A Simple FIFO-Based Scheme for Differentiated Loss Guarantees - Technical Report

The emergence of the Internet as the de facto communication infrastructure means that it is asked to carry an ever broadening range of application traffic with different requirements. This in turn has stressed its original, one-class, best-effort model, and has been one of the main drivers behind the many efforts aimed at introducing QoS. Those efforts have, however, experienced only limited success because the added complexity QoS introduces is at odds with the scaling requirements of the Internet. This has motivated a number of proposals that have strived to balance the need for service differentiation with the requirement for low complexity that the Internet scale mandates. This paper shares similar goals and proposes a simple scheme, BoundedRandomDrop (BRD), that supports multiple service classes. BRD focuses on loss differentiation, as although both losses and delay are important performance parameters, the steadily rising speed of Internet links, including access links, is progressively limiting the potential impact of delay differentiation. BRD offers strong loss differentiation capabilities with minimal implementation and deployment cost. BRD does not require the specification of a traffic profile, nor does it rely on call admission to control the amount of traffic in different classes. It guarantees each class losses that, when feasible, are no worse than a specified bound, but enforces differentiation only when required to meet those bounds. In addition, BRD is implemented using a single FIFO queue and a simple random dropping mechanism. The performance of BRD is investigated for a broad range of traffic mixes and shown to consistently achieve its goal of effective service differentiation.