Presentation is loading. Please wait.

Presentation is loading. Please wait.

Tony Doyle - University of Glasgow 10 January 2005Oversight Committee GridPP: status report Andy Parker (Taken from GridPP report at OSC by Tony Doyle)

Similar presentations


Presentation on theme: "Tony Doyle - University of Glasgow 10 January 2005Oversight Committee GridPP: status report Andy Parker (Taken from GridPP report at OSC by Tony Doyle)"— Presentation transcript:

1 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee GridPP: status report Andy Parker (Taken from GridPP report at OSC by Tony Doyle)

2 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee Contents What was GridPP1? What is GridPP2? Vision Challenges LCG –Data Challenges –Issues Deployment Status (9/1/05) –Tier-1/A, Tier-2, NGS M/S/N EGEE Middleware Applications Dissemination What lies ahead? Beyond GridPP2 Grid and e-Science Support in 2008 Executive Summary

3 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee What was GridPP1? A team that built a working prototype grid of significant scale > 2,000 (9,000) CPUs > 1,000 (5,000) TB of available storage > 1,000 (6,000) simultaneous jobs A complex project where 88% of the milestones were completed and all metrics were within specification A Success “The achievement of something desired, planned, or attempted”

4 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee What is GridPP2? Structures agreed and in place (except LCG phase-2) 253 Milestones, 112 Monitoring Metrics at present. Must deliver a “Production Grid”: robust, reliable, resilient, secure, stable service delivered to end-user applications. The Collaboration aims to develop, deploy and operate a very large Production Grid in the UK for use by the worldwide particle physics community.

5 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee Vision 1.SCALE: GridPP will deliver Grid middleware and hardware infrastructure to enable the construction of a UK Production Grid for the LHC of significant scale. 2.INTEGRATION: The GridPP project is designed to integrate with the existing Particle Physics programme within the UK, thus enabling full use of Grid technology and efficient use of shared resources. 3.DISSEMINATION: The project will disseminate the GridPP deliverables in the multi- disciplinary e-Science environment and will seek to build collaborations with emerging non-PPARC Grid activities both nationally and internationally. 4.UK LHC COMPUTING: The main aim is to provide a computing environment for the UK Particle Physics Community capable of meeting the challenges posed by the unprecedented data, processing and analysis requirements of the LHC experiments. 5.OTHER UK PARTICLE PHYSICS COMPUTING: The process of creating and testing the computing environment for the LHC will naturally support the current and next generation of highly data intensive Particle Physics experiments. 6.EGEE: Grid technology is the framework used to develop the required capability: key components will be developed as part of the EGEE project and elsewhere. 7.LCG: The collaboration builds on the strong computing traditions of the UK at CERN. GridPP will make a strong contribution to the LCG deployment and operations programme. 8.INTEROPERABILITY: The project is integrated with national and international developments from other Grid projects and the GGF in order to ensure a common set of principles, protocols and standards that can support a wide range of applications. 9.INFRASTRUCTURE: Provision is made for a Tier-1 facility at RAL and four Regional Tier-2s, encompassing the collaborating Institutes. 10.OTHER FUNDING: The Tier-1 and Tier-2s will provide a focus for dissemination to the academic and commercial sector and will attract additional funds such that the full programme can be realised.

6 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee Must share data between thousands of scientists with multiple interests link major (Tier-0 [Tier-1]) and minor (Tier-1 [Tier-2]) computer centres ensure all data accessible anywhere, anytime grow rapidly, yet remain reliable for more than a decade cope with different management policies of different centres ensure data security be up and running routinely by 2007 What are the Grid challenges?

7 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee What are the Grid challenges? Data Management, Security and Sharing 1. Software process 2. Software efficiency 3. Deployment planning 4. Link centres 5. Share data 6. Manage data7. Install software 8. Analyse data9. Accounting 10. Policies

8 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee LCG Overview By 2007: - 100,000 CPUs - More than 100 institutes worldwide - building on complex middleware being developed in advanced Grid technology projects, both in Europe (Glite) and in the USA (VDT) - prototype went live in September 2003 in 12 countries - Extensively tested by the LHC experiments during this summer

9 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee Data Challenges Ongoing.. Grid and non-Grid Production Grid now significant CMS - 75 M events and 150 TB: first of this year’s Grid data challenges ALICE - 35 CPU Years Phase 1 done Phase 2 ongoing LCG Entering Grid Production Phase..

