Performance modeling of big data applications in the cloud centers

Cloud computing has evolved as an efficient paradigm to process big data applications. Performance evaluation of cloud center is a necessary prerequisite to guarantee quality of service. However, it is a challenge task to effectively analyze the performance of cloud service due to the complexity of cloud resources and the diversity of big data applications. In this paper, we leverage queuing theory and probabilistic statistics to propose a performance evaluation model for cloud center under big data application arrivals. In this model, the tasks (i.e., big data applications) are with Poisson arrivals, each task is divided into lots of parallel subtasks, and the number of subtasks follows a general distribution. The model allows to calculate the important performance indicators such as mean number of subtasks in the system, the probability that a task obtains immediate service, task waiting time and blocking probability. The model can also be used to predict the time cost of performing application. Finally, we use the simulations and benchmarking running WordCount and TeraSort applications on a Hadoop platform to demonstrate the utility of the model.