Modeling the interactions of congestion control and switch scheduling

Shpiner, Alex; Keslassy, Isaac

doi:10.1109/iwqos.2009.5201395

Cited by 7 publications

(2 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Maximum weight matching (MWM) is a switch scheduling algorithm and has similar properties as the max-weight scheduling algorithm and backpressure. Similar to the backpressure, there is incompatibility between TCP and MWM [31], [32]. Yet, we consider backpressure routing and scheduling over wireless networks rather than switch scheduling, and we take a holistic approach to address this problem; i.e., we propose TCP-aware backpressure to make TCP and backpressure compatible.…”

Section: Related Workmentioning

confidence: 99%

TCP-aware backpressure routing and scheduling

Seferoğlu

Modiano

2014

2014 Information Theory and Applications Workshop (ITA)

View full text Add to dashboard Cite

Abstract-In this work, we explore the performance of backpressure routing and scheduling for TCP flows over wireless networks. TCP and backpressure are not compatible due to a mismatch between the congestion control mechanism of TCP and the queue size based routing and scheduling of the backpressure framework. We propose a TCP-aware backpressure routing and scheduling that takes into account the behavior of TCP flows. TCP-aware backpressure (i) provides throughput optimality guarantees in the Lyapunov optimization framework, (ii) gracefully combines TCP and backpressure without making any changes to the TCP protocol, (iii) improves the throughput of TCP flows significantly, and (iv) provides fairness across competing TCP flows.

show abstract

Section: Related Workmentioning

confidence: 99%

TCP-aware backpressure routing and scheduling

Seferoğlu

Modiano

2014

2014 Information Theory and Applications Workshop (ITA)

View full text Add to dashboard Cite

show abstract

“…Recently [33] and [37] showed that possible extreme unfairness and rate oscillations may occur at routers implementing a max-scalar scheduling policy when the traffic is originated by TCP sources. However we emphasize that, differently from our work, both [33] and [37] assume a classical drop-tail packet discarding policy at the queues. We believe that conjugating max-scalar scheduling policy with a properly designed AQM packet dropping scheme is necessary to achieve a good degree of fairness.…”

Section: Introductionmentioning

confidence: 99%

On the interaction between TCP-like sources and throughput-efficient scheduling policies

Giaccone¹,

Leonardi²,

Neri³

2013

Performance Evaluation

View full text Add to dashboard Cite

A switch-based approach to throughput collapse and starvation in data centers

et al. 2012

Self Cite

View full text Add to dashboard Cite

Abstract-Data center switches need to satisfy stringent lowdelay and high-capacity requirements. To do so, they rely on small switch buffers. However, in case of congestion, data center switches can incur throughput collapse for short TCP flows as well as temporary starvation for long TCP flows.In this paper, we introduce a lightweight hash-based algorithm called HCF (Hashed Credits Fair) to solve these problems at the switch level while being transparent to the end users. We show that it can be readily implemented in data center switches with O(1) complexity and negligible overhead. We illustrate using simulations how HCF mitigates the throughput collapse of short flows. We also show how HCF reduces unfairness and starvation for long-lived TCP flows as well as for short TCP flows, yet maximizes the utilization on the congested link. Last, even though HCF can store packets of a same flow in different queues, we also prove that it prevents packet reordering.

show abstract

Modeling the interactions of congestion control and switch scheduling

Cited by 7 publications

References 39 publications

TCP-aware backpressure routing and scheduling

TCP-aware backpressure routing and scheduling

On the interaction between TCP-like sources and throughput-efficient scheduling policies

A switch-based approach to throughput collapse and starvation in data centers

Contact Info

Product

Resources

About