D-Grid Progress Towards Sustainability Workshop on Sustainable National Grid Services

advertisement
Workshop on Sustainable National Grid Services
Edinburgh, Feb 22 – 23, 2007
D-Grid Progress Towards Sustainability
Wolfgang Gentzsch
D-Grid
February, 2007
Wolfgang Gentzsch, D-Grid & RENCI
1
Today’s Topics
 A little history of D-Grid
 D-Grid: a few details
 2 ways towards a sustainability strategy:

1. Learn from others (analysis of major grids)

2. Learn from our own requirements
 Analyzing major grid projects
 D-Grid Sustainability Workshop
 Conclusions
February, 2007
Wolfgang Gentzsch, D-Grid & RENCI
2
History of D-Grid Initiative
• 01/2003: German scientists started D-Grid Initiative (‘UK pressure’);
report with recommendations for German Government
• 03/2004: BMBF announced 100 ME e-Science Initiative for Germany
• 08/2004: BMBF Call for Proposals for e-Learning, Knowledge
Networks, and Grid Computing
• 09/2005: D-Grid-1: 25 ME, early adopters, ‘Services for Science’
• 06/2007: D-Grid-2: new communities and services providers
• 06/2008: D-Grid-3 (?): Service Grids for research, industry, society
February, 2007
Wolfgang Gentzsch, D-Grid & RENCI
3
Sustainability, Ideas in the Beginning
 Learn from others, collaborate with others
 Sustainability in architecture (standards), technology (robust),
users (applications), market, legal, government,…
 Start with a plan for sustainability
 Users and applications drive sustainability (not only!)
 Develop clear benefits for users
 Make everything easy to use
 Political and policy landscape has to be right
February, 2007
Wolfgang Gentzsch, D-Grid & RENCI
4
D-Grid
Im Wissensnetz
...
WIKINGER
ONTOVERSE
WISENT
Textgrid
Knowledge Management
MediGrid
IN-Grid
HEP-Grid
C3-Grid
Astro-Grid
D-Grid-1
Generic Grid Middleware and Grid Services
Integration Project
February, 2007
Wolfgang Gentzsch, D-Grid & RENCI
Courtesy
Helmut Loewe, BMBF
5
D-Grid-2
Services Level Agreements
Im Wissensnetz
...
WIKINGER
...
ONTOVERSE
WISENT
Knowledge Management
Textgrid
MediGrid
IN-Grid
HEP-Grid
C3-Grid
Astro-Grid
D-Grid-1 + 2
Generic Grid Middleware and Grid Services
Integration Project
February, 2007
Wolfgang Gentzsch, D-Grid & RENCI
6
D-Grid-3
Services Level Agreements
Im Wissensnetz
...
WIKINGER
...
Knowledge Management
ONTOVERSE
Knowledge Management
WISENT
Textgrid
MediGrid
IN-Grid
HEP-Grid
C3-Grid
Astro-Grid
D-Grid-1 + 2 + 3
Generic Grid Middleware and Grid Services
Integration Project
February, 2007
Wolfgang Gentzsch, D-Grid & RENCI
7
D-Grid-3
Virtual Competence Centers for
Services
Level Agreements
Middleware,
Resources,
Support, Knowledge
Im Wissensnetz
...
WIKINGER
...
ONTOVERSE
Knowledge Management
WISENT
Textgrid
MediGrid
IN-Grid
HEP-Grid
C3-Grid
Astro-Grid
D-Grid-1 + 2 + 3
Generic Grid Middleware and Grid Services
February, 2007
Wolfgang Gentzsch, D-Grid & RENCI
8
D-Grid Middleware Stack
User
Application
Development
and
User Access
GAT API
GridSphere
Plug-In
Nutzer
Scheduling
Workflow Management
High-level
Grid
Services
Monitoring
Data management
Basic Grid
Services
UNICORE
LCG/gLite
Accounting
Billing
User/VO-Mngt
Globus 4.0.1
Security
Resources
in D-Grid
December, 2006
Distributed
Data Archive
Data/
Software
Network
Infrastructur
Wolfgang Gentzsch, D-Grid & RENCI
Distributed
Compute
Resources
9
Learn from Others:
February, 2007
Wolfgang Gentzsch, D-Grid & RENCI
10
e-Science Grid Initiatives Investigated
Initiative
Time
Funding
People *)
UK e-Science-I: 2001 - 2004
UK e-Science-II: 2004 - 2006
$180M
$220M
900
1100
TeraGrid-I:
TeraGrid-II:
2001 - 2004
2005 - 2010
$90M
$150M
500
850
Res.
