Why Spark on Kubernetes Breaks in Production
Konstantin Zelmanovich
If you’re running Spark on Kubernetes, the production symptoms are familiar: exe...
Latest Blog Posts
Featured
HPA’s Three Architectural Flaws (And Why Your Autoscaling Keeps Failing)
Nic Vermandé
The Promise vs. Reality of HPA HPA is the most deployed autoscaler in Kubernetes. It’s also architecturally limited in ways that matter for production workloads...
Why Pod Rightsizing Fails in Production: A Deep Dive into VPA and What Actually Works
Nic Vermandé
The Cost of Stagnation Kubernetes has evolved through three eras: survival (get ...
GKE Cost Optimization: How to Cut Kubernetes Spend at Scale in 2026
Rob Croteau
Google Kubernetes Engine (GKE) is the default Kubernetes platform for many produ...
AKS Pricing Explained: 10 Best Practices to Cut Kubernetes Costs on Azure
Konstantin Zelmanovich
Azure Kubernetes Service (AKS) removes much of the operational heavy lifting of ...
AI Infra for Production: Why GPU Resource Management in Kubernetes Demands a New Approach
Nic Vermandé
Kubernetes was never designed for the realities of real-time, production inferen...
What Is Amazon EKS Cost Optimization? (And How to Actually Do It)
Daniel Kleinstein
Amazon Elastic Kubernetes Service (EKS) cost optimization is the process of mini...
GKE Workload Optimization: 9 Best Practices for Performance, Reliability, and Cost
Rob Croteau
Google Kubernetes Engine (GKE) enables users to easily create clusters, deploy a...
Kubernetes v1.35 Deep Dive: In-Place Resize GA, Gang Scheduling & the Cgroup v2 Cliff
Nic Vermandé
Kubernetes 1.34 gave us the building blocks: DRA went GA, PSI metrics landed in ...
ScaleOps Is Now FIPS-Compatible for FedRAMP Environments
Yuval Nelinger
ScaleOps is now FIPS-compatible, enabling secure deployment inside FedRAMP-certi...