DATE: Thursday, October 30, 2014
TIME: 12:00 - 1:00 pm - NOTE NEW RESCHEDULED TIME
PLACE: RMCIC 4th Floor Panther Hollow Room
SPEAKER: Daniel Peek, Facebook
TITLE: An Introduction to Disaster Recovery at Facebook: Capacity
ABSTRACT:
Facebook recently completed a disaster recovery test, demonstrating the ability to run the site despite the loss of a datacenter region. In this talk, we’ll discuss the basic ideas behind disaster readiness and cover in depth the way we measure capacity. Load testing of a set of interconnected services in a safe and scalable way proved to be a powerful tool for measuring capacity and diagnosing bottlenecks and other inefficiencies.
BIO:
Daniel Peek is a software engineer at Facebook. For the last five years, he has been working on a variety of issues related to performance, availability, and consistency across geographically distributed data centers. Most recently, he has been working on disaster planning for Facebook infrastructure. He received a PhD from the University of Michigan in 2009 working on distributed file systems.
SDI / ISTC SEMINAR QUESTIONS?
Karen Lindenfelser, 86716, or visit www.pdl.cmu.edu/SDI/