Abstract
Optimizing cloud gaming experience is no easy task due to the complex tradeoff between gamer Quality of Experience (QoE) and provider net profit. We tackle the challenge and study an optimization problem to maximize the cloud gaming provider’s total profit while achieving just-good-enough QoE. Moreover, we conduct expeirments using a modern GPU and a cloud gaming platform to answer the following question: Are modern GPUs ready for cloud gaming? For the optimization problem, We conduct measurement studies to derive the QoE and performance models. We formulate and optimally solve the problem. The optimization problem has exponential running time, and we develop an efficient heuristic algorithm. We also present an alternative for- mulation and algorithms for closed cloud gaming services with dedicated in- frastructures, where the profit is not a concern and overall gaming QoE needs to be maximized. We present a prototype system and testbed using off-the- shelf virtualization software, to demonstrate the practicality and efficiency of our algorithms. Our experience on realizing the testbed sheds some lights on how cloud gaming providers may build up their own profitable services. Moreover, we conduct extensive trace-driven simulations to evaluate our pro- posed algorithms. The simulation results show that the proposed heuristic algorithms: (i) produce close-to-optimal solutions, (ii) scale to large cloud gaming services with 20000 servers and 40000 gamers, and (iii) outperform the state-of-the-art placement heuristic, e.g., by up to 3.5 times in terms of net profits. For the measurement study of modern GPU, the observations are different from earlier studies, our measurement results reveal several findings that are counter to common beliefs. First, with the latest GPU virtualization technique, shared GPUs may run faster than dedicated GPUs. Second, more context switches not necessarily lead to lower FPS (frame-per-second). In summary, we conclude that modern GPUs are powerful enough and can be shared by multiple GPU-intensive cloud games. Last, we present some sug- gestions for future cloud gaming platforms, e.g., the latest GPU servers may be CPU-bounded, which require the platforms to offload the video encoding from CPUs to dedicated codec chips for good gaming experience.