Network level perspective in web sessions troubleshooting

摘要

In the last years, the quantity of data and the number of applications carried over web traffic have been continuously increasing and nowadays web browsing accounts for most of the Internet traffic. In such a scenario, a poor browsing experience can result very annoying to the end user, and the effective identification of the root cause of such bad performance is of primary interest to both the users and the network operators. In this paper, we present a unified framework, based on a novel lightweight open-source publicly available probe and on an original statistical diagnosis algorithm, to correctly and effectively point out the segment of a web connection (eg, local client, backbone network, and DNS server) responsible for a poor web browsing experience. The extensive experimental evaluation carried out in the paper demonstrates the effectiveness of the proposed approach to diagnose poor quality of experience at a large scale.