Load Testing ML Microservices for Robustness and Scalability

About The Demo

The demo is aimed at getting started with load testing a microservice before taking it to production. We use FastAPI microservice (to predict weather) and Locust to load test the service (locally or on cloud). You can find detailed instructions in the Engineering MLOps book.

Built With

Major frameworks used to build the project:

• FastAPI
• Docker
• Locust

Installation

These are instructions to install and get the services up and running.

1. Clone the repo

   git clone https://github.com/emmanuelraj7/loadtesting-microservices.git

2. Install Locust.io

   pip install locust

3. Go to FastAPI_microservice folder and build the FastAPI service docker image

   docker build -t fastapi .

4. Run the FastAPI service docker container locally

   docker run -d -p 80:80 fastapi

5. Go to Load_testing folder and run locust.io service for load testing

   Locust -f load_test-py

License

Distributed under the MIT License. See LICENSE for more information.

Contact

Emmanuel Raj - Linkedin

Project Link: https://github.com/emmanuelraj7/loadtesting-microservices

Engineering MLOps (book): Amazon