Luigi Rizzo wrote: > Bottom line -- the whole architecture has been designed with > FIFO in mind, and implementing any different queueing policy > will involve some significant rewriting of the device drivers, > plus, potentially, some significant performance loss.
Thank you for detailed explanation. I hope that dummynet's WFQ would be sufficient but not sure: will it correctly process weights whith zero-bandwidth pipe? I mean one dummynet pipe (bw 0) and two dummynet queues for that pipe assigning weight 1 and weight 100. That's for each direction of traffic, of course. Eugene _______________________________________________ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-net To unsubscribe, send any mail to "[EMAIL PROTECTED]"
