Affiliation:
1. Devi Ahilya University, Indore, India
Abstract
This paper presents a toolkit for evaluation of resource management algorithms developed for Grid computing. This simulator named as EcoGrid and it is devised to support large number of resource or computing nodes and processes. Generally, grid simulators represent each resource using a thread that occupies large amount of space on the thread stack in main memory. However, EcoGrid models each node by an object instead of a thread. Memory space used by an object is much smaller than a thread, thus EcoGrid is highly scalable as compared to state-of-the-art simulators. EcoGrid is dynamically configurable and works with real as well as synthetic workloads. The simulator is bundled with a synthetic load generator that generates the workload using appropriate statistical distributions.
Subject
Computer Networks and Communications
Reference24 articles.
1. SETI@ home: an experiment in public-resource computing. Communications of the ACM, 45(11), 56-61. Sulistio, A., & Buyya, R. (2004, November). A grid simulation infrastructure supporting advance reservation.;D. P.Anderson;16th International Conference on Parallel and Distributed Computing and Systems (PDCS 2004),2002
2. Beberg, A. L., Ensign, D. L., Jayachandran, G., Khaliq, S., & Pande, V. S. (2009, May). Folding@ home: Lessons from eight years of volunteer distributed computing. In Parallel & Distributed Processing, 2009. IPDPS 2009. IEEE International Symposium on (pp. 1-8). IEEE.
3. Scalable Multi-purpose Network Representation for Large Scale Distributed System Simulation
4. Buyya, Rajkumar, and Manzur Murshed. “Gridsim: A toolkit for the modeling and simulation of distributed resource management and scheduling for grid computing.” Concurrency and computation: practice and experience 14.13‐15 (2002) (pp. 1175-1220).
5. Analysis of Scheduling and Replica Optimisation Strategies for Data Grids Using OptorSim