Hyperscaling Self-Service Infrastructure: Transitioning from Ticketing to Load-Balancing-as-a-Service at Criteo
At Criteo, we work at the cutting edge of commerce marketing, using Machine Learning and Artificial Intelligence to help our customers grow their businesses through hyper-relevant advertising. We run tens of thousands of servers, host containers that continuously move across data centers, and scale services through our managed APIs, with HAProxy playing a critical role across our fast-paced, event-driven infrastructure. This presentation will describe our journey to achieve load balancing served via a user-centric API in such a large and complex environment. We will share tricks and design considerations that helped us to go from a user intent expressed through an API to a scalable service running globally.
William Dauchy
SRE in load balancer team
William Dauchy has been an SRE at Criteo since 2016. After some time in the observability team, he is currently in charge of the load balancer team which handles all the traffic coming from Internet. The main target has been to automate and industrialise all components linked to the Criteo load balancers infrastructure. Before Criteo, William worked on the hosting platform of gandi.net.
Pierre Cheynier
SRE in load balancer team
Pierre Cheynier is a SRE at Criteo, a world leader in performance advertising. Since 2015, he mainly focuses on automating and industrialize a large retargeting platform, troubleshooting performance issues and developing API-driven systems for developers to operate their services at large scale. Prior to working at Criteo, Pierre worked in the IPTV field for a French ISP.