diff --git a/docs/.vitepress/config.mts b/docs/.vitepress/config.mts index 34459869..1edfeb80 100644 --- a/docs/.vitepress/config.mts +++ b/docs/.vitepress/config.mts @@ -176,6 +176,7 @@ function getGuideSidebarZhCN() { { text: '设置每月重置流量统计', link: '/guide/q6.html' }, { text: '自定义 Agent 监控项目', link: '/guide/q7.html' }, { text: '使用 Cloudflare Access 作为 OAuth2 提供方', link: '/guide/q8' }, + { text: '启用 GPU 监控', link: '/guide/q9' }, ] }, { @@ -246,6 +247,7 @@ function getGuideSidebarEnUS() { { text: 'Reset Traffic Statistics Monthly', link: '/en_US/guide/q6.html' }, { text: 'Custom Agent Monitoring Projects', link: '/en_US/guide/q7.html' }, { text: 'Use Cloudflare Access As OAuth2 Provider', link: '/en_US/guide/q8' }, + { text: 'Enable GPU monitoring', link: '/en_US/guide/q9' }, ] }, { diff --git a/docs/en_US/guide/q7.md b/docs/en_US/guide/q7.md index 8aca162f..fd6c58d3 100644 --- a/docs/en_US/guide/q7.md +++ b/docs/en_US/guide/q7.md @@ -24,4 +24,5 @@ If you installed the Agent using the one-click script, you can edit `/etc/system - `--disable-auto-update`: Disables **automatic updates** for the Agent (security feature). - `--disable-force-update`: Disables **forced updates** for the Agent (security feature). - `--disable-command-execute`: Disables the execution of scheduled tasks and the opening of the online terminal on the Agent (security feature). -- `--tls`: Enables SSL/TLS encryption (required if you use nginx to reverse proxy the Agent's gRPC connection and nginx has SSL/TLS enabled). \ No newline at end of file +- `--tls`: Enables SSL/TLS encryption (required if you use nginx to reverse proxy the Agent's gRPC connection and nginx has SSL/TLS enabled). +- `--gpu`: Enable GPU monitoring (may need extra dependencies while monitoring GPU utilization. Refer to FAQ - Enable GPU monitoring for any questions.) \ No newline at end of file diff --git a/docs/en_US/guide/q9.md b/docs/en_US/guide/q9.md new file mode 100644 index 00000000..f88ab804 --- /dev/null +++ b/docs/en_US/guide/q9.md @@ -0,0 +1,78 @@ +# Enable GPU monitoring + +GPU monitoring is a new feature implemented in Nezha Monitoring v0.17.x. Before using the feature, please check you Dashboard version is higher than v0.17.2 and Agent version is higher than v0.17.0. + +## Enable + +### From Command-Line Flag + +Append the `--gpu` flag to the Agent argument. For example: + +```bash +/opt/nezha/agent/nezha-agent -s example.com:5555 -p example --gpu +``` + +### From configuration file + +Execute the following command to modify Agent configuration to enable GPU monitoring. + +```bash +/opt/nezha/agent/nezha-agent edit +``` + +In the returned interactive menu, choose to enable GPU monitoring. + +## Enable GPU utilization monitoring + +GPU model and GPU utilization are two different monitor items, which uses different approaches to obtain their value. + +Windows and macOS supports getting GPU utilization without extra dependencies, and support multiple graphics card brands. + +Linux distros support only NVIDIA and AMD cards and need to install extra dependencies. + +Below are the instructions on how to enable GPU utilization monitoring on Linux for NVIDIA / AMD graphics cards. + +### NVIDIA + +NVIDIA cards need the `nvidia-smi` utility to get GPU utilization. This utility is included in the official driver by default. + +If you use unofficial drivers like `nouveau`, then it's not possible to get GPU utilization. + +### AMD + +AMD cards need to install the official `amdgpu` driver and the `rocm-smi` utility. + +Mainstream distros have already packaged `rocm-smi`, below are commands to install the utility on these distros: + +```bash +# Arch Linux +pacman -Sy rocm-smi-lib + +# Debian / Ubuntu +apt install rocm-smi + +# Fedora / RHEL 8+ +dnf install rocm-smi +``` + +If your distro doesn't have the package, then you will need to compile `rocm_smi_lib` manually. + +Required dependencies：`git` `cmake` `gcc` + +First, clone the git repository of `rocm_smi_lib`: + +```bash +git clone https://github.com/ROCm/rocm_smi_lib +``` + +Then compile the libraries and install them on your system. + +```bash +cd rocm_smi_lib +mkdir -p build +cd build +cmake .. +make -j $(nproc) +# Install library file and header; default location is /opt/rocm +make install +``` diff --git a/docs/guide/q7.md b/docs/guide/q7.md index ec50fa33..29892da3 100644 --- a/docs/guide/q7.md +++ b/docs/guide/q7.md @@ -24,4 +24,5 @@ - `--disable-auto-update`：禁止 **自动更新** Agent（安全特性）。 - `--disable-force-update`：禁止 **强制更新** Agent（安全特性）。 - `--disable-command-execute`：禁止在 Agent 上执行定时任务、打开在线终端（安全特性）。 -- `--tls`：启用 SSL/TLS 加密（使用 nginx 反向代理 Agent 的 grpc 连接，并且 nginx 开启 SSL/TLS 时，需要启用该项配置）。 \ No newline at end of file +- `--tls`：启用 SSL/TLS 加密（使用 nginx 反向代理 Agent 的 grpc 连接，并且 nginx 开启 SSL/TLS 时，需要启用该项配置）。 +- `--gpu`: 启用 GPU 监控（其中 GPU 使用率监控可能需要安装额外依赖。相关问题请参见常见问题 - 启用 GPU 监控。） \ No newline at end of file diff --git a/docs/guide/q9.md b/docs/guide/q9.md new file mode 100644 index 00000000..eaa3e55c --- /dev/null +++ b/docs/guide/q9.md @@ -0,0 +1,78 @@ +# 启用 GPU 监控 + +GPU 监控是哪吒监控 v0.17.x 引入的新功能，使用前请检查您的 Dashboard 版本是否为 v0.17.2+ / Agent 版本是否为 v0.17.0+。 + +## 启用 + +### 通过启动参数 + +在 Agent 运行参数后添加 `--gpu` 即可。例如： + +```bash +/opt/nezha/agent/nezha-agent -s example.com:5555 -p example --gpu +``` + +### 通过配置文件 + +执行以下命令修改 Agent 配置文件以启用 GPU 监控： + +```bash +/opt/nezha/agent/nezha-agent edit +``` + +在返回的互动菜单中选择启用 GPU 功能即可。 + +## 打开 GPU 占用率监控支持 + +GPU 型号与 GPU 使用率为两个不同的监控项目，使用了不同实现获取。 + +其中 Windows 和 macOS 支持无依赖获取 GPU 使用率，并支持多个品牌显卡； + +Linux 平台则仅支持 NVIDIA / AMD 显卡，且需要安装额外依赖。 + +以下将介绍如何在 Linux 上为 NVIDIA / AMD 显卡启用 GPU 使用率监控。 + +### NVIDIA + +NVIDIA 显卡获取 GPU 使用率需要用到 `nvidia-smi` 工具，一般为官方驱动自带。 + +如果您使用的是非官方驱动，例如 `nouveau`，那么将无法获取 GPU 使用率。 + +### AMD + +AMD 显卡获取 GPU 使用率需要安装官方 `amdgpu` 驱动和 `rocm-smi` 工具。 + +主流系统均已打包 `rocm-smi` ，以下是部分系统的安装命令： + +```bash +# Arch Linux +pacman -Sy rocm-smi-lib + +# Debian / Ubuntu +apt install rocm-smi + +# Fedora / RHEL 8+ +dnf install rocm-smi +``` + +如果您的系统并没有相应包，那么则需要手动编译安装 `rocm_smi_lib`。 + +您的系统需要安装这些依赖：`git` `cmake` `gcc` + +首先 Clone `rocm_smi_lib` 的 git 仓库： + +```bash +git clone https://github.com/ROCm/rocm_smi_lib +``` + +然后进行编译并安装即可。 + +```bash +cd rocm_smi_lib +mkdir -p build +cd build +cmake .. +make -j $(nproc) +# Install library file and header; default location is /opt/rocm +make install +```