Comparison of tail drop and active queue management performance for bulk-data and Web-like Internet traffic

Brandauer, Christof; Iannaccone, Gianluca; Diot, Christophe; Ziegler, Thomas; Fdida, Serge; May, Martin

doi:10.1109/iscc.2001.935364

Cited by 77 publications

(47 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate RED performance, research at INRIA [21], [6] provides an analytical model and experimental results for tuning RED by taking into account both queuing delay and drop rates at the router. Based on their analysis, RED routers with standard parameters behave similar to tail-drop routers when queue length is close to the maximum threshold.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Harsh RED: Improving RED for Limited Aggregate Traffic

Järvinen

Ding

Nyrhinen

et al. 2012

2012 IEEE 26th International Conference on Advanced Information Networking and Applications

View full text Add to dashboard Cite

Abstract-A bottleneck router typically resides close to the edge of the network where the aggregate traffic is often limited to a single or a few users only. With such limited aggregate traffic Random Early Detection (RED) on the bottleneck router is not able to properly respond to TCP slow start that causes rapid increase in load of the bottleneck. This results in falling back to tail-drop behavior or, at worst, triggers the RED maximum threshold cutter that drops all packets causing undesired break for all traffic that is passing through the bottleneck. We explain how TCP slow start, ACK clock and RED algorithm interact in such a situation, and propose Harsh RED (HRED) to properly address slow start in time. We perform a simulation study to compare HRED behavior to that of FIFO and RED with recommended parameters. We show that HRED avoids tail-drop and the maximum threshold cutter, has smaller queues, and provides less bursty drop distribution.

show abstract

Section: Related Workmentioning

confidence: 99%

“…To achieve this, RED allows a number of its parameters to be configured in order to take into account heterogeneous path characteristics present in the Internet. However, it is generally perceived as challenging task to come up with right parameterization for RED [3], [4], [5], [6], [7].…”

Section: Introductionmentioning

confidence: 99%

Harsh RED: Improving RED for Limited Aggregate Traffic

Järvinen

Ding

Nyrhinen

et al. 2012

2012 IEEE 26th International Conference on Advanced Information Networking and Applications

View full text Add to dashboard Cite

show abstract

“…With the traditional approach to buffer management, named Tail Drop [6], the activity to drop packets will not start until the queue space is exhausted. When the queue becomes full, Tail Drop is immediately in effect and all forthcoming packets will be dropped until the congestion is eliminated and some space becomes available in the queue.…”

Section: Introductionmentioning

confidence: 99%

“…When the queue becomes full, Tail Drop is immediately in effect and all forthcoming packets will be dropped until the congestion is eliminated and some space becomes available in the queue. Unfortunately, such a method often causes high packet delays, bursty packet drops, degrading system stability and bandwidth fairness in the presence of persistent congestion [6][7][8].…”

Section: Introductionmentioning

confidence: 99%

“…GRED-I uses an instantaneous queue length instead of the average queue length and the dropping probability varies smoothly from 0 to 1 between the threshold and the queue size. The surprised results in [6,13] have revealed that GRED-I performs better than both RED and GRED in terms of the throughput, packet delay, loss probability, and number of consecutive losses.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Performance analysis of buffer allocation schemes under MMPP and Poisson traffic with individual thresholds

2007

View full text Add to dashboard Cite

Various buffer management and congestion control mechanisms have been proposed to support differentiated Quality-of-Service (QoS) requirements due to the heterogeneous properties of real-world network traffic and applications. Active Queue Management (AQM) with multiple thresholds, which starts dropping packets before the queue becomes full in order to notify incipient stages of congestion, is a promising buffer allocation mechanism. With the aim to capture the effects of heterogeneous traffic and justify the choice of appropriate parameters, this paper develops an original analytical model for a finite buffer queueing system with AQM under two heterogeneous classes of traffic which are modelled, respectively, by the non-bursty Poisson Process and bursty Markov-Modulated Poisson Process (MMPP). We derive the aggregated and marginal performance metrics including the mean queue length, response time, utilization, throughput, and loss probability. Extensive simulation experiments are used to validate the accuracy of the analytical model. Furthermore the model is adopted to evaluate the performance of AQM with heterogeneous traffic and under different working conditions.

show abstract

Modeling and evaluation of congestion control for different classes of network traffic

Wang

Min

Awan

2007

Concurrency and Computation

View full text Add to dashboard Cite

SUMMARYTraffic congestion has become a crucial problem in wireless networks due to its detrimental effects on the end-to-end Quality-of-Service (QoS) of mobile users. This issue has posed various challenges to developing effective congestion control mechanisms and devising new performance evaluation tools. Various congestion control schemes have been proposed to support differentiated QoS. Among these schemes, Active Queue Management (AQM) has been recognized as an effective mechanism to manage downlink buffers in wireless networks. Most existing studies on AQM are based on the use of averaged queue length and the related performance analysis is carried out via software simulation. This paper contributes to the development of an analytical performance model for a finite capacity queuing system subject to AQM and multiple traffic classes based on the instantaneous queue length. Expressions for the aggregated and marginal performance metrics including the mean queuing length, packet loss probability, mean waiting time, system throughput, response time, and utilization are analytically derived. The validity of this new model is demonstrated by comparing the analytical results against those obtained from simulation experiments. The analytical model is then used to investigate the effects of varying thresholds on the aggregated and marginal performance metrics under different combinations of arriving rates for multiple traffic classes.

show abstract

Comparison of tail drop and active queue management performance for bulk-data and Web-like Internet traffic

Abstract: This paper compares the performance of Tail Drop and three different flavors of the RED (Random Early

Cited by 77 publications

References 19 publications

Harsh RED: Improving RED for Limited Aggregate Traffic

Harsh RED: Improving RED for Limited Aggregate Traffic

Performance analysis of buffer allocation schemes under MMPP and Poisson traffic with individual thresholds

Modeling and evaluation of congestion control for different classes of network traffic

Contact Info

Product

Resources

About