This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Multiclass Replicated Data Management: Exploiting Replication to Improve Efficiency
February 1994 (vol. 5 no. 2)
pp. 121-138

Research efforts in replication-control protocols primarily use replication as a means ofincreasing availability in distributed systems. It is well-known, however, that replicationcan reduce the costs of accessing remotely-stored data in distributed systems. Wecontribute a classification of replicas and a replication-control protocol which introducethe availability benefits of replication and, at the same time, exploit replication to improve performance, by reducing response time. Each replica class has different consistency requirements. Metareplicas keep track of up-to-date replicas for recently-accessed objects and help exploit data-reference localities. Thus they allow many transaction operations to execute synchronously at only a single (and often local) replica.Pseudoreplicas are nonpermanent replicas that facilitate "localized execution" oftransaction operations. True replicas are ordinary, permanent replicas as used in otherreplication schemes. For many commonly occurring replication scenarios, the protocoloutperforms both replication-control protocols in the literature and nonreplicatedsystems, while offering the availability benefits of replication.

[1] D. Agrawal and A. El Abbadi, "The tree quorum protocol: An efficient approach for managing replicated data," inProc. Int. Conf. Very Large Data Bases, Aug. 1990, pp. 243-254.
[2] P. A. Bernstein and N. Goodman, "The failure and recovery problem for replicated databases," inProc. 2nd Ann. Symp. Principles of Distributed Computing, 1983, pp. 114-122.
[3] P. A. Bernstein and N. Goodman, "An algorithm for concurrency control and recovery in replicated distributed databases,"ACM Trans. Database Syst., vol. 9, no. 4, pp. 596-615, Dec. 1984.
[4] P.A. Bernstein, V. Hadzilacos, and N. Goodman,Concurrency Control and Recovery in Database Systems, Addison-Wesley, Reading, Mass., 1987.
[5] D. Davcev and W. Burkhard, "Consistency and recovery control for replicated files," inProc. 10th Symp. Operating System Principles, Orcas Island, WA, Dec. 1985, pp. 87-96.
[6] D. Duchamp, "Analysis of Transaction Management Performance,"Proc. 12th ACM Symp. Operating Systems Principles, ACM, New York, 1989, pp. 177-190.
[7] A. El Abbadi and S. Toueg, "Maintaining availability in partitioned replicated databases,"ACM Trans. Database Syst., vol. 14, no. 2, pp. 264-290, June 1989.
[8] B. Gavish and O. R. Liu Sheng, "Dynamic file migration in distributed computer systems,"Commun. ACM, vol. 33, no. 2, pp. 177-189, Feb. 1990.
[9] D. Gifford, "Weighted voting for replicated data," inProc. 7th ACM Symp. Oper. Syst. Principles, Dec. 1979, pp. 150-162.
[10] M. A. Greer, "Performance measurement of remote IPC," M. Math thesis, Dept. of Comput. Sci., Univ. of Waterloo, 1989.
[11] M. P. Herlihy, "A quorum-consensus replication method for abstract data types,"ACM Trans. Comput. Syst., vol. 4, no. 1, Feb. 1986.
[12] S. Jajodia and D. Mutchler, "A hybrid replica control algorithm combining static and dynamic voting,"IEEE Trans. Knowledge Data Eng., vol. 1, no. 4, pp. 459-469 Dec. 1989.
[13] T. Joseph and K. Birman, "Low cost management of replicated data in fault tolerant distributed systems,"ACM Trans. Comput. Syst., vol. 4, pp. 54-70, 1986.
[14] J.P. Kearns and S. DeFazio, "Diversity in Database Reference Behavior,"Performance Evaluation Review, Vol. 15, No. 1, May 1989, pp. 11-19.
[15] A. Kumar, "Hierarchical quorum consensus: A new algorithm for managing replicated data,"IEEE Trans. Comput., vol. 40, no. 9, pp. 996-1004, Sept. 1991.
[16] B. Lampson, "Atomic transactions," inDistributed Systems: Architecture and Implementation(Lecture Notes in Computer Science, vol. 105). Berlin: Springer-Verlag, 1981, pp. 246-265.
[17] T. Mann, A. Hisgen, and G. Swart, "An algorithm for data replication," Digital Syst. Res. Center Res. Rep. 46, June 1989.
[18] C. Mohan, B. Lindsay, and R. Obermarck, "Transaction management in the R*distributed database management system,"ACM Trans. Database Syst., vol. 11, Dec. 1986.
[19] S. Mullender et al.,Distributed Systems, ACM Press, New York, 1989.
[20] B. Oki and B. Liskov, "Viewstamped replication: A new primary copy method to support highly-available distributed systems," inProc. Seventh ACM Symp. Principles Distributed Comput., Aug. 1988, pp. 8-17.
[21] C.H. Papadimitriou, "The serializability of concurrent database updates,"J. ACM, vol. 26, pp. 631-653, Oct. 1979.
[22] J-F. Paris, "Voting with witnesses: A consistency scheme for replicated files, " inProc. 6th Int. Conf. Distributed Computing Syst., May 1986, pp. 606-612.
[23] C. Pu, J. D. Noe, and A. B. Proudfoot, "Regeneration of replicated objects: A technique and its Eden implementation,"IEEE Trans. Software Eng., vol. SE-14, no. 7, pp. 936-945, July 1988.
[24] A. Siegel, K. Birman and K. Marzullo, "Deceit: A flexible distributed file system," presented at theProc. USENIX Summer Conf., June 1990.
[25] C. D. Tait and D. Duchamp, "Service interface and replica management algorithm for mobile file system clients," inProc. 1st Int. Conf. Parallel and Distributed Inform. Syst., Dec. 1991, pp. 190-197.
[26] P. Triantafillou and D. J. Taylor, "A new paradigm for high availability and efficiency in replicated distributed databases," inProc. 2nd IEEE Symp. Parallel and Distributed Processing, Dec. 9-13, 1990, pp. 136-143.
[27] P. Triantafillou and D. J. Taylor, "Efficiently maintaining availability in the presence of partitionings in distributed systems," inProc. IEEE 7th Int. Conf. on Data Eng., Apr. 8-12, 1991, pp. 34-41.
[28] P. Triantafillou, "Employing replication to achieve efficiency and high availability in distributed systems," Ph.D. thesis, Univ. of Waterloo, July 1991. (Available as Res. Rep. CS-91-28.)

Index Terms:
Index Termsprotocols; distributed databases; concurrency control; transaction processing; multiclassreplicated data management; replication-control protocols; distributed systems; responsetime; data-reference localities; pseudoreplicas
Citation:
P. Triantafillou, D.J. Taylor, "Multiclass Replicated Data Management: Exploiting Replication to Improve Efficiency," IEEE Transactions on Parallel and Distributed Systems, vol. 5, no. 2, pp. 121-138, Feb. 1994, doi:10.1109/71.265941
Usage of this product signifies your acceptance of the Terms of Use.