Service Migration in Distributed Virtual Machines for Adaptive Grid Computing

Computational grids can integrate geographically dis-tributed resources into a seamless environment. To facilitate managing these heterogenous resources, the virtual machine technology provides a powerful layer of abstraction and allows multiple applications to multiplex the resources of a grid com-puter. On the other hand, the grid dynamics requires the vir-tual machine system be distributed and reconfigurable. How-ever, the existing migration approaches only move the execution entities, such as processes, threads, and mobile agents, among servers and leave the runtime services behind. They are not po-tent to achieve service reconfiguration in face of server over-load or failures. In this paper, we propose a service migration mechanism, which moves the computational services of a vir-tual server, for instance a shared array runtime support system, to available servers for adaptive grid computing. In this way, parallel jobs can resume computation on a remote server with-out requiring service preinstallation. As an illustration of the service migration mechanism, we incorporated it into a Java-compliant distributed virtual machine, DSA, and formed a Mo-bile DSA (M-DSA) to accommodate adaptive parallel applica-tions in grids. We measured the performance of M-DSA in the execution of applications from the SPLASH-2 benchmark suite on a campus grid. Experimental results show that service mi-gration can achieve system adaptivity effectively.