On the importance of migration for fairness in online grid markets

Until recently, only few grid and cluster systems provided preemptive migration (e.g. [4]), which is the ability of dynamically moving computational tasks across machines during runtime. The emergent technology of virtualization (e.g. [10]) provides off-the-shelf support for migration, thus making the use of this feature widely accessible. Existing literature largely neglects the close interrelationship between technical migration and economic fairness. In this paper we take a first step towards closing this gap. We present fairness and quality of service properties for economic online scheduling algorithms. Under mild assumptions we analytically show that it is impossible to achieve these properties without the use of migration. On the other hand, if zero cost migration is used, then these properties can be satisfied. In order to evaluate the effect of migration cost on the scheduling algorithm, we performed extensive empirical analysis based on real data. The results indicate that migration gives designers of economic online schedulers a tremendous pull on the algorithm’s fairness properties even in the presence of worst-case realistic migration cost.