Fwd: Re: Karn's rule in Linux TCP

["Stuart W. Card" <stu@xxxxxxxxxxxx>]

Andi Kleen <ak@xxxxxxx> wrote --

> On Wed, Nov 08, 2000 at 08:19:08PM +0300, kuznet@xxxxxxxxxxxxx wrote:
> >
> > > Any suggestions on that?  Any other ideas?
> >
> > Right idea, in theory. But Andi, where did you find connections with 
> rtt>3sec?
>
> A misconfigured VPN with too long queues causes such long rtts when slightly
> congested :-(

Our work for the military, involving very low bandwidth (for instance, 2400 
bps)
links, that often run over geostationary satellites (additional 250 mS per hop
speed of light lag), that require link encryption (typically implemented
using long shift registers, in this case clocking at our very low bit rates),
and that are generally time division duplex, have round trip times that in
the _best_ case are _far_ longer than 3 seconds.

pgprALqlSBVcA.pgp
Description: PGP signature