Matt Riesz

"Fault Tolerant Computers"

MEETING DATE: March 16, 2012

Fault tolerant computers are all around us, but most of us never know it. Matt will talk about what fault tolerant computing is, who uses it, why you should care and how it works.  While many of us might consider this a bit esoteric, we’ll see that we have all touched and used a fault tolerant computer in our daily lives. Think about your desktop or laptop computer, whatever that may be, and think how often you shut it down either intentionally or unintentionally. How long does that take you and how often does it happen? Then imagine that your computer was being used to drive automated teller machines, or handle electronic healthcare records for a hospital, or perhaps handling connection services for cell phones. What would happen if that application were unavailable for several minutes or longer?

Matt will talk about where fault tolerant computers are used, and shed some light on the cost of downtime to businesses. There are many causes of downtime and the most significant of these have changed over time as computer technology has evolved.  He will discuss some of the differences between fault tolerant computing and high availability computing, and the architectures of the computer systems that implement these. He will talk about some of the things that must be taken into consideration when designing a fault tolerant computer system, and provide detail about some of the techniques used in HP’s NonStop™ Computer Systems and how they contribute to fault tolerance.

Finally, Matt will talk about the emerging technology of Cloud Computing and the importance fault tolerance plays in that environment.