GPU metrics
The gpu_metrics input plugin collects graphics processing unit (GPU) performance metrics from graphics cards on Linux systems. It provides real-time monitoring of GPU utilization, memory usage (VRAM), clock frequencies, power consumption, temperature, and fan speeds.
The plugin reads metrics directly from the Linux sysfs filesystem (/sys/class/drm/) without requiring external tools or libraries. Only AMD GPUs are supported through the amdgpu kernel driver. NVIDIA and Intel GPUs aren't supported.
Metrics collected
The plugin collects the following metrics for each detected GPU:
gpu_utilization_percent
GPU core utilization as a percentage (0 to 100). Indicates how busy the GPU is when processing workloads.
gpu_memory_used_bytes
Amount of video RAM (VRAM) currently in use, measured in bytes.
gpu_memory_total_bytes
Total video RAM (VRAM) capacity available on the GPU, measured in bytes.
gpu_clock_mhz
Current GPU clock frequency in MHz. This metric has multiple instances with different type labels (see Clock metrics).
gpu_power_watts
Current power consumption in watts. Can be disabled with enable_power set to false.
gpu_temperature_celsius
GPU die temperature in degrees Celsius. Can be disabled with enable_temperature set to false.
gpu_fan_speed_rpm
Fan rotation speed in Revolutions per Minute (RPM).
gpu_fan_pwm_percent
Fan PWM duty cycle as a percentage (0-100). Indicates fan intensity.
Clock metrics
The gpu_clock_mhz metric is reported separately for three clock domains:
graphics
GPU core/shader clock frequency.
memory
VRAM clock frequency.
soc
System-on-chip clock frequency.
Configuration parameters
The plugin supports the following configuration parameters:
cards_exclude
Pattern specifying which GPU cards to exclude from monitoring. Uses the same syntax as cards_include.
none
cards_include
Pattern specifying which GPU cards to monitor. Supports wildcards (*), ranges (0-3), and comma-separated lists (0,2,4).
*
enable_power
Enable collection of power consumption metrics (gpu_power_watts).
true
enable_temperature
Enable collection of temperature metrics (gpu_temperature_celsius).
true
path_sysfs
Path to the sysfs root directory. Typically used for testing or non-standard systems.
/sys
scrape_interval
Interval in seconds between metric collection cycles.
5
GPU detection
The GPU metrics plugin scans for any supported AMD GPU using the amdgpu kernel driver. Any GPU using legacy drivers is ignored.
To check if your AMD GPU will be detected run:
Example output:
Multiple GPU systems
In systems with multiple GPUs, the GPU metrics plugin will detect all AMD cards by default. You can control which GPUs you want to monitor with the cards_include and cards_exclude parameters.
To list the GPUs running in your system run the following command:
Example output:
Getting started
To get GPU metrics from your system, you can run the plugin from either the command line or through the configuration file:
Command line
Run the following command from the command line:
Example output:
Configuration file
In your main configuration file append the following:
Last updated
Was this helpful?