**檢查系統啟動與執行中**

nvidia@tegra-ubuntu:~$ kubectl get no
NAME           STATUS   ROLES                  AGE   VERSION
tegra-ubuntu   Ready    control-plane,master   76s   v1.28.10+k3s1
nvidia@tegra-ubuntu:~$ kubectl get po -A
NAMESPACE     NAME                                      READY   STATUS      RESTARTS   AGE
kube-system   coredns-6799fbcd5-82v8q                   1/1     Running     0          63s
kube-system   local-path-provisioner-6c86858495-698f5   1/1     Running     0          63s
kube-system   helm-install-traefik-crd-twgs7            0/1     Completed   0          64s
kube-system   helm-install-traefik-rd98d                0/1     Completed   1          64s
kube-system   svclb-traefik-d1387147-jxfll              2/2     Running     0          41s
kube-system   traefik-7d5f6474df-4trqj                  1/1     Running     0          41s
kube-system   metrics-server-54fd9b65b-8dwhf            1/1     Running     0          63s

## 4. 檢測是否看到GPU

nvidia@tegra-ubuntu:~$ kubectl create -f devcheck.yaml
job.batch/devicequery created

**devcheck.yaml**

apiVersion: batch/v1
kind: Job
metadata:
  name: devicequery
spec:
  template:
    metadata:
    spec:
      runtimeClassName: nvidia
      containers:
      - command:
        - ./deviceQuery
        image: xift/jetson_devicequery:r32.5.0
        name: devicequery
        resources: {}
      restartPolicy: Never



## 5. 透過程式碼確認GPU

nvidia@tegra-ubuntu:~$ kubectl create -f tf.yaml
pod/tf created

**tf.yaml**

apiVersion: v1
kind: Pod
metadata:
  name: tf
spec:
  runtimeClassName: nvidia
  containers:
  - name: nvidia
    image: xift/l4t-tensorflow:r32.5.0-tf2.3.1-py3
    command: [ "sleep" ]
    args: [ "1d" ]

root@tf:/# python3 -c "from tensorflow.python.client import device_lib; print(device_lib.list_local_devices());"
...
...
...
root@tf:/# exit
exit


## 執行一個sample(nbody)

## 其他

### 1. inportant !!
要是發現Jetson三不五時會自動關機或網路異常，有很高的機會是過熱了，直接風扇全開吧。

sudo jetson_clocks --fan