Router mechanisms designed to achieve fair bandwidth allocations, like Fair Queueing, have many desirable properties for congestion control in the Internet. However, such mechanisms usually need to maintain state, manage buffers, and/or perform packet scheduling on a per flow basis, and this complexity may prevent them from being cost-effectively implemented and widely deployed. In this paper, we propose an architecture that significantly reduces this implementation complexity yet still achieves approximately fair bandwidth allocations. We apply this approach to an island of routers -- that is, a contiguous region of the network -- and we distinguish between edge routers and core routers. Edge routers maintain per flow state; they estimate the incoming rate of each flow and insert a label into each packet header based on this estimate. Core routers maintain no per flow state; they use FIFO packet scheduling augmented by a probabilistic dropping algorithm that uses the packet labels and an estimate of the aggregate traffic at the router. We call the scheme Core-Stateless Fair Queueing. We present simulations and analysis on the performance of this approach.

Many researchers have argued that the Internet architecture would be more robust and more accommodating of heterogeneity if routers allocated bandwidth fairly. However, most of the mechanisms proposed to accomplish this, such as Fair Queueing [16], [6] and its many variants [2], [23], [15], involve complicated packet scheduling algorithms. These algorithms, while increasingly common in router designs, may not be inexpensively implementable at extremely high speeds; thus, finding more easily implementable variants of such algorithms may be of significant practical value. This paper proposes an algorithm that -- similar to FRED [13], CSFQ [24], and several other designs [17], [14], [5], [25] -- combines FIFO packet scheduling with differential dropping on arrival. Our design, called Approximate Fair Dropping (AFD), bases these dropping decisions on the recent history of packet arrivals. AFD retains a simple forwarding path and requires an amount of additional state that is small compared to current packet buffers. Simulation results, which we describe here, suggest that the design provides a reasonable degree of fairness in a wide variety of operating conditions. The performance of our approach is aided by the fact that the vast majority of Internet flows are slow but the fast flows send the bulk of the bits. This allows a small sample of recent history to provide accurate rate estimates of the fast flows.

Today’s Internet provides one simple service: best effort datagram delivery. This minimalist service allows the Internet to be stateless, that is, routers do not need to maintain any fine grained information about traffic. As a result of this stateless architecture, the Internet is both highly scalable and robust. However, as the Internet evolves into a global commercial infrastructure that is expected to support a plethora of new applications such as IP telephony, interactive TV, and e-commerce, the existing best effort service will no longer be sufficient. In consequence, there is an urgent need to provide more powerful services such as guaranteed services, differentiated services, and flow protection. Over the past decade, there has been intense research toward achieving this goal. Two classes of solutions have been proposed: those maintaining the stateless property of the original Internet (e.g., Differentiated Services), and those requiring a new stateful architecture (e.g., Integrated Services). While stateful solutions can provide more powerful and flexible services such as per flow bandwidth and delay guarantees, they are less scalable than stateless solutions. In particular, stateful solutions require each router to maintain and manage per flow state on the control path, and to perform per flow classification, scheduling, and buffer management on the data path. Since today’s routers can

Many per-flow scheduling algorithms have been proposed to provide rate and delay guarantees to flows. It is often argued that the need for maintaining per-flow state and performing per-packet classification seriously limits the scalability of routers that employ such per-flow scheduling algorithms. Consequently, design of algorithms that can provide per-flow rate and delay guarantees without requiring per-flow functionality in the network core routers has become an active area of research. In this paper, we propose a methodology to transform any Guaranteed Rate (GR) per-flow scheduling algorithm into a version that does not require per-flow state to be maintained in the core routers. We prove that a network of such core-stateless servers provides the same delay guarantee as a corresponding network of GR servers.

In multi-hop networks, packet schedulers at downstream nodes have an opportunity to make up for excessive latencies due to congestion at upstream nodes. Similarly, when packets incur low delays at upstream nodes, downstream nodes can reduce priority and schedule other packets first. The goal of this paper is to define a framework for design and analysis of Coordinated Multihop Scheduling (CMS) which exploit such inter-node coordination. We first provide a general CMS definition which enables us to classify a number of schedulers from the literature including, G-EDF, FIFO+, CEDF, and work-conserving CJVC as examples of CMS schedulers. We then develop a distributed theory of traffic envelopes which enables us to derive end-to-end statistical admission control conditions for CMS schedulers. We show that CMS schedulers are able to limit traffic distortion to within a narrow range resulting in improved end-to-end performance and more efficient resource utilization. Consequently, our technique exploits statistical resource sharing among flows, classes, and nodes, and our results provide the first statistical multi-node multi-class admission control algorithm for networks of work conserving servers.

