On Tue, 21 Feb 2006 16:37:46 -0800 (PST) "David S. Miller" <[EMAIL PROTECTED]> wrote:
> From: Rick Jones <[EMAIL PROTECTED]> > Date: Tue, 21 Feb 2006 15:48:57 -0800 > > > I disagree as to whether it is "foolhardy" but regardless, they are > > perfectly _legal_ whereas a TCP stack interpreting the window field > > as a signed quantity is most certainly _illegal_. So the Linux > > stack as it behaves is rewarding explicitly broken stacks at the > > expense of stacks that are behaving perfectly legal manner. > > A lot of things are legal which result in bad performance. And that > is exactly the kind of choice these stacks are making. > > > Unless I've missed an RFC, Window scaling is an _option_ not a requirement. > > Just like this TCP option, good TCP performance is also optional :-) > > > I'm not conceding the main point just yet, but would ask if you > > agree that seeing either Timestamp or SACK options would also > > identify a stack as being one that is not in error interpreting the > > window field? > > That's one possibility. > > I still think it's foolhardy for thes stacks to behave this way, and > it's certainly asking for bad TCP performance. Some of the really old stacks were embedded devices (like printers). Rick, can you see if old HP printers work right? - To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
