Answers are grounded in this paper and cite their sources.
This paper presents a new implementation of the SACK option and RFC 6675 loss recovery algorithm in ns-3. As is already happening in the Linux kernel, we have merged the loss recovery algorithm in the part of the code shared by all TCP variants. This merge allows bringing the performance improvements under correlated losses to all congestion control algorithms. The paper then shows the performance of TCP Hybla, Highspeed, and Vegas, under a scenario with different packet error rates, comparing the performance obtained with and without the use of the TCP SACK option. The results allow concluding that the main characteristics of the congestion control algorithms are untouched, but thanks to the implemented option their resilience to correlated losses is improved.
No takes yet. Share an insight, caveat, or question.
Natale Patriciello (2017) studied this question.
Synapse has enriched 2 closely related papers on similar clinical questions. Consider them for comparative context: