mirror of
https://github.com/XuehaiPan/nvitop.git
synced 2026-05-21 06:45:24 -06:00
docs: add more examples
Signed-off-by: Xuehai Pan <XuehaiPan@pku.edu.cn>
This commit is contained in:
Xuehai Pan
parent
cf9e10dc7e
commit
2906d4f043
3 changed files with 121 additions and 4 deletions
58
README.md
58
README.md
|
|
@ -416,6 +416,8 @@ Please refer to [Resource Metric Collector](#resource-metric-collector) for an e
|
|||
|
||||
#### Quick Start
|
||||
|
||||
A minimal script to monitor the GPU devices based on APIs from `nvitop`:
|
||||
|
||||
```python
|
||||
from nvitop import Device
|
||||
|
||||
|
|
@ -434,9 +436,63 @@ for device in devices:
|
|||
print(f' - Processes ({len(processes)}): {sorted_pids}')
|
||||
for pid in sorted_pids:
|
||||
print(f' - {processes[pid]}')
|
||||
print('-' * 80)
|
||||
print('-' * 120)
|
||||
```
|
||||
|
||||
Another more advanced approach with coloring:
|
||||
|
||||
```python
|
||||
import time
|
||||
|
||||
from nvitop import Device, GpuProcess, NA, colored
|
||||
|
||||
print(colored(time.strftime('%a %b %d %H:%M:%S %Y'), color='red', attrs=('bold',)))
|
||||
|
||||
devices = Device.cuda.all() # or `Device.all()` to use NVML ordinal instead
|
||||
separator = False
|
||||
for device in devices:
|
||||
processes = device.processes() # type: Dict[int, GpuProcess]
|
||||
|
||||
print(colored(str(device), color='green', attrs=('bold',)))
|
||||
print(colored(' - Fan speed: ', color='blue', attrs=('bold',)) + f'{device.fan_speed()}%')
|
||||
print(colored(' - Temperature: ', color='blue', attrs=('bold',)) + f'{device.temperature()}C')
|
||||
print(colored(' - GPU utilization: ', color='blue', attrs=('bold',)) + f'{device.gpu_utilization()}%')
|
||||
print(colored(' - Total memory: ', color='blue', attrs=('bold',)) + f'{device.memory_total_human()}')
|
||||
print(colored(' - Used memory: ', color='blue', attrs=('bold',)) + f'{device.memory_used_human()}')
|
||||
print(colored(' - Free memory: ', color='blue', attrs=('bold',)) + f'{device.memory_free_human()}')
|
||||
if len(processes) > 0:
|
||||
processes = GpuProcess.take_snapshots(processes.values(), failsafe=True)
|
||||
processes.sort(key=lambda process: (process.username, process.pid))
|
||||
|
||||
print(colored(f' - Processes ({len(processes)}):', color='blue', attrs=('bold',)))
|
||||
fmt = ' {pid:<5} {username:<8} {cpu:>5} {host_memory:>8} {time:>8} {gpu_memory:>8} {sm:>3} {command:<}'.format
|
||||
print(colored(fmt(pid='PID', username='USERNAME',
|
||||
cpu='CPU%', host_memory='HOST-MEM', time='TIME',
|
||||
gpu_memory='GPU-MEM', sm='SM%',
|
||||
command='COMMAND'),
|
||||
attrs=('bold',)))
|
||||
for snapshot in processes:
|
||||
print(fmt(pid=snapshot.pid,
|
||||
username=snapshot.username[:7] + ('+' if len(snapshot.username) > 8 else snapshot.username[7:8]),
|
||||
cpu=snapshot.cpu_percent, host_memory=snapshot.host_memory_human,
|
||||
time=snapshot.running_time_human,
|
||||
gpu_memory=(snapshot.gpu_memory_human if snapshot.gpu_memory_human is not NA else 'WDDM:N/A'),
|
||||
sm=snapshot.gpu_sm_utilization,
|
||||
command=snapshot.command))
|
||||
else:
|
||||
print(colored(' - No Running Processes', attrs=('bold',)))
|
||||
|
||||
if separator:
|
||||
print('-' * 120)
|
||||
separator = True
|
||||
```
|
||||
|
||||
<p align="center">
|
||||
<img width="100%" src="https://user-images.githubusercontent.com/16078332/177041142-fe988d58-6a97-4559-84fd-b51204cf9231.png" alt="Demo">
|
||||
</br>
|
||||
An example monitoring script built with APIs from <code>nvitop</code>.
|
||||
</p>
|
||||
|
||||
#### Status Snapshot
|
||||
|
||||
`nvitop` provides a helper function to retrieve the status of both GPU devices and GPU processes at once. You can type `help(nvitop.take_snapshots)` in Python REPL for detailed documentation.
|
||||
|
|
|
|||
|
|
@ -5,9 +5,11 @@ Welcome to nvitop's documentation!
|
|||
|
||||
An interactive NVIDIA-GPU process viewer, the one-stop solution for GPU process management.
|
||||
|
||||
.. image:: https://user-images.githubusercontent.com/16078332/171005261-1aad126e-dc27-4ed3-a89b-7f9c1c998bf7.png
|
||||
.. figure:: https://user-images.githubusercontent.com/16078332/171005261-1aad126e-dc27-4ed3-a89b-7f9c1c998bf7.png
|
||||
:align: center
|
||||
|
||||
The CLI from ``nvitop``.
