1PWJ/6th ITSS
Conference/21 June 2001
OUCS, Oxford and the Grid
•Introduce Myself•OUCS
– Break-out Groups
•Grid Activities–Overview–Oxford Regional Grid Centre
Paul Jeffreys
2PWJ/6th ITSS
Conference/21 June 2001
Introducing Myself
• From where have I come?!– 26 years in academic life
• First degree in physics from Manchester• PhD from Bristol in Particle Physics (‘strange decays of
hyperons’!)• Scientific Fellow at CERN in Geneva, Switzerland• Joined Rutherford Appleton Laboratory in 1982• Started teaching at Keble in 1990
– Interests• Experimental Particle Physics• Building Detectors• Scientific Computing, managing services for UK • e-Science and the ‘Grid’• Commissioned CLRC e-Science Centre
http://www.escience.clrc.ac.ukhttp://www.escience.clrc.ac.uk
3PWJ/6th ITSS
Conference/21 June 2001
OUCS• Personal Observations:
– Enjoyed my first 2 months– Significant change, very different from RAL– Some great traditions in OUCS– Considerable amount of good-will and commitment
• I believe:-– There is a crucial and exciting role to play– Recent changes to Governance Structure, and to
computing, mean that we have to re-focus and this will be challenging
– Wealth of knowledge/expertise/skills/experience• Aims for the future:
– Create an overall plan which is owned by all staff, and will ensure excellent relations with our Users, which has:-
• a revised ‘Corporate Image’• priorities re-evaluated
• First OUCS Departmental Meeting – 19 June!
4PWJ/6th ITSS
Conference/21 June 2001
Organisational ‘Break-Out’ Groups
• To encourage fresh thinking, whilst ensuring that developments owned by all members of OUCS
• Timetable:-– Start to form membership of OBGs now– Can begin when ready, but certainly by start of MT– Deliverables:-
• Short report(s?) (2-3 sides A4, structured bullet points, stating key issues and priorities for action)
• Presentation at departmental meeting at end of MT– Summary of conclusions, plans for future
• Final reports (and presentation?) submitted to ICTC
• Two of direct relevance to ITSS…
5PWJ/6th ITSS
Conference/21 June 2001
OBG1: Career Development and Internal Structure
• To revitalise a structure within OUCS which:– Encourages professional growth
• builds career path• fosters training/learning• updates job description
– Aims:• To make sure skills of staff fully used, appreciated,
developed within career structure, and to ‘enhance CV’– Best Approach?:
– Annual Reviews?, RO and SRO? Open Appraisal? IiP?
– Entire emphasis must be on benefiting the reportee
• Should this be “extended” to include IT staff outside OUCS?– How?– Part of OBG1?
6PWJ/6th ITSS
Conference/21 June 2001
OBG3: Establishing Users’ Needs
• OUCS’s future must be closely ‘connected’ with Users– Could be titled ‘Market Research’…
• How do we establish Users’ requirements?– Resort to questionnaire?!
• To whom exactly?• ITSSG, University’ and Colleges’ IT Groups• Non IT-related members of University
– Build on OxTalent survey?– How do other large scale service organisations poll
users?– What are the priorities of other service organisations
similar to OUCS?
• Should this be extended to include people outside OUCS?– Tony Brett prepared to help!
7PWJ/6th ITSS
Conference/21 June 2001
OUCS and ITSS
8PWJ/6th ITSS
Conference/21 June 2001
Front page FT, 7th Mar 2000
“‘The Grid’, as it is provisionally known, will work far more quickly and reliably than today’s internet. It should eventually enable computer users to receive exactly the information they want from anywhere in the world within seconds – and without having to go through a tortuous search process.”
9PWJ/6th ITSS
Conference/21 June 2001
Grid Overview
• Tremendous momentum established!– ‘Science will never be the same again’ DGRC, Sept
2000– Widely believed that the Grid may lead to a
revolution as profound as the World Wide Web– For more details, http://www.escience.clrc.ac.ukhttp://www.escience.clrc.ac.uk
• What are e-Science and the Grid?
