[ur-wg] some doubts about the UR-Spec

[Lombrera Lombrera]

Hi Rosario,
 
first, thanks for your reply. 
 
Yes, I think you are right about the NodeCount.
 
Do you know (or someone else know) if there is a ER model that need to be followed about the "commun usage record properties"?
 
Something like this: "ProjectName" can have none or more "JobId" associated with it. A "JobId" is always associated with only one "ProjectName".... and so on?
 
Or it can be invented it other ways?
 
Thanks all,
Carlos.


Rosario Michael Piro <piro at to.infn.it> escreveu:Hi Carlos,

I'm not one of the authors so I might be wrong, but I suppose there is 
some inconsistency between Table A-4 and the rest of the document.
What is called "NumNodes" in Table A-4 most probably is the "NodeCount" 
described in the Sections 2.23 (on page 15, draft of May 2005) and 10.5 
(page 38).
Am I right?

If yes, on page 15 it says:
"... Number of nodes used. A node definition may be dependent on the 
architecture, but typically a node is a physical machine. For example a 
cluster of 16 physical machines with each machine having one processor 
each is a 16 "node" machine, each with one "processor". A 16 processor 
SMP machine however, is 1 physical node (machine) with 16 processors. ..."

So immagine one job (one job ID) that runs on a small cluster of 8 
dual-processor machines ... you would have 1 job ID, 8 nodes and 16 
processors.

Cheers,

Rosario.

Lombrera Lombrera wrote:
> Hi all,
> 
> My name is Carlos and I am devepoping a tool in my graduation course 
> that gonna generate some graphs about statistics data in a grid.
> 
> Searching the web I found the UR-WG project and I think it would be cool 
> to use the proposed format recommendation.
> 
> I just have some doubts that I hope someone could help me:
> 
> a) In the table A-4 "Common Usage Record Fields" from the document 
> "UR-WG-Spec",
> 
> When the "NumNodes" Resource Name would be more than 1?
> In what kind of situations this could occur?
> In my head, if it is related to JobId, it will ever be 1.
> 
> I am wrong? Someone could clarify me?
> 
> 
> b) Is there a ER model about this table (Common Usage Record Fields)?
> 
> Well... that´s it. Excuse-me for my begginer questions and my poor english.
> Thanks in advance.
> 
> Carlos.
> 
> ------------------------------------------------------------------------
> Yahoo! Acesso Grátis < 
> http://us.rd.yahoo.com/mail/br/taglines/*http://br.acesso.yahoo.com/>: 
> Internet rápida e grátis. Instale o discador agora! < 
> http://us.rd.yahoo.com/mail/br/taglines/*http://br.acesso.yahoo.com/>


-- 
-------------------------------------
Rosario Piro (piro at to.infn.it)
http://www.to.infn.it/~piro/
-------------------------------------
Istituto Nazionale di Fisica Nucleare
Sezione di Torino
-------------------------------------
National Insitute for Nuclear Physics
Section of Turin, Italy
-------------------------------------



		
---------------------------------
Yahoo! Acesso Grátis: Internet rápida e grátis. Instale o discador agora!
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://www.ogf.org/pipermail/ur-wg/attachments/20050713/2ecc45e1/attachment.htm