Standalone Debian Package Install

Standalone Debian Package Install#

System Requirements#

Before installing the AMD GPU Metrics Exporter, you need to install the following:

Operating System: Ubuntu 22.04 or Ubuntu 24.04
ROCm Version: 6.3.x (specific to each .deb pkg)

Each Debian package release of the Standalone Metrics Exporter is dependent on a specific version of the ROCm amdgpu driver. Please see table below for more information:

Metrics Exporter Debian Version	ROCm Version	AMDGPU Driver Version
amdgpu-exporter-1.2.0	ROCm 6.3.x	6.10.5

Installation#

Step 1: Install System Prerequisites#

Update the system:

sudo apt update
sudo apt install "linux-headers-$(uname -r)" "linux-modules-extra-$(uname -r)"

Add user to required groups:

sudo usermod -a -G render,video $LOGNAME

Step 2: Install AMDGPU Driver#

Note

For the most up-to-date information on installing dkms drivers please see the ROCm Install Quick Start page. The below instructions are the most current instructions as of ROCm 6.2.4.

Download the driver from the Radeon repository (repo.radeon.com) for your operating system. For example if you want to get the latest ROCm 6.3.4 drivers for Ubuntu 22.04 you would run the following command:
```
wget https://repo.radeon.com/amdgpu-install/6.3.4/ubuntu/jammy/amdgpu-install_6.3.60304-1_all.deb
```
Please note that the above url will be different depending on what version of the drivers you will be installing and type of Operating System you are using.

Install the driver:

sudo apt install ./amdgpu-install_6.3.60304-1_all.deb
sudo apt update
amdgpu-install --usecase=dkms

Load the driver module:
```
sudo modprobe amdgpu
```

Step 3: Install the APT Prerequisites for Metrics Exporter#

Update the package list and install necessary tools, keyrings and keys:

# Install necessary tools
sudo apt update
sudo apt install vim wget gpg

# Create the keyrings directory with the appropriate permissions:
sudo mkdir --parents --mode=0755 /etc/apt/keyrings

# Download the ROCm GPG key and add it to the keyrings:
wget https://repo.radeon.com/rocm/rocm.gpg.key -O - | gpg --dearmor | sudo tee /etc/apt/keyrings/rocm.gpg > /dev/null

Edit the sources list to add the Device Metrics Exporter repository:

For Ubuntu 22.04, add the following line:

deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/device-metrics-exporter/apt/1.2.0 jammy main

For Ubuntu 24.04, add the following line:

deb [arch=amd64 signed-by=/etc/apt/keyrings/rocm.gpg] https://repo.radeon.com/device-metrics-exporter/apt/1.2.0 noble main

Update the package list again:
```
sudo apt update
```

Step 4: Install the Prerequisites for Metrics Exporter#

Install the Device Metrics Exporter:
```
sudo apt install amdgpu-exporter
```

Enable and start services:

sudo systemctl enable amd-metrics-exporter.service
sudo systemctl start amd-metrics-exporter.service

Check service status:

sudo systemctl status amd-metrics-exporter.service

Metrics Exporter Default Settings#

Metrics endpoint: http://localhost:5000/metrics
Configuration file: /etc/metrics/config.json
GPU Agent port (default): 50061

The Exporter HTTP port is configurable via the ServerPort field in the configuration file.

Metrics Exporter Custom Configuration#

Using a custom config.json#

If you need to customize ports or settings:

Download a copy of the default config.json from the Metrics Exporter Repo. Note that you can change the path to save the config.json file into a different direct. Just be sure to also update the path in the server ExecStart command in step 3.
```
wget -O /etc/metrics/config.json https://raw.githubusercontent.com/ROCm/device-metrics-exporter/refs/heads/main/example/config.json
```
Make any required changes to your config.json file and ensure the port number you want to use is correct. Example of the first few lines of the config.json shown below:
```
{
"ServerPort": 5000,
"GPUConfig": {
    "Fields": [
    "GPU_NODES_TOTAL",
    "GPU_PACKAGE_POWER",
...
...
```

Edit the amd-metrics-exporter service file:

sudo vi /lib/systemd/system/amd-metrics-exporter.service

Update the ExecStart line to read in the config.json file:

ExecStart=/usr/local/bin/amd-metrics-exporter -amd-metrics-config /etc/metrics/config.json

Reload systemd:
```
sudo systemctl daemon-reload
```

Custom Port Configuration - Change GPU Agent Port#

Edit the GPU Agent service file:

sudo vi /lib/systemd/system/gpuagent.service

Update ExecStart with desired port:

ExecStart=/usr/local/bin/gpuagent -p <port_number>

Change Metrics Exporter Port#

Edit the configuration file:
```
sudo vi /etc/metrics/config.json
```
Update ServerPort to your desired port.

Removing Metrics Exporter and other components#

To remove this application, follow these commands in reverse order:

Uninstall the Metrics Exporter:

Ensure the .deb package is removed:

sudo dpkg -r amdgpu-exporter
sudo apt-get purge amdgpu-exporter

(Optional) If you would also like to uninstall the AMDGPU Driver:
- Uninstall any associated DKMS packages:
```
sudo dpkg -r amdgpu-install
```
- Unload the driver module:
```
sudo modprobe -r amdgpu
```

(Optional) If you would also like to remove the system prerequisites that were installed:

Remove Linux header and module packages:

sudo apt remove linux-headers-$(uname -r)
sudo apt remove linux-modules-extra-$(uname -r)

Remove the user from groups:

sudo gpasswd -d $LOGNAME render
sudo gpasswd -d $LOGNAME video