K网络节点标识符重复与别名现象测量  

Measuring the Identifier Repetition and Aliasing Phenomena in K Networks

作　　者：刘祥涛[1,2] 李文法[3] 段洣毅[2] 赵新昱[3] 季统凯 

机构地区：[1]广东电子工业研究院,广东东莞523808 [2]中国科学院计算技术研究所,北京100190 [3]北京交通大学计算技术研究所,北京100029

出　　处：《计算机研究与发展》2012年第4期679-690,共12页Journal of Computer Research and Development

基　　金：国家"八六三"高技术研究发展计划基金项目(2011AA040506);广东省中国科学院全面战略合作项目(2011A090100003)

摘　　要：为方便P2P网络的内容投递,Kademlia协议作为一个鲁棒性强的分布式Hash表协议,被BitTorrent和eMule等P2P文件共享应用部署.在此,将这些被部署的基于Kademlia协议的网络称为K网络.K网络中每个节点拥有唯一的IP地址(或ID)是至关重要的,因为K网络中的"节点查询"和"资源搜索"都依赖于此.然而,据分析发现,K网络中相当一部分节点存在IP重复与ID别名.为深入理解IP重复与ID别名的分布特征,提出了几个度量IP重复与ID别名的测度.基于这些测度和Rainbow采集器,对K网络中的IP重复与ID别名进行了测量,发现了许多有助于P2P网络挖掘研究的IP重复与ID别名特征.Kademlia,as a robust distributed Hash table（DHT） protocol,has been deployed by peer-to-peer（P2P） file sharing applications（e.g.BitTorrent and eMule） to facilitate the delivery of content.In this paper,these Kademlia-based networks deployed by BitTorrent and eMule are called K networks.It is essential for each peer in K networks to possess a unique IP address（or ID）,on which both ＂peer lookup＂ and ＂resource searching＂ rely.However,it is noticed that a significant portion of peers have IP repetition and ID aliasing,through our analysis.In this paper,we propose a couple of metrics to deeply understand the distribution characteristics of IP repetition and ID aliasing.Based on these metrics,we carry out a series of measurement using the P2P crawler named Rainbow.We identify many interesting characteristics of IP repetition and ID aliasing in K networks,which could help promote P2P-network mining.

关 键 词：对等网络 KADEMLIA协议 网络测量 IP重复 ID别名 

分 类 号：TP393.02[自动化与计算机技术—计算机应用技术]