BBR: Congestion-Based Congestion Control

@article{Cardwell2016BBRCC,
  title={BBR: Congestion-Based Congestion Control},
  author={N. Cardwell and Yuchung Cheng and C. Gunn and S. Yeganeh and V. Jacobson},
  journal={Queue},
  year={2016},
  volume={14},
  pages={20 - 53}
}
When bottleneck buffers are large, loss-based congestion control keeps them full, causing bufferbloat. When bottleneck buffers are small, loss-based congestion control misinterprets loss as a signal of congestion, leading to low throughput. Fixing these problems requires an alternative to loss-based congestion control. Finding this alternative requires an understanding of where and how network congestion originates. 
Interactions between Congestion Control Algorithms
Congestion control algorithms are crucial in achieving high utilization while preventing overloading the network. Over the years, many different congestion control algorithms have been developed,Expand
Interactions between Congestion Control Algorithms
TLDR
Through head-to-head comparisons of loss-based, delay-based and hybrid types of congestion control algorithms, it is revealed that fairness in resources claimed is often not achieved, especially when flows sharing a link have different round-trip times or belong to different groups. Expand
Congestion-Control Throwdown
TLDR
In this throwdown-as-paper, the authors find themselves at loggerheads over the fundamental tenets of congestion control. Expand
Fifty Shades of Congestion Control: A Performance and Interactions Evaluation
TLDR
Through head-to-head comparisons of representatives from loss-based, delay-based and hybrid types of congestion control algorithms, it is revealed that fairness in resources claimed is often not attained, especially when flows sharing a link have different RTTs. Expand
Cocoa: Congestion Control Aware Queuing
TLDR
This work proposes the new AQM scheduler cocoa based on fair queuing, which adapts the buffer size depending on the needs of each flow without requiring active participation from the endpoint, and implements this scheduler for the Linux kernel and shows that it interacts well with the most common congestion control algorithms. Expand
Poster: FFBquick: fast convergence to fairness for delay-bounded congestion controls
Simultaneously achieving high throughput, a low and bounded queuing delay, and providing fairness among competing flows is very challenging for end-to-end congestion controls. Table 1 shows theExpand
Efficiency of BQL Congestion Control under High Bandwidth- Delay Product Network Conditions
BQL congestion control is aimed to utilize full available bottleneck bandwidth while keeping bottleneck buffer queue load on some low level to prevent it from producing avoidable additional delays orExpand
An Optimized Congestion Control Scheme for Mice Flows in Named Data Networking
TLDR
A Packet-Pair based startup for NDN congestion control schemes is proposed, by exploiting the available bandwidth estimation during the flow startup, to approach the maximum throughput faster and can improve the transmission efficiency of mice flows without harming elephant flows. Expand
A Low Latency Congestion Control That Can Compete
TLDR
The proposed solution is a delay based end-to-end scheme which uses ideas from several popular low delay algorithms but tries to adapt itself to a variety of network conditions instead of targeting a specific use-case. Expand
TCP LoLa: Congestion Control for Low Latencies and High Throughput
TLDR
TCP LoLa achieves high link utilization and attains convergence to fairness even among flows with different round-trip times, due to its novel mechanism called "fair flow balancing". Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 27 REFERENCES
TCP Vegas: End to End Congestion Avoidance on a Global Internet
TLDR
The three key techniques employed by Vegas are described, and the results of a comprehensive experimental performance study, using both simulations and measurements on the Internet, of the Vegas and Reno implementations of TCP are presented. Expand
The macroscopic behavior of the TCP congestion avoidance algorithm
TLDR
A performance model for the TCP Congestion Avoidance algorithm that predicts the bandwidth of a sustained TCP connection subjected to light to moderate packet losses, such as loss caused by network congestion is analyzed. Expand
CUBIC: a new TCP-friendly high-speed TCP variant
TLDR
The CUBIC protocol modifies the linear window growth function of existing TCP standards to be a cubic function in order to improve the scalability of TCP over fast and long distance networks. Expand
Taming the elephants: New TCP slow start
TLDR
A new slow start algorithm, called Hybrid Start (HyStart), is proposed, that finds a ''safe'' exit point for slow start at which it can terminate and safely advance to the congestion avoidance phase without causing heavy packet loss. Expand
An Internet-Wide Analysis of Traffic Policing
TLDR
This work developed a heuristic to identify policing from server-side traces and built a pipeline to deploy it at scale on traces from a large online content provider, collected from hundreds of servers worldwide. Expand
Practical experience with TCP over GPRS
TLDR
It is shown how a simple transparent proxy interposed between the fixed and GPRS networks can be used to significantly improve TCP connection performance, particularly for activities like Web browsing. Expand
Flow Control Power is Nondecentralizable
  • J. Jaffe
  • Computer Science
  • IEEE Trans. Commun.
  • 1981
TLDR
It is shown that no "decentralized flow control algorithm" can maximize network power and no objective based only on the users' throughputs and average delay is decentralizable. Expand
Bufferbloat: Dark Buffers in the Internet
  • J. Gettys
  • Computer Science
  • IEEE Internet Computing
  • 2011
We have conflated "speed" with "band width." As Stuart Chesire wrote in "It's the Latency, Stupid" (http://rescomp.stanford.edu/~cheshire/rants/Latency.html), "Making more bandwidth is easy. Once youExpand
B4: experience with a globally-deployed software defined wan
TLDR
This work presents the design, implementation, and evaluation of B4, a private WAN connecting Google's data centers across the planet, using OpenFlow to control relatively simple switches built from merchant silicon. Expand
A Guided Tour through Data-center Networking
TLDR
This article provides a "guided tour" through the principles and central ideas surrounding the network at the heart of a data center -- the modern-day loom that weaves the digital fabric of the Internet. Expand
...
1
2
3
...