FAST '04 Abstract
Pp. 59-72 of the Proceedings
Designing for disasters
Kimberley Keeton, Cipriano Santos, and Dirk Beyer, Hewlett-Packard Laboratories; Jeffrey Chase, Duke University; John Wilkes, Hewlett-Packard Laboratories
Losing information when a storage device or data center fails can bring a company to its kneesor put it out of business altogether. Such catastrophic outcomes can readily be prevented with today's storage technology, albeit with some difficulty: the design space of solutions is surprisingly large, the configuration choices are myriad, and the alternatives interact in complicated ways. Thus, solutions are often over- or under-engineered, and administrators may not understand the degree of dependability they provide.
Our solution is a tool that automates the design of disaster-tolerant solutions. Driven by financial objectives and detailed models of the behaviors and costs of the most common solutions (tape backup, remote mirroring, site failover, and site reconstruction), it appropriately selects designs that meet its objectives under specified disaster scenarios. As a result, designing for disasters no longer needs to be a hit-or-miss affair.
- View the full text of this paper in HTML and
Until March 2005, you will need your USENIX membership identification in order to access the full papers. The Proceedings are published as a collective work, © 2004 by the USENIX Association. All Rights Reserved. Rights to individual papers remain with the author or the author's employer. Permission is granted for the noncommercial reproduction of the complete work for educational or research purposes. USENIX acknowledges all trademarks within this paper.
- If you need the latest Adobe Acrobat Reader, you can download it from Adobe's site.