TCP Performance over Current Cellular Access: A Comprehensive Analysis

Atxutegi, Eneko; Arvidsson, Åke; Liberal, Fidel; Grinnemo, Karl-Johan; Brunström, Anna

doi:10.1007/978-3-319-90415-3_14

Cited by 8 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, a majority of web flows are often short-lived (page loads) and therefore behavior during slow start dramatically affects page load performance. This observation becomes even more important when we consider recent studies that show that delay-based congestion control algorithms fail to accurately estimate the actual congestion window in mobile, jittery network conditions [15,16]. We speculate that when delay-based congestion control algorithms are combined with mobile networks, H1 can outperform H2.…”

Section: Http and Tcp Interplaymentioning

confidence: 92%

Mind the delay

Agarwal

Varvello

Auçinas

et al. 2020

Proceedings of the 16th International Conference on Emerging Networking EXperiments and Technologies

View full text Add to dashboard Cite

The last three decades have seen much evolution in web and network protocols: amongst them, a transition from HTTP/1.1 to HTTP/2 and a shift from loss-based to delay-based TCP congestion control algorithms. This paper argues that these two trends come at odds with one another, ultimately hurting web performance. Using a controlled synthetic study, we show how delay-based congestion control protocols (e.g., BBR and CUBIC + Hybrid Slow Start) result in the underestimation of the available congestion window in mobile networks, and how that dramatically hampers the effectiveness of HTTP/2. To quantify the impact of such finding in the current web, we evolve the web performance toolbox in two ways. First, we develop Igor, a client-side TCP congestion control detection tool that can differentiate between loss-based and delay-based algorithms by focusing on their behavior during slow start. Second, we develop a Chromium patch which allows fine-grained control on the HTTP version to be used per domain. Using these new web performance tools, we analyze over 300 real websites and find that 67% of sites relying solely on delay-based congestion control algorithms have better performance with HTTP/1.1.

show abstract

Section: Http and Tcp Interplaymentioning

confidence: 92%

Mind the delay

Agarwal

Varvello

Auçinas

et al. 2020

Proceedings of the 16th International Conference on Emerging Networking EXperiments and Technologies

View full text Add to dashboard Cite

show abstract

“…To assess the limit of the available bandwidth, Hystart mainly checks the RTT increases. With variable or high latency, Hystart may exit prematurely the slow start phase [20], [21]. We evaluate its impact in Section III-C1.…”

Section: B Congestion Control Algorithmsmentioning

confidence: 99%

When BBR beats FEC coded CUBIC flows over SATCOM

Petrou

Pradas

Kuhn

et al. 2022

2022 11th Advanced Satellite Multimedia Systems Conference and the 17th Signal Processing for Space Communications Workshop (As

View full text Add to dashboard Cite

This paper assesses the benefits of using Sliding Windows Forward error codes (SWF) to protect transport protocol sessions over a SATCOM link within IP tunnels. We consider two commonly deployed protocols and congestion control algorithms : TCP/CUBIC, currently deployed by default inside most of recent OS kernels and a QUIC/BBR implementation named Picoquic. Our objective is to evaluate the performance of these protocols in challenging SATCOM environments and to assess if SWF can contribute to improve their performance. We consider two different scenarios based on real loss mobility patterns played over the OpenSAND satellite emulator. Results show that using SWF tunnels can hide losses to a CUBIC server: this reduces the download time of 20MB by more than 90%. However, the main finding is that SWF does not contribute to the download time reduction for BBR, making useless its deployment. We conclude that the use of BBR over SATCOM could be an efficient way to perform communications over unreliable links, resulting from a high mobility context for instance, considering BBR flows are managed by an adequate QoS allocation.

show abstract

“…Server-oriented end-to-end congestion control protocols: Since a large part of mobile traffic is constituted by TCP flows, TCP congestion control is always one of the hottest research topics, and its performance is critically important [7,20]. So far, numeric TCP variants have been proposed, which fall into three categories, namely, loss-based, delay-based, and combined loss- and delay-based.…”

Section: Related Workmentioning

confidence: 99%

Receiver-Side TCP Countermeasure in Cellular Networks

Dong

Gao

Xie

et al. 2019

Sensors

View full text Add to dashboard Cite

Cellular-based networks keep large buffers at base stations to smooth out the bursty data traffic, which has a negative impact on the user’s Quality of Experience (QoE). With the boom of smart vehicles and phones, this has drawn growing attention. For this paper, we first conducted experiments to reveal the large delays, thus long flow completion time (FCT), caused by the large buffer in the cellular networks. Then, a receiver-side transmission control protocol (TCP) countermeasure named Delay-based Flow Control algorithm with Service Differentiation (DFCSD) was proposed to target interactive applications requiring high throughput and low delay in cellular networks by limiting the standing queue size and decreasing the amount of packets that are dropped in the eNodeB in Long Term Evolution (LTE). DFCSD stems from delay-based congestion control algorithms but works at the receiver side to avoid the performance degradation of the delay-based algorithms when competing with loss-based mechanisms. In addition, it is derived based on the TCP fluid model to maximize the network utility. Furthermore, DFCSD also takes service differentiation into consideration based on the size of competing flows to shorten their completion time, thus improving user QoE. Simulation results confirmed that DFCSD is compatible with existing TCP algorithms, significantly reduces the latency of TCP flows, and increases network throughput.

show abstract

TCP Performance over Current Cellular Access: A Comprehensive Analysis

Cited by 8 publications

References 21 publications

Mind the delay

Mind the delay

When BBR beats FEC coded CUBIC flows over SATCOM

Receiver-Side TCP Countermeasure in Cellular Networks

Contact Info

Product

Resources

About