[gin-info] [Fwd: Re: Memo on GIN-info discussions on June 20]

[Yuji Saeki]

I forward mails among Satoshi, Laura and Laurence. (5)

Yuji

-------- Original Message --------
Subject: Re: Memo on GIN-info discussions on June 20
Date: Wed, 28 Jun 2006 02:24:46 +0900
From: Satoshi Matsuoka <matsu at is.titech.ac.jp>
Reply-To: matsu at is.titech.ac.jp
To: Laura Pearlman <laura at ISI.EDU>
CC: matsu at is.titech.ac.jp, Laurence Field
<Laurence.Field at cern.ch>,saga at grid.nii.ac.jp, ysaeki at grid.nii.ac.jp,
hitoshi.sato at is.titech.ac.jp
References: <7CDDCC4ADBB6504993824620A385CA0B780665 at cernxchg14.cern.ch>
<44A015FC.2070104 at isi.edu>


On Mon, 26 Jun 2006 10:14:36 -0700
Laura Pearlman <laura at ISI.EDU> wrote:

laura> >
laura> > We need to clarify our objective, is it the minimal set of
attributes 
that we need for "Hello World" job submission? A useful VO job? Full
service discovery or full schema interoperation? I assume that for SC06
it is the "Hello World" job.
laura> I agree, although I'm not sure what "Hello World" means in this
case.  I 
laura> would like to see this clarified to, perhaps, a set of simple
queries 
laura> that we should be able to ask any of the monitoring systems
(e.g., "find 
laura> all clusters across the participating grids that have at least N
nodes 
laura> with processor type X").

laura> > We should already have mapping documents between ARC/Glue and
Glue/Naregi. From these, we should highlight the minimal attributes from
each schema that are require for "Hello World" job submission.
laura> My understanding from last week's call is that this is somewhat 
laura> complicated for CIM -- apparently CIM expresses information at a
finer 
laura> granularity than the minimal attribute set, so while it seems to
be 
laura> fairly straightforward to map CIM data to the minimal attribute
set 
laura> (using aggregation operations such as counting numbers of jobs or
in 
laura> some cases adding or multiplying numeric-valued attributes), it's
more 
laura> difficult to map the minimal attribute set onto the CIM schema.


Yes, maybe Yuji can give examples to concretify the discussions here
==> Yuji?

In any case can we now move the discussions to the gin-info malling
list?
THe new gridforge page seems ready, so it will be safe to move.

I am on the gin-wheels call now. Laura should put herself on the
Gin-wheels list now that I have other people's agreement---Laura, can
you do that (the usual majordomo mailing list)

Apparently for the moment we should be using the gin-jobs wiki, but they
are talking about moving to gridforge wiki that is being set up.

THe above question of what constitutes a grid to be "gin-ready", which
would imply that the "hello world" as we are trying to define above as
runnable as a test suite. I hope everyone would look at and review the
gin
resources the page ASAP.

						Satoshi

Satoshi Matsuoka,  Professor
Global Scientific Information and Computing Center 
 & Dept. of Mathematical and Computing Sciences
Tokyo Institute of Technology
Address: 2-12-1 Oo-okayama, Meguro-ku, Tokyo 152-8552 Japan
Tel&fax: +81-3-5734-3876   E-mail: matsu at acm.org, matsu at is.titech.ac.jp