117-20002错误排查

Debug

老哥你好、 我们这边做了检查。

1、机器这边没有自动升级package。
2、相关日志没有机器的重启记录。
3、没有oom等报错信息。

在对您项目的运行日志进行检查的时候发现

Closing server running on port: 581330it/s]
Restarting UI...
################################################################
Install script for stable-diffusion + Web UI
Tested on Debian 11 (Bullseye)
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
Cannot locate TCMalloc (improves CPU memory usage)
Python 3.10.9 (main, Mar  1 2023, 18:23:06) [GCC 11.2.0]
Commit hash: 5ab7f213bec2f816f9c5644becb32eb72c8ffb89
Installing requirements
Launching Web UI with arguments: --listen --api --share --port 58133
No module 'xformers'. Proceeding without it.
Loading weights [9aba26abdf] from /home/bkyes/ai/stable-diffusion-webui/models/Stable-diffusion/deliberate_v2.safetensors
Creating model from config: /home/bkyes/ai/stable-diffusion-webui/configs/v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying cross attention optimization (Doggettx).
Textual inversion embeddings loaded(0):
Model loaded in 14.0s (load weights from disk: 0.3s, create model: 1.0s, apply weights to model: 8.0s, apply half(): 2.0s, move model to device: 2.5s).
Traceback (most recent call last):
  File "/home/bkyes/ai/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/networking.py", line 118, in start_server
    s.bind((LOCALHOST_NAME, server_port))
OSError: [Errno 98] Address already in use
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
  File "/home/bkyes/ai/stable-diffusion-webui/launch.py", line 353, in <module>
    start()
  File "/home/bkyes/ai/stable-diffusion-webui/launch.py", line 348, in start
    webui.webui()
  File "/home/bkyes/ai/stable-diffusion-webui/webui.py", line 316, in webui
    app, local_url, share_url = shared.demo.launch(
  File "/home/bkyes/ai/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/blocks.py", line 1703, in launch
    server_name, server_port, local_url, app, server = networking.start_server(
  File "/home/bkyes/ai/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/networking.py", line 121, in start_server
    raise OSError(
OSError: Port 58133 is in use. If a gradio.Blocks is running on the port, you can close() it or gradio.close_all().
Running on local URL:  http://0.0.0.0:58133
Running on public URL: https://4883c86661238ab84b.gradio.live
This share link expires in 72 hours. For free permanent hosting and GPU upgrades (NEW!), check out Spaces: https://huggingface.co/spaces
Startup time: 4.7s (load scripts: 0.6s, create ui: 0.3s, gradio launch: 3.8s).
100%|██████████| 20/20 [00:02<00:00,  7.94it/s]
Total progress: 1020it [2:59:57,  4.68it/s]

第一行和第二行的日志有异步操作，我们认为应该是机器一边在推理，一边收到了restart ui的请求，于是A线程继续推理，B线程重启UI然后重新绑定端口。

在这个过程中出现了端口占用的情况。

在A线程处理结束之后，释放了端口，然后B线程就可以成功绑定端口继续运行了。