From owner-freebsd-hackers Thu Dec 18 05:10:41 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.7/8.8.7) id FAA16956 for hackers-outgoing; Thu, 18 Dec 1997 05:10:41 -0800 (PST) (envelope-from owner-freebsd-hackers) Received: from arg1.demon.co.uk (arg1.demon.co.uk [194.222.34.166]) by hub.freebsd.org (8.8.7/8.8.7) with ESMTP id FAA16944 for ; Thu, 18 Dec 1997 05:10:30 -0800 (PST) (envelope-from arg@arg1.demon.co.uk) Received: (from arg@localhost) by arg1.demon.co.uk (8.8.5/8.8.5) id NAA18799; Thu, 18 Dec 1997 13:10:03 GMT Date: Thu, 18 Dec 1997 13:10:03 +0000 (GMT) From: Andrew Gordon X-Sender: arg@server.arg.sj.co.uk To: John Kelly cc: FreeBSD Hackers Subject: Re: 3com 3c509 card In-Reply-To: <34992437.46914518@mail.cetlink.net> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-hackers@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk On Thu, 18 Dec 1997, John Kelly wrote: > On Thu, 18 Dec 1997 01:15:50 +0000 (GMT), Andrew Gordon > wrote: > > >Note that a _standard_ cycle isn't the fastest possible cycle: 16-bit > >memory cycles have one wait state, but a board can generate 0 w/s > >cycles by holding NOWS* low. Since this is only applicable to memory > >cycles > > What prevents use of 0 WS for I/O cycles? > The ISA bus. The NOWS* signal is defined to apply only to memory cycles. This dates back to 286 machines with their main memory on the ISA bus: making the memory run at full speed was critical, dropping an extra cycle for I/O devices (many of which would insert even more wait states of their own) was not.