Analysis of careful resumption of internet congestion control from retained path state

This paper presents the first detailed evaluation of Careful Resume, a new Congestion Control mechanism for Internet transports designed to accelerate connection startup based on retained path state. Traditional Congestion Control relies on Slow Start, which introduces significant latency for paths with a high Bandwidth-Delay Product. Careful Resume employs safety mechanisms to prevent excessive congestion when end-to-end signals suggest that the path characteristics, such as bandwidth or round-trip time (RTT), may have changed. We evaluate this safety using a testbed, followed by experiments using real-world Internet paths, and finally present initial experiences from use in a content delivery node. Results show that this new mechanism can significantly reduce the Time To Last Byte for a connection. In our tested scenarios, the reduction was by more than three RTTs. This finding aligns with results from testing Internet paths, where we observed reductions ranging from 2.8 to 3.4 RTTs on geostationary satellite and 4G/5G mobile paths. Our results also show that Careful Resume can be effectively used with HyStart++ to avoid further path capacity overshoot. This analysis demonstrates the benefit of using Careful Resume, and provides evidence that this mechanism does not unduly harm other connections that share the capacity of a network bottleneck.

Authors

Institutions

Publication Details

Journal
Computer Networks
Published
2025-12-20
DOI
https://doi.org/10.1016/j.comnet.2025.111950
Primary Topic
Network Traffic and Congestion Control
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Analysis of careful resumption of internet congestion control from retained path state

Raffaello Secchi, Mihail Yanev, Gorry Fairhurst, Ana Custura
Computer Networks
Network Traffic and Congestion Control
article

Analysis of careful resumption of internet congestion control from retained path state

Raffaello Secchi, Mihail Yanev, Gorry Fairhurst, Ana Custura
article en

Abstract

This paper presents the first detailed evaluation of Careful Resume, a new Congestion Control mechanism for Internet transports designed to accelerate connection startup based on retained path state. Traditional Congestion Control relies on Slow Start, which introduces significant latency for paths with a high Bandwidth-Delay Product. Careful Resume employs safety mechanisms to prevent excessive congestion when end-to-end signals suggest that the path characteristics, such as bandwidth or round-trip time (RTT), may have changed. We evaluate this safety using a testbed, followed by experiments using real-world Internet paths, and finally present initial experiences from use in a content delivery node. Results show that this new mechanism can significantly reduce the Time To Last Byte for a connection. In our tested scenarios, the reduction was by more than three RTTs. This finding aligns with results from testing Internet paths, where we observed reductions ranging from 2.8 to 3.4 RTTs on geostationary satellite and 4G/5G mobile paths. Our results also show that Careful Resume can be effectively used with HyStart++ to avoid further path capacity overshoot. This analysis demonstrates the benefit of using Careful Resume, and provides evidence that this mechanism does not unduly harm other connections that share the capacity of a network bottleneck.

Computer NetworksVol. 276
University of Aberdeen (GB)
Openalex Percentile: Top 54%
Network Traffic and Congestion Control
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.