Res.
ChinaGrid-I:
ChinaGrid-II:
2003 - 2006
2007 – 2010
20M RMB
50M RMB *)
400
1000
Res.
Res.
NAREGI-I:
NAREGI-II
2003 - 2005
2006 - 2010
$25M
$40M
EGEE-I:
EGEE-II:
2004 - 2006
2006 - 2008
$40M
$45M
D-Grid-I:
D-Grid-II:
2005 - 2008
2007 - 2009
$25M
$25M
*)
*) estimate
February, 2007
Wolfgang Gentzsch, D-Grid & RENCI
Users
Res.
Res. Ind.
150
250
Res.
Res. Ind.
800
1000
Res.
Res. Ind.
220
220 (= 440)
Res.
Res. Ind.
11
Main Objectives of e-Science Projects
UK e-Science:
To enable the next generation of multi-disciplinary collaborative science and
engineering, to enable faster, better or different research.
EGEE:
To provide a seamless Grid infrastructure for e-Science that is available for
scientists 24 hours-a-day.
ChinaGrid:
To provide a research and education platform by using grid technology for the
faculties and students among the major universities in China.
NAREGI:
To do research, development and deployment of science grid middleware.
TeraGrid:
Create a unified Cyberinfrastructure supporting a broad array of US science
activities using the suite of NSF HPC facilities
D-Grid:
Build and operate a sustainable grid service infrastructure for German
research (D-Grid1) and research and industry (D-Grid2)
February, 2007
Wolfgang Gentzsch, D-Grid & RENCI
12
Components of e-Infrastructures for Science
(Tony Hey, 2003)
1.
Resources: Networks with computing and data nodes, etc.
2.
Development/support of standard middleware & grid services
3.
Internationally agreed AAA infrastructure
4.
Discovery services and collaborative tools
5.
Data provenance, curation and preservation
6.
Open access to data and publications via interoperable repositories
7.
Remote access to large-scale facilities: Telescopes, LHC, ITER, ..
8.
Industrial collaboration
Ideally: having well-defined specific service & support centres
Examples, UK: OMII, DCC, NGS
13
Grid Middleware Stacks, major modules
UK e-Science:
Phase 1: Globus 2.4.3, Condor, SRB.
Phase 2: Globus 3.9.5 und 4.0.1, OGSA-DAI, Web services.
EGEE:
gLite distribution: elements of Condor, Globus 2.4.3 (via VDT distribution).
ChinaGrid:
ChinaGrid Supporting Platform (CGSP) 1.0 is based on Globus 3.9.1, and
CGSP 2.0 is implemented based on Globus 4.0.
NAREGI: NAREGI middleware and Globus 4.0.1 GSI and WS-GRAM
TeraGrid:
GT 2.4. and 4.0.1: Globus GRAM, MDS for information, GridFTP & TGCP
file transfer, RLS for data replication support, MyProxy for credential mgmnt
D-Grid:
Globus 2.4.3 (gLite) and 4.0.3, Unicore 5, dCache, SRB/iRODS, OGSA-DAI,
GridSphere, GAT, VOMS and Shibboleth
February, 2007
Wolfgang Gentzsch, D-Grid & RENCI
14
Sustainability
UK e-Science:
National Grid Service (NGS), Grid Operations Support Center (GOSC),
National e-Science Center (NeSC), Regional e-Science Centers,
Open Middleware Infrastructure Institute (OMII), Digital Curation Center (DCC)
EGEE:
Plans to establish a European Grid Initiative (EGI), together with NGIs, to provide
persistent grid service federating national grid programmes starting in 2008
ChinaGrid:
Increasing numbers of grid applications using CGSP grid middleware packages
NAREGI:
Software will be managed and maintained by Cyber Science Infrastructure Center
of National Institute of Informatics
TeraGrid:
NSF Cyberinfrastructure Office: 5 year Coop. Agreement. Partnerships with peer
grid efforts and commercial web services activities in order to integrate broadly
D-Grid:
DGI WP 4: sustainability, services strategies, and business models
February, 2007
Wolfgang Gentzsch, D-Grid & RENCI
15
e-Science Applications drive Sustainability
UK e-Science:
Particle physics, astronomy, chemistry, bioinformatics, healthcare, engineering,
environment, pharmaceutical, petro-chemical, media and financial sectors
EGEE:
2 pilot applications (physics, life science) and applications from other 7 disciplines.
