PF> HPFS386 really won't do anything for your local machine (except for
 PF> security) -- its performance features are for remote
 PF> users (in many cases, unlike regular hpfs,  hpfs386
 PF> can serv a network request at ring 0, without having
 PF> to switch up to ring 3).

 CS> I still don't agree with your assessment on this for computers with lots 
 CS> of RAM (i.e., 32MB RAM or more) and fast CPU chips 
 CS> (Pentium or faster).  For instance, a Pentium with 
 CS> 64MB RAM being used for heavy disk I/O can probably 
 CS> benefit from the larger than 2MB cache size available 
 CS> with HPFS386.

You can always design a test to skew the results in the direction you want.

My own tests statisfy me that in all but a few isolated (ie: dedicated task
PC's) real world situations OS/2 always does better with more RAM for
itself,  than stolen by a vdisk or disk cache.

I have 32mb of ram, run hpfs386,  and only use a 2mb cache.   Using a
larger cache will cause more swapping (which is not cached at all;  a
catch-22 by necessity).

I think people will see a much larger change in performance playing with
the write-back times and the /CRECL value than they will with a >2mb
disk cache.


--- Maximus/2 3.00