| With the ongoing increase of network rate, extension of scale and diversity of application demands, the data flow becomes complex and changeable. All those posed higher and newer requirements on the management, security and maintenance of network. Network management software, firewall and monitoring systems, etc. all require the packet collection and packet classification in high speed. The implement methods of data collection and classification can be categorized into hardware and software ones by and large. As for the application of the small-scaled and low speed network, the hardware one is usually expensive and in long term, whereas the software one avoids all those shortcomings. This thesis basing on the development of IPNM flow monitoring subsystem, lucubrates the flow monitoring subsystem with integrative functions by purely using of software, in a purpose of establishing efficient and flexible infrastructure of network flow classification.This thesis firstly analyzed the significance of the research of the network flow monitoring, and carefully researches the mode of real-time network flow measurement. Basing on those studies, this thesis summarizes three key problems: high-speed network packet capture technology,packet filter technology and multidimensional packet classification algorithm respectively. After that, the thesis focuses on the solutions to the three problems. This solutions includes adopting the NDIS protocol driver as packet capture module , the KPF filter as packet filter which came from the revising and improving of the BPF filter, HyperCuts with rule updating ability as packet classification algorithm.. After having researched and implemented those key functions, this thesis proposes the general design, implementation and testing result of IPNM flow monitoring subsystem. As seen from the results, final implement of the subsystem has totally reached the function and performance requirements of IPNM platform to obtain network flow information. |
PDF Full Text Request