Online Scheduling of Multiprocessor Jobs with Idle Regulation

摘要

In this paper, we focus on on-line scheduling of multiprocessor jobs with emphasis on the regulation of idle periods in the frame of general list policies. We consider a new family of scheduling strategies based on two phases which successively combine sequential and parallel executions of the jobs. These strategies are part of a more generic scheme introduced in [6]. The main result is to demonstrate that it is possible to estimate the amount of resources that should remain idle for a better regulation of the load and to obtain approximation bounds.