End-to-end throughput guarantee is an important service semantics that network providers would like to offer to their customers. A network provider can offer such service semantics by deploying a network where each router employs a fair packet scheduling algorithm to allocate network bandwidth to competing flows. Unfortunately, these scheduling algorithms require every router to maintain per-flow state and perform per-packet flow classification; these requirements limit the scalability of the routers. This paper makes two primary contributions: (1) We present the first tight analysis for deriving end-to-end throughput guarantees for a network of routers that employ per-flow fair scheduling algorithms. (2) We propose the Core-stateless Guaranteed Throughput (CSGT) network architecture that, without maintaining per-flow state or performing per-packet flow classification in core routers, provides to flows throughput guarantees that are within a constant of what is attained by a network of core-stateful fair routers. 1

Finding an appropriate end-to-end congestion control scheme for each type of flow, such as real-time or multicast flows, may be difficult. But it becomes even more complex to have these schemes be friendly among themselves and with TCP. The assistance of routers within the network for fair bandwidth sharing among the flows is therefore helpful. However, most of the existing mechanisms that provide this fair sharing imply complex buffer management and maintaining flow state in the routers. In this paper, we propose to realize this fair bandwidth sharing without perflow state in the routers, using only a trivial queueing discipline. Packets are tagged near the source, depending on the nature of the flow. In the core of the network, routers use FIFO queues, and simply drop the packet with the highest tag value in case of congestion. Contrarily to other stateless fair queueing algorithms in the core routers, we do not try to maintain instantaneous flow rates equal. Instead, we take into account the responsiveness nature of the flows, and adjust loss rates such that average rates are equal. The novel approach of our scheme, called TUF , Tag-Based Unified Fairness, not only improves the overall fairness but enables us to maintain it in realistic environments, with non-negligible round trip times or bursty traffic, where other schemes fail. The corresponding cost is the need for models of the end-to-end responsive natures of the flows. Keywords---Stateless fair queueing, end-to-end congestion control, multicast, responsive flows, TCP, max-min fairness. I.

Abstract — Reliability is critical to a variety of network applications. Unfortunately, due to lack of QoS support across ISP boundaries, it is difficult to achieve even two 9s (99%) reliability in today’s Internet. In this paper, we propose SmartTunnel, an end-to-end approach to achieving reliability. A SmartTunnel is a logical point-to-point tunnel between two end points that spans multiple physical network paths. It achieves reliability by strategically allocating traffic onto multiple paths and performing FEC coding. Such an end-to-end approach requires no explicit QoS support from intermediate ISPs, and is therefore easy to deploy in today’s Internet. To fully realize the potential of SmartTunnel, we analytically derive near-optimal traffic allocation schemes that minimize loss rates. We extensively evaluate our approach using trace-driven simulations, ns-2 simulations, and experiments on PlanetLab. Our results clearly demonstrate that SmartTunnel is effective in achieving high reliability. I.

End-to-end fairness guarantee is an important service semantics that network providers would like to offer to their customers. A network provider can offer such service semantics by deploying a network where each router employs a fair packet scheduling algorithm. Unfortunately, these scheduling algorithms require every router to maintain per-flow state and perform per-packet flow classification; these requirements limit the scalability of the routers. In this paper, we propose the Core-stateless Guaranteed Fair (CSGF) network architecture--- the first work-conserving architecture that, without maintaining per-flow state or performing per-packet flow classification in core routers, provides to flows fairness guarantees similar to those provided by a network of core-stateful fair routers.

Inter-server coordinated scheduling is a mechanism for downstream nodes to increase or decrease a packet's priority according to the congestion incurred at upstream nodes. In this paper, we derive an endto -end schedulability condition for a broad class of coordinated schedulers that includes CJVC and CEDF. In contrast to previous approaches, our technique purposely allows flows to violate their local priority indexes while still providing an end-to-end delay bound. We show that under a simple priority assignment scheme, coordinated schedulers can outperform WFQ schedulers, while replacing per-flow scheduling operations with a simple coordination rule. Finally, we illustrate the performance advantages of coordination through numerical examples and simulation experiments.