A tcam - based two - dimensional prefix packet classification algorithm 的二維前綴報(bào)文分類算法
In this paper , we first do a systemic , detail research on all classical packet classification algorithms and analysis the time and space request of all algorithms , then forward three questions of the packet classification 本文首先對現(xiàn)有的各種報(bào)文分類算法進(jìn)行了系統(tǒng)、詳細(xì)的研究,并對各種算法的查找性能和存儲(chǔ)空間需求進(jìn)行了分析比較,分析總結(jié)出當(dāng)前報(bào)文分類領(lǐng)域面臨的三個(gè)問題。
This paper discuss the map process using the class equivalent class deeply and program to implement the three phases process . secondly , we introduce the principle and flow of the tuple space search base on the detail explaining of tuple space 接著本文在深入闡述tuplespace概念的基礎(chǔ)上介紹了元空間算法的原理和算法流程,該算法是目前適應(yīng)于大規(guī)模規(guī)則庫且支持快速更新的多域報(bào)文分類算法。
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 . 該方案包括以ndis協(xié)議驅(qū)動(dòng)程序?qū)崿F(xiàn)報(bào)文捕獲、以對bpf過濾器改進(jìn)和增強(qiáng)后的kpf為報(bào)文過濾器,以增加了規(guī)則更新能力的hypercuts算法為報(bào)文分類算法。
Finally , we introduce the concept of the rule subset and the multiple fields packet classification algorithms can make use of the fast ip routing search algorithms base on the new concept . so we put forward the field - divided classification algorithms in the ipv6 circumstance and the new algorithms need seven times to access memory in the worse case 最后考慮ipv6下的報(bào)文分類算法,本文引入了規(guī)則子集的概念,并利用該概念使多維報(bào)文分類可以利用現(xiàn)有的一維快速ip路由查找算法,提出了可適用于ipv6的分域查找算法,該算法在最壞情況下只需要7次訪存。
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 本文首先分析了從事網(wǎng)絡(luò)流量監(jiān)測研究的現(xiàn)實(shí)意義,并仔細(xì)研究了rtfm實(shí)時(shí)網(wǎng)絡(luò)流量測量模型,在此基礎(chǔ)上,歸結(jié)出了實(shí)現(xiàn)一個(gè)高性能的測量器將遇到的三個(gè)關(guān)鍵問題,即高速報(bào)文捕獲技術(shù)、報(bào)文過濾器實(shí)現(xiàn)技術(shù)和多維報(bào)文分類算法。
We put forward a principle of design multiple field packet classification algorithms base on the analyzing of the basic theory , algorithms structure and flow . now the speed of link is more and more high and the size of rule set is more and more large , it is difficult to design fast multiple field classification algorithms and the design principle is combine or improve the classical algorithms base on the analyzing the distributing law of the actual rule set 分析上述各種算法的基本思想、算法結(jié)構(gòu)及流程,本文總結(jié)出設(shè)計(jì)多域報(bào)文分類算法的原則:針對當(dāng)前鏈路速度不斷提高和規(guī)則庫規(guī)模不斷擴(kuò)大的現(xiàn)狀,設(shè)計(jì)快速的多域報(bào)文分類算法已經(jīng)成為一個(gè)技術(shù)難點(diǎn),一般的原則是在分析實(shí)際規(guī)則庫規(guī)則的分布規(guī)律地基礎(chǔ)上對現(xiàn)有的經(jīng)典算法進(jìn)行組合或者優(yōu)化改進(jìn)。