YueGuobin d640050d4b
docs(features): quantify the kernel netem correl bias that collapses small rates
The kernel's correlated-random generator (get_crandom, sch_netem.c) truncates
instead of wrapping, starving both edges of the stationary distribution: an
event threshold below the correlation value is almost never reached. Measured
with stock iproute2 on this kernel — uBridge's netlink encoding is identical:
loss 1% + correl 25% drops nothing over 2000 pings (expected ~2%), 10%/25%
measures ~1.8% one way, only the 50% symmetry point survives. duplicate and
reorder correl share the same comparison structure and collapse the same way;
gemodel is immune (Markov chain over plain uniform draws) and is the honest
tool for bursty loss at a chosen mean rate.

Documented in the packet-filters correlation-bias bullet, and surfaced in the
two machine-facing descriptions (MCP link_update packet_loss note, controller
filter schema) so agents and clients stop walking into the trap.
2026-10-08 19:42:18 +08:00
..
2026-09-27 18:59:42 +02:00
2026-08-18 18:02:53 +02:00
2026-09-27 19:10:11 +02:00
2024-04-22 18:51:29 +07:00
2026-10-03 19:43:58 +03:00
2026-09-27 20:21:12 +02:00