Towards to virtual infrastructure allocation on multiple IaaS providers with survivability and reliability requirements

Abstract

The diversity of services, prices, and geographical footprints has turned the clouds into a complex and heterogeneous environment. Moreover, the survivability and reliability aspects are often disregarded by tenants, eventually resulting in heavy losses due to unavailability of services that are hosted on Virtual Infrastructures (VIs). We present an alternative to improve Vis' survivability and reliability, which considers the use of replicas and the spreading of virtual resources atop providers, regions, and zones. We formulate the VI allocation with survivability and reliability requirements as a mixed integer program, and three strategies to solve the formulation are proposed. First, the binary constraints are relaxed to obtain a Linear Program (LP), and the LP solution is given as input for the simulated annealing technique. Then, two GPU-accelerated algorithms are proposed to speed up the allocation of large-scale scenarios. Simulation with different reliability requests indicate an increasing in survivability without inflating costs.