In a message dated 11-23-94, Lynn Nash said to Raetus Egli:

PF>    - HPFS386 is probably slower for local use.  (This is not new
PF>      either, and I have known it all along,  but people still say
RE>they
PF>      want it included in base OS/2 because it will be faster -- it
PF>      isn't).

[snip]

RE>In conclusion, I firmly believe that HPFS386 improves the performance
RE>under most circumstances.  Using my system, a high volume I/O bound
RE>systems improvements are even higher (30-35%).  However, this seems to
RE>be a resonable benchmark and I consider 17% significant enough to
RE>worry about.  The difference is obviously larger on longer compiles.

LN>Same here but with a big caveat. You have a bus master controller and so do
LN>I. The results always seem marginal on IDE/PIO systems that I have tested.
LN>I have not tested PIO SCSI so I don't really know about them. It could be
LN>that the skeptics are all using PIO or a much smaller cache.

I was very skeptical when I read your post.  Not that I don't respect
your opinions and knowledge but because I ran extensive tests on IDE
and SCSI busmasters about 2 years ago.  The difference then between
HPFS16 and HPFS386 was significant.

However, after I read your post I did run a few tests using WARP on an 
IDE machine and have to agree with you.  There is no discernible difference
between the two.

Can you think of some obvious reasons why this would be the case?

...Raetus
___
 * MR/2 2.1 #179 * Tagline stealing is the sincerest form of flattery.

--- Maximus/2 2.02