Transcript OSG Science Advisory Group Bill Kramer NERSC/LBNL June 12th 2007 Agenda 9am – Introduction to the Open Science Grid - Background and Activities  Introductions and.

OSG Science Advisory Group
Bill Kramer
NERSC/LBNL
June 12th 2007
Agenda
9am – Introduction to the Open Science
Grid - Background and Activities
 Introductions and Logistics - Bill
 OSG Overview - Ruth
 OSG Users and Applications - Torre
 OSG Facility – Miron
12-1 – Lunch/Discussion
Scientific Advisory Group 11/6/2015
2
Agenda
1 PM – 3 PM – Topic Discussions
 Discussion – How do we know our stakeholders and
users are satisfied with OSG services including
reliability, availability, usability, support?
 Discussion - Is the OSG road map on course to have
impact on improved science for our stakeholders?
 Discussion - How do we match user expectations to
the realities of resources - both physical
(computational, storage, etc.) and human?
 Discussion - Growth in Impact and Growth of
funding. How much do we need to diversify between
now and 2011?
Scientific Advisory Group 11/6/2015
3
Agenda
3 - Present Summary Slides from
Discussion
3:30 - Committee Executive Time
4:30 pm – Conclusion and Out Brief
5pm – Depart
Scientific Advisory Group 11/6/2015
4
Introductions
• OSG Participants
 Bill Kramer – OSG Council Chair
 Ruth Pordes – OSG Executive Director
 Miron Livny – OSG Facility Manger
 Paul Avery - – Resource Co-Manager
 Kent Blackburn – Resource Co-Manager
 Torre Wenaus – Application Co-Coordinator
 Mike Wilde – Education, Training and Outreach
Coordinator
 Ian Foster – Council Member and Globus Alliance
 Chander Sehgal – OSG Project Associate
Scientific Advisory Group 11/6/2015
5
Introductions
• Advisors
 Dr. Barry Barish
 Dr. David Schwartz
 Dr. Helene Armitage
• Not Attending
 Dr. Ari Patrinos
Scientific Advisory Group 11/6/2015
6
Questions for the SAC
•
•
•
Is the OSG road map appropriate and will it likely
result in substantial impact on improved science
impact for our stakeholders?
Please make recommendations on how OSG
should assess its impact on current and future
scientific projects and recommend areas of
NSF/DOE science that OSG should engage for
wider impact.
Please provide comments on the steps OSG
should take to define a sustaining model of service
after this phase of the OSG project completes in
2011.
Scientific Advisory Group 11/6/2015
7
A Collaboration of Many Roles
• Consortium and Project
• Virtual Organizations and Sites
• DOE and NSF
Scientific Advisory Group 11/6/2015
8
The OSG Consortium and the OSG
Project
• OSG is a large collaborative activity.
• The OSG Consortium comprises all institutions and
projects that contribute to OSG.
 The OSG Council is the governing body of the Consortium.
The OSG Council provides the scientific coordination and
oversight of OSG activities. The OSG Council shall self
select a chair to lead the council. The term for the Chair
shall be two years. Individuals can serve no more than two
full consecutive terms as chair.
• The OSG Project is funded to provide staff for
specific aspects of managing and sustaining the
OSG.
 The OSG Council elects an Executive Director to manage
programmatic activities with the help of an Executive Team.
The Executive Director appoints an Executive Board to direct
the OSG program of work, draw up policies and represent
the OSG Consortium in dealing with other organizations and
committees
Scientific Advisory Group 11/6/2015
9
Virtual Organizations and Sites
•
OSG brings together many VOs for
•
A Virtual Organization (VO) is a collection of people (VO members),
•
A Site is a collection computing/storage resources (sites) and services
(e.g., databases). and the terms "Site," "Computing Element" ("CE"),
and/or "Storage Element" ("SE") to refer to the resources owned and
operated by a VO or other organization.
 opportunistic sharing of resources in a grid environment
 allowing for more effective use of their collective resources
 Allowing easier use of dedicated/allocated resources that are distributed
 A VO's member structure may include groups, subgroups and/or roles into
which it divides its members according to their responsibilities and tasks,
such that they are accorded appropriate levels of authorization.
 In order to receive the appropriate authorization at another VO's site, a
user's grid job must be able to present an authentication token along with a
token indicating the desired computing privileges.
 Use of the resources at a site is determined by a combination of the site's
local policies and the user VO's policies. VOs are responsible for
contracting individually with each other for guaranteed access to resources.
 Groups the provide software are also known as resource providers
Scientific Advisory Group 11/6/2015
10
DOE and NSF
• OSG is Co-funded by the DOE and NSF
 Proportion
• Multiple Stakeholders
• Different sites and VOs funded by one
or the other
• Many VOs and some sites not funded
by primary stakeholders
Scientific Advisory Group 11/6/2015
11
OSG Organization
Scientific Advisory Group 11/6/2015
12
OSG Council Membership
Brookhaven National Laboratory
Howard Gordon
Site
Collider Detector at Fermilab (CDF)
Ashutosh Kotwal
VO
Condor Project
Miron Livny
Site/Resource Provider
DZero Collaboration
Brad Abbott
VO
Fermi National Accelerator Laboratory
Vicky White
Site
Globus Alliance
Ian Foster
Resource Provider
ISI
Ann Chervenak
Site
Grid Research and Education Group at
Iowa (GROW)
Shaowen Wang
VO
Indiana University
Site
International Virtual Data Grid Laboratory
(iVDGL)
Paul Avery
VO
Laser Interferometer Gravitational-Wave
Observatory (LIGO)
Warren Anderson
VO
Lawrence Berkley National Laboratory
Bill Kramer*
Site
Nanohub Project
Sebastien Goasguen
VO
Purdue University
Gary Bertoline
Site
Sloan Digital Sky Survey (SDSS)
Chris Stoughton
VO
Scientific Advisory Group 11/6/2015
13
OSG Council Membership
Solenoidal Tracker at RHIC (STAR)
Jerome Lauret
VO
Stanford Linear Accelerator Center (SLAC)
Richard Mount, Bob
Cowles
Site
Storage Resource Manager (SRM)
Don Petravick
Resource Provider
Texas Advanced Computing Center
Warren Smith, Maytal
Dahan
Site
Thomas Jefferson National Accelerator
Facility
Andy Kowalksi
Site
United States ATLAS Collaboration
John Huth
VO
US Atlas S&C
Jim Shank
VO
United States Compact Muon Solenoid
(CMS) Collaboration
Lothar Bauerdick,
Harvey Newman
VO
Ex-Officio (Partners)
Enabling Grids for E-Science (EGEE)
Project
Bob Jones, Erwin
Laure
TeraGrid
Dane Skow
Worldwide LHC Computing Grid
Collaboration (WLCG)
Les Robertson
Scientific Advisory Group 11/6/2015
14
OSG Cultural Issues
• Diverse community with individual
working cultures
• Setting Expectations
 Resources
 Services
 Schedule
 Software
• Few people are full time
Scientific Advisory Group 11/6/2015
15
Long Term Issues OSG Is Facing
• How to set expectations for providing
opportunistic services
 Surplus, probability, joint scheduling
• Sites and VO alignments/mis-alignments
• OSG does not develop nor does it control any
SW it uses
• What does it mean to be a facility that has not
physical resources
• How to evolve to a sustaining effort
Scientific Advisory Group 11/6/2015
16
Role of the Science Advisory Group
• The Scientific Advisory Group periodically reviews
OSG activities and advises the OSG Council (and
Executive Team) on matters related to OSG.
• The SAG members are appointed by the OSG
Council Chair with input from the Council and the
Executive Team.
• The comments of the SAG will be summarized
and shared with the Council and others
Scientific Advisory Group 11/6/2015
17
Questions for the SAC
•
•
•
Is the OSG road map appropriate and will it likely
result in substantial impact on improved science
impact for our stakeholders?
Please make recommendations on how OSG
should assess its impact on current and future
scientific projects and recommend areas of
NSF/DOE science that OSG should engage for
wider impact.
Please provide comments on the steps OSG
should take to define a sustaining model of service
after this phase of the OSG project completes in
2011.
Scientific Advisory Group 11/6/2015
18