Makoto Yoshida
ABSTRACT
Large scale loosely coupled PCs can organize a cluster and form the grid computing on sharing each processing power; power of PCs, code migration and transaction distribution characterize the performance of distributed systems. This paper describes object code migration control mechanism in large scale loosely coupled distributed systems. The prototype of the middleware which migrates object code for computing is implemented, and the tradeoff of code migration was observed. Based on these experiments, several simulations for large scale loosely coupled PC clusters were performed, and the methodology to control code migration to have stable response time in the system is derived. The mechanism for object code migration is proposed based on the results of the simulations. The result will be applied to design the grid computing systems and mobile systems to maintain the proper performance.
- Andrew S. Tanenbaum, Maarten Van Steen, Distributed Systems Principles and Paradigms 2nd Edition, Prentice Hall, 2007. Google Scholar
Digital Library
- M Yoshida, ct al, Time and Cost Evaluation of Multiple Copies of Data in Distributed Database Systems, IEEE Trans. on Software Engineering, Vol. SE-11, No. 9, September 1985. Google ScholarDigital Library
- K. Sakamoto, M. Yoshida, Design and Evaluation of Large Scale Loosely Coupled Cluster-Based Distributed Systems, IFIP International Conference on Network and Parallel Computing-PAMA Workshop, Dalian, China, September 2007. Google ScholarDigital Library
- Yu. H, Vahdat. A, Design and Evaluation of a Conit-Based Continuous Consistency Model for Replicated Services, ACM Trans. Comp. Syst., (20)3:239--282, 2002. Google ScholarDigital Library
- Srikumar Venugopal, Rajkumar Buyya, Kotagoro Ramamohanarao, A Taxonomy of Data Grids for Distributed Data Sharing, Management and Processing, ACM Computing Surveys, Vol. 28, March 2006. Google ScholarDigital Library
- Stephanos Androutsellis-Theotokis, Diomidis Spinellis, A Survey of Peer-to-Peer Content Distribution Technologies, ACM Computing Surveys, Vol. 36, No. 4, December 2004. Google ScholarDigital Library
- Ncil Daswani, Hector Garcia-Molina, Beverly Yang, Open Problems in Data-Sharing Peer-to-Peer Systems, Proc. 9th Int. Conf. On Database Theory, Siena, Italy, 2003. Google ScholarDigital Library
- Report of the NSF Workshop, Science of Design for Information Systems, SIGMOD Record, Vol. 33, No. 1, March 2004. Google ScholarDigital Library
- Valeria Cardellini, Emiliano Casalicchio, Michele Colajanni and Philip S. Yu, The state of the art in locally distributed Web-Server systems, ACM Computing Surveys, Vol. 34, No. 2, 2002. Google ScholarDigital Library
- Marta Patino-Martinez, Ricardo Jimencz-Peris, Bettina Kemme, and Gustavo Alonso, MIDDLE-R: Consistent database replication at the middleware level, ACT TOCS, Vol. 23, No. 4, 2005. Google ScholarDigital Library
- Sukumar Ghosh, Distributed Systems an Algorithmic Approach, Chapman&Hall/CRC, pp. 303--310, 2007.Google Scholar
- M. Tamer Ozsu, Patrick Valduriez, Pronciples of Distributed Database Systems, 2nd Edition, Prentice Hall, pp 99--104 1999. Google ScholarDigital Library
- Alonso R, Cava L, Sharing Jobs Among Independently Owned Processors, Proc. of the 8th ICDCS, 1988.Google Scholar
Index Terms
- Code migration control in large scale loosely coupled distributed systems
Recommendations
Improving the live migration process of large enterprise applications
VTDC '09: Proceedings of the 3rd international workshop on Virtualization technologies in distributed computingRecent developments in virtualisation technology have resulted in its proliferation of usage across datacentres. Ultimately, the goal of this technology is to more efficiently utilise server resources to reduce Total Cost of Ownership (TCO) by ...
Design and Evaluation of Large Scale Loosely Coupled Cluster-based Distributed Systems
NPC '07: Proceedings of the 2007 IFIP International Conference on Network and Parallel Computing WorkshopsLarge scale loosely coupled PCs can organize clusters and form the grid computing on sharing each processing power; power of PCs and code migration characterize the performance of distributed systems. This paper describes the performance evaluation of ...
Comments