GPU is becoming attractive around multiple academic and industrial area because of its massively parallel computing ability. However, there are still some obstacles which the GPU virtualization technologies should overcome to reach their maturity. These obstacles mainly include the problem of resource allocation strategy to guarantee possible higher yield. This shortage has already become an obvious barrier to the practical GPU usage in the cloud for satisfying business and academical requirements. There are many mature pieces of research in the area of oversubscribed cloud computing to enhance economic efficiency. However, the study on GPU oversubscription is almost blank for the just started use of GPU in cloud computing. This paper introduces gOver, an economy-oriented GPU resource oversubscription system based on the GPU virtualization platform. gOver is able to share and modulate GPU resource among workloads in an adaptive and dynamic manner, guaranteeing the QoS level at the same time. We evaluate the proposed gOver strategy with designed experiments with specific workload characteristics. The experimental results show that our dynamic GPU oversubscription solution improves the economic efficiency by 20% over traditional GPU sharing strategy, and outperforms the static oversubscription method by much better stability in QoS control.

From the perspective of economic and efficient benefits, modern data center oversubscribes power supplies to deploy as many servers as possible. The oversubscription is based on the varied loads among servers to modulate power demand. Nevertheless, power oversubscription has potential threats to system availability, the data center may collapse as a result of overloading. Current solutions to the oversubscription usually focus on managing the datacenter workload to avoid the peak power demand time in the data center. However, none of the current research considers the influence of the failure of the power or utility components, where the component failure may affect the effectiveness of these strategies. Meanwhile, none of these current research can answer the question that how many servers should be deployed in the data centers under an availability constraint. In this paper, we propose quantitative availability analysis of hierarchical datacenter under power oversubscription. To this end, we use Markov chain and Stochastic Reward Net (SRN) to model the failure and repair processes of data center components. The servers at the bottom level are distributed in two pools: main pool and backup pool, where running servers are in main pool and turned-off servers in backup pool. Migration from backup pool to main pool is conducted once any running server fails. SRNs are implemented to model these two pools, and Markov chain is used to model the components in the upper level. The evaluation is based on the real-life Google and Wikipedia traces. The result shows the relationship between oversubscription and data center availability, which can guide the data center operators to choose the appropriate oversubscription ratio under the availability constraint.