Link Buffer Sizing: A New Look at the Old Problem

Gorinsky, Sergey; Kantawala, A.; Turner, Jonathan S.

doi:10.1109/iscc.2005.93

Cited by 33 publications

(27 citation statements)

References 18 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FCT is problematic, however, because as an end-to-end performance metric it is beyond the purview of any single network within which specific buffer sizing decisions are made. Gorinsky et al suggest a formulation that considers end-to-end goodput at the right performance target (directly related to FCT), and show that small buffers can still result in high goodput [18]. The related problem of understanding performance in the context of AQM, specifically Random Early Detection (RED) [16], has been widely examined [14].…”

Section: Router Buffer Sizingmentioning

confidence: 99%

An SLA perspective on the router buffer sizing problem

Sommers

Barford

Greenberg

et al. 2008

SIGMETRICS Perform. Eval. Rev.

View full text Add to dashboard Cite

In this paper, we discuss recent work on buffer sizing in the context of an ISP's need to offer and guarantee competitive Service Level Agreements (SLAs) to its customers. Since SLAs specify the performance that an ISP guarantees to its customers, they provide critical context for many configuration and provisioning decisions and have specific relevance to buffer sizing. We use a controlled laboratory environment to explore the tradeoffs between buffer size and a set of performance metrics over a range of traffic mixtures for three different router designs. Our empirical study reveals performance profiles that are surprisingly robust to differences in router architecture and traffic mix and suggests a design space within which buffer sizing decisions can be made in practice. We then present a preliminary approach for making buffer sizing decisions within this framework that relates directly to performance and provisioning requirements in SLAs.

show abstract

Section: Router Buffer Sizingmentioning

confidence: 99%

An SLA perspective on the router buffer sizing problem

Sommers

Barford

Greenberg

et al. 2008

SIGMETRICS Perform. Eval. Rev.

View full text Add to dashboard Cite

show abstract

“…The goal of buffer sizing is to find out how small we can make Internet router buffers without any degradation in network performance. A plethora of recent work emerged to reduce buffer sizes [1,2,3,4,5] and to understand the relationships between buffer sizing and other parameters of the network [8,9,10,11,12,13,14], such as, throughput, delay, loss, stability [7,6], and the impacts of various traffic conditions [8,15].…”

Section: Motivation and Introductionmentioning

confidence: 99%

The Effects of Fairness in Buffer Sizing

Wang

Ganjali

2007

NETWORKING 2007. Ad Hoc and Sensor Networks, Wireless Networks, Next Generation Internet

View full text Add to dashboard Cite

Abstract. Buffer sizing in Internet routers is a fundamental problem that has major consequences in the design, implementation, and economy of the routers, as well as on the performance observed by the end users. Recently, there have been some seemingly contradictory results on buffer sizing. On the one hand, Appenzeller et al. show that as a direct consequence of desynchronization of flows in the core of the Internet, buffer sizes in core routers can be significantly reduced without any major degradation in network performance. On the other hand, Raina and Wischik show that such reduction in buffer sizing comes at the cost of synchronization and thus instability in the network.This work unifies these results by studying the effects of fairness in buffer sizing. We show that the main difference arises from the implicit assumption of fairness in packet dropping in the latter result. We demonstrate that desynchronization among flows observed by Appenzeller et al. is caused by unfair packet dropping when a combination of TCP-Reno and the drop-tail queue management is used. We also show that bringing fairness in packet dropping will introduce synchronization among flows, and will make the system unstable as predicted by Raina and Wischik.Our analysis suggests that there is an intrinsic trade-off between fairness in packet drops and desynchronization among TCP-Reno flows when routers use the drop-tail queue management. Achieving fairness, desynchronization, small buffer size, and 100% link utilization at the same time is desirable and feasible yet challenging. The studies in this paper provide insights for further explorations in reaching this goal.

show abstract

“…Gorinsky et al [8] showed by simulation that the above result does not hold when the number of flows is in the order of 100 flows, which would be the case in slower access links serving fewer connections.…”

Section: Buffer Requirementsmentioning

confidence: 99%

Light-Weight Control of Non-responsive Traffic with Low Buffer Requirements

Ramaswamy

Cuellar

Eidenbenz

et al. 2007

NETWORKING 2007. Ad Hoc and Sensor Networks, Wireless Networks, Next Generation Internet

View full text Add to dashboard Cite

Abstract. We propose ESREQM (Efficient Sending Rate EstimationQueue Management), a novel active queue management scheme that achieves almost perfect max-min fairness among flows with minimum (constant) per-flow state and a constant number of CPU operations to handle an incoming packet using a single queue with very low buffer requirements. ESREQM estimates sending rates of flows through a history discounting process that allows it to guarantee max-min fairness by automatically adapting parameters. It can also be used to punish non-responsive flows. The per-flow state is limited to a single value per flow, which allows the flow memory to be in SRAM, thereby making packet processing scalable with link speeds. ESREQM results in good link utilization with low buffer size requirements because it provably desynchronizes TCP flows as a by-product. We show our results through a mixture of analysis and simulation. Our scheme does not make assumptions on what transport protocols are used.

show abstract

Link Buffer Sizing: A New Look at the Old Problem

Cited by 33 publications

References 18 publications

An SLA perspective on the router buffer sizing problem

An SLA perspective on the router buffer sizing problem

The Effects of Fairness in Buffer Sizing

Light-Weight Control of Non-responsive Traffic with Low Buffer Requirements

Contact Info

Product

Resources

About