Catalog

Netflix operates at full active across four AWS Regions, serving their global traffic by intelligently steering users and managing costs via thousands of auto scaling compute server groups. At various times, traffic surges hit their service that could exceed capacity. In this session, walk through how Netflix solves these problems by pairing predictive automated pre-scaling with fast reactive auto scaling in combination with advanced resilience techniques like prioritized load shedding, cross-Region traffic shifting, targeted capacity injection by service criticality, and more. Discover how to maintain a low level of spend while being ready for sudden load spikes.