[rm-wg] Some Questions :o)
Sergio Andreozzi
sergio.andreozzi at cnaf.infn.it
Wed Jul 25 12:08:02 CDT 2007
Hi Paul
Strong, Paul wrote:
> So, if I understand correctly, the management abstractions behind the
> Service are only important in that...
>
> 1) The Job must have a way of expressing it's dependencies - that is
> what binaries it may need, what data it may need, what types of CPU it
> can run on etc. JSDL can supply this - right?
yes, JSDL is the solution for this; in its evolution, a JSDL document
will contain an XQuery expression for expressing the requirements on the
resource (e.g., OSType); the resource is expected to be modeled by GLUE;
in other words, GLUE will provide the resource description on which
users can express requirements for their jobs
> 2) The Job must have a way of expressing the desired service level
> objectives, for example desired completion time (absolute), maximum job
> duration, maximum % of resources to be consumed and so forth.
yes
> 3) The User must be able to get monitoring information and results
> from the service that include progress versus service level, resources
> consumed versus share and so forth.
yes, this is typically provided by the BES interface;
> This brings us back to what Dave was suggesting about drilling down on
> Share (to some degree). The area to be refined is perhaps more on the
> side of the interaction of the user with the service and between the two
> organizations. For example when submitting the Job and querying
> progress of the Job. Examples -
>
> 1) Do Users simply know what services they can access based on a
> set of Shares or agreements already in place between their organization
> and the Admin Domain? Do they poll services (that are presumably
> advertized) to see which ones they have shares with and which have spare
> capacity?
yes, this is the scenario in current production Grids like EGEE and the
one that we want to support for GLUE 2
> Or can they dynamically negotiate access/Shares and so forth?
this is a more complex situation; BES does not support negotiation;
there is a specific language for this (WS-Agreement), but this is not in
our focus so far
> 2) How complete or self contained does the job submission have to
> be? Thus is it simply a request for a binary already installed and made
> available by the service or can the submission include the binary and
> instructions on how this should be deployed? :o)
the second option; GLUE 1.3 includes attributes to support this
scenario; you can see a raw summary of the potential attributes for each
class in the GLUE 2 draft that you already have (below each table
there is a flat list coming from GLUE 1.3 and NorduGrid)
> This makes a big
> difference in terms of the level of detail that needs to be exposed by
> the Service and expressed in the Share concept.
I still have to digest your proposal. A couple of early comments:
1. I see the Share as a specialization of Policy; can you remind me what
are management concepts that apply to a policy? and also, what do you
think about moving from share concept to SLA?
2. can you give a draft definition of what a container is in this context?
Cheers, Sergio
More information about the rm-wg
mailing list