In multi-tier cloud service systems, performance evaluation relies on numerous experiments in order to collect key metrics such as resources usage. The approach may result in highly time-consuming in practice. In this paper, we propose an automated framework for performance tracking, data management and analysis to minimize human intervention in multitier cloud service systems. The framework support fine-grained analysis of the mixed workloads through the Discrete-time Markov-modulated Poisson process (DMMPP). A general multitier application is theoretically formulated as a queueing network to evaluate the performance. The effectiveness of the model has been validated through extensive experiments conducted in the RUBiS benchmark system.