>[As an aside, the minimum MTU for IPv6 has been moved up to 1280 bytes.  
>Link layers that have smaller MTUs will have to have link layer driver 
>hacks to fragment and reassemble across the link.  If anybody wants

I'll pass that on, but think my colleagues would be in the pro-upping
camp, though. For

>Since you'll all just run out and read the archive, I know
>I better point out that it looked to me like the consensus on
>a conservative value was the interface MTU, rather than
>max(all interfaces).  If no one objects, I'd be delighted 
>to add a knob to allow that tweak.  There was significant
>enthusiasm for max(all interfaces) [and I want it] so I'll
>leave that in as well.  There was not much enthusiasm for, 
>and there was no insistance on, "negotiated MSS".

Kevin, that would be very kind of you.  Advertising the MSS of the
received interface be enough for me.

But where I'm coming from is that the correct thing to do _is_ the
conservative option.  I'm not saying those who, like you guys at NAS,
have HIPPI and FDDI around, cannot turn on if_maxmtu; but the default
should be ``Be conservative in what you send'', &c.

That's so fundamental to what's considered good Internet engineering
that I really dont understand why we're fighting about it.

>The simple solution is for me to stop using NetBSD and to advise other
>people here at Stanford to do the same thing.
>Is that really what you want?

>Frankly, it doesn't matter to me.  If I wanted everybody in the
>world to run my code, I'd be hacking Linux.  Now, OTOH, if somebody
>looks me in the eye and says politely, "Gee, Kevin, I 
>think you missed a case, and if you put this knob into the
>stack, it sure would help me (and possibly others) out...",
>THAT would matter to me.  I already spent my morning ride on 
>CalTrain trying to fix up the loopback MSS to do what you said 
>you needed it to do.

And thank-you for that.  I havent' seen the code, but if it were me,
I'd pass in the if pointer to the mss computation functions and let
them, uh `DTRT', whatever we agree that is.

I think my point is that I'm trying to look you and Jason in the eye
and say, well, you missed the loopback case and that's being fixed
Thank you.  But I do think you both missed a few cases, and there
needs to be a knob  to control it.

But it seems to me you're also missing another point: that the
fundamental rules of the Internet suggest, rather strongly, that the
knob should default to the other way than its current setting.

>I'm perfectly willing, even delighted, to discuss this stuff 
>with you; you and I been discussing TCP performance issues in 
>private mail for at least a couple of years, and I appreciate
>your input.  I just feel more than a little patronized here, 
>which is not what I feel when I deal with lots of other TCP 
>wizards. 

That may be so.  But those other TCP wisards don't have to put up with
Jason Thorpe accusing them of being unprofessional, or of being
incompptent, a liar, or of faking their data at every turn, now do
they?

If these TCP wizards say ``but that violates be liberal in what you
accept, conservative in what you send'', do you think Jason would tell
them ``I don't CARE''?

Do you think that might have something to do with it?

And I'm sorry if you misunderstood the `bibliograhy', cthat's just
some papers I've reread, _carefully_, in the recent future.  I
mentioned it only because as best I recall, I mentioned the Hoe paper
and a couple of others to you last month and you didn't seem familliar
with them at the time.