Hi all,
The following is a proposed agenda for OGSA-WG telecon on Oct. 9th
Monday from 5pm to 7pm (CDT).
The dial-in number for Monday;
US: +1 718 3541071 (New York) or
+1 408 9616509 (San Jose)
UK: +44 (0)207 3655269 (London)
Japan: +81 (0)3 3570 8225 (Tokyo)
PIN: 4371991
See more information:
- https://forge.gridforum.org/sf/go/wiki1477?nav=1
Screen share service will be provided.
URL: http://ogsa.glance.net
Session key: 1009
See more explanation:
https://forge.gridforum.org/sf/go/wiki1584?nav=1
1) Early discussion (20 min)
Note taker assignment
Roll call
Telecon minutes approval (Oct. 5)
- https://forge.gridforum.org/sf/go/doc13922?nav=1
Action Items status review (see the bottom of this email)
Agenda bashing
2) HPC profile usecase for EGA reference model (60 min)
> AI-092625b: Jem to pull definitions together and produce a new
> merged first draft.
> - Send a mail to the ogsa list about this work
> - Set Oct. 9 as the target for the first Glossary draft
> - Mike Behrens also volunteered to help out on the Glossary
Jem will write-up his first draft before the call.
> - At GGF18 the proposal was to consider OGSA as a rendering of the
> EGA reference model. Agreed that this seems a good starting
> point. It should be tested by picking a candidate topic and see
> if it is really the case.
> - Hiro proposed the OGSA HPC Profile as a test case (a concrete
> use case)
> - The HPC Profile is more detailed when compared to the style of
> the use cases in the EGA Reference Model. Therefore it would
> help flesh out what is needed in the context of OGSA. Doing UML
> would be good.
> - It was noted that EGA graphs (DAGS) are specific to
> instantiation
> - Tentative agreement on the HPC Profile proposal but need more
> information before making a decision.
Hiro will write-up draft proposal before the call.
4) Roadmap document v1.1 discussion (Chris Jordon, 20 min)
ChrisJ will report out the status of roadmap v1.1.
He will ask if current direction is on the right track or not.
The latest roadmap document:
- https://forge.gridforum.org/sf/go/doc13733?nav=1
List of included documents and associated contacts:
- https://forge.gridforum.org/sf/go/wiki1486?nav=1
Minutes from Oct. 4th roadmap call:
- https://forge.gridforum.org/sf/go/doc13923?nav=1
3) Wrap up (10 min)
AOB
<*NEXT CALL*>
https://forge.gridforum.org/sf/go/wiki1477?nav=1
Oct. 12 (Thu): <No call?>
Oct. 16 (Mon): DMTF Workregister
Oct. 19 (Thu): Information/data modeling,
Security, secure channel profile review
Oct. 23 (Mon): EGA reference model, OGSA roadmap
Oct. 26 (Thu): Information/data modeling
Oct. 30 (Mon): <TBD>
<*ACTION ITEMS*>
https://forge.gridforum.org/sf/go/wiki1569?nav=1
> From Oct. 5 call.
AI-1005a: Alan Sill willing to take responsibility for pushing
the process for getting a charter ready
AI-1005b: People to send Dave Snelling more information, ideas
for more security calls to complete coverage
(Since this does not have any specific owners, it will
be closed Oct. 19)
> From Sept. 28 call.
AI-0928a: Takuya will issue a final call on BSP-Core on the list.
AI-0928b: Takuya will get another opinion on TLS 1.1 and
ciphersuites (probably ask Frank Siebenlist)
AI-0928c: Andreas will propose new text for the reference to the
NIST document to make it clearer that it is an informative
statement
> From Sept. 25 call.
AI-0925b: Jem to pull definitions together and produce a new
merged first draft.
- Send a mail to the ogsa list about this work
- Set Oct. 9 as the target for the first Glossary draft
AI-0925c: Hiro to ask Alan Clark to ask EGA TC member who want to
contribute to join the OGSA list and this convergence work. -
Members may have changed but organizations have not
AI-0925g: Tom will send a note to the list (to: Ellen S and Fred M)
on why the current separation of service/info model may
not be quite right.
> From Sept. 21 call.
AI-0921b: Security members to discuss the BoF proposal(s) further
- For example, one outcome could be some standards
activity to mirror CAOPS activities and tie-in to OGSA
AI-0921d: Dave S to collect additional material in order to identify
security issues better.
- (AI-0921e is an issue instance)
> From Sept. 15 OGSA F2F
AI-0915a: (A Savva, S McGough): Set up a telephone conference to
collect workflow (BPEL) experience
AI-0915d: Tom will post BP base faults issue to tracker
AI-0915e: Hiro to talk with OGF Editor to start an errata process
> From Sept. 14 OGSA F2F
AI-0914f (Fred Brisard and Hiro Kishimoto): Fix the location of the
next F2F and inform the group vial the mailing list
> From Aug. 17 call
AI-0817a: Dave Berry and Jay Unger will approach groups (GIN,
Globus, etc) that have implemented practical grids and
start a discussion on how they handle data:
- how data is treated as a resource that can be scheduled
- how transfers are modeled
- how files are advertised
- how applications find files (query, by knowledge,?)
