Surprising results on task assignment in server farms with high-variability workloads
Proceedings of the eleventh international joint conference on Measurement and modeling of computer systems
Why segregating short jobs from long jobs under high variability is not always a win
Allerton'09 Proceedings of the 47th annual Allerton conference on Communication, control, and computing
Review: Task assignment policies in distributed server systems: A survey
Journal of Network and Computer Applications
| Hi-index | 0.00 |
Size-based load distribution approaches are proposed todeal with high variation of task size. One of the most criticalproblem of these approaches is that they do not considertask deadlines (which if not met may cause task starvation).This paper proposes an extension of our early work on dynamicload balancing [8, 7, 2] (called LFF) which takesthe relative processing time of a task into account and dynamicallyassigns it to the fittest server with a lighter loadand higher processing capacity. LFF-PRIORITY dynamicallycomputes the task size priority and task deadline priorityand puts them in a priority based multi-section queue.The testing results clearly show that LFF-PRIORITY outperforms existing load distribution strategies. More importantly,more than 80% of tasks meet their task deadlinesunder LFF-PRIORITY strategy.