DATE: Monday, June 17, 2013
TIME: 1:15 - 2:15 pm
PLACE: CIC - 4th floor (ISTC Panther Hollow Room)

SPEAKER: Marcos K. Aguilera, Microsoft

TITLE: Detecting Remote Failures Intelligently in Distributed Systems

ABSTRACT:
Distributed systems often detect remote failures using an end-to-end timeout mechanism. We argue this mechanism is responsible for several practical and conceptual problems faced by distributed system developers today. We propose a better way to detect remote failures that eliminates these problems, based on a network of spies that provide inside information from various layers of the system. We describe the implementation and evaluation of this approach.

BIO:
Marcos received a Ph.D. from Cornell University in 2000. We has worked at Compaq's Systems Research Center and HP Labs. He is now a senior researcher at Microsoft Research Silicon Valley. His interests include distributed systems, distributed algorithms, fault tolerance, and storage systems.

HOST: Garth Gibson
VISITOR COORDINATOR: Jennifer Landefeld, jennsbl@cs.cmu.edu

SDI / ISTC SEMINAR QUESTIONS?
Karen Lindenfelser, 86716, or visit www.pdl.cmu.edu/SDI/