Exploiting Our Computational Surroundings for Better Mobile Collaboration

Mobile collaborative environments, being naturally loosely-coupled, call for optimistic replication solutions in order to attain the requirement of decentralized highly available access to data. However, such connectivity assumptions are also a decisive hindrance to the ability of optimistic replication protocols to rapidly guarantee consistency among the set of loosely-coupled replicas. This paper proposes the extension of conventional optimistic replication protocols to exploit the presence of extraneous nodes surrounding the group of replica nodes in an increasingly ubiquitous computational universe. In particular, we show that using such extra nodes as temporary carriers of lightweight consistency meta-data may significantly improve the efficiency of a replicated system; notably, it reduces commitment delay and conflicts, and allows more network-efficient propagation of updates. We support such a statement with experimental results obtained from a simulated environment.

[1]  P. Cederqvist,et al.  Version Management with CVS , 1993 .

[2]  Darrell D. E. Long,et al.  MODELING REPLICA DIVERGENCE IN A WEAK-CONSISTENCY PROTOCOL FOR GLOBAL-SCALE DISTRIBUTED DATA BASES , 1993 .

[3]  Peter J. Keleher,et al.  Decentralized replicated-object protocols , 1999, PODC '99.

[4]  Yasushi Saito,et al.  Optimistic replication , 2005, CSUR.

[5]  Antony I. T. Rowstron,et al.  The IceCube approach to the reconciliation of divergent replicas , 2001, PODC '01.

[6]  Mahadev Satyanarayanan,et al.  Disconnected Operation in the Coda File System , 1999, Mobidata.

[7]  João Pedro Barreto,et al.  An Efficient and Fault-Tolerant Update Commitment Protocol for Weakly Connected Replicas , 2005, Euro-Par.

[8]  David Saff,et al.  Footloose: a case for physical eventual consistency and selective conflict resolution , 2003, 2003 Proceedings Fifth IEEE Workshop on Mobile Computing Systems and Applications.

[9]  Mark Weiser.  The computer for the 21st century , 1991 .

[10]  Hector Garcia-Molina,et al.  Consistency in a partitioned network: a survey , 1985, CSUR.

[11]  Alley Stoughton,et al.  Detection of Mutual Inconsistency in Distributed Systems , 1983, IEEE Transactions on Software Engineering.

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

[13]  Doug Terry,et al.  Epidemic algorithms for replicated database maintenance , 1988, OPSR.

[14]  Jehan-François Pâris.  A highly available replication control protocol using volatile witnesses , 1994, 14th International Conference on Distributed Computing Systems.

[15]  Marvin Theimer,et al.  Flexible update propagation for weakly consistent replication , 1997, SOSP.

[16]  Vincent P. Laviano,et al.  The Roma Personal Metadata Service , 2000, Mob. Networks Appl..

[17]  Brian D. Noble,et al.  Fast reconciliations in fluid replication , 2001, Proceedings 21st International Conference on Distributed Computing Systems.

[18]  Magnus Karlsson,et al.  Taming aggressive replication in the Pangaea wide-area file system , 2002, OPSR.

[19]  M. Weiser.  The Computer for the Twenty-First Century , 1991 .

[20]  Peter L. Reiher,et al.  Rumor: Mobile Data Access Through Optimistic Peer-to-Peer Replication , 1998, ER Workshops.

[21]  Lei Gao,et al.  PRACTI Replication , 2006, NSDI.

[22]  Zygmunt J. Haas,et al.  A Sensor Network for Biological Data Acquisition ∗ , 2004 .