2020-zhu-characterizing
findings extracted from this paper
-
Hop-by-hop bottleneck localization showed that in more than 71% of measured paths the first lossy hop is located deep inside China (beyond the border), with only 34.45% of bottleneck hops coinciding with the GFW hop as detected by RST injection probing — suggesting Chinese ISP infrastructure underprovisioning rather than GFW intervention as the primary cause.
-
The bottleneck exhibits strong and consistent diurnal patterns: 80–95% of receiver–sender pairs show a standard deviation of less than 3 hours in daily slowdown duration, and the patterns persist unchanged across weekends and national holidays (May 1–2 and October 1 national day). Packet loss is strictly asymmetric — occurring only for traffic entering China (inbound data and outbound ACK packets), not for traffic leaving China.
-
The Great Bottleneck of China affects 79% of measured receiver–sender pairs, with more than 70% of those pairs suffering throughput below 1 Mbps for more than 5 hours every day. M-Lab NDT data independently corroborates this: in 64% of 75,464 tests from China, download speed was below 500 kbps.
-
Hong Kong is the sole geographic exception: it experiences no measurable slowdowns when accessing the foreign Internet, and Chinese mainland receivers accessing Hong Kong as a sender averaged only ~3 hours of slowdown per day — compared to 5–17 hours for US, European, and most Asian senders — making it an effective high-performance relay between mainland China and the rest of the world.
-
A/B testing across HTTP, HTTPS, VPN, and Shadowsocks traffic found no measurable difference in packet loss rates, ruling out censorship-targeted protocol throttling as the cause. Even at probe rates as low as one packet per 10 seconds, loss rates were similar across all protocol variants, indicating no per-connection or per-protocol speed throttling by the GFW.