DLC:可擴展式點對點查詢與資料分享架構

Abstract

近年來，隨著用戶端的設備日漸強悍，點對點的應用軟體也日漸普及，目前已有許多不同種類的點對點架構，然而大部分的架構都著重於資料查詢或者如何維護與其他用戶之間的溝通。往往沒有考慮到部分用戶端因被選為熱點(中繼點)而造成該用戶系統網路壅塞及效能低落。

本論文提出的DLC是修改自既有點對點架構Chord，試圖解決上述問題。另外，我們額外在查詢與傳輸著墨，試圖提升有效查詢、有效傳輸、減少網路資源浪費特別是針對熱門資料。

In recent years, as the end users’ equipments get more and more powerful, the peer- to-peer applications become more and more popular. There are many different kinds of peer-to-peer architectures. However, most of them only focus on how to search data and/or how to maintain neighbor relations. Unfortunately, some hosts selected to be hot points (via points) may result in low performance due to heavy overhead. In order to solve these problems, we propose a new P2P architecture, called DLC, that base on Chord. In DLC, we pay more attention to the transmission and search over this logical topology. Experimental results show that our approach can improve the efficiency of query and data transmission and thus reduce the network resources consumption, especially for popular data.