🚀 go-pugleaf

RetroBBS NetNews Server

Inspired by RockSolid Light RIP Retro Guy

Article View: comp.sys.ibm.pc.hardware
Article #20089

Re: local bus hard disk

#20089
From: Morgan Stair
Date: Mon, 25 Jan 1993 21:41
58 lines
3261 bytes
>First of all, bus master DMA on the ISA bus (which is a local bus, just
>for the 286 instead of the 486) _will_ prevent the CPU from accessing
>main memory. The big deal about having a faster bus is that on a hard
>drive transfer (for example) instead of the CPU grinding to a halt
>(because the bus is being used to capacity) it may still run at
>80% of peak performance. This is a big deal if you're using a
>multitasking OS like OS/2 or whatever.
>
>Dan

  This message has been cross-posted to some of the comp.os... groups
because I'd like to know whether or not they are multitasking when it
comes to disk I/O.

  Okay, have I got this right?!?!?!

(1)
  VL stands for VESA LOCAL right?

(2)
  If an MS-DOS system has a very fast hard drive it still won't notice
that much speedup, if any, because the ISA bus (at 5MB/sec) outruns
just about every available drive's ability to read its media, and
MS-DOS is going to sit around and do nothing until the file has been
read anyway.

  All a VESA system will really do here is improve the performance of
the cache on a caching controller.

(3)
  The real impact of having a VL hard drive controller will be in a
multitasking operating system, but not because disk transfers will be
sped up.  When a DMA transfer is happening on an ISA (and EISA?) bus,
the CPU can't do ANY processing (even from it's cache?) because the
bus is locked.

  A VL card will help a multitasking operating system because there
are processes which are NOT waiting for disk I/O which WOULD get held
up during the slow DMA transfer from an ISA I/O card to memory.

(4)
  Windows 3.1 enhanced mode doesn't count as a REAL multitasking
operating system in this case because it will still sit around doing
nothing while it waits for its disk I/O request to finish up (?).

  Does OS/2, does Linux, does MS-Windows 32 / MS-Windows NT count as
REAL in this sense (no I'm not trying to get flamed)?

Morgan
--
*************************************************************************
* W. Morgan Stair                        Phone: (617) 552-8783          *
* Boston College                         FAX:   (617) 552-8778          *
* Institute for Space Research           Email: morgan@dl5000.bc.edu    *
* 4 Alfred Circle                                                       *
* Bedford MA  01730                                                     *
*************************************************************************
Technical Details
Message-ID: <MORGAN.93Jan25164129@dl5000.bc.edu>
Path: arc1-ca.pugleaf.net!sparky!uunet!paladin.american.edu!europa.asd.contel.com!darwin.sura.net!ukma!hsdndev!news.cs.umb.edu!morgan
References: <1993Jan23.231824.24755@rose.com> <C1E0A1.HIq@unix.portal.com>

Show Full Headers
Complete Article Headers
Path: arc1-ca.pugleaf.net!sparky!uunet!paladin.american.edu!europa.asd.contel.com!darwin.sura.net!ukma!hsdndev!news.cs.umb.edu!morgan
From: morgan@dl5000.bc.edu (Morgan Stair)
Newsgroups: comp.sys.ibm.pc.hardware,comp.os.ms-windows.advocacy,comp.os.ms-windows.programmer.win32,comp.os.os2.advocacy,comp.os.os2.programmer,comp.os.linux
Subject: Re: local bus hard disk
Message-ID: <MORGAN.93Jan25164129@dl5000.bc.edu>
Date: 25 Jan 93 21:41:29 GMT
References: <1993Jan23.231824.24755@rose.com> <C1E0A1.HIq@unix.portal.com>
Sender: news@cs.umb.edu (USENET News System)
Distribution: all
Organization: Institute for Space Research, Boston College
Lines: 58
In-Reply-To: danb@shell.portal.com's message of 25 Jan 93 02: 01:13 GMT
Nntp-Posting-Host: dl5000.bc.edu