An efficient network-switch scheduling for real-time applications

The Third IEEE Symposium on Computers and Communications, Athens, Greece, pp. 455-461, 30 June - 2 July 1998

Fair queueing is a useful queueing discipline for packet switching systems. It was developed in last decade and was aimed at the general packet switching systems with varying packet length. However, it is not suitable for use in the ATM networking, because the ATM cell length is very small and fixed, and so the scheduling scheme on a per cell basis isn't practical. Here we introduce the burst and quality unit concepts in the scheduling algorithm and we make some significant modification on the fair queueing and adapt it to ATM networking to meet QoS requirements. Under the Work-Conserving assumption, we show that the burst based nonpreemptive and preemptive algorithms provide throughput and fairness guarantees.

Input queuing is becoming increasingly important for high-bandwidth switches and routers. In this paper, it is proposed a scheduling algorithm formaking a uniform traffic in input-queued cell switch, called WFMC. The proposed algorithm has based on two units: Length of the head of line (HOL) and the number of cells in the queue. Then we proposed a hardware scheme based WFMC algorithm for high performance input queued crossbar switch scheduling. The simulation results show that proposed algorithm has a high performance in delay and jitter while it can avoid unfairness and starvation under unbalanced traffic. INTRODUCTION Nowadays Internet traffic is growing rapidly, and this puts an increasing demand for high capacity routers. Some real-time applications, e.g., IPTV, Video-on-demand, and Voice-over-IP service have stringent delay requirements. One of the most used architectures for design of high-speed switches is crossbar. Crossbar switching fabric is interesting for implementation ...

A. T. Chronopoulos, C. Tang, An Efficient Implementation of Burst Fair Queuing for ATM Networking, Proceedings of the 10th IASTED International Conference on Parallel and Distributed Computing Systems, Las Vegas, Nevada, pp. 326-333, 23-31 October 1998

Fair queueing, which was developed in last decade and was aimed at general packet switching systems with varying packet length, is not suitable for use in the ATM networking. The reason is that the ATM cell length is very small and fixed, and so the scheduling scheme on per cell basis isn't practical. The scheduling scheme of a switch affects the delay, throughput and fairness of a network, and thus it has a great impact on the quality of service (QoS).

IEEE Transactions on Broadcasting, 2003

The problem of allocating network resources to application sessions backlogged at an individual switch has a great impact on the end-to-end delay and throughput guarantees offered by the network. There exists a class of algorithms based on weighted fair queueing (WFQ) for scheduling packets which are work-conserving and they guarantee fairness to the backlogged sessions. These algorithms also apply to ATM networks with a packet equal to a single cell or an ATM block (of fixed size). Bursts are groups of varying numbers of cells. We generalize WFQ to schedule bursts. Our motivation is to derive an adaptive algorithm which generalizes the (fixed size) packet level to a varying size packet level. The new algorithm enhances the performance of the switch service for many important applications. The proposed scheme maintains the work-conserving property, and also provides throughput and fairness guarantees. The worst-case delay bound is also given. We use simulation to study the performance characteristics of our algorithm. Our results demonstrate the efficiency of the new algorithm.

IEEE/ACM Transactions on Networking, 2000

Input-queued (IQ) switches overcome the scalability problem suffered by output-queued switches. In order to provide differential quality of services (QoS), we need to efficiently schedule a set of incoming packets so that every packet can be transferred to its destined output port before its deadline. If no such a schedule exists, we wish to find one that allows a maximum number of packets to meet their deadlines. Recently, this problem has been proved to be NP-complete if three or more distinct deadlines (classes) are present in the set. In this paper, we propose a novel algorithm named Flow-based Iterative Packet Scheduling (FIPS) for this scheduling problem. A key component in FIPS is a non-trivial algorithm that solves the problem for the case where two classes are present in the packet set. By repeatedly applying the algorithm for two classes, we solve the general case of an arbitrary number of classes more efficiently. Applying FIPS to a frame-based model effectively achieves differential QoS provision in IQ switches. Using simulations, we have compared FIPS performance with five well-known existing heuristic algorithms including Earliest-Deadline-First (EDF), Minimum-Laxity-First (MLF) and their variants. The simulation results demonstrate that our new algorithm solves the deadline guaranteed packet scheduling problem with a much higher success rate and a much lower packet drop ratio than all other algorithms.

