An Arbitrary 2D Structured Replica Control Protocol

Traditional replication protocols that logically arrange the replicas into a specific structure have reasonable availability, lower communication cost as well as system load than those that do not require any logical organisation of replicas. We propose in this paper the A2DS protocol: a single protocol that, unlike the existing proposed protocols, can be adapted to any 2D structure. Its read operation is carried out on any replica of every level of the structure whereas write operations are performed on all replicas of a single level of the structure. We present several basic 2D structures and introduce the new idea of obtaining other 2D structures by the composition of several basic ones. Two structures are proposed that have near optimal performance in terms of the communication cost, availability and system load of their read and write operations. Also, we introduce a new protocol that provides better performance for its write operations than those of ROWA protocol while preserving similar read performance.

[1]  David Peleg,et al.  The Availability of Quorum Systems , 1995, Inf. Comput..

[2]  Hee Yong Youn,et al.  Symmetric Tree Replication Protocol for Efficient Distributed Storage System , 2003, International Conference on Computational Science.

[3]  Philip A. Bernstein,et al.  An algorithm for concurrency control and recovery in replicated distributed databases , 1984, TODS.

[4]  Moni Naor,et al.  The Load, Capacity, and Availability of Quorum Systems , 1998, SIAM J. Comput..

[5]  Akhil Kumar,et al.  Hierarchical Quorum Consensus: A New Algorithm for Managing Replicated Data , 1991, IEEE Trans. Computers.

[6]  Mostafa H. Ammar,et al.  The Grid Protocol: A High Performance Scheme for Maintaining Replicated Data , 1992, IEEE Trans. Knowl. Data Eng..

[7]  Divyakant Agrawal,et al.  An efficient and fault-tolerant solution for distributed mutual exclusion , 1991, TOCS.

[8]  H ThomasRobert.  A Majority consensus approach to concurrency control for multiple copy databases , 1979 .

[9]  Rachid Guerraoui,et al.  An Arbitrary Tree-Structured Replica Control Protocol , 2008, 2008 The 28th International Conference on Distributed Computing Systems.

[10]  Robert H. Thomas,et al.  A Majority consensus approach to concurrency control for multiple copy databases , 1979, ACM Trans. Database Syst..

[11]  Henning Koch,et al.  An efficient replication protocol exploiting logical tree structures , 1993, FTCS-23 The Twenty-Third International Symposium on Fault-Tolerant Computing.

[12]  Mamoru Maekawa,et al.  A N algorithm for mutual exclusion in decentralized systems , 1985, TOCS.

[13]  Leslie Lamport,et al.  Reaching Agreement in the Presence of Faults , 1980, JACM.

[14]  Divyakant Agrawal,et al.  The Tree Quorum Protocol: An Efficient Approach for Managing Replicated Data , 1990, VLDB.