[ale] Re: Multi-drop PPPoE (Re: Mind/link DSL and linux?) -- 386-486sx/dx

[Frank Zamenski]

I hope nobody is minding (much, anyway) a slight hardware tangent,
I'm rather interested in this stuff myself, even the old stuff. Anyway...

> buggz wrote:
> >
> > On Sun, 3 Sep 2000, Joe Knapka wrote:
> >
> > I'm really not understanding how everyone is using a pos 386 or 486 as a
> > router.
> > How are you going to get a pair of nics worth having in such a machine ?
> > Am I mis-understanding here ?
> > I thought most 100mb nics are pci.
>
> True, but most home networks are 10mbps, I'd guess, and certainly
> ISDN, ADSL, or cable routers are not going to need 100mbps interfaces
> when the outbound media top out at <2mbps. Even a 16Mhz 386
> ought to be able to push that kind of data volume around without
> much trouble.
>
> My firewall/router is a P75 with the L2 cache disabled (won't
> boot if I enable it), and a pair of 10mbps nics. It's actually
> slower bogomips-wise than my old 486DX33, but it does the job.
>
> -- Joe

Been wondering about same things buggz was myself, as I've some 386s
lying around gathering dust, and am thinking of doing a router firewall
eventually.

Now... granted many home nets are 10mbps, and many still have slow modem
dialups (like me). It seems logical that a 386/16 router should handle it
given
outbound is <2mbps as you describe, and that true 10mbps on the wire just
ain't going to happen. So let's say one can get 2-4mbps. Will the 386 as a
router really handle that, not forgetting all the overhead the OS has to
still do
to examine packets?

Anyone have any hard data for this? I have to beleive an 'average' geek
10mbps
home net with three to five PCs (or more) is going to require a min 486.

Also, interesting that your 486DX33 tops the P75. Okay, L2 is disabled,
but I've still experienced many 486s easily outperforming a P75 (with MS
as common OS to both), and IMO a 486DX4 subjectively outperforms my
old P75 significantly.

-fgz

>
> *** Joseph Knapka ***
> In any formula, constants (especially those obtained from handbooks)
> are to be treated as variables.
> --
> To unsubscribe: mail majordomo at ale.org with "unsubscribe ale" in message
body.
>

--
To unsubscribe: mail majordomo at ale.org with "unsubscribe ale" in message body.