10 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee Data Challenge 7.7 M GEANT4 events and 22 TB UK ~20% of LCG Ongoing.. (3) Grid Production ~150 CPU years so far Largest total computing requirement Small fraction of what ATLAS need.. Entering Grid Production Phase..

11 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee LHCb Data Challenge 424 CPU years (4,000 kSI2k months), 186M events UK’s input significant (>1/4 total) LCG(UK) resource: –Tier-1 7.7% –Tier-2 sites: –London 3.9% –South 2.3% –North 1.4% DIRAC: –Imperial 2.0% –L'pool 3.1% –Oxford 0.1% –ScotGrid 5.1% DIRAC alone LCG in action /day LCG paused Phase 1 Completed /day LCG restarted 186 M Produced Events Entering Grid Production Phase..

12 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee Paradigm Shift Transition to Grid… Jun: 80%:20% 25% of DC’04 Aug: 27%:73% 42% of DC’04 May: 89%:11% 11% of DC’04 Jul: 77%:23% 22% of DC’ CPU · Years

13 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee Issues https://edms.cern.ch/file/495809/2.2/LCG2-Limitations_and_Requirements.pdf First large-scale Grid production problems being addressed… at all levels “LCG-2 MIDDLEWARE PROBLEMS AND REQUIREMENTS FOR LHC EXPERIMENT DATA CHALLENGES”

14 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee Is GridPP a Grid? 1.Coordinates resources that are not subject to centralized control 2.… using standard, open, general-purpose protocols and interfaces 3.… to deliver nontrivial qualities of service 1.YES. This is why development and maintenance of LCG is important. 2.YES. VDT (Globus/Condor-G) + EDG/EGEE(Glite) ~meet this requirement. 3.YES. LHC experiments data challenges over the summer of

15 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee GridPP Deployment Status (9/1/05) Three Grids on Global scale in HEP (similar functionality) sitesCPUs LCG (GridPP)90 (16)9000 (2029) Grid3 [USA] NorduGrid GridPP deployment is part of LCG (Currently the largest Grid in the world) The future Grid in the UK is dependent upon LCG releases totalCPUfreeCPUrunJobwaitJobseAvail TBseUsed TBmaxCPUavgCPU Total

16 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee UK Tier-1/A Centre Rutherford Appleton Laboratory High quality data services National and international role UK focus for international Grid development 1000 CPU 200 TB Disk 60 TB Tape (Capacity 1PB) Grid Resource Discovery Time = 8 Hours 2004 CPU Utilisation2004 Disk Use

17 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee Tier-1/A Capacity Planning Resource planning estimates required for all experiments, esp. BaBar and each of the 4 LHC experiments for Int’l. MoUs ( ) UK author cost model implemented

18 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee UK Tier-2 Centres ScotGrid Durham, Edinburgh, Glasgow NorthGrid Daresbury, Lancaster, Liverpool, Manchester, Sheffield SouthGrid Birmingham, Bristol, Cambridge, Oxford, RAL PPD, Warwick LondonGrid Brunel, Imperial, QMUL, RHUL, UCL

19 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee Level-2 Grid In future will include services to facilitate collaborative (grid) computing Authentication (PKI X509) Job submission/batch service Resource brokering Authorisation Virtual Organisation management Certificate management Information service Data access/integration (SRB/OGSA-DAI/DQPS) National Registry (of registry’s) Data replication Data caching Grid monitoring Accounting * Leeds Manchester * * Oxford RAL * * DL

20 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee Middleware Development Configuration Management Storage Interfaces Network Monitoring Security Information Services Grid Data Management

21 Enabling Grids for E-sciencE INFSO-RI LHCC Comprehensive Review – November Prototype Middleware Status & Plans (I) Workload Management –AliEn TaskQueue –EDG WMS (plus new TaskQueue and Information Supermarket) –EDG L&B Computing Element –Globus Gatekeeper + LCAS/LCMAPS  Dynamic accounts (from Globus) –CondorC –Interfaces to LSF/PBS (blahp) –“Pull components”  AliEn CE  gLite CEmon (being configured) Blue: deployed on development testbed Red: proposed

