The optimization of HTTP packets reassembly based on multi-core platform

HTTP is the most popular application-layer protocol in the Internet. Improving the performance of HTTP packets reassembly is the key point of HTTP traffic analysis. In this paper, we first parallel the traditional serial HTTP packets reassembly system according to the HTTP protocol features. This optimization improves the throughput of packets reassembly system by 45% on the generic multi-core platform. Second, by considering the parallelization extra cost on the multi-core platform, we propose a new method to calculate system speedup based on the Amdahl´s law. Furthermore, we make a theoretical analysis to discuss the relationship between system speedup and throughput improvement and then we can estimate the upper bound on throughput improvement.