Lad Mohit, Massey Dan, Zhang Lixia
Computer Science Department, University of California, Los Angeles 90095-1596, USA.
IEEE Trans Vis Comput Graph. 2006 Nov-Dec;12(6):1450-60. doi: 10.1109/TVCG.2006.108.
Today's Internet provides a global data delivery service to millions of end users and routing protocols play a critical role in this service. It is important to be able to identify and diagnose any problems occurring in Internet routing. However, the Internet's sheer size makes this task difficult. One cannot easily extract out the most important or relevant routing information from the large amounts of data collected from multiple routers. To tackle this problem, we have developed Link-Rank, a tool to visualize Internet routing changes at the global scale. Link-Rank weighs links in a topological graph by the number of routes carried over each link and visually captures changes in link weights in the form of a topological graph with adjustable size. Using Link-Rank, network operators can easily observe important routing changes from massive amounts of routing data, discover otherwise unnoticed routing problems, understand the impact of topological events, and infer root causes of observed routing changes.
如今的互联网为数百万终端用户提供全球数据传输服务，而路由协议在这项服务中起着关键作用。能够识别和诊断互联网路由中出现的任何问题至关重要。然而，互联网规模庞大，使得这项任务颇具难度。人们无法轻易从多个路由器收集的大量数据中提取出最重要或相关的路由信息。为解决这一问题，我们开发了Link-Rank，这是一种在全球范围内可视化互联网路由变化的工具。Link-Rank根据每条链路承载的路由数量对拓扑图中的链路进行加权，并以大小可调的拓扑图形式直观呈现链路权重的变化。使用Link-Rank，网络运营商可以轻松地从海量路由数据中观察到重要的路由变化，发现原本未被注意到的路由问题，了解拓扑事件的影响，并推断观察到的路由变化的根本原因。
