Congestion Control in the Wild—Investigating Content Provider Fairness

Kunze, Ike; Rüth, Jan; Hohlfeld, Oliver

doi:10.1109/tnsm.2019.2962607

Cited by 8 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…TCP Congestion Control. Many of the congestion control studies have especially looked at CUBIC [17] and BBR [10] and found that BBR dominates in under-buffered scenarios causing packet loss and making CUBIC back off, while it is disadvantaged in over-buffered scenarios [18,23,26,28]. Here, CUBIC, as a loss-based algorithm, fills the buffer and increases the queuing delay which makes BBR back off.…”

Section: Background and Related Workmentioning

confidence: 99%

“…Today, this idea is most commonly implemented through a stochastic fair queuing (SFQ) which performs similar to a true fair queuing when the number of flows is limited. In fact, several works (e.g., [22,23]) show that AQM using this SFQ (often called flow-queuing) can create flow-rate fairness while effectively limiting congestion, even though there are no comprehensive studies available in literature.…”

Section: Background and Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Video Conferencing and Flow-Rate Fairness: A First Look at Zoom and the Impact of Flow-Queuing AQM

Sander¹,

Kunze²,

Wehrle³

et al. 2021

Passive and Active Measurement

Self Cite

View full text Add to dashboard Cite

Congestion control is essential for the stability of the Internet and the corresponding algorithms are commonly evaluated for interoperability based on flow-rate fairness. In contrast, video conferencing software such as Zoom uses custom congestion control algorithms whose fairness behavior is mostly unknown. Aggravatingly, video conferencing has recently seen a drastic increase in use -partly caused by the COVID-19 pandemic -and could hence negatively affect how available Internet resources are shared. In this paper, we thus investigate the flow-rate fairness of video conferencing congestion control at the example of Zoom and influences of deploying AQM. We find that Zoom is slow to react to bandwidth changes and uses two to three times the bandwidth of TCP in low-bandwidth scenarios. Moreover, also when competing with delay aware congestion control such as BBR, we see high queuing delays. AQM reduces these queuing delays and can equalize the bandwidth use when used with flow-queuing. However, it then introduces high packet loss for Zoom, leaving the question how delay and loss affect Zoom's QoE. We hence show a preliminary user study in the appendix which indicates that the QoE is at least not improved and should be studied further.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

Section: Background and Related Workmentioning

confidence: 99%

Video Conferencing and Flow-Rate Fairness: A First Look at Zoom and the Impact of Flow-Queuing AQM

Sander¹,

Kunze²,

Wehrle³

et al. 2021

Passive and Active Measurement

Self Cite

View full text Add to dashboard Cite

show abstract

“…Unfairness between paced and unpaced Reno flows was shown by [2,86]. Fairness work is about how algorithms ought to share resources, and usually shows that algorithms are unfair in simulations or in a lab [5,15,16,23,43,44,50,56,71,81,82,85]. Our work does not address how algorithms should share resources, but rather how to avoid experimental bias when they do.…”

Section: Related Workmentioning

confidence: 99%

“…There has been extensive study of the fairness of congestion control algorithms (e.g. [5,15,16,23,43,44,56,71,81,82,84,85]). A treatment algorithm is often said to be unfair if it gets a larger share of throughput when competing against a control algorithm.…”

Section: Test 3: Congestion Control Algorithmsmentioning

confidence: 99%

“…Both treatment and control groups in our test used the same network, and their packets traversed the same links and same queues. There is a long line of networking research showing that algorithms compete with each other when sharing a congested network [2,5,8,15,16,23,43,44,50,56,71,81,82,[84][85][86]. If capping bitrates freed up bandwidth, the uncapped control traffic could take up that bandwidth and get better performance.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Unbiased experiments in congested networks

Spang

Hannan

Kunamalla

et al. 2021

Proceedings of the 21st ACM Internet Measurement Conference

View full text Add to dashboard Cite

When developing a new networking algorithm, it is established practice to run a randomized experiment, or A/B test, to evaluate its performance. In an A/B test, traffic is randomly allocated between a treatment group, which uses the new algorithm, and a control group, which uses the existing algorithm. However, because networks are congested, both treatment and control traffic compete against each other for resources in a way that biases the outcome of these tests. This bias can have a surprisingly large effect; for example, in lab A/B tests with two widely used congestion control algorithms, the treatment appeared to deliver 150% higher throughput when used by a few flows, and 75% lower throughput when used by most flowsdespite the fact that the two algorithms have identical throughput when used by all traffic.Beyond the lab, we show that A/B tests can also be biased at scale. In an experiment run in cooperation with Netflix, estimates from A/B tests mistake the direction of change of some metrics, miss changes in other metrics, and overestimate the size of effects. We propose alternative experiment designs, previously used in online platforms, to more accurately evaluate new algorithms and allow experimenters to better understand the impact of congestion on their tests.

show abstract

Contextualized Fairness for Recommender Systems in Premium Scenarios

Hedia

et al. 2022

Big Data Research

View full text Add to dashboard Cite

Congestion Control in the Wild—Investigating Content Provider Fairness

Cited by 8 publications

References 27 publications

Video Conferencing and Flow-Rate Fairness: A First Look at Zoom and the Impact of Flow-Queuing AQM

Video Conferencing and Flow-Rate Fairness: A First Look at Zoom and the Impact of Flow-Queuing AQM

Unbiased experiments in congested networks

Contextualized Fairness for Recommender Systems in Premium Scenarios

Contact Info

Product

Resources

About