An Efficient Resource Discovery Methodology for HPGRID Systems

Abstract

An efficient resource discovery mechanism is one of the fundamental requirements for grid computing systems, as it aids in resource management and scheduling of applications. Resource discovery activity involves searching for the appropriate resource types that match the user’s application requirements. Classical approaches to Grid resource discovery are either centralized or hierarchical, and it becomes inefficient when the scale of Grid systems increases rapidly. On the other hand, the Peer-to-Peer (P2P) paradigm emerged as a successful model as it achieves scalability in distributed systems. Grid system using P2P technology can improve the central control of the traditional grid and restricts single point of failure. In this paper, we propose a new approach based on P2P techniques for resource discovery in grids using Hypercubic P2P Grid (HPGRID) topology connecting the grid nodes. A scalable, fault-tolerant, self-configuring search algorithm is proposed as Parameterized HPGRID algorithm, using isomorphic partitioning scheme. By design, the algorithm improves the probability of reaching all the working nodes in the system, even in the presence of non-alive nodes (inaccessible, crashed or nodes loaded by heavy traffic). The scheme can adapt to a complex, heterogeneous and dynamic resources of the grid environment, and has a better scalability