Super resource-managment for Grid Computing
Adrian Li Mow, Paul McKee · 2002
Grid computing has emerged as the new paradigm in distributed computing and has undergone significant developments over recent years. To realise the long term goal of the ‘Global Grid’ requires a convergence between commercial and technical Grid applications , from large scale computationally intensive applications to real-time services. More importantly the need arises for an infrastructure capable of supporting an ‘always on’ Grid service. In this context the provision of services across such large, distributed and heterogeneous platforms requires a distributed resource management mechanism with capabilities beyond traditional centralised management. Coupled with the challenges of scale are the complexities associated with the heterogeneity of shared platforms and tiered administrative domains. Resources in a fully Grid enabled environment will be administered locally and constrained by local policies, therefore higher level resource management systems have to accommodate for this dynamic availability. In this paper we discuss the challenges facing higher level resource management within a Grid environment, looking in particular at a distributed, self organised, approach to Grid resource management in a global context.