Solving the Kubernetes Autoscaling Challenge with StormForge

Autoscaling is a significant challenge (and opportunity) for Kubernetes users. Out of the box, Kubernetes comes with two primary ways of dynamically scaling – the Horizontal Pod Autoscaler (HPA) and the Vertical Pod Autoscaler (VPA) – but it’s not possible to use both together without extensive effort and customization. Additionally, the HPA requires users to configure a target utilization used to determine when to scale, but setting that target utilization in an optimal way is a challenge.

Scott Moore interviews Patrick Bergstrom, Chief Technology Officer of StormForge. They discuss the new release of their StormForge Optimize Live product, and how advanced machine learning solves the problem of using horizontal and vertical auto scaling on the same workloads for Kubernetes deployed applications. It works at both the node and container level, replacing guesswork with science to eliminate the choice between cost and performance.

Scott Moore Consulting:
SMC Journal: