Addressing Resource Fragmentation in Grids through Network-Aware Meta-scheduling in Advance

Abstract

Grids are made of heterogeneous computing resources geographically dispersed where providing Quality of Service (QoS) is a challenging task. One way of enhancing the QoS perceived by users is by performing scheduling of jobs in advance, since reservations of resources are not always possible. This way, it becomes more likely that the appropriate resources are available to run the job when needed. One drawback of this scenario is that fragmentation appears as a well known effect in job allocations into resources and becomes the cause for poor resource utilization. So, a new technique has been developed to tackle fragmentation problems, which consists of rescheduling already scheduled tasks. To this end, some heuristics are implemented to calculate the intervals to be replanned and to select the jobs involved in the process. Moreover, another heuristic is implemented to put rescheduled jobs as close together as possible to minimize the fragmentation. This technique has been tested using a real test bed.