Newsgroups: comp.os.minix
Path: utzoo!henry
From: henry@utzoo.uucp (Henry Spencer)
Subject: Re: minix on the macintosh
Message-ID: <1989Sep13.165538.24266@utzoo.uucp>
Organization: U of Toronto Zoology
References: <359@crash.cts.com>
Date: Wed, 13 Sep 89 16:55:38 GMT

In article <359@crash.cts.com> jca@pnet01.cts.com (John C. Archambeau) writes:
>The issue of DMA is more of a performance issue...

And a non-obvious one, at that.  Non-DMA systems can be faster than ones
with DMA.  If your processor keeps the bus pretty busy -- very likely
nowadays unless it's got nice big caches (the tiny ones on the 68030 do
not qualify) -- then stalling the CPU while the DMA device does its
transfers may be a net loss.  Most modern CPUs can do data copying at
full bus bandwidth (since they are usually faster than the bus), and the
protocol needed to exchange bus ownership can introduce considerable
overhead into DMA.  A non-DMA device with considerable buffering can be
a net performance win over a DMA one.  If you want an example, that's
how add-on Ethernet interfaces for Suns work.
-- 
V7 /bin/mail source: 554 lines.|     Henry Spencer at U of Toronto Zoology
1989 X.400 specs: 2200+ pages. | uunet!attcan!utzoo!henry henry@zoo.toronto.edu
