Traditionally, the "best effort, cost free" model of Supercomputers/Grids does not consider pricing. Clouds have progressed towards a service-oriented paradigm that enables a new way of service provisioning based on "pay-as-you-go" model. Large scale many-task workflow (MTW) may be suited for execution on Clouds due to its scale-* requirement (scale up, scale out, and scale down). In the context of scheduling, MTW execution cost must be considered based on users' budget constraints. In this paper, we address the problem of scheduling MTW on Clouds and present a budget-conscious scheduling algorithm, referred to as ScaleStar (or Scale-*). ScaleStar assigns the selected task to a virtual machine with higher comparative advantage which effectively balances the execution time-and-monetary cost goals. In addition, according to the actual charging model, an adjustment policy, refer to as DeSlack, is proposed to remove part of slack without adversely affecting the overall makespan and the total monetary cost. We evaluate ScaleStar with an extensive set of simulations and compare with the most popular HEFT-based LOSS3 algorithm and demonstrate the superior performance of ScaleStar.
展开▼
