Date: Thu, 15 Jan 1998 16:24:20 -0700 (MST) From: Marc Slemko <marcs@znep.com> To: Luigi Rizzo <luigi@labinfo.iet.unipi.it> Cc: hackers@FreeBSD.ORG Subject: Re: delayed ACKs (fwd) Message-ID: <Pine.BSF.3.95.980115161846.15188C-100000@alive.znep.com> In-Reply-To: <Pine.BSF.3.95.980115160938.15188B-100000@alive.znep.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Erm... unless you are referring to the feature of not doing delayed acks for non-fullsized segments. See the TCP_ACK_HACK ifdef in tcp_input.c On Thu, 15 Jan 1998, Marc Slemko wrote: > On Tue, 13 Jan 1998, Luigi Rizzo wrote: > > > I found this on the tcp-impl list... can someone comment if the feature > > is still there in -current (or it ever was) ? > > Yes, as far as I know it is, however I don't have a box to try it on. > > This was the subject of the short "why 100 byte TCP segments?" thread > on hackers on Sta. or so starting with > <Pine.BSF.3.95.980110210531.3955C-100000@alive.znep.com> > > FreeBSD isn't alone in this by any means and you don't run into it that > often, but when you do it is a real pain. > >
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.BSF.3.95.980115161846.15188C-100000>