ChinaGrid:
Bioinformatics, image processing, computational fluid dynamics, remote education,
and massive data processing
NAREGI:
Nano-science applications
TeraGrid:
Physics (Lattice QCD calculations, Turbulence simulations, Stellar models),
Molecular Bioscience (molecular dynamics), Chemistry, Atmospheric Sciences
D-Grid-1:
Astrophysics, high-energy physics, earth science, medicine, engineering, humanities
February, 2007
Wolfgang Gentzsch, D-Grid & RENCI
16
D-Grid: Towards a Sustainable
Infrastructure for Science and Industry
 Govt is changing policies for resource acquisition (HBFG ! )
to enable a service model
 2nd Call: Focus on Service Provisioning for Sciences & Industry
 Strong collaboration with: Globus Project, EGEE, Deisa,
CrossGrid, CoreGrid, GridCoord, GRIP, UniGrids, NextGrid, …
 Application and user-driven, not infrastructure-driven
 Focus on implementation and production, not grid research, in a
multi-technology environment (Globus, Unicore, gLite, etc)
 D-Grid is the Core of the German e-Science Initiative
December, 2006
Wolfgang Gentzsch, D-Grid & RENCI
17
Challenges for Research and Industry
•
•
•
•
•
•
•
•
•
•
•
•
Sensitive data, sensitive applications (medical patient records)
Different organizations get different benefits
Accounting, who pays for what (sharing!)
Security policies: consistent and enforced across the grid !
Lack of standards prevent interoperability of components
Current IT culture is not predisposed to sharing resources
Not all applications are grid-ready or grid-enabled
Open source is not equal open source (read the small print)
SLAs based on open source (liability?)
“Static” licensing model don’t embrace grid
Protection of intellectual property
Legal issues (e.g. FDA, HIPAA, multi-country grids)
December, 2006
Wolfgang Gentzsch, D-Grid & RENCI
18
Lessons Learned and Recommendations
– During development, operation, the grid infrastructure should be modified and
improved in large cycles only: all applications depend on this infrastructure !
– Continuity especially for the infrastructure part of grid projects is important.
Therefore, funding should be available after the project, to guarantee services,
support and continuous improvement and adjustment to new developments.
– Interoperability: Use software components and standards from open-source
and standards initiatives especially in the infrastructure and application
middleware layer.
– Close collaboration is mandatory between developers of the grid infrastructure
and the applications to best utilize grid services and to avoid application silos.
– Infrastructure should be user-friendly for easy adoption for new communities.
The infrastructure group should offer installation/operation service and support.
December, 2006
Wolfgang Gentzsch, D-Grid & RENCI
19
Lessons Learned and Recommendations
– For complex projects (infrastructure and application projects), a management
board (consisting of the leaders of the different projects) should steer
coordination and collaboration among the projects.
– On top of grid infrastructure, new projects should utilize the generic
infrastructure and focus on an application or on a specific service, to avoid
complexity and re-inventing wheels and building grid application silos. .
– Centers of Excellence should specialize on specific services, e.g. integration of
new communities, grid operation, utility services, training, support, etc.
– Participation of industry has to be industry-driven. Push from outside, even with
government funding, is not promising. Success will come only from real needs
e.g. through existing collaborations with research and industry, as a first step.
– Implement utility computing in small steps, enhancing existing service models
moderately, testing utility models first as pilots. Often, today’s government
funding models are counter-productive for utility services.
December, 2006
Wolfgang Gentzsch, D-Grid & RENCI
20
Workshop
Sustainability in D-Grid
Oct 9 – 10 2006
 Sustainability in Grids
 S. and the funding Organization (Govt)
 S. and monitoring, accounting, billing
 S. of the D-Grid Infrastructure
 S. and application communities
 Example DFN German Research Network
 S. and Industry
 S. and support
 The European Grid Initiative (EGI)
December, 2006
Wolfgang Gentzsch, D-Grid & RENCI
21
Results of the Workshop
Requirements
 There is a general need for a sustainable infrastructure
 Funding agency demands cost-neutral operation
 But: not only monetary considerations, but also research
 Benefits for all constituencies
 Long-term data preservation
 International integration
 Acceptance of infrastructure through ease of use
 Long-term planning safety for grid communities
 Include learning (GridKa), testing, support, and production
December, 2006
Wolfgang Gentzsch, D-Grid & RENCI
22
Results of the Workshop
Challenges
 Heterogeneous middleware complicates building sustainable grid
 Today: user unfriendly and complex environments
 Integration of new hardware from new partners and communities
 Currently, D-Grid is not a ‘legal’ entity
 Long-term financing of resources and their usage is not clear
 Grid-enabled software licensing model is unclear
 Broadening community grids beyond their current core members
 Germany: “Laender” investments restricted to local usage
December, 2006
Wolfgang Gentzsch, D-Grid & RENCI
23
Results of the Workshop
Steps towards a sustainable infrastructure
 Increase significantly the number of grid users
 Govt funding for D-Grid specific resources was key
 Support of several middlewares important
 Long-term goal: independence of D-Grid from funding
 Encourage Govt to change current funding policies for resources
 User-friendly user support of utmost importance (DGI & CGs)
 Industry participation as users (SMEs) and providers (IT companies)
December, 2006
Wolfgang Gentzsch, D-Grid & RENCI
24
Results of the Workshop
Conclusions and Recommendations
 D-Grid seems to be on track towards a sustainable infrastructure
 A centralized resource infrastructure is important, but the how
still has to be discussed (DGI vs CGs)
 Implementation of sustainable D-Grid only together with users (CGs)
 Sustainable usage (business) models only with users (CGs)
 Integration of D-Grid in European infrastructure is important
 Central D-Grid institution should encourage broad acceptance
of D-Grid, incl certification of and support for resources
 Role of industry unclear, but participation possible today
December, 2006
Wolfgang Gentzsch, D-Grid & RENCI
25
Lessons Learned and Recommendations
– Continuity: Grid infrastructure should be modified and improved in large cycles
only: applications depend on infrastructure !
– Sustainability: Funding should be available after end of project, to guarantee
services, support and continuous improvement.
– Interoperability: Use open-source software and standards especially in the
infrastructure and application middleware layer.
– Collaboration: between infrastructure developers and the applications, to best
utilize grid services and to avoid application silos.
– User-Friendliness: for easy adoption for new communities. Infrastructure group
should offer installation, operation and support services.
– Grid Services: Centers of Excellence should specialize on specific services,
e.g. integration of new communities, grid operation, utility services, training,
support, etc.
– Participation of Industry: has to be industry-driven. Push from outside, even
with govmnt funding, is not promising. Success comes only from real needs
e.g. through already existing collaborations between research and industry.
December, 2006
Wolfgang Gentzsch, D-Grid & RENCI
26
Many Thanks to:
• UK-e-Science:
Tony Hey, Steven Newhouse, Carole
Goble, Malcolm Atkinson, John Darlington, Trevor Cooper
Chadwick, Monica Schraefel, Luc Moreau, Paul Watson,
Aaron Turner
• TeraGrid: Charlie Catlett, Dane Skow
• ChinaGrid: Hai Jin
• Naregi: Kazushige Saga, Satoshi Matsuoka, Kenichi
Miura
• EGEE:
• D-Grid:
Bob Jones, Dieter Kranzlmueller, Erwin Laure
Uwe Schwiegelshohn, Wolfgang Guerich, Klaus
Ullmann, Klaus Peter Mickel, Matthias Steinmetz, Matthias
Kasemann, Wolfgang Hiller, Otto Rienhoff, Michael Resch,
Elmar Mittler, Wilhelm Hasselbring
• RENCI:
February, 2007
Dan Reed and Alan Blatecky
Wolfgang Gentzsch, D-Grid & RENCI
27
Download