Well well well, a discussion that has caught my interest.
Unfortunately, we can't do a comparison of apples to apples,
but I have a theory that all computers cost the same per pound (or kilogram
for our non-USA friends).
So, given an NT box that weighs the same as an AIX box that weighs the same
as an MVS box,
(and with the assumption that you have the latest and greatest
hardware/software for each platform, having similar applications and
capabilities, i.e.
100mbps Ethernet, etc.)
Which one will be the better performer?  I do not know the answer.
I can see potential and various advantages that each system may have.
An NT system has the lowest threshold costs, but is not as scaleable, and
probably has a lower level of functionality (at least in the TCP/IP arena).
An AIX (or generic UNIX) system can probably be implemented near the cost of
a mid to high-tier NT system, will probably perform better and have a higher
level of functionality (again in the TCP/IP arena, but would suffer somewhat
in a pure NT network environment).
An MVS system would be the most scaleable, be able to support a higher
amount of simultaneous discrete functions (i.e. batch processing AND
transaction processing AND data-mining, etc., not necessary ADSM related).
Of course the right answer for you would be some type of vision thing.  That
is, where do you want to go to.
Assuming that the goal is the lowest TCO (total cost of ownership), you
should be interested in reducing the big costs.
What are the big costs?  Well, I suspect it is not a big cost difference of
buying an NT or UNIX of MVS (again assuming the hardware weighs the same).
Nor would I suspect the cost difference be big between the hardware (again
assuming the hardware weighs the same).
So what other costs would there be?  People!!!
So, other than paying people less, how do you keep people costs down?
You minimize the amount of people you need.
How do you do that?  Well, an educated guess (I was taught this is school
many years ago) was that most people can only manage/perform 5 (or is it 7
or 9???) plus or minus 2 tasks effectively.  More than that and they get
overwhelmed.  (under that they get bored?).
If each server is considered a task, it would make sense then to minimize
the need for multiple (many) servers.
Thus, I would tend to think that an MVS system, that is much more scaleable
for all your applications, would be a better choice (with the assumptions
that were made earlier).
Just some thoughts.

Mark Mapes
PG&E




> ----------
> From:         Richard Sims[SMTP:rbs AT BU DOT EDU]
> Reply To:     ADSM: Dist Stor Manager
> Sent:         Thursday, February 11, 1999 8:45AM
> To:   ADSM-L AT VM.MARIST DOT EDU
> Subject:      Re: transfer speed
>
> >The money spent trying to make that environment fast, IMHO, would be
> better
> >spent getting away from that environment.  Big NT iron is pretty cheap at
> >this point.
>
> Indeed, it has always been an expensive struggle to get mainframes to
> serve at speeds proportional to their expense.
> I could only add that big linux iron is even cheaper than NT, and
> becoming a mission-critical platform for many companies (who are
> uncomfortable
> depending upon a monopolistic software supplier).
> I've heard rumors of IBM coming to support linux, and perhaps we
> will see an ADSM server for it.  Linux has made tremendous strides in
> the past year, with an ever-increasing amount of commercial software
> becoming available for it.
>       Richard Sims, BU
>