A General and Practical Datacenter Selection Framework for Cloud Services
Many cloud services nowadays are running on top of geographically distributed infrastructures for better reliability and performance. They need an effective way to direct the user requests to a suitable datacenter, depending on factors including performance, cost, etc. Previous work focused on efficiency and invariably considered the simple objective of maximizing aggregated utility. These approaches favor users closer to the infrastructure. In this paper, the authors argue that fairness should be considered to ensure users at disadvantageous locations also enjoy reasonable performance, and performance is balanced across the entire system. They adopt a general fairness criterion based on Nash bargaining solutions, and present a general optimization framework that models the realistic environment and practical constraints that a cloud faces.