From the course: Deploying Scalable Machine Learning for Data Science
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Monitoring service performance
From the course: Deploying Scalable Machine Learning for Data Science
Monitoring service performance
- [Instructor] Once you have wrapped your machine learning model in a service and made it accessible by an API, and you've created containers to run the service, and you've deployed those containers in Kubernetes so that the service will scale, you might think that your work is done. But it's not. We need to monitor our services once they're in production. Scaling machine learning models requires that we employ DevOps practices to ensure that our applications are running as expected. Ideally, we'd like to know if there's a performance problem before the users of our service encounter problems in their own applications because of a failure on our side. Monitoring is the practice of reviewing application logs and metrics to understand how well an application is performing. Broadly speaking, there are two kinds of information we want to understand. The first is baseline performance. This is a set of measurements that describe how the system performs when under normal conditions, that is,…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.