[Bloat] bbr vs cubic network performance on high speed rail networks

[Dave Taht]

It's really weird to worry about throughput and latency at 300km/h vs
350km/hr, being as the fastest US train I've ever been on rarely
cracks 100kph.

https://arxiv.org/pdf/1812.04823.pdf - the handover bit (section 5.2
and later) was pretty interesting.

Round-trip-time (RTT). As shown in Fig. 6, BBR has more than twice
lower RTTs than CUBIC (e.g., 191.53 ms versus 431.35 ms at 300 km/h,
and 148.63 ms versus 345.02 ms at 350 km/h for median value) due to
their different CCA design rationales: BBR intends to suppress the RTT
to overcome the bufferbloat problem [24


-- 

Dave Täht
CTO, TekLibre, LLC
http://www.teklibre.com
Tel: 1-831-205-9740