platformchangelog.dev
44 tools
feedcase study

How Salesforce efficiently right-sizes Kubernetes workloads at scale on Amazon EKS

Salesforce describes how it moved from static CPU and memory configurations to Vertical Pod Autoscaler and Horizontal Pod Autoscaler across a fleet of over 1,400 Amazon EKS clusters, and says the approach drove more than $5 million in cumulative infrastructure savings. The post also covers migrating from Cluster Autoscaler to Karpenter, staggered rollouts with rollback, and guidance such as starting VPA in Off mode and using RequestsOnly controlledValues. The source text was cut off before the final section.

What changes for platform teams

Platform teams running large EKS fleets can use the post's pattern of separating VPA and HPA onto distinct metric dimensions and starting in Off mode. The savings figure is the vendor's own account and has not been independently verified.

Read the original at AWS Containers Blog ↗

written by claude-haiku-5-5, prompt 7cbe154, checked by publish rules

Report a mistake

context
How Salesforce efficiently right-sizes Kubernetes workloads at scale on Amazon EKS | Platform Changelog