>
> On Wed, 2 Sep 1998, Alan Cox wrote:
>
> > > If I corrupt loopback so it fails to transmit a few packets, I can
> > > emulate the same kind of TCP stalls that have frequented the kernel.
> >
> > I'd expect exactly what you describe. TCP cannot cope with loss above
> > 1 frame per pipe length without seriois performance loss. Typically thats
> > 5-10% loss. Above that it will back off a lot.
> >
> > Your model is then flawed because the back off doesnt induce lower error
> > rates through reduced congestion. You model a continuous 25% loss link
> > layer - and that is something that unaided is beyond the capabilities
> > of an IP network.
> >
> > Alan
> >
>
> Okay. That's good. This might point to a serious problem with the PPP
> link (losing lots of packets), because that's where the bad stalls occur.
>
> I can run serial I/O to serial I/O (regular 'C' programs in Linux) between
> two computers with two modems _and_ the phone line with only an occasional
> lost character (actually a group of 6), far less than 1/2 percent. Maybe
> flow-control isn't working in PPP??
Try using a smaller window for ppp (works for me.)
My ppp startup script executes the following after bringing up ppp:
/sbin/route del default dev ppp0
/sbin/route add default window 16384 dev ppp0
Without it, certain files are impossible to download from some ISP's;
with it, I have no problems whatsoever. (This is with only 2.0.* --
there is too much I need to use that is still broken on 2.1.* so I
have not tried it yet (although I did notice that there was talk of a
major change in the Window code.))
(Just a possibly off-topic comment from the peanut gallery -- gentle
flames only please.)
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.altern.org/andrebalsa/doc/lkml-faq.html