The Third IEEE Symposium on Computers and Communications, Athens, Greece, pp. 462-467, 30 June 30-2 July 1998

The scheduling scheme of a switch affects the delay, throughput and fairness of a network and thus has a great impact on the quality of service (QoS). In Part I, we present a theoretical analysis of a burst scheduling for ATM switches and proved QoS guarantees on throughput and fairness of the applications. Here, we use simulation to demonstrate the superiority of the burst based weighted fair queueing over the non-burst version. Our simulation study is based on backbone and access subnetworks, which are common in the real world.

The scheduling scheme in packet switching networks is one of the most critical features that can affect the performance of the network. Hence, many scheduling algorithms have been suggested and some indices, such as fairness and latency, have been proposed for the comparison of their performances. While the nature of Internet traffic is bursty, traditional scheduling algorithms try to smooth the traffic and serve the users based on this smoothed traffic. As a result, the fairness index mainly considers this smoothed traffic and the service rate as the main parameter to differentiate among different sessions or flows. This work uses burstiness as a differentiating factor to evaluate scheduling algorithms proposed in the literature. To achieve this goal, a new index that evaluates the performance of a scheduler with bursty traffic is introduced. Additionally, this paper introduces a new scheduler that not only uses arrival rates but also considers burstiness parameters in its scheduling algorithms.

ICC 2001. IEEE International Conference on Communications. Conference Record (Cat. No.01CH37240), 2001

This paper concentrates on obtaining uniform weighted round robin schedules for input queued packet switches. The desired schedules are uniform in the sense that each connection is serviced at regularly spaced time slots, where the spacing is proportional to the inverse of the guaranteed data rate. Suitable applications include ATM networks as well as satellite switched TDMA systems that provide per packet delay guarantees. Three heuristic algorithms are proposed to obtain such schedules under the constraints imposed by the unit speedup of input queued switches. Numerical experiments indicate that the algorithms have remarkable performance in finding uniform schedules.

IEEE/ACM Transactions on Networking, 2003

Weighted fair queueing (WFQ)-based packet scheduling schemes require processing at line speeds for tag computation and tag sorting. This requirement presents a bottleneck for their implementation at high transmission speeds. In this paper, we propose an alternative and lower complexity approach to packet scheduling, based on modifications of the classical round-robin scheduler. Contrary to conventional belief, we show that appropriate modifications of the weighted round-robin (WRR) service discipline can, in fact, provide tight fairness properties and efficient delay guarantees to multiple sessions. Two such modifications are described: 1) list-based round robin, in which the server visits different sessions according to a precomputed list which is designed to obtain the desirable scheduling properties and 2) multiclass round robin, a version of hierarchical round robin with controls designed for good scheduling properties. The schemes considered are compared with well-known WFQ schemes and with deficit round robin (a credit-based WRR), on the basis of desirable properties such as bandwidth guarantees, fairness in excess bandwidth sharing, worst-case fairness, and efficiency of latency (delay guarantee) tuning. The scheduling schemes proposed and analyzed here operate with fixed packet sizes, and hence can be used in applications such as cell scheduling in ATM networks, time-slot scheduling on wireless links as in GPRS air interface, etc. A credit-based extension of the proposed schemes to handle variable packet sizes is also possible.

2011

The pervasiveness of the Internet and its applications lead to the potential increment of the users' demands for more services with economical prices. The diversity of Internet traffic requires some classification and prioritisation since some traffic deserve much attention with less delay and loss compared to others. Current scheduling mechanisms are exposed to the trade-off between three major properties namely fairness, complexity and protection. Therefore, the question remains about how to improve the fairness and protection with less complex implementation. This research is designed to enhance scheduling mechanism by providing sustainability to the fairness and protection properties with simplicity in implementation; and hence higher service quality particularly for real-time applications. Extra elements are applied to the main fairness equation to improve the fairness property. This research adopts the restricted charge policy which imposes the protection of normal user. In terms of the complexity property, genetic algorithm has an advantage in holding the fitness score of the queue in separate storage space which potentially minimises the complexity of the algorithm. The integrity between conceptual, analytical and experimental approach verifies the efficiency of the proposed mechanism. The proposed mechanism is validated by using the emulation and the validation experiments involve real router flow data. The results of the evaluation showed fair bandwidth distribution similar to the popular Weighted Fair Queuing (WFQ) mechanism. Furthermore, better protection was exhibited in the results compared with the WFQ and two other scheduling mechanisms. The complexity of the proposed mechanism reached O(log(n)) which is considered as potentially low. Furthermore, this mechanism is limited to the wired networks and hence future works could improve the mechanism to be adopted in mobile ad-hoc networks or any other wireless networks. Moreover, more improvements could be applied to the proposed mechanism to enhance its deployment in the virtual circuits switching network such as the asynchronous transfer mode networks.