Abhijeet Rastogi, LinkedIn
Do you serve customers across the world with varying network conditions? Do you struggle with automatically sending your users away from an unavailable POP/DC to the next best one? Wouldn’t it be great if you magically knew about the regional issues related to last mile connectivity from the users?
LinkedIn uses real user measurements backed by triple-vendor DNS. These measurements are collected from members’ browsers to gain insight into our performance from every last mile. We then leverage Big Data to send members to closest edges in real-time and deliver fast member experience.
LinkedIn members from Mumbai visiting LinkedIn will be sent to our Mumbai POP using member’s geolocation. If the POP is unreachable, member browsers elsewhere will report this to our RUM backend and our DNS will learn to stop resolving to the unreachable POP - all within a matter of a few seconds.
Attendees will learn about:
- Web Performance: CDNs, POPs, RUM steering
- Multi-vendor strategy for redundancy & performance
- Tools for cross-vendor consistency, vendor fail-out, global site monitoring & status boards
Abhijeet has been working with LinkedIn for around 2.5 years and a total of 5 years as an SRE. He joined LinkedIn with experience of architecting VPS hosting using OpenStack and hosting email infrastructure at scale. He has worked on managing DNS, CDN and Traffic infrastructure at LinkedIn.
He has been a contributor to Logstash and his current favorite language is Golang. In his free time, he tries to find reasons for writing more Golang code to make his life easier.
Open Access Media
USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.