When performing recall tests, docker-api-1 caused the system CPU usage to reach 100%.

Self Checks

[X] This is only for bug report, if you would like to ask a question, please head to Discussions.
[X] I have searched for existing issues search for existing issues, including closed ones.
[X] I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
[X] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
[X] Please do not modify this template :) and fill in all the required fields.

Dify version

0.6.8

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

When performing recall tests, docker-api-1 caused the system CPU usage to reach 100%.

✔️ Expected Behavior

No response

❌ Actual Behavior

No response

@liduang Hello there! I'm here to help you with any issues or questions you have regarding the repository. I can assist you in solving bugs, answering questions, or becoming a contributor.

To address the issue of the docker-api-1 container causing the system CPU usage to reach 100% during recall tests, you can try the following steps:

Check Resource Limits: Ensure that the docker-api-1 container has appropriate resource limits set in the docker-compose.yml file. You can limit the CPU usage by adding the cpus option.
```
services:
  docker-api-1:
    image: your-image
    deploy:
      resources:
        limits:
          cpus: '0.50'
```
Optimize the Application: Investigate the application running inside the docker-api-1 container to identify any performance bottlenecks or inefficient code that could be causing high CPU usage.
Monitor and Debug: Use Docker's built-in tools to monitor the container's resource usage and debug the issue.
```
docker stats docker-api-1
```
Check Logs: Review the logs of the docker-api-1 container to identify any errors or warnings that might indicate the cause of the high CPU usage.
```
docker logs docker-api-1
```
Scale the Service: If the high CPU usage is due to high load, consider scaling the service to distribute the load across multiple instances.
```
docker-compose up --scale docker-api-1=3 -d
```

Additionally, during recall tests, specific functionalities such as choosing retrieval strategies, debugging TopK and recall score thresholds, and calculating similarity scores can be CPU-intensive. Adjusting these parameters might help reduce CPU usage ^[1]^[2].

By following these steps, you should be able to identify and mitigate the issue causing the docker-api-1 container to use excessive CPU resources.

To continue talking to Dosu, mention @dosu.

langgenius / dify