Stanford EE Computer Systems Colloquium

4:15PM, Wednesday, April 14, 2010
HP Auditorium, Gates Computer Science Building B01
http://ee380.stanford.edu

RAMCloud: Scalable High-Performance Storage Entirely in DRAM

John Ousterhout
tanford University
About the talk:

Disk-oriented approaches to online storage are becoming increasingly problematic: they do not scale gracefully to meet the needs of new large-scale Web applications, and improvements in disk capacity have out-stripped improvements in access speed. In this talk I will describe a new approach to datacenter storage called RAMCloud, where information is kept entirely in DRAM and large-scale systems are created by aggregating the main memories of thousands of commodity servers. A RAMCloud can provide durable and available storage with 100-1000x the throughput of disk-based systems and 100-1000x lower access latency. By combining low latency and large scale, RAMClouds will enable a new class of applications that manipulate large datasets more intensively than has ever been possible.

Paper:

Download the associated paper in PDF format.

Slides:

There is no downloadable version of the slides for this talk available at this time.

About the speaker:

John Ousterhout received a BS in Physics from Yale University in 1975 and a PhD in Computer Science from Carnegie Mellon University in 1980.

From 1980-1994 he was a Professor of Computer Science at the University of California, Berkeley. His research projects included design tools for integrated circuits such as the Magic layout editor and the Crystal timing analyzer, the Sprite network operating system, log-structured file systems, and the Tcl scripting language and Tk toolkit.

In 1994 John left Berkeley to fulfill a long-standing desire to build commercial software. From 1994-1998 he was a Distinguished Engineer at Sun Microsystems Laboratories. In 1998 he founded Scriptics Corporation to commercialize Tcl development tools, where he was CEO until 2000. In 2002 he founded Electric Cloud, where he worked until 2007. At Electric Cloud he led the development of a parallel build system (ElectricAccelerator) and a Web-based server for managing distributed processes such as nightly builds and automated tests (ElectricCommander).

In 2008 John returned to academia as Professor (Research) in the Department of Computer Science at Stanford University.

Ousterhout is a member of the National Academy of Engineering and a Fellow of the ACM. He has won numerous awards, including the ACM Software System Award, the ACM Grace Murray Hopper Award, the National Science Foundation Presidential Young Investigator Award, and the U.C. Berkeley Distinguished Teaching Award.

Contact information:

John K. Ousterhout
Computer Science Department
Stanford University
email: ouster (at) cs . stanford . edu