Domain-Based Dynamic Resource Management Mechanism Supporting Large-Scale Grid Application

Abstract

A grid computing environment enables sharing of loosely coupled resources and services required by various applications in a large-scale. In such an environment, one of the key challenges is to develop a flexible, scalable, and self-adaptive resource management system which would allow users to carry out their jobs by transparently accessing autonomous, distributed, and heterogeneous resources. A Domain-based dynamic resource self maintain mechanism (DDRM) supporting large-scale distributed application is proposed. Grid distributed applications can be ensured to run regularly and stably by maintaining dynamic resource information, detecting abnormality and adjusting system timely. Conceptions of Monitoring Domain and domain agent are defined. Global resource view is acquired through resource pool and the corresponding triggering update algori-thm. Dynamic resource maintenance mechanism are adopted to handle resource abnormality. DDRM can scale to any large distributed application system with strong real-time and reliability. Finally, complexity and convergence time of DDRM are analyzed.