Xref: utzoo comp.unix.xenix:3505 comp.unix.questions:9534 comp.unix.microport:1706 comp.sys.ibm.pc:19904
Path: utzoo!attcan!uunet!husc6!mailrus!purdue!decwrl!pyramid!ctnews!starfish!cdold
From: cdold@starfish.Convergent.COM (Clarence Dold)
Newsgroups: comp.unix.xenix,comp.unix.questions,comp.unix.microport,comp.sys.ibm.pc
Subject: Re: *nix performance
Message-ID: <736@starfish.Convergent.COM>
Date: 2 Oct 88 17:41:44 GMT
References: <9902@ico.ISC.COM>
Organization: Convergent Technologies, San Jose, CA
Lines: 20

From article <9902@ico.ISC.COM>, by rcd@ico.ISC.COM (Dick Dunn):
>> | One of my main interests is whether a fast (25MHz with cache etc) 386 with
>> | some users attached to it can compare itself with a VAX/750 or other minis.
> 
> Also, think very carefully about what sort of disk(s) you're going to put
This also harks back to the MAC - vs - PC discussion of a particular DMA
not being as fast as CPU data transfer.  A DMA activity does take some setup
time.  If the system (single-tasking) is going to be idle until the disk
transfer is complete, -and- the CPU is fast enough to handle disk data on the
fly, -then- CPU will be faster than DMA.
As soon as you talk multi-user, that argument goes away, because the CPU could
be working on a different process, while the DMA occurs offline.
Multi-user performance is distinctly different from single user.
Do buy the fastest disk you can.  Don't forget that with the proper controller,
two slower disks might actually be faster in a multi-user setup.
-- 
---
Clarence A Dold - cdold@starfish.Convergent.COM		(408) 435-5274
		...pyramid!ctnews!mitisft!professo!dold
		P.O.Box 6685, San Jose, CA 95150-6685