[Beowulf] How Can Microsoft's HPC Server Succeed?

Mehmet Suzen mehmet.suzen at physics.org
Thu Apr 3 12:48:06 PDT 2008

On Thu, Apr 3, 2008 at 12:44 AM, Greg Byshenk <gbyshenk at byshenk.net> wrote:
> On Wed, Apr 02, 2008 at 03:04:28PM -0700, Jon Forrest wrote:
>  > But, the question remains. How can Microsoft compete with free?
>  > How much better will they have to be than standard Linux
>  > clusters before they get any mainstream interest? What technical
>  > features could they add that couldn't be added to a Linux
>  > cluster?
>  The thing to remember is that a cluster (even one running "free" --
>  as in beer -- software) is not without cost. Apart from hardware,
>  licenses (if required), etc., a business will also have to find
>  (and pay) someone to build and maintain the cluster.

It is VERY important to be clear about one point. This argument must
NOT imply that using
proprietary software to built a cluster does not require any
work-force (someone) or no training needed to operate it. At the end of the day
building a cluster is a  technological business,  you  need to hire
someone or a monkey
in order to click on buttons for installation or maintenance.  Having
proprietary software is NOT a necessary and sufficient condition that
working on these products need less training then free software counter parts,
("free" as in freedom, NOT free beer software).

>  A former co-worker of mine now works elsewhere, at a company where
>  they are looking to build a cluster for some research he will be
>  doing, and it will almost certainly run Windows. And this is not
>  because there is something "better" about Windows, but because they
>  are a Windows shop, and thus the cost of hiring or training staff
>  would more than outweigh any savings on licenses.

More information about the Beowulf mailing list