Abstract
We present a new replication algorithm that supports repli- cation of a large number of objects on a diverse set of nodes. The algo- rithm allows replica sets to be changed dynamically on a per-object basis. It tolerates most types of failures, including multiple node failures, net- work partitions, and sudden node retirements. These advantages make the algorithm particularly attractive in large cluster-based data services that experience frequent failures and configuration changes. We prove the correctness of the algorithm and show that its performance is near- optimal.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Yair Amir. Replication using group communication over a partitioned network. PhD thesis, Hebrew University of Jerusalem, 1995.
Gaurav Banga, Fred Douglis, and Michael Rabinovich. Optimistic deltas for WWW latency reduction.In USENIX Annual Technical Conference, 1997.
P. Bernstein and E. Newcomer.Principles of Tranasction Processing. Morgan Kaufmann, 1997.
K. Birman and T. Joseph.Reliable communication in the presence of failures. ACM Trans, on Computer Systems, 5(1):272–314, February 1987.
Flaviu Christian and Frank Schmuck. Agreeing on processor group membership in asynchronous distributed systems.Technical Report CSE95-428, UC San Diego, 1995.
A. Demers, D. Greene, C. Hauser, W. Irish, and J. Larson. Epidemic algorithms for replicated database maintenance.In ACM Symp. on Princ. of Distr. Computing, pages 1–12,1987.
David K. Gifford. Weighted voting for replicated data. In 7th Symp. on Operating Systems Principles, pages 150–162,1979.
M. Harchol-Balter, T. Leighton, and D. Lewin. Resource discovery in distributed networks.In ACM Symp. on Princ. of Distr. Computing, pages 229–237,1999.
Maurice Herlihy. A quorum-consensus replication method for abstract data types. ACM Trans, on Computer Systems, 4(l):32–53, February 1986.
Peter J. Keleher. Decentralized replicated-object protocols. In 18th ACM Symp. on Princ. of Distr. Computing, April 1999.
Leslie Lamport. Time, clocks, and the ordering of events in a distributed system. Communications of the ACM, 21(7):558–565, July 1978.
Barbara Liskov, Liuba Shrira, and John Wroclawski. Efficient at-most-once mes-sages based on synchronized clocks. ACM Trans, on Computer Systems, 9(2): 125–142, 1991.
Microsoft. Windows 2000 Server Resource Kit. Microsoft Press, 2000.
David L. Mills. Improved algorithms for synchronizing computer network clocks. In SIGCOMM, pages 317–327, London, UK, September 1994. ACM.
P. V. Mockapetris and K. Dunlap. Development of the domain name system. In ACM SIGCOMM, August 1988.
K. Petersen, M. Spreitzer, D. Terry, M. Theimer, and A. Demers. Flexible update propagation for weakly consistent replication. In 16th Symp. on Operating Systems Principles, pages 288–301, October 1997.
M. Rabinovich, I. Rabinovich, and R. Rajaraman. Dynamic replication on the Internet. Technical Report HA6177000-980305-01-TM, AT&T Labs, March 1998.
David H. Ratner. Roam: A Scalable Replication System for Mobile and Distributed Computing. PhD thesis, UC Los Angeles, 1998. UCLA-CSD-970044.
Y. Saito, B. Bershad, and H. Levy. Manageability, availability and performance in Porcupine: a highly scalable, cluster-based mail service. In 17th Symp. on Operating Systems Principles, December 1999.
Yasushi Saito, Jeffrey Mogul, and Ben Verghese. A Usenet performance study. http://www.research.digital.com/wrl/projects/newsbench/, September 1998.
Robert Thomas. A majority consensus approach to concurrency control for multi-ple copy databases. ACM Trans, on Database Systems, 4(2): 180–209, June 1979.
R.van Renesse, Y. Minsky, and M. Hayden. A gossip-style failure detection service. In Middleware, 1998.
O. Wolfson and S. Jajodia. Distributed algorithms for adaptive replication of data. In 11th ACM Symp. on Princ. of Database Systems, pages 149–163, 1992.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Saito, Y., Levy, H.M. (2000). Optimistic Replication for Internet Data Services. In: Herlihy, M. (eds) Distributed Computing. DISC 2000. Lecture Notes in Computer Science, vol 1914. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-40026-5_20
Download citation
DOI: https://doi.org/10.1007/3-540-40026-5_20
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-41143-7
Online ISBN: 978-3-540-40026-4
eBook Packages: Springer Book Archive