September 19–20, 2016: Training
September 20–22, 2016: Tutorials & Conference
New York, NY

Designing large-scale distributed systems

1:30pm–5:00pm Tuesday, 09/20/2016
Average rating: ***..
(3.75, 4 ratings)

Prerequisite knowledge

  • Basic Unix, networking, and HTTP experience
  • What you'll learn

  • Build awareness of technologies and approaches for large-scale design
  • Description

    This tutorial offers attendees practical experience with the issues surrounding large-scale system design, presented by Andrea Spadaccini and other members of Google’s Site Reliability Engineering (SRE) team. You’ll learn how to take a problem such as “design imgur,” reason about what designs would be appropriate, figure out how to implement them (what is required in terms of machines, network bandwidth, how site reliability concerns influence the implementation, some discussion of distributed systems design patterns and Paxos, etc.), discuss this in group session, and communicate these suggestions to Andrea. Each group will have a facilitator to help keep things efficient. You’ll leave with stronger analysis skills and awareness of technologies and approaches for large-scale design.

    Photo of Andrea Spadaccini

    Andrea Spadaccini


    Andrea Spadaccini is a Dublin-based site reliability manager for Google. Andrea joined Google as an SRE working on the systems that distill, store, and serve all the metrics about Google’s Ads platforms. Previously, he worked on Linux-based PBX products, hacked on open source CPU simulators, and cofounded a nonprofit for students to get work experience while pursuing their studies. Andrea earned a PhD in computer engineering from the University of Catania, where he focused mostly on biometric recognition.