10PWJ/6th ITSS
Conference/21 June 2001
e-Science and the Grid
• e-Science …– “means science increasingly done through
distributed global collaborations enabled by the Internet, using very large data collections, terascale computing resources and high performance visualisation”
• Grid ...– “the word ‘Grid’ is chosen by analogy with the
electric power grid, which provides pervasive access to power and, like the computer and a small number of other advances, has had a dramatic impact on human capabilities and society. We believe that by providing pervasive, dependable, consistent and inexpensive access to advanced computational capabilities, databases, sensors and people, computational grids will have a similar transforming effect, allowing new classes of applications to emerge.”
Foster & Kesselman, 1999
11PWJ/6th ITSS
Conference/21 June 2001
Jack Dongarra’s Vision
12PWJ/6th ITSS
Conference/21 June 2001
JD: Pictorial View
13PWJ/6th ITSS
Conference/21 June 2001
The Web vs The Grid
• The Web supports wide area data/information location and retrieval
• The Grid supports complete process initiation and execution including any necessary data location and retrieval– offers the potential to carry out significantly
large tasks– opens up new capabilities for knowledge
generation
• Currently Grid tools provide a relatively low level of operational control– higher level tools will be developed to
automate low level processes– agent technology will eventually support real
time dynamic process optimisation
14PWJ/6th ITSS
Conference/21 June 2001
NASA IPG: Motivation
• NASA … ‘Information Power Grid’
• Large-scale science and engineering is done through the interaction of people, heterogeneous computing resources, information systems, and instruments, all of which are geographically and organizationally dispersed.
• The overall motivation for “Grids” is to facilitate the routine interactions of these resources in order to support large-scale science and engineering.
• Motivation– Many facilities are moving toward making resources
available on the Grid– The Information Power Grid is NASA’s push for a persistent,
secure, robust implementation of the “Grid”
15PWJ/6th ITSS
Conference/21 June 2001
LHC Computing Challenge• Data written to “tape” ~5 Petabytes/Year (1 PB = 10Data written to “tape” ~5 Petabytes/Year (1 PB = 101515
Bytes)Bytes)
• 0.1 to 1 Exabyte (1 EB = 100.1 to 1 Exabyte (1 EB = 101818 Bytes) Bytes) (~2010) (~2020 ?) Total for the LHC Experiments(~2010) (~2020 ?) Total for the LHC Experiments
• HiggsHiggs
• New New ParticlesParticles
• Quark-Gluon Quark-Gluon PlasmaPlasma
• CP ViolationCP Violation
16PWJ/6th ITSS
Conference/21 June 2001
The Large Hadron Collider Challenge
Scalability cost management 200,000 1GHz PCs 28 PB of tape storage (2,800,000 X10GB PC disk
equivalents) 10PB of disk (1,000,000 X10GB PC disk equivalents)
Wide-area distribution WANs are only and will only be ~1% of LANs Distribute, replicate, cache, synchronise the data Multiple ownership, policies, …. Integration of this amorphous collection of Regional
Centres .. with some attempt at optimisation
Adaptability Only know how analysis is done properly once the
data arrives!! Relevance
Multiple ownership, security… generic issues
17PWJ/6th ITSS
Conference/21 June 2001
The Globus Project
• The most widely accepted ‘toolkit’• Basic research
– resource management, storage, security,networking, QoS, policy, etc.
