On Tue, Sep 28, 1999 at 07:05:49PM -0700, Jonathan Stone wrote:
> In message <19990929030333.A14856@acm.org>, Feico Dillema writes:
> 
> Um.  My take is that if disabling PMTU causes a significant TCP
> throughput reduction over a fast LAN, that's a performance bug in
> NetBSD's TCP.  Others may disagree though -- perhaps strongly :).

It has been some time ago that I saw this, and the machine I saw it 
on has changed it hardware config quite somewhat. There was no science
involved in my `comparison' between the NetBSD and FeeBSD machine.
The hardware was quite different for each of them. However, the
performance difference was significant to get me wondering and look
around. My guess is that it was not a problem in the NetBSD TCP
stack, but a problem with the Ethernet adapter n that machine
(putting an effective limit on the number of packets per second).

 
> Do you also have bigger-than-Ethernet media on the NetBSD machine
> in question?

Nope.

Feico