oBBR: Optimize Retrmissions of BBR Flows on the Internet
summary
Analyzes why Google’s BBR congestion control produces high retransmission rates—linking losses to shallow bottleneck buffers, BBR’s in-flight data cap, and bandwidth drops—and validates these causes with experiments. Presents oBBR, a modification that adaptively scales the in-flight cap and updates bandwidth estimates more promptly to avoid injecting excessive data, and reports Internet experiments showing higher goodput and fewer retransmissions compared to BBRv2 and BBR-S, plus improved streaming QoE.
AI-written summary · about
related talks
16mR-TCP: A Framework to Optimize TCP Performance Over Rate-Limiting Networks
17mTowards provably performant congestion control
23mACK to the Future: TCP in 2025
17mEnabling Users to Control their Internet
17mBarre: Empowering Simplified and Versatile Programmable Congestion Control in...
16mFRCC: Towards Provably Fair and Robust Congestion Control
16mBolt: Sub-RTT Congestion Control for Ultra-Low Latency
12mBreaking the Transience-Equilibrium Nexus: A New Approach to Datacenter Packet Transport