• Running across the UK
• Toolkit - bag of services, NOT an integrated solution– Information Service (MDS) - GRIS/GIIS– Remote file management - GASS– Process monitoring - HBM– Executable management - GEM– Resource management - GRAM– Security - GSI
• Many users of Globus…increasing
18PWJ/6th ITSS
Conference/21 June 2001
£80m Collaborative projects
E-ScienceSteering
Committee
DG Research Councils
Director Director’s
Management RoleDirector’s
Awareness and Co-ordination Role
Generic Challenges EPSRC (£15m), DTI (£15m)
Industrial Collaboration (£40m)
Academic Application SupportProgramme
Research Councils (£74m), DTI (£5m)
PPARC (£26m) BBSRC (£8m) MRC (£8m) NERC (£7m) ESRC (£3m) EPSRC (£17m) CLRC (£5m)
Grid TAG
SR2000 e-Science Allocation
19PWJ/6th ITSS
Conference/21 June 2001
Core Programme Resources
• Director of e-Science, Core Programme– Proposed:
• 1 national + 8 regional ‘Grid Application Centres’– Access to development funds for Grid applications– Close links with industry, responsibility for dissemination
• Grid Start Pack• Fellowships to EU-Datagrid and iVDGL• Networking Task Force• National Grid Support Centre
• Financial break-down:-– Grid Application Centres £20M– Grid Middleware and Demos £6M– Grid IRC Research Projects £5M– e-Science Testbeds £2M– International Involvement £2M– UK Grid Support £5M
Total £40M
20PWJ/6th ITSS
Conference/21 June 2001
CERN
Cambridge
Newcastle
EdinburghUS Sites
EU
Oxford
Glasgow
Manchester
Cardiff
Soton
London
Belfast
Dublin
Proposed Regional Grid Centres
• ~£470k to ‘pass go’• £1M pot for testbed --
to be matched by industry
21PWJ/6th ITSS
Conference/21 June 2001
‘Vision’ for Oxford Bid
Bio-nanoSciences
Biomolecular Simulations
Physiology /FunctionalGenomics
MedicalImagingAnd Signals
ComputerScience
Physics(CDF)
CLRC/PPARC
StructuralBiology
OUCSBioinformatics
andComputational
Biology
22PWJ/6th ITSS
Conference/21 June 2001
Process• 6 June, Technical Advisory Group gave provisional
endorsement for ORGC• 15 June, ORGC met with representative of Tony
Hey (Anne Trefethen) to establish additional information required
• ‘Organisation of Oxford Centre’, a distributed Centre, proposed
• 18 June, ASUC approve proposed organisation• 19 June, received strong endorsement for ORGC
from Sue Iversen• 20 June, received strong endorsement from
University• Resources:-
– £0.47M to ‘pass go’– Then.. £1M DTI pot for Oxford, to be matched by
industry, and then further resources– Next SR – double resources for e-Science!
23PWJ/6th ITSS
Conference/21 June 2001
Oxford Regional Grid Centre
• ‘Distributed regional grid centre’– OSC -- will offer up to 5% of their facilities– OUBC will take responsibility for linking with the
life sciences– ComLab will house some of the Centre's staff and
will specialise in Grid training and security– BLU will be the focus for industrial outreach and
collaboration– The coordination centre, and point of contact, will
be OUCS• organise Grid activities across the University• PWJ Director – at least at start
– OUCS and Physics will commission and manage the ORGC's hardware running GLOBUS, probably a Beowulf cluster
• OUCS Hierarchical File Store will be connected?
24PWJ/6th ITSS
Conference/21 June 2001
Grid Conclusions (1)
• Considerable existing e-Science activity within OU• Tony Hey has succeeded in ‘mobilising’
Universities– Promise of OST/DTI funds worked wonders
• Established Centres– Oxford’s least well developed of any…
• Forming an institutional focus for scientific computing– Coordinate organisation (eg bids to e-Science funds)– Coordinate activities and share resources
• Creating a national academic Grid• Obliging Universities to invest themselves
– Enabled e-Science activities within OU to be brought under one umbrella
• Centres are designed to disseminate– To industry– Outside e-Science (OU very strongly placed)
25PWJ/6th ITSS
Conference/21 June 2001
Grid Conclusions (2)
• Impact on Oxford– My belief, is that this will affect the appreciation of,
provision for, and support of, IT through the University
– In turn this will have far-reaching consequences:-• Improved IT facilities for our researchers• New possibilities in teaching and distance learning• Opportunities to make our unique resources more
widely accessible– Access to new resources
• And increased collaboration with industry
• … and therefore– IT will become an even more important tool– … and we are in for an exciting time!
26PWJ/6th ITSS
Conference/21 June 2001
SETI - Searching for Life
• Arecibo telescope in Puerto Rico
• Screensaver• Home page in
33 languages• (Grid in spirit rather than practice)
• http://setiathome.ssl.berkeley.edu/