Published on October 29, 2007
The Grid: The Grid What is it? what is it for? Web: information sharing: Web: information sharing Invented at CERN by Tim Berners-Lee No. of Internet hosts (millions) Year Agreed protocols: HTTP, HTML, URLs Anyone can access information and post their own Quickly crossed over into public use Tim Berners-Lee [email protected]: [email protected] Search for Extra-Terrestrial Intelligence Uses home PCs to analyse radio telescope data in bits Distributed computing project, not a grid Users - 5,414,992 Results received - 1,862,972,261 Years of CPU Time – 2,286,333 Extraterrestrials found – 0 Other @home projects ClimatePrediction.net United Devices Cancer Research Project File-sharing: File-sharing No centralised database of files Legal problems with sharing copyrighted material Security problems Peer to peer Centralised network Peer-to-peer network Flashmob Computing: Flashmob Computing Over 700 PCs connected Best run – 150 PCs, 77 GFlops Good for interdependent parallel problems Cheap, ad hoc, relies on volunteers Not permanent Idea of graduate students at University of San Francisco Connect PCs via a LAN, all working on the same problem = instant supercomputer FlashMob 1 San Francisco, 7 April 2004 Grid: Resource Sharing: Grid: Resource Sharing Share more than information Data, computing power, applications MIDDLEWARE CPU Cluster User Interface Machine CPU Cluster Resource Broker Disk Server Your Program Word/Excel Email/Web Your Program Games Middleware handles everything Single computer The Grid Electricity Grid: Electricity Grid Analogy with the Electricity Power Grid Power Stations Computing Grid: Computing Grid Computing and Data Centres Fibre Optics of the Internet How does it work?: How does it work? What can you do with a Grid?: What can you do with a Grid? Astronomy Healthcare Bioinformatics Digital curation To create digital Libraries and Museums Scanning Remote consultancy Digitize almost anything Particle Physics: Particle Physics The CERN LHC: The CERN LHC 4 Large Experiments The world’s most powerful particle accelerator - 2007 ATLAS and CMS: ATLAS and CMS General purpose Origin of mass Supersymmetry 2,000 scientists from 34 countries ATLAS General purpose detector 1,800 scientists from over 150 institutions CMS LHCb and ALICE: LHCb and ALICE Studying the differences between matter and anti-matter LHCb will detect over 100 million b and b-bar mesons each year LHCb These experiments will produce Petabytes of data 1 PByte = 1,000,000 GByte Heavy ion collisions, to create quark-gluon plasmas 50,000 particles in each collision ALICE Looking for the Higgs: What is the origin of mass? Is it the Higgs Particle? Looking for the Higgs Massless Particle – Travels at the speed of light Low Mass Particle – Travels slower High Mass Particle – Travels slower still Not yet proven experimentally Bigger and better particle accelerator - LHC Why do particle physicists need the Grid?: Why do particle physicists need the Grid? Large amounts of data International collaborations Example from LHC: starting from this event… …we are looking for this “signature” Selectivity: 1 in 1013 Like looking for 1 person in a thousand world populations Or for a needle in 20 million haystacks! ~100,000,000 electronic channels 800,000,000 proton-proton interactions per second 0.0002 Higgs per second 10 PBytes of data a year (10 Million GBytes = 14 Million CDs) GridPP: GridPP 19 UK Universities, CCLRC (RAL & Daresbury) and CERN Funded by PPARC (Particle Physics and Astronomy Research Council) Currently used by running US experiments BaBar (b mesons), D0 and CDF (proton-antiproton collisions) 20 Sites 3 Countries (England, Scotland, Wales) 2,740 CPUs 67 Tbytes storage Our Grid works! LCG: LCG GridPP is part of LCG – currently the largest Grid in the world 138 Sites 34 Countries 13,784 CPUs 4402 Tbytes storage Tier Structure: Tier 0 Where data comes from Tier 1 National centres Tier 2 Regional groups Tier 3 Institutes Tier 4 Workstations Offline farm Online system CERN computer centre RAL,UK ScotGrid NorthGrid SouthGrid London Italy USA Glasgow Edinburgh Durham Tier Structure France Germany Detector UK Tier-1/A Centre: UK Tier-1/A Centre High quality data services National and International Role UK focus for International Grid development 1000 Dual CPU 200 TB Disk 220 TB Tape (Capacity 1PB) Grid Operations Centre UK Tier-2 Centres: UK Tier-2 Centres ScotGrid Durham, Edinburgh, Glasgow NorthGrid Daresbury, Lancaster, Liverpool, Manchester, Sheffield SouthGrid Birmingham, Bristol, Cambridge, Oxford, RAL PPD, Warwick London Brunel, Imperial, QMUL, RHUL, UCL Mostly funded by HEFCE Other Grids: Other Grids UK National Grid Service UK’s core production computational and data Grid EGEE (Europe) Enabling Grids for E-sciencE Nordugrid (Europe) Grid Research and Development collaboration Open Science Grid (USA) Science applications from HEP to biochemistry The Future: The Future Grow the LHC Grid Spread beyond science Healthcare, commercial uses, government, games Will it become part of everyday life?