No project description provided
Project description
nvidia-smi2
A tool for enriching the output of nvidia-smi.
Usage
Install
pip install nvidia-smi2
Run
nvidia-smi2 [-l [length]] [-u [username]]
print GPU utilization with usernames and CPU stats for each GPU-utilizing process
-l|--command-length [length] Print longer part of the commandline. If `length'
is provided, use it as the commandline length,
otherwise print first 100 characters.
-c|--color Colorize the output (green - free GPU, yellow -
moderately used GPU, red - fully used GPU)
-u|--user Name of user to summarize
Or run from src
pip install termcolor
chmod a+x nvidia-htop.py
./nvidia-htop.py [-l [length]] [-u [username]]
print GPU utilization with usernames and CPU stats for each GPU-utilizing process
-l|--command-length [length] Print longer part of the commandline. If `length'
is provided, use it as the commandline length,
otherwise print first 100 characters.
-c|--color Colorize the output (green - free GPU, yellow -
moderately used GPU, red - fully used GPU)
-u|--user Name of user to summarize
Note: for backward compatibility, nvidia-smi | ./nvidia-htop.py [-l [length]] [-u [username]]
is also supported.
Note: running inside a container (docker, singularity, ...), nvidia-smi
can only see processes running in the container.
Example output
rnd@rnd:~$ nvidia-smi2 -l
Wed Jul 12 10:41:16 2023
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 470.57.02 Driver Version: 470.57.02 CUDA Version: 11.4 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|===============================+======================+======================|
| 0 NVIDIA GeForce ... On | 00000000:01:00.0 Off | N/A |
| 55% 73C P2 88W / 280W | 3248MiB / 11176MiB | 64% Default |
| | | N/A |
+-------------------------------+----------------------+----------------------+
| 1 NVIDIA GeForce ... On | 00000000:02:00.0 Off | N/A |
| 59% 67C P2 91W / 280W | 9397MiB / 11178MiB | 7% Default |
| | | N/A |
+-------------------------------+----------------------+----------------------+
+-------------------------------------------------------------------------------------------------------------------------------------------------------------+
| GPU PID USER GPU MEM %CPU %MEM TIME COMMAND |
| 0 1242 root 9MiB 0.0 0.0 175 days /usr/lib/xorg/Xorg vt1 xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx |
| 0 1966 gdm 4MiB 0.0 0.0 175 days /usr/bin/gnome-shell |
| 0 6963 anonym1 2365MiB 2.9 3.1 7 days python train.py |
| 0 8200 root 135MiB 0.1 0.4 117 days python3 app.py xxxxxxxxx |
| 0 12474 rnd 135MiB 0.1 0.8 11 days python3 main.py xxxxxxxxxxx |
| 0 19369 root 455MiB 62.4 2.5 20 days python3 read_rtsp.py --path_stream xxxxxxxxxxxxxxxxxx |
| 0 30502 root 135MiB 0.0 1.8 16:24:10 python build_index.py |
| 1 1242 root 4MiB 0.0 0.0 175 days /usr/lib/xorg/Xorg vt1 -displayfd 3 -auth xxxxxxx |
| 1 19422 root 455MiB 86.7 3.7 20 days python3 read_rtsp.py --path_stream xxxxxxxxxxxxxxxxxxxxxxx |
| 1 25255 anonym2 6917MiB 128 4.3 22:30:29 python train_image_classifier.py xxxx |
| 1 27877 root 2017MiB 9.4 1.4 15 days python consumer.py |
+-------------------------------------------------------------------------------------------------------------------------------------------------------------+
| USER TOTAL GPU MEM TOTAL %CPU TOTAL %MEM |
+----------------------------------------------------------------+
| root 13MiB 0.0 0.0 |
| gdm 4MiB 0.0 0.1 |
| anony1 1086MiB 0.5 3.2 |
| anony2 6930MiB 478.8 9.5 |
| anony3 7418MiB 111.0 5.4 |
|----------------------------------------------------------------|
| all-users 15451MiB / 22528MiB 590.3 18.2 |
+----------------------------------------------------------------+
rnd@rnd:~$ nvidia-smi2 -l -u root
Wed Jul 12 10:51:06 2023
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 470.57.02 Driver Version: 470.57.02 CUDA Version: 11.4 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|===============================+======================+======================|
| 0 NVIDIA GeForce ... On | 00000000:01:00.0 Off | N/A |
| 58% 69C P2 106W / 280W | 3248MiB / 11176MiB | 5% Default |
| | | N/A |
+-------------------------------+----------------------+----------------------+
| 1 NVIDIA GeForce ... On | 00000000:02:00.0 Off | N/A |
| 59% 65C P2 80W / 280W | 9397MiB / 11178MiB | 7% Default |
| | | N/A |
+-------------------------------+----------------------+----------------------+
+-------------------------------------------------------------------------------------------------------------------------------------------------------------+
| GPU PID USER GPU MEM %CPU %MEM TIME COMMAND |
| 0 1242 root 9MiB 0.0 0.0 175 days /usr/lib/xorg/Xorg vt1 xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx |
| 0 8200 root 135MiB 0.1 0.4 117 days python3 app.py xxxxxxxxx |
| 0 19369 root 455MiB 62.4 2.5 20 days python3 read_rtsp.py --path_stream xxxxxxxxxxxxxxxxxx |
| 0 30502 root 135MiB 0.0 1.8 16:33:59 python build_index.py |
| 1 1242 root 4MiB 0.0 0.0 175 days /usr/lib/xorg/Xorg vt1 -displayfd 3 -auth xxxxxxx |
| 1 19422 root 455MiB 86.7 3.7 20 days python3 read_rtsp.py --path_stream xxxxxxxxxxxxxxxxxxxxxxx |
| 1 27877 root 2017MiB 9.4 2.2 15 days python consumer.py |
+-------------------------------------------------------------------------------------------------------------------------------------------------------------+
| USER TOTAL GPU MEM TOTAL %CPU TOTAL %MEM |
+----------------------------------------------------------------+
| root 3210MiB 158.6 10.6 |
|----------------------------------------------------------------|
| all-users 15451MiB / 22528MiB 590.3 18.2 |
+----------------------------------------------------------------+
Reference
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file nvidia_smi2-0.0.2.post6.tar.gz
.
File metadata
- Download URL: nvidia_smi2-0.0.2.post6.tar.gz
- Upload date:
- Size: 5.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.0.0 CPython/3.8.10
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 7caa4524c635d241328c1d8eadac2c3a01b927c533784bcb27257919940d3f0b |
|
MD5 | 973d9ffa3c01f21ad6a1d768d69480fe |
|
BLAKE2b-256 | c2300f61716c0c10265e1b2436a6954f3320d4fef4807cca72115cb19d405021 |
File details
Details for the file nvidia_smi2-0.0.2.post6-py3-none-any.whl
.
File metadata
- Download URL: nvidia_smi2-0.0.2.post6-py3-none-any.whl
- Upload date:
- Size: 6.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.0.0 CPython/3.8.10
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 7bacd4983f3b36467fcf5b6988dddffba8fbb205362756a7d3c9cda5c95dfe1d |
|
MD5 | 79d18b3739e38e3ff5523d49aebfc894 |
|
BLAKE2b-256 | ff3a6f41c09a28684475cba999e71929ef2539c68812fe03b9278d139724e03e |