This paper compares the performance of Tail Drop and three different flavors of the RED (Random Early Detection) queue management mechanism: RED with a standard parameter setting, RED with an optimized parameter setting based on a model of RED with TCP flows, and finally a version of RED with a smoother drop function called "gentle RED". Performance is evaluated under various load situations for FTP-like and Web-like flows, respectively. We use measurements and simulations to evaluate the performance of the queue management mechanisms and assess their impact on a set of operator oriented performance metrics. We find that in total (i) no performance improvements of RED compared to Tail Drop can be observed; (ii) fine tuning of RED parameters is not sufficient to cope with undesired RED behavior due to the variability in traffic load; (iii) gentle RED is capable of resolving some of the headaches on RED but not all.

In the context of the DiffServ architecture, active queue management (AQM) algorithms are used for the differentiated forwarding of packets. However, correctly setting the parameters of an AQM algorithm may prove difficult and errorprone. Besides, many studies have shown that the performance of AQM mechanisms is very sensitive to network conditions. In this paper we present an adaptive AQM algorithm, which we call Adaptive RIO (A-RIO), addressing both of these problems. A-RIO draws directly from the original RIO proposal of Clark and Fang (1998) and the Adaptive RED (A-RED) algorithm described by Floyd et al. (2001). Our simulation results show that A-RIO outperforms RIO in terms of stabilizing the queue occupation (and, hence, queuing delay), while maintaining a high throughput and a good protection of high-priority packets; A-RIO could then be used for building controlled-delay, AF-based services. These results also provide some engineering rules that may be applied to improve the behaviour of the classical, non-adaptive RIO.

Active queue management (AQM) refers to a family of packet dropping mechanisms for router queues that has been proposed to support end-to-end congestion control mechanisms in the Internet. In this paper, we examine the performance of AQM mechanisms by varying two parameters: the queue size and the dropping function. AQM flavors considered include “RED”, the more recently proposed “Gentle RED ” and an additional mechanism we call “Gentle RED with instantaneous queue size”. We use experimentation to analyze the performance of the AQM mechanisms identified above on the aggregate traffic going through a congested router. The metrics used are: TCP goodput, TCP and UDP loss rate, queueing delay and consecutive loss probability. The AQM mechanisms are compared to Drop from Tail, the buffer management mechanism currently found in most operational routers. The major observation is that AQM mechanisms have a minor impact on the aggregate performance metrics we observe. On the other hand, we observe an important sensitivity of the AQMs considered to traffic characteristics that may compromise their operational deployment. 1.

Abstract not found