Re: A Customer's Request For Open Source Software

[Christopher Browne <cbbrowne@acm.org>]

In an attempt to throw the authorities off his trail, Jacob Sparre Andersen <sparre@crs4.it> transmitted:
> Christopher Browne wrote:
>> The world rejoiced as "Robert I. Eachus" <rieachus@attbi.com> wrote:
>>>Alexander Kopilovitch wrote:
>
> [ viewing CPU's as just another resource ]
>
>> That can only conceivably be supported on hardware that conciously
>> supports adding and dropping CPUs while the system is "hot."
>
> I am not sure I agree with you on this point.  I beleive that MOSIX
> actually allows you to do something like that, although the units
> you add or drop are whole physical machines and not just single
> CPU's or memory blocks.

That agrees with what I have heard about MOSIX.

There's a BIG efficiency difference between the approaches, to the
point of massively changing the approaches you would take to using the
'cluster.'

If the CPUs are on the same bus, then you can assume quick inter-CPU
communications, and that changes task scheduling rather a lot as
compared to off-host scheduling of work.

>> But mandating an OS design that mandates this
>> "many-times-more-expensive" sort of hardware in days when
>> over-the-counter hardware is so cheap and available seems almost as
>> limiting as the lack of an "adding CPUs" feature.
>
> If it is sufficient to be able to add or drop physical machines from
> a networked cluster of machines that make up the Multics site, then
> I don't see it as a problem.

If that were the proper interpretation, I wouldn't see it as a big
problem.  Which interpretation is right seems to me to be a pretty big
/design/ question...
-- 
output = reverse("moc.enworbbc" "@" "enworbbc")
http://www.ntlug.org/~cbbrowne/
Coming  Soon  to a  Mainframe  Near  You!   MICROS~1 Windows  NT  6.0,
complete with VISUAL JCL...