The design of distributed systems involves the
partitioning of the system into components or partitions and the
allocation of these components to physical nodes. Techniques have
been proposed for both the partitioning and allocation process.
However these techniques suffer from a number of limitations. For
instance object replication has the potential to greatly improve the
performance of an object orientated distributed system but can be
difficult to use effectively and there are few techniques that support
the developer in harnessing object replication.
This paper presents a methodological technique that helps
developers decide how objects should be allocated in order to
improve performance in a distributed system that supports
replication. The performance of the proposed technique is
demonstrated and tested on an example system.
[1] G. C. Low and G. Rasmussen, "Partitioning and Allocation of Objects in
Distributed Application Development," Journal of Research and Practice
on Information Technology,, vol. 32, pp. 75-106, 2000.
[2] W. T. Chang and C. C. Tseng, "Clustering Approach to Grouping
Objects in Message-Passing Systems," Journal of Object Orientated
Programming, vol. 7, pp. 42-43, 46-50, 1995.
[3] S. Purao, H. K. Jain, and D. L. Nazareth, "Exploiting Design Information
to Derive Object Distribution Models," IEEE Transactions on Systems,
Man, and Cybernetics, vol. 32, pp. 320-334, 2002.
[4] S. M. Shatz, Development of Distributed Software: Concepts and Tools:
Macmillan Publishing, 1993.
[5] K. Efe, "Heuristic Models of Task Assignment Scheduling in Distributed
Systems," IEEE Computer, vol. 15, pp. 50 - 6, 1982.
[6] S. Ceri and P. G., Distributed Databases: Principles and Systems: Mc
Graw-Hill, 1984.
[7] A. M. Tamhankar and S. Ram, "Database Fragmentation and Allocation:
An Integrated Technique and Case Study," IEEE Transactions on
Systems, Man, and Cybernetics, vol. 28, pp. 288-305, 1998.
[8] K. Karlapalem and Q. Li, "A Framework for Class Partitioning in
Object-Oriented Databases," Distributed and Parallel Databases, vol. 8,
pp. 333-366, 2000.
[9] H. Barney, "Object Replication: a methodology for improving the
performance of object oriented systems," in School of Information
Systems, Technology and Management, vol. BSc. (Hons). Sydney:
UNSW, 2003, pp. 205.
[1] G. C. Low and G. Rasmussen, "Partitioning and Allocation of Objects in
Distributed Application Development," Journal of Research and Practice
on Information Technology,, vol. 32, pp. 75-106, 2000.
[2] W. T. Chang and C. C. Tseng, "Clustering Approach to Grouping
Objects in Message-Passing Systems," Journal of Object Orientated
Programming, vol. 7, pp. 42-43, 46-50, 1995.
[3] S. Purao, H. K. Jain, and D. L. Nazareth, "Exploiting Design Information
to Derive Object Distribution Models," IEEE Transactions on Systems,
Man, and Cybernetics, vol. 32, pp. 320-334, 2002.
[4] S. M. Shatz, Development of Distributed Software: Concepts and Tools:
Macmillan Publishing, 1993.
[5] K. Efe, "Heuristic Models of Task Assignment Scheduling in Distributed
Systems," IEEE Computer, vol. 15, pp. 50 - 6, 1982.
[6] S. Ceri and P. G., Distributed Databases: Principles and Systems: Mc
Graw-Hill, 1984.
[7] A. M. Tamhankar and S. Ram, "Database Fragmentation and Allocation:
An Integrated Technique and Case Study," IEEE Transactions on
Systems, Man, and Cybernetics, vol. 28, pp. 288-305, 1998.
[8] K. Karlapalem and Q. Li, "A Framework for Class Partitioning in
Object-Oriented Databases," Distributed and Parallel Databases, vol. 8,
pp. 333-366, 2000.
[9] H. Barney, "Object Replication: a methodology for improving the
performance of object oriented systems," in School of Information
Systems, Technology and Management, vol. BSc. (Hons). Sydney:
UNSW, 2003, pp. 205.
@article{"International Journal of Information, Control and Computer Sciences:62532", author = "H. T. Barney and G. C. Low", title = "Harnessing Replication in Object Allocation", abstract = "The design of distributed systems involves the
partitioning of the system into components or partitions and the
allocation of these components to physical nodes. Techniques have
been proposed for both the partitioning and allocation process.
However these techniques suffer from a number of limitations. For
instance object replication has the potential to greatly improve the
performance of an object orientated distributed system but can be
difficult to use effectively and there are few techniques that support
the developer in harnessing object replication.
This paper presents a methodological technique that helps
developers decide how objects should be allocated in order to
improve performance in a distributed system that supports
replication. The performance of the proposed technique is
demonstrated and tested on an example system.", keywords = "Allocation, Distributed Systems, Replication.", volume = "2", number = "4", pages = "1296-6", }