news.ycombinator.com• Sep 18, 2025• 1 min read
Ask HN: Experienced the counter-intuitive cost reduction by increasing CPU?Wanted to share the insights I learned while working on RudderStack. It was counter-intuitive to see this much cost saving by vertical scaling, by increasing CPU. Have you experienced something similar? In my story, the Kubernetes Vertical Pod Autoscaler (VPA) is the hero.Anyone thinking about vertical scaling or using VPA in production, I hope my experience helps you learn a thing or two. Do share your experience as well for a well-rounded discussion.-----Background (The challenge and the subject system)My goal was to improve performance/cost ratio for my Kubernetes cluster. For performance, the focus was on increasing throughput.The operations in the subject system were primarily CPU-bound, we had a good amount of spare memory available at our disposal. Horizontal scaling was not possible architecturally. If you want to dive deeper, here's the code for key components of the system (and architecture in readme) -* rudder-server - https://github.com/rudderlabs/rudder-server* rudder-tran
