J Supercomput (2007) 42: 59–82 DOI 10.1007/s11227-006-0036-x Dimensioning and on-line scheduling in Lambda Grids using divisible load concepts Pieter Thysebaert · Bruno Volckaert · Marc De Leenheer · Filip De Turck · Bart Dhoedt · Piet Demeester Published online: 10 March 2007 © Springer Science+Business Media, LLC 2007 Abstract Due to the large amounts of data required to be processed by the typi- cal Grid job, it is conceivable that the use of optical transport networks in Grid de- ployment (hence the term “Lambda Grid”) will increase. The exact topology of the interconnecting network is obtained by solving a dimensioning problem, and the out- come of this strongly depends on both the expected workload characteristics and Grid scheduling policy. Solving this combined scheduling and dimensioning prob- lem using straightforward ILP modelling is cumbersome; however, for steady-state Grid operation, Divisible Load Theory (DLT) can yield scalable formulations of this problem. In this paper, the on-line hierarchical scheduling on a lambda Grid of workload ap- proaching the Grid’s capacity in a two-tier Grid mode of operation is studied. A num- ber of these algorithms are goal-driven, in the sense that target per-resource goals are obtained from the off-line solution to the Divisible Load model. We compare these on-line multiresource scheduling policies for different workloads, Grid interconnec- tion topologies and Grid parameters. We show that these algorithms perform well in the studied scenarios when compared to a fully centralized scheduling algorithm. Keywords Lambda Grids · Optical Transport Networks · Optimization · Divisible Load 1 Introduction The term Grid [1, 2] has been coined to refer to an aggregation of heterogeneous, possibly geographically dispersed resources of various types. These resources can be P. Thysebaert ( ) · B. Volckaert · M. De Leenheer · F. De Turck · B. Dhoedt · P. Demeester Department ofInformation Technology, Ghent University—IBBT—IMEC, Gaston Crommenlaan 8, 9050, Gent, Belgium e-mail: pieter.thysebaert@intec.ugent.be