(Due Oct. 9)
> From Aug. 3 call
AI-0803e: Jun will provide an example of the CDL mechanism and why
using ID/IDREF is not a good idea.
AI-0803f: Jun will update the CDL document to remove the Environment
variables
> From July 20 F2F
- EGR-WG (Ravi) will contact Geoffrey Fox and invites him to
contribute use cases.
- Andreas to go through the minutes and formulate a reply mail to
Geoffrey on each artifact covered in these minutes.
Postponed:
Until Oct. 13 call:
AI-0915b: Ellen to check the status of the items on the
DMTF work register: report which have been done, and what
DMTF is doing for the rest.
AI-0915c: Ellen to propose new text to update the DMTF register
Until next EMS call (date TBD):
AI-0914a (Andreas Savva): Integrate the simple Data scenario just
presented into the scenarios document
AI-0913a: Andreas to update function names of BES.
AI-0913b: Andrew to write-up a couple of such JM functionalities
(short paragraph for each, e.g. time constraint as JSDL
extension.)
AI-0913c: Andreas to add another scenario to use this “terminate”
method of activity interface.
AI-0913e: Andreas to separate un-deployment as a separate scenario.
AI-0913f: Andreas to describe relation between ACS and CDDLM.
AI-0913g: Donal to provide his proposal on
"ActivityExecutionCandidate."
AI-0831e: (A Savva) Talk to ACS working group for refining this
scenario.
AI-0831f: (A Savvva) Research RNS and probably update the EMS Arch
Scenarios document
AI-0921c: Dave S (as Standards VP) to talk to the next
Security AD (when one is selected) about the Security Area
task list.
----
Hiro Kishimoto
Hi,
AI-092625b: Jem to pull definitions together and produce a new merged first draft. - Send a mail to the ogsa list about this work - Set Oct. 9 as the target for the first Glossary draft - Mike Behrens also volunteered to help out on the Glossary
Jem will write-up his first draft before the call.
I've uploaded a first draft of the converged glossary to: http://forge.gridforum.org/sf/go/doc13938?nav=1 I copied the EGA terms into a separate table at the start of the main section, and did some minor editing for format and consistency. I've also highlighted some terms and phrases that need attention, and (in column 1) indicated terms that are common to both glossaries. - Jem
Hi all,
2) HPC profile usecase for EGA reference model (60 min)
Hiro will write-up draft proposal before the call.
I've uploaded my first thoughts of OGSA HPC cluster usecase to GridForge. https://forge.gridforum.org/sf/go/doc13939 Slide deck include: - OGSA HPC cluster - Workload - Batch job: grid component mapping - OGSA HPC usecase diagram - OGSA HPC job status Have a look and give your feedback at the Monday call. Thanks, ---- Hiro Kishimoto
Hi Hiro, The issue you raise on slide 6 is key, and one which we were aware of. The question is - is it really an issue? Perhaps the real question is how we relate that object's life-cycle to a "unit of work" - i.e. a job or transaction. But maybe that's a rat hole we don't want to dive down right now. Anyway back to the class/instance question specifically. One way of modeling the HPC service in the EGA reference model would be to separate the concept of the job from the binary - see attached GIF. Each is a separate grid component. Thus multiple jobs depend on a single binary (blast or whatever) that can then be provisioned once. The active state of the deployed binary then equates to the binary being accessible and instantiable (if there is such a word) by the user who wants to run a job. Provisoning of the Job is then facilitated by the provisioning of the binary (already done) and then instantiating it within the context of the cluster. Provisioning of a specific job may of course include the creation of instance specific configuration files (another dependency of a job instance), target data (another dependency...) and command line options. Regards Paul -----Original Message----- From: ogsa-wg-bounces@ogf.org [mailto:ogsa-wg-bounces@ogf.org] On Behalf Of Hiro Kishimoto Sent: Monday, October 09, 2006 8:07 AM To: OGSA WG; Bob Thome Subject: Re: [ogsa-wg] Proposed agenda for Oct. 9th call Hi all,
2) HPC profile usecase for EGA reference model (60 min)
Hiro will write-up draft proposal before the call.