|
||||
|
||||
.. |GitHub| image:: https://img.shields.io/badge/GitHub-Homepage-blue?logo=github
|
||||
.. _GitHub: https://github.com/XuehaiPan/nvitop
|
||||
|
||||
|
|
@ -77,6 +79,8 @@ If this repo is useful to you, please star ⭐️ it to let more people know
|
|||
Quick Start
|
||||
"""""""""""
|
||||
|
||||
A minimal script to monitor the GPU devices based on APIs from ``nvitop``:
|
||||
|
||||
.. code-block:: python
|
||||
|
||||
from nvitop import Device
|
||||
|
|
@ -96,7 +100,62 @@ Quick Start
|
|||
print(f' - Processes ({len(processes)}): {sorted_pids}')
|
||||
for pid in sorted_pids:
|
||||
print(f' - {processes[pid]}')
|
||||
print('-' * 80)
|
||||
print('-' * 120)
|
||||
|
||||
Another more advanced approach with coloring:
|
||||
|
||||
.. code-block:: python
|
||||
|
||||
import time
|
||||
|
||||
from nvitop import Device, GpuProcess, NA, colored
|
||||
|
||||
print(colored(time.strftime('%a %b %d %H:%M:%S %Y'), color='red', attrs=('bold',)))
|
||||
|
||||
devices = Device.cuda.all() # or `Device.all()` to use NVML ordinal instead
|
||||
separator = False
|
||||
for device in devices:
|
||||
processes = device.processes() # type: Dict[int, GpuProcess]
|
||||
|
||||
print(colored(str(device), color='green', attrs=('bold',)))
|
||||
print(colored(' - Fan speed: ', color='blue', attrs=('bold',)) + f'{device.fan_speed()}%')
|
||||
print(colored(' - Temperature: ', color='blue', attrs=('bold',)) + f'{device.temperature()}C')
|
||||
print(colored(' - GPU utilization: ', color='blue', attrs=('bold',)) + f'{device.gpu_utilization()}%')
|
||||
print(colored(' - Total memory: ', color='blue', attrs=('bold',)) + f'{device.memory_total_human()}')
|
||||
print(colored(' - Used memory: ', color='blue', attrs=('bold',)) + f'{device.memory_used_human()}')
|
||||
print(colored(' - Free memory: ', color='blue', attrs=('bold',)) + f'{device.memory_free_human()}')
|
||||
if len(processes) > 0:
|
||||
processes = GpuProcess.take_snapshots(processes.values(), failsafe=True)
|
||||
processes.sort(key=lambda process: (process.username, process.pid))
|
||||
|
||||
print(colored(f' - Processes ({len(processes)}):', color='blue', attrs=('bold',)))
|
||||
fmt = ' {pid:<5} {username:<8} {cpu:>5} {host_memory:>8} {time:>8} {gpu_memory:>8} {sm:>3} {command:<}'.format
|
||||
print(colored(fmt(pid='PID', username='USERNAME',
|
||||
cpu='CPU%', host_memory='HOST-MEM', time='TIME',
|
||||
gpu_memory='GPU-MEM', sm='SM%',
|
||||
command='COMMAND'),
|
||||
attrs=('bold',)))
|
||||
for snapshot in processes:
|
||||
print(fmt(pid=snapshot.pid,
|
||||
username=snapshot.username[:7] + ('+' if len(snapshot.username) > 8 else snapshot.username[7:8]),
|
||||
cpu=snapshot.cpu_percent, host_memory=snapshot.host_memory_human,
|
||||
time=snapshot.running_time_human,
|
||||
gpu_memory=(snapshot.gpu_memory_human if snapshot.gpu_memory_human is not NA else 'WDDM:N/A'),
|
||||
sm=snapshot.gpu_sm_utilization,
|
||||
command=snapshot.command))
|
||||
else:
|
||||
print(colored(' - No Running Processes', attrs=('bold',)))
|
||||
|
||||
if separator:
|
||||
print('-' * 120)
|
||||
separator = True
|
||||
|
||||
.. figure:: https://user-images.githubusercontent.com/16078332/177041142-fe988d58-6a97-4559-84fd-b51204cf9231.png
|
||||
:align: center
|
||||
|
||||
An example monitoring script built with APIs from ``nvitop``.
|
||||
|
||||
Please refer to section `More than a Monitor <https://github.com/XuehaiPan/nvitop#more-than-a-monitor>`_ in README for more examples.
|
||||
|
||||
------
|
||||
|
||||
|
|
|
|||
|
|
@ -702,7 +702,9 @@ class GpuProcess: # pylint: disable=too-many-instance-attributes,too-many-publi
|
|||
self, *,
|
||||
host_process_snapshot_cache: Optional[Dict[int, Snapshot]] = None
|
||||
) -> Snapshot:
|
||||
"""Returns a onetime snapshot of the process on the GPU device."""
|
||||
"""Returns a onetime snapshot of the process on the GPU device.
|
||||
See also :meth:`take_snapshots` and :meth:`failsafe`.
|
||||
"""
|
||||
|
||||
host_process_snapshot_cache = host_process_snapshot_cache or {}
|
||||
try:
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue