Subject: Re: NetBSD master CVS tree commits
To: Chris G Demetriou <Chris_G_Demetriou@UX2.SP.CS.CMU.EDU>
From: Dave Rand <firstname.lastname@example.org>
Date: 03/15/1996 18:53:07
[In the message entitled "Re: NetBSD master CVS tree commits" on Mar 15, 14:39, Chris G Demetriou writes:]
> I would say that if you're running PPP over a T1, then your CPU
> probably can't afford to be doing the compression, even if you wanted
> it (which you probably wouldn't).
Rubbish. A 386 at 25 Mhz is *quite* capable of running LAPB, and Predictor
compression at E1 (2.048Mbps) rates, and handling an Ethernet, and showing
(on ridiculously compressable data) over 6Mbps throughput. I have this
implemented - this isn't a guess.
> When you have enough bandwidth to cause a problem for a user-land
> implementation, you have enough bandwidth that you either do not need,
> or cannot do, compression...
This is a separate issue. If your CPU is bound up with other things,
which is unusual, then your througput drops, or you stop doing compression,