I've uploaded my first thoughts of OGSA HPC cluster usecase to GridForge. https://forge.gridforum.org/sf/go/doc13939 Slide deck include: - OGSA HPC cluster - Workload - Batch job: grid component mapping - OGSA HPC usecase diagram - OGSA HPC job status Have a look and give your feedback at the Monday call. Thanks, ---- Hiro Kishimoto -- ogsa-wg mailing list ogsa-wg@ogf.org http://www.ogf.org/mailman/listinfo/ogsa-wg
Hiro, I've had a meeting crop up at 4PM Pacific. I'd be most grateful if we could address this in the first hour. Regards Paul -----Original Message----- From: ogsa-wg-bounces@ogf.org [mailto:ogsa-wg-bounces@ogf.org] On Behalf Of Strong, Paul Sent: Monday, October 09, 2006 9:23 AM To: Hiro Kishimoto; OGSA WG; Bob Thome Subject: Re: [ogsa-wg] Proposed agenda for Oct. 9th call Hi Hiro, The issue you raise on slide 6 is key, and one which we were aware of. The question is - is it really an issue? Perhaps the real question is how we relate that object's life-cycle to a "unit of work" - i.e. a job or transaction. But maybe that's a rat hole we don't want to dive down right now. Anyway back to the class/instance question specifically. One way of modeling the HPC service in the EGA reference model would be to separate the concept of the job from the binary - see attached GIF. Each is a separate grid component. Thus multiple jobs depend on a single binary (blast or whatever) that can then be provisioned once. The active state of the deployed binary then equates to the binary being accessible and instantiable (if there is such a word) by the user who wants to run a job. Provisoning of the Job is then facilitated by the provisioning of the binary (already done) and then instantiating it within the context of the cluster. Provisioning of a specific job may of course include the creation of instance specific configuration files (another dependency of a job instance), target data (another dependency...) and command line options. Regards Paul -----Original Message----- From: ogsa-wg-bounces@ogf.org [mailto:ogsa-wg-bounces@ogf.org] On Behalf Of Hiro Kishimoto Sent: Monday, October 09, 2006 8:07 AM To: OGSA WG; Bob Thome Subject: Re: [ogsa-wg] Proposed agenda for Oct. 9th call Hi all,
2) HPC profile usecase for EGA reference model (60 min)
Hiro will write-up draft proposal before the call.
I've uploaded my first thoughts of OGSA HPC cluster usecase to GridForge. https://forge.gridforum.org/sf/go/doc13939 Slide deck include: - OGSA HPC cluster - Workload - Batch job: grid component mapping - OGSA HPC usecase diagram - OGSA HPC job status Have a look and give your feedback at the Monday call. Thanks, ---- Hiro Kishimoto -- ogsa-wg mailing list ogsa-wg@ogf.org http://www.ogf.org/mailman/listinfo/ogsa-wg
Hi Paul, Reference model discussion is the first agenda item. Let's try to finish it at one hour mark. Thanks, --- Hiro Kishimoto Strong, Paul wrote:
Hiro,
I've had a meeting crop up at 4PM Pacific. I'd be most grateful if we could address this in the first hour.
Regards Paul
-----Original Message----- From: ogsa-wg-bounces@ogf.org [mailto:ogsa-wg-bounces@ogf.org] On Behalf Of Strong, Paul Sent: Monday, October 09, 2006 9:23 AM To: Hiro Kishimoto; OGSA WG; Bob Thome Subject: Re: [ogsa-wg] Proposed agenda for Oct. 9th call
Hi Hiro,
The issue you raise on slide 6 is key, and one which we were aware of. The question is - is it really an issue? Perhaps the real question is how we relate that object's life-cycle to a "unit of work" - i.e. a job or transaction. But maybe that's a rat hole we don't want to dive down right now.
Anyway back to the class/instance question specifically. One way of modeling the HPC service in the EGA reference model would be to separate the concept of the job from the binary - see attached GIF. Each is a separate grid component. Thus multiple jobs depend on a single binary (blast or whatever) that can then be provisioned once. The active state of the deployed binary then equates to the binary being accessible and instantiable (if there is such a word) by the user who wants to run a job. Provisoning of the Job is then facilitated by the provisioning of the binary (already done) and then instantiating it within the context of the cluster. Provisioning of a specific job may of course include the creation of instance specific configuration files (another dependency of a job instance), target data (another dependency...) and command line options.
Regards Paul
-----Original Message----- From: ogsa-wg-bounces@ogf.org [mailto:ogsa-wg-bounces@ogf.org] On Behalf Of Hiro Kishimoto Sent: Monday, October 09, 2006 8:07 AM To: OGSA WG; Bob Thome Subject: Re: [ogsa-wg] Proposed agenda for Oct. 9th call
Hi all,
2) HPC profile usecase for EGA reference model (60 min)
Hiro will write-up draft proposal before the call.
I've uploaded my first thoughts of OGSA HPC cluster usecase to GridForge.
https://forge.gridforum.org/sf/go/doc13939
Slide deck include: - OGSA HPC cluster - Workload - Batch job: grid component mapping - OGSA HPC usecase diagram - OGSA HPC job status
Have a look and give your feedback at the Monday call.
Thanks, ---- Hiro Kishimoto
-- ogsa-wg mailing list ogsa-wg@ogf.org http://www.ogf.org/mailman/listinfo/ogsa-wg
participants (3)
-
Hiro Kishimoto -
Strong, Paul -
Treadwell, Jem