jetson-stats is a package to monitoring and control your NVIDIA Jetson [Nano, Xavier, TX2i, TX2, TX1] embedded board. When you install jetson-stats are included:
Read the Wiki for more detailed information
sudo -H pip install jetson-stats
There are not require other information to use your jetson stats
Update the jetson-stats version
Now update your system monitor is easier then before.
sudo -H pip install -U jetson-stats
It is a system monitoring utility that runs on the terminal and see and control realtime the status of your NVIDIA Jetson. CPU, RAM, GPU status and frequency and other...
You can run the jtop with (Suggested to run with sudo)
Other options are availables with
nvidia@jetson-nano:~/$ sudo jtop -h usage: jtop [-h] [-r REFRESH] [--debug] [--page PAGE] [--version] jtop is a system monitoring utility and control. Runs on terminal optional arguments: -h, --help show this help message and exit -r REFRESH refresh interval --debug Run with debug logger --page PAGE Open fix page --version show program's version number and exit
To control the your NVIDIA Jetson are available this keyboard commands:
- a Start/Stop jetson_clocks service (Note: jetson_clocks start only after 60s from up time)
- e Enable/Disable jetson_clocks on board boot
- + and - Increase and decrease the NVPmodel
jtop have four different pages to control your NVIDIA Jetson:
- ALL Are collected all information about your board: CPUs status, Memory, GPU, disk, fan and all status about jetson_clocks, NVPmodel and other
- GPU A real time GPU history about your NVIDIA Jetson
- CTRL You can control the status of you
- INFO Are collected all information about libraries, CUDA, Serial Number, interfaces, ...
The command show the status and all information about your NVIDIA Jetson
This script generate the easy environment variables to know which is your Hardware version of the Jetson and which Jetpack you have already installed
It is a bridge to use the NVIDIA core inside your doker container. This bridge share CUDA library, and all devices (nvmap and gpu)