From owner-freebsd-hackers Tue Jul 11 10:21:35 1995 Return-Path: hackers-owner Received: (from majordom@localhost) by freefall.cdrom.com (8.6.10/8.6.6) id KAA27775 for hackers-outgoing; Tue, 11 Jul 1995 10:21:35 -0700 Received: from gndrsh.aac.dev.com (gndrsh.aac.dev.com [198.145.92.241]) by freefall.cdrom.com (8.6.10/8.6.6) with ESMTP id KAA27769 for ; Tue, 11 Jul 1995 10:21:33 -0700 Received: (from rgrimes@localhost) by gndrsh.aac.dev.com (8.6.11/8.6.9) id KAA16247; Tue, 11 Jul 1995 10:20:57 -0700 From: "Rodney W. Grimes" Message-Id: <199507111720.KAA16247@gndrsh.aac.dev.com> Subject: Re: Wanted: 100bT EISA ethernet recommendation To: dennis@et.htp.com (dennis) Date: Tue, 11 Jul 1995 10:20:57 -0700 (PDT) Cc: md@dcs.qmw.ac.uk, freebsd-hackers@freebsd.org In-Reply-To: <199507111529.LAA07234@mail.htp.com> from "dennis" at Jul 11, 95 11:29:33 am X-Mailer: ELM [version 2.4 PL24] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Content-Length: 1326 Sender: hackers-owner@freebsd.org Precedence: bulk > > >> The question is, who would build one? EISA cards are too expensive to build > >> and EISA is too slow for a 100mbs medium. If someone is making them then > >> I'll bet they have a much bigger marketing dept than engineering. > > > > > >EISA bus speed is 33Mb per sec which is 3.3 times faster than 100bT > >ethernet, so speed is not a problem. > > > >There are a couple of manufacturers offering EISA cards at the moment. > >The problem is really driver support under FreeBSD. This is the big > >question from my point of view. > > > You're arguing against yourself here. I hope that EISA is more than 33mbs > since I get 40mbs on my 10mhz ISA bus. But I was pretty sure that 100bT was > 100mbs..... You seem to like to stick your foot places that you don't have the background to stand up on. EISA is 264mbs (33MBytes/sec), and as I already stated it has plenty of umpfff to run both a 100mbs network card and a 80mbs SCSI channel full tilt and not even grunt very hard, though this does tend to kill slightly more than 50% of main memory bandwidth (which in either a _current_ PCI or EISA design becomes the contention point in this type of application). -- Rod Grimes rgrimes@gndrsh.aac.dev.com Accurate Automation Company Reliable computers for FreeBSD