1/k Phase Timestamping for Replica Consistency in Interactive Collaborative Applications

Interactive Collaborative applications, such as distributed virtual environments, collaborative CAD and multiplayer games, are enabled by the data being shared across distributed users. The need to support such applications in a wide-area environment, and at the same time provide fast response to users, motivates replication of this shared data. The key characteristics of this shared data include short, incremental atomic operations for modifying this data, and the application's ability to predeclare access information for these operations. This and certain other differences from conventional replicated databases, motivate a different architecture for algorithms maintaining replica consistency. The main architectural differences include a complete separation of timestamping (for consistently ordering the operations) and execution of operations, propagation of the operation itself (instead of its effect) and local commit. We describe a specific consistency algorithm which does 2 phase timestamping (analogous to 2 phase locking) by sequentially acquiring stamps for objects accessed by an operation. Then we show how to eliminate the shrink phase and reduce the grow phase by a factor of (when an operation accesses objects), by concurrently getting all the stamps. This new algorithm is deadlock free and does not abort any operations.

[1]  Atul Prakash,et al.  DistView: support for building efficient collaborative applications using replicated objects , 1994, CSCW '94.

[2]  Leslie Lamport,et al.  Time, clocks, and the ordering of events in a distributed system , 1978, CACM.

[3]  Atul Prakash,et al.  Concurrency control and view notification algorithms for collaborative replicated objects , 1997, Proceedings of 17th International Conference on Distributed Computing Systems.

[4]  André Schiper,et al.  Lightweight causal and atomic group multicast , 1991, TOCS.

[5]  Guruduth Banavar,et al.  Responsiveness and consistency tradeoffs in interactive groupware , 1998, PODC '98.

[6]  Gail E. Kaiser,et al.  Concurrency control in advanced database applications , 1991, CSUR.

[7]  Alain Karsenty,et al.  An algorithm for distributed groupware applications , 1993, [1993] Proceedings. The 13th International Conference on Distributed Computing Systems.

[8]  Divyakant Agrawal,et al.  Relative Serializability: An Approach for Relaxing the Atomicity of Transactions , 1997, J. Comput. Syst. Sci..

[9]  Clarence A. Ellis,et al.  Concurrency control in groupware systems , 1989, SIGMOD '89.

[10]  Partha Dasgupta,et al.  The five color concurrency control protocol: non-two-phase locking in general databases , 1990, TODS.

[11]  Mustaque Ahamad,et al.  The Design Space for Data Replication Algorithms in Interactive Groupware , 1998 .

[12]  R. Stephenson A and V , 1962, The British journal of ophthalmology.

[13]  Mustaque Ahamad,et al.  Flexible batching and consistency mechanisms for building interactive groupware applications , 1998, Proceedings. 18th International Conference on Distributed Computing Systems (Cat. No.98CB36183).