Xref: utzoo comp.windows.ms:3864 comp.sys.ibm.pc.misc:386
Path: utzoo!attcan!uunet!cs.utexas.edu!news-server.csri.toronto.edu!utgpu!watserv1!daemon
From: tom@mims-iris.waterloo.edu (Tom Haapanen)
Newsgroups: comp.windows.ms,comp.sys.ibm.pc.misc
Subject: Re: Hyperdisk -- the Smartdrive replacement
Message-ID: <1990Jul31.133423.19743@watserv1.waterloo.edu>
Date: 31 Jul 90 13:34:23 GMT
References: <1990Jul30.203704.13570@ncsuvx.ncsu.edu>
Sender: daemon@watserv1.waterloo.edu
Organization: University of Waterloo, WATMIMS Research Group
Lines: 26

George Browning <george@shumv1.ncsu.edu> writes:
> I downloaded a benchmarks file from Compuserve and it looks like
> Hyperdisk is a much better product.  Hyperdisk can use an optional write
> cache which speeds up disk access considerably.
>
> Cache used:     	   none	     SD     SD    HD     HD     HD    HD
> Cache size (kb):          0        1024   2048  1024   2048   1024  2048
> DOS memory used (kb):     0        14     16    21     23     21    23
> Write cache:              n/a      n/a    n/a   no     no     yes   yes
> Overall results:          87.45    47.73  48.01 49.48  49.38  6.97  7.14

Well, to me it lloks like Hyperdisk is slower than SamrtDrive unless you
enable write caching, and it takes another 7K of DOS memory, too --- which
matters when you're running non-Windows apps.  Also, I find that in real
life, my disk ends up doing *MUCH* more reading than writing, reducing the
improvement available from write caching.

Personally I wouldn't take a chance by caching writes; a power failure or
a system crash might wipe out what you thought had already been written
to disk.

If you want higher disk performance, consider a disk controller with a
built-in cache.

[ \tom haapanen --- university of waterloo --- tom@mims-iris.waterloo.edu ]
[ "i don't even know what street canada is on"               -- al capone ]