I've been comparing simple ns drop experiments with FreeBSD. Based on
your explanation (below), I've accounted for one difference and switched
to FreeBSD 4.5.
I'm seeing another discrepancy and would like to verify that it is
intended behavior. Though this is related to my original questioni
I'm seeing what I believe to be a bug in FreeBSD 4.3's New Reno fast
retransmit algorithm-- delays of up to 1 second between
retransmissions. Would someone please verify and/or correct me? If
this is a bug, has it been fixed?
I'm using dummynet between two nodes to drop the 10th _data_ pack
To compare against simulation, I'm trying to collect any available TCP
implementations -- preferably compatible with a
recent(ish) kernel. We run 4.3, but could upgrade. I was hoping to find
the usual suspects -- Tahoe, Reno, Vegas, New-Reno, and SACK.
I realize this question is probably bette
