基于Kademlia协议的DHT网络的测量研究

针对目前缺乏对KAD网络节点特性研究的问题,对KAD网络的全域节点和局部域节点进行了测量和分析。首先,提出了新型分布式KAD爬行系统的架构,并利用该系统快速而完整地获取了KAD网络全域和特性域的节点信息。然后,对网络中的节点地理分布、节点ID前缀分布、存储节点前缀分布、存贮节点稳定性进行了研究和分析。最后,在分析的基础上,发现了KAD网络节点ID分布均匀、较不流行关键字的存贮节点与目标关键字的距离更近、网络中存贮节点比较稳定等特性。测量结果表明KAD网络的搜索机制是稳定而有效的。

A Measurement Study of the Kademlia-based DHT Network

In recent years, a large number of distributed hash tables have been proposed, but only very few of them have been applied actually. KAD, a Kademlia based DHT, is only an exception which is widely used in eMule peer-to-peer system, which has more than 1.5 million simultaneous users. The measurement of the network will be able to guidance for the designing of such systems, and improve the performance of the system. First of all, a novel distributed KAD crawler was introduced. Secondly, a distributed crawler was developed and the user information was crawled as much as possible. Finally, the characteristics of the network were analyzed and some interesting facts were discovered to prove the effectiveness of KAD network.