Akamas Live Optimizations - Supporting human experts in optimizing Kubernetes apps

Learn how Akamas Live Optimizations enables human experts in leveraging AI-based recommended configurations while retaining control before they get applied.

Akamas provides a single platform to optimize applications both in pre-production environment, for example to anticipate planned changes, cloud migration or chaos engineering scenarios, and directly live in production while applications are running under a dynamically varying workload.

In this demo, we apply Akamas to optimize a payment processing app, and specifically the “Order” microservice, which runs on Kubernetes and has been developed in GO.

The optimization scope includes both Kubernetes and Golang parameters, such as the GC target percentage which controls the "aggressiveness" of the Garbage Collector. The optimization goal is to minimize the cost of the container running the microservice, expressed by a formula that combines the container memory and CPU limits with maximum response time constraints.

You'll see how Akamas can run in "automatic mode" i.e. autonomously generating and applying optimal configurations, or in "manual mode" i.e. generating recommended configurations that must be approved by humans experts.

For more videos, articles and case studies, visit the Akamas Resource Center: https://www.akamas.io/resources/