All Events
Autoscaling Isn't Set-and-Forget: Tuning KEDA & Karpenter for Real Workloads
Please join Christian Melendez (Principal Specialist Solutions Architect at AWS) and Jan Wozniak (KEDA maintainer, Kedify) at ContainerDays Hamburg 2026 for a deep dive into running KEDA and Karpenter in production. If you’re attending the conference September 2 to 4, come say hi after the talk to dig into your own autoscaling setup.
The talk
You’ve deployed KEDA and Karpenter, now what? Most talks stop at “it scales.” This one starts there. We’ll walk through the advanced configurations, failure modes, and optimization patterns that separate demo clusters from production workloads.
On the Karpenter side
- Node Disruption Budgets to control voluntary disruptions
- Surviving Spot interruptions gracefully
- Bootstrap optimizations that shave minutes off node startup
On the KEDA side
- Scaling modifiers that combine multiple metrics into smarter decisions
- Cooldown tuning to prevent thrashing
- The shift from reactive scaling to proactive workload sizing
We’ll show how Karpenter and KEDA together change the equation: what you get out of the box, what you still need to configure, and how all of this fits into building an efficient Kubernetes cluster.
