Back to the future: dependable computing = dependable services

ABSTRACT

Clients are coming to rely more and more on external services to meet the needs of their users, and the clients are increasingly simple caches of soft state -- "truth" is maintained elsewhere. As a result, the user experience of dependability is better served by making those services ultra-dependable than by increasing the reliability of an individual client. We explore here some of the consequences of this statement, and conclude that developing scalable, dependable services may be a more fruitful approach than an extreme emphasis on "dependable OSes". Along the way we look at quantifying "dependability" in this new world; some of what it takes to provide dependable, large-scale services; and some approaches that we are exploring to do so.

REFERENCES

• 1: Eric Anderson , Michael Hobbs , Kimberly Keeton , Susan Spence , Mustafa Uysal , Alistair C. Veitch, Hippodrome: Running Circles Around Storage Administration, Proceedings of the Conference on File and Storage Technologies, p.175-188, January 28-30, 2002
• 2: Rebecca Braynard, Dejan Kostić, Adolfo Rodriguez, Jeffrey Chase, and Amin Vahdat. Opus: an Overlay Peer Utility Service. In Proceedings of the 5th International Conference on Open Architectures and Network Programming (OPENARCH), June 2002.
• 3: Jeffrey S. Chase , Darrell C. Anderson , Prachi N. Thakar , Amin M. Vahdat , Ronald P. Doyle, Managing energy and server resources in hosting centers, Proceedings of the eighteenth ACM symposium on Operating systems principles, October 21-24, 2001, Banff, Alberta, Canada
• 4: Hewlett Packard Corporation. Utility Data Center. www.hp.com/solutions1/infrastructure/solutions/utilitydata/overview/, 2001.
• 5: Ian Foster, Carl Kesselman, Jeffrey Nick, and Steven Tuecke. The Physiology of the Grid: An Open Grid Services Architecture for Distributed Systems Integration, January 2002.
• 6: Patrick Goldsack. SmartFrog: a framework for configuration. In Large Scale System Configuration Workshop, November 2001.
• 7: John Wilkes, Traveling to Rome: QoS Specifications for Automated Storage System Management, Proceedings of the 9th International Workshop on Quality of Service, p.75-91, June 06-08, 2001
• 8: John Wilkes, Patrick Goldsack, G. (John) Janakiraman, Lance Russell, Sharad Singhal, and Andrew Thomas. eOS - The Dawn of the Resource Economy. Technical report, HP Laboratories, May 2001. Available from http://www.hpl.hp.com/ssp/papers.
• 9: Haifeng Yu and Amin Vahdat. Design and Evaluation of a Continuous Consistency Model for Replicated Services. In Proceedings of Operating Systems Design and Implementation (OSDI), October 2000.
• 10: Haifeng Yu and Amin Vahdat. Minimal Replication Cost for Availability. Technical report, Duke University, January 2002. Submitted for publication.