I have sometimes thought that allowing the deficit to go negative (either one quantum or one mtu) might result in slightly better service times, or tcp, or aqm behavior, given tcp's requirement for two back to back packets to release an ack.
similarly, scaling to 2 MTU at higher rates might reduce cpu load. (sch_fq uses 2mtu) -- Fixing Starlink's Latencies: https://www.youtube.com/watch?v=c9gLo6Xrwgw Dave Täht CEO, TekLibre, LLC _______________________________________________ Cake mailing list Cake@lists.bufferbloat.net https://lists.bufferbloat.net/listinfo/cake
