Cluster Poll Results (tangent into OS choices)

Josip Loncaric josip at
Fri Oct 31 16:17:35 EST 2003

Vann H. Walke wrote:

> On Fri, 2003-10-31 at 12:38, John Hearns wrote:
>>On Fri, 31 Oct 2003, Robert G. Brown wrote:
>>>It is also very interesting to me that RH (for example) thinks that
>>>there is something that they are going to provide that is worth e.g.
>>>several hundred thousand dollars in the case of a 1000+ node cluster
>>>running their "workstation" product.  Fifty dollars certainly.  Five
>>>hundred dollars maybe.  A thousand dollars possibly, but only if they
>>>come up with a cluster-specific installation with some actual added
>>I'll second that.
> Hmm... Let's take the case of a 1000 node system.  If we assume a
> $3000/node cost (probably low once rack, UPS, hardware support, and
> interconnect are added in), we arrive at an approximate hardware cost of
> $3,000,000.  If we were to use the RHEL WS list price of $179/node, we
> get $179,000 or about 6% of the hardware cost.  That is assuming RedHat
> will not provide any discount on large volume purchases (unlikely).  Is
> 6% unreasonable?    

These days, one seldom builds 1000 node systems out of basic x86 boxes. 
  Consider a 1024 node AMD64 system instead: The list price on RHEL WS 
Standard for AMD64 is $792 per node, or $811,008 for the whole cluster. 
  This is unlikely to create any sales.

RH should be paid for the valuable service they provide (patch streams 
etc.) but this is not worth $811K to builders of large clusters.  There 
are other good alternatives, most of them *MUCH* cheaper.  I fully agree 
with RGB that RH needs to announce a sensible pricing structure for 
clusters in order to participate in this market.

Would a single system image (BProc) cluster constructed by recompiling 
the kernel w/BProc patches fit RH's legal definition of a single 
"installed system" and a single "platform"?  If so, $792 for a 1024-node 
cluster would be quite acceptable...


Beowulf mailing list, Beowulf at
To change your subscription (digest mode or unsubscribe) visit

More information about the Beowulf mailing list