Issues and trends in router design

Keshav, Srinivasan; Sharma, Reema

doi:10.1109/35.668285

Cited by 161 publications

(73 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Routers in our network do store-and-forward, as opposed to cut through [12]. This operation imposes a minimum amount of delay on every packet, proportional to its size, which is likely to explain those remaining peaks in Fig.…”

Section: ) Transmission Delay On the Output Linkmentioning

confidence: 99%

See 1 more Smart Citation

Measurement and analysis of single-hop delay on an IP backbone network

Papagiannaki

Moon

Fraleigh³

et al. 2003

IEEE J. Select. Areas Commun.

150

View full text Add to dashboard Cite

Abstract-We measure and analyze the single-hop packet delay through operational routers in the Sprint Internet protocol (IP) backbone network. After presenting our delay measurements through a single router for OC-3 and OC-12 link speeds, we propose a methodology to identify the factors contributing to single-hop delay. In addition to packet processing, transmission, and queueing delay at the output link, we observe the presence of very large delays that cannot be explained within the context of a first-in first-out output queue model. We isolate and analyze these outliers.Results indicate that there is very little queueing taking place in Sprint's backbone. As link speeds increase, transmission delay decreases and the dominant part of single-hop delay is packet processing time. We show that if a packet is received and transmitted on the same linecard, it experiences less than 20 s of delay. If the packet is transmitted across the switch fabric, its delay doubles in magnitude. We observe that processing due to IP options results in single-hop delays in the order of milliseconds. Milliseconds of delay may also be experienced by packets that do not carry IP options. We attribute those delays to router idiosyncratic behavior that affects less than 1% of the packets. Finally, we show that the queueing delay distribution is long-tailed and can be approximated with a Weibull distribution with the scale parameter = 0 5 and the shape parameter = 0 6 to 0.82. Index Terms-Link utilization, queueing delay, single-hop delay measurement.

show abstract

Section: ) Transmission Delay On the Output Linkmentioning

confidence: 99%

“…The router can use various policies to resolve this contention. The first-in first-out (FIFO) output queue model captures the essence of how a router should serve packets contending for the same resource in a best-effort fashion [12]. Thus, we model an output port of a router as a single output queue.…”

Section: Filtering Based On a Single Output Queue Modelmentioning

confidence: 99%

Measurement and analysis of single-hop delay on an IP backbone network

Papagiannaki

Moon

Fraleigh³

et al. 2003

IEEE J. Select. Areas Commun.

150

View full text Add to dashboard Cite

show abstract

“…Specifically, FIFO queues are easy to implement. Each FIFO only needs two pointers for the head and tail of the queue [28], and the implementation is not affected by the aforementioned issue related to the number of dissimilar T/H values. Since the number of priority levels is small, the hardware cost is not significant.…”

Section: Practicality Of T/h-p In High-speed Routersmentioning

confidence: 99%

Deadline-based scheduling in support of real-time data delivery

Liu

Wong

2008

Computer Networks

View full text Add to dashboard Cite

“…The capability to provide QOS support has become an important issue for the design of modern switches and routers [10]. Switches and routers control the departure order of packets from different flows, and the scheduling algorithms adopted largely determine the quality of service that can be provided by the networks.…”

Section: Introductionmentioning

confidence: 99%