In the Internet today, users and applications must often make decisions based on the performance they expect to observe. For example, many Web pages are available in low-bandwidth and high-bandwidth versions, while other pages present users with long lists of mirror sites to choose from. Current techniques to perform these decisions are often ad-hoc and/or poorly designed. The most common solution used today is to require the user to manually decide based on experience and information provided by the application. Previous efforts to automate this process have focused on isolated, active network probes from a host. Unfortunately, this method of making measurements has several problems. Active probing introduces unnecessary network traffic that can quickly become a significant part of the total traffic handled by busy web servers. Probing from a single host results in less accurate information and additional redundant network probes than a system that shares information with nearby hosts. In this paper, we propose a system called SPAND (Shared Passive Network Performance Discovery) that determines network characteristics by making shared, passive measurements from a collection of hosts. In this paper, we show why passive measurements from a collection of hosts has advantages over active measurements from a single host. We also show that sharing measurements can dramatically increase the accuracy and timeliness of predictions. In addition, we present a initial prototype design of SPAND, a plan for incremental deployment, and the current implementation status of our system.




Download Full History