22 Enabling Grids for E-sciencE INFSO-RI LHCC Comprehensive Review – November Prototype Middleware Status & Plans (II) Storage Element –Existing SRM implementations  dCache, Castor, …  FNAL & LCG DPM –gLite-I/O (re-factored AliEn-I/O) Catalogs –AliEn FileCatalog – global catalog –gLite Replica Catalog – local catalog –Catalog update (messaging) –FiReMan Interface –RLS (globus) Data Scheduling –File Transfer Service (Stork+GridFTP) –File Placement Service –Data Scheduler Metadata Catalog –Simple interface defined (AliEn+BioMed) Information & Monitoring –R-GMA web service version; multi-VO support

23 Enabling Grids for E-sciencE INFSO-RI LHCC Comprehensive Review – November Prototype Middleware Status & Plans (III) Security –VOMS as Attribute Authority and VO mgmt –myProxy as proxy store –GSI security and VOMS attributes as enforcement  fine-grained authorization (e.g. ACLs)  globus to provide a set-uid service on CE Accounting –EDG DGAS (not used yet) User Interface –AliEn shell –CLIs and APIs –GAS  Catalogs  Integrate remaining services Package manager –Prototype based on AliEn backend –evolve to final architecture agreed with ARDA team

24 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee Application Development ATLAS LHCbCMS BaBar (SLAC) SAMGrid (FermiLab) QCDGridPhenoGrid

25 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee More Applications ZEUS uses LCG needs the Grid to respond to increasing demand for MC production 5 million Geant events on Grid since August 2004 QCDGrid For UKQCD Currently a 4-site data grid Key technologies used - Globus Toolkit European DataGrid - eXist XML database managing a few hundred gigabytes of data

26 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee Dissemination much has happened.. more people are reading about it.. LHCb-UK members get up to speed with the GridWed 5 Jan 2005 GridPP in PittsburghThu 9 Dec 2004 GridPP website busier than everMon 6 Dec 2004 Optorsim 2.0 releasedWed 24 Nov 2004 ZEUS produces 5 million Grid eventsMon 15 Nov 2004 CERN 50th anniversary receptionTue 26 Oct 2004 GridPP at CHEP'04Mon 18 Oct 2004 LHCb data challenge first phase a success for LCG and UKMon 4 Oct 2004 Networking in Nottingham - GLIF launch meetingMon 4 Oct 2004 GridPP going for Gold - website award at AHMMon 6 Sep 2004 GridPP at the All Hands MeetingWed 1 Sep 2004 R-GMA included in latest LCG releaseWed 18 Aug 2004 LCG2 administrators learn tips and tricks in OxfordTue 27 Jul 2004 Take me to your (project) leaderFri 2 Jul 2004 ScotGrid's 2nd birthday: ScotGrid clocks up 1 million CPU hoursFri 25 Jun 2004 Meet your production managerFri 18 Jun 2004 GridPP10 report and photographsWed 9 Jun 2004 CERN recognizes UK's outstanding contribution to Grid computingWed 2 Jun 2004 UK particle physics Grid takes shapeWed 19 May 2004 A new monitoring map for GridPPMon 10 May 2004 Press reaction to EGEE launchTue 4 May 2004 GridPP at the EGEE launch conferenceTue 27 Apr 2004 LCG2 releasedThu 8 Apr 2004 University of Warwick joins GridPPThu 8 Apr 2004 Grid computing steps up a gear: the start of EGEEThu 1 Apr 2004 EDG gets glowing final reviewMon 22 Mar 2004 Grids and Web Services meeting, 23 April, LondonTue 16 Mar 2004 EU DataGrid Software License approved by OSIFri 27 Feb 2004 GridPP Middleware workshop, March , UCLFri 20 Feb 2004 Version 1.0 of the Optorsim grid simulation tool released by EU DataGridTue 17 Feb 2004 Summary and photographs of the 9th GridPP Collaboration MeetinThu 12 Feb ,976 hits in December

27 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee Annual data storage: PetaBytes per year 100 Million SPECint2000  100,000 PCs (3 GHz Pentium 4) Concorde (15 km) CD stack with 1 year LHC data (~ 20 km) What lies ahead? Some mountain climbