BitTorrent网络节点间流量的数据采集和分析  

Data Collection and Analysis of Traffic Flow between Peers in BitTorrent Networks

作　　者：鄢羽[1] 唐红[1] 

机构地区：[1]重庆邮电大学计算机科学与技术学院,重庆400065

出　　处：《计算机科学》2014年第6期75-78,共4页Computer Science

基　　金：国家自然科学基金项目(6104004);国家科技重大专项(2012ZX03006001-004);国家973项目(2012CB315806);重庆市自然科学基金项目(CSTC.2009BA2089)资助

摘　　要：BitTorrent网络流量占据了互联网总流量的很大比例,吸引了大量专家学者的专注,然而现有实测工具无法实时记录BT网络中节点间的流量交互情况,有关真实BT网络中节点间流量的研究很少。建立了一个BT网络节点间流量的数据采集系统,将其部署在全球性实验平台Planetlab之后得到了真实数据,并验证了数据的正确性。通过对实测数据的分析和研究发现:(1)Tracker服务器在为各下载节点随机返回邻居节点列表时会受到各节点入网时间的影响;(2)50%以上的下载节点从种子处下载的数据为零,大部分下载节点的数据下载对种子的依赖性不大,从而深刻地体现出P2P应用模式的优越性。The fact that BitTorrent networks generate a large portion of the Internet traffic has attracted many experts to focus on it.Unfortunately,due to the existing tools＇ inability to measure dynamic volume of traffic between two individual peers,there＇s few research on the traffic flow between the peers in real BT networks.The authors designed an inter-peer traffic data collection system,got the real data after implementing it on the Planetlab platform and verified the data＇s correctness,analyzed the measured data and found that （1） the return of list of neighbor peers from Tracker server to a downloading peer will be affected by the peers＇ joining time into the network,（2） for 50％ or more peers,the downloaded data from the seed is zero,and for most peers,the downloading seldom depends on seed,which demonstrates the advantage of the P2P mechanism.

关 键 词：BITTORRENT网络 节点间流量 Tracker算法 邻居节点 种子 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]