TCP trunking: design, implementation and performance

Kung, H. T.; Wang, S.Y.

doi:10.1109/icnp.1999.801942

Cited by 38 publications

(22 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other studies (e.g., [12,1,15]) proposed that modification in transmission control rules be done on aggregates rather than individual flows, with the notion of flows sharing congestion information. For example, in [12], congestion information from a separate management connection (or using an architecture such as the Congestion Manager [1]) is used to regulate the aggregate traffic. Other techniques, such as Aggregate TCP (ATCP) [15] provides a congestion window lookup for an appropriate window size for new connections to start with.…”

Section: Related Workmentioning

confidence: 99%

Providing soft bandwidth guarantees using elastic TCP-based tunnels

Guirguis

Bestavros

Matta

et al. 2004

Proceedings. ISCC 2004. Ninth International Symposium on Computers and Communications (IEEE Cat. No.04TH8769)

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

Providing soft bandwidth guarantees using elastic TCP-based tunnels

Guirguis

Bestavros

Matta

et al. 2004

Proceedings. ISCC 2004. Ninth International Symposium on Computers and Communications (IEEE Cat. No.04TH8769)

View full text Add to dashboard Cite

show abstract

“…We study several longer time scales and find interesting implications of the long flows. Trunking (with TCP or optical networks [2,11,16]) gathers together groups of flows to achieve throughput benefits. Our work identifies long-duration flows that could be used by trunking.…”

Section: Related Workmentioning

confidence: 99%

“…First, understanding long-lived flows is important for network management. While capacity planning can be done on measures of aggregate traffic, several kinds of on-line traffic control have been proposed: protocol trunking [16], optical trunking [11], lambda switching [2], and low-buffer operation [1]. Understanding the feasibility and impact of these approaches requires flow-level traffic characterization.…”

Section: Introductionmentioning

confidence: 99%

On the characteristics and reasons of long-lived internet flows

Quan¹,

Heidemann²

2010

Proceedings of the 10th ACM SIGCOMM Conference on Internet Measurement

View full text Add to dashboard Cite

Prior studies of Internet traffic have considered traffic at different resolutions and time scales: packets and flows for hours or days, aggregate packet statistics for days or weeks, and hourly trends for months. However, little is known about the long-term behavior of individual flows. In this paper, we study individual flows (as defined by the 5-tuple of protocol, source and destination IP address and port) over days and weeks. While the vast majority of flows are short, and most bytes are in short flows, we find that about 20% of the overall bytes are carried in flows that last longer than 10 minutes, and flows lasting 100 minutes or longer make up 2% of traffic. We show that long-lived flows are qualitatively different from short flows: they are generally slower, less bursty, and are due to different applications and protocols. We investigate the causes of short-and long-lived flows, and show that the traffic mix varies significantly depending on duration time scale, with computer-to-computer traffic more and more dominating in larger time scales.

show abstract

“…Several approaches to congestion control for flow aggregates have been proposed (e.g., [3], [4]). The most relevant to this dissertation, however, is that of the Congestion Manager (CM), proposed by Balakrishnan et al in [1].…”

Section: Related Workmentioning

confidence: 99%