netease-youdao / QAnything

Question and Answer based on Anything.
https://qanything.ai
GNU Affero General Public License v3.0
11.54k stars 1.12k forks source link

[BUG] qanything-container-local容器里的sanic_api服务一直起不来,是显存不足么? #55

Open BuptPeter opened 8 months ago

BuptPeter commented 8 months ago

是否已有关于该错误的issue或讨论? | Is there an existing issue / discussion for this?

该问题是否在FAQ中有解答? | Is there an existing answer for this in FAQ?

当前行为 | Current Behavior

期望行为 | Expected Behavior

sanic_api服务应该可以正常启动

运行环境 | Environment

- OS:Ubuntu 18.04
- NVIDIA Driver:535.146.02
- CUDA:12.2
- Docker Compose:v2.24.0-birthday.10
- NVIDIA GPU Memory:RTX 2080Ti (11G) x2

QAnything日志 | QAnything logs

nohup: ignoring input UPLOAD_ROOT_PATH: /workspace/qanything_local/QANY_DB/content rerank_port: 8001 embed_port: 9001 [2024-01-23 13:54:07 +0800] [6768] [INFO] Sanic v23.6.0 [2024-01-23 13:54:07 +0800] [6768] [INFO] Goin' Fast @ http://0.0.0.0:8777 [2024-01-23 13:54:07 +0800] [6768] [INFO] mode: production, w/ 4 workers [2024-01-23 13:54:07 +0800] [6768] [INFO] server: sanic, HTTP/1.1 [2024-01-23 13:54:07 +0800] [6768] [INFO] python: 3.10.12 [2024-01-23 13:54:07 +0800] [6768] [INFO] platform: Linux-5.4.0-150-generic-x86_64-with-glibc2.35 [2024-01-23 13:54:07 +0800] [6768] [INFO] packages: sanic-routing==23.12.0, sanic-ext==23.6.0 [2024-01-23 14:20:47 +0800] [6768] [ERROR] Not all workers acknowledged a successful startup. Shutting down.

It seems that one or more of your workers failed to come online in the allowed time. Sanic is shutting down to avoid a deadlock. The current threshold is 600.0s. If this problem persists, please check out the documentation https://sanic.dev/en/guide/deployment/manager.html#worker-ack. [2024-01-23 14:20:47 +0800] [6768] [INFO] Killing Sanic-Server-0-0 [7943] [2024-01-23 14:20:47 +0800] [6768] [INFO] Killing Sanic-Server-1-0 [7944] [2024-01-23 14:20:47 +0800] [6768] [INFO] Killing Sanic-Server-2-0 [7945] [2024-01-23 14:20:47 +0800] [6768] [INFO] Killing Sanic-Server-3-0 [7946] [2024-01-23 14:20:47 +0800] [6768] [INFO] Server Stopped UPLOAD_ROOT_PATH: /workspace/qanything_local/QANY_DB/content rerank_port: 8001 embed_port: 9001

复现方法 | Steps To Reproduce

bash run.sh 0,1

备注 | Anything else?

日志里有以下提示信息: None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.

liuyijiang1994 commented 7 months ago

+1 求问,

[2024-01-23 13:54:07 +0800] [6768] [INFO] packages: sanic-routing==23.12.0, sanic-ext==23.6.0
[2024-01-23 14:20:47 +0800] [6768] [ERROR] Not all workers acknowledged a successful startup. Shutting down.

话说这等的时间也太长了

liuyijiang1994 commented 7 months ago

+1 求问,

[2024-01-23 13:54:07 +0800] [6768] [INFO] packages: sanic-routing==23.12.0, sanic-ext==23.6.0
[2024-01-23 14:20:47 +0800] [6768] [ERROR] Not all workers acknowledged a successful startup. Shutting down.

话说这等的时间也太长了

加载完了,用了14分钟,有点久啊,貌似local_file.py中import langchain的一些文件解析的loader用了很久,不是很清楚为啥