A Framework for Allocating Server Time to Spot and On-Demand Services in Cloud Computing

Xiaohu Wu, Francesco De Pellegrini, Guanyu Gao, Giuliano Casale
2019 ACM Transactions on Modeling and Performance Evaluation of Computing Systems  
Cloud computing delivers value to users by facilitating their access to servers in periods when their need arises. An approach is to provide both on-demand and spot services on shared servers. The former allows users to access servers on demand at a fixed price and users occupy different periods of servers. The latter allows users to bid for the remaining unoccupied periods via dynamic pricing; however, without appropriate design, such periods may be arbitrarily small since on-demand users
more » ... e randomly. This is also the current service model adopted by Amazon Elastic Cloud Compute. In this paper, we provide the first integral framework for sharing the time of servers between on-demand and spot services while optimally pricing spot service. It guarantees that on-demand users can get served quickly while spot users can stably utilize servers for a properly long period once accepted, which is a key feature to make both on-demand and spot services accessible. Simulation results show that, by complementing the on-demand market with a spot market, a cloud provider can improve revenue by up to 461.5%. The framework is designed under assumptions which are met in real environments. It is a new tool that other cloud operators can use to quantify the advantage of a hybrid spot and on-demand service, eventually making the case for operating such service model in their own infrastructures. Proof. The optimal spot price at t is some value in V t under which G(t) achieves the maximal value, by Lemma 4.2; hence, the proposition holds. At every slot t, the expression (6) could be used to decide the optimal spot price, and the corresponding procedure is presented in Algorithm 2: it checks every possible value in V t to see which can maximize the revenue function (3). A key feature of our algorithm is that such decisions are implementable in practice, since the CSP has full knowledge of all parameters in G(t) except the control parameter, i.e., the spot price π t , at every t. Running Spot and On-demand Services So far, we have shown in Sec. 3 and Sec. 4 an integral framework for running spot and on-demand services. Now, we explain how this framework works as a whole.
doi:10.1145/3366682 fatcat:4lhagfdyxjftdbg2ns37bclnyi