What’s up with Starlink speeds?

In this study, we conducted sustained throughput measurements across the United States, Europe, and Australia using Starlink, the leading satellite internet constellation. Our comprehensive analysis uncovers significant discrepancies between advertised speeds, those reported by popular services such as Speedtest, and the actual sustained throughput. While factors like packet loss, latency, and peering strategies may contribute to these discrepancies, we highlight the substantial impact that underlying TCP mechanisms have on overall performance.Kemal Sanjta: Kemal is a result-oriented engineer focusing on designing, operating and troubleshooting large-scale networks. Passionate Linux user with a deep understanding of SRE/NRE practices. Over the last two decades, he worked at several large-scale companies applying NRE practices and automating remediation actions. As a Principal Internet Analyst at ThousandEyes, he focuses on research and providing deep and meaningful insights into outages through the lenses of ThousandEyes.Mike Hicks: Mike Hicks is a recognized expert in network and application performance, with more than 30 years of industry experience supporting large, complex networks and working closely with infrastructure vendors on application profiling and management. He is the author of "Managing Distributed Applications: Troubleshooting in a Heterogeneous Environment" (Prentice Hall 2000) and "Optimising Applications on Cisco Networks" (Cisco Press 2004).
Speakers:
Kemal Sanjta - Cisco ThousandEyesMike Hicks - Cisco ThousandEyes

[@nentis]

Nice of Todd Foggoa to respond to Anton Kapela's comment around BBR retransmissions. Now get out there and "sysctl net.ipv4.tcp_congestion_control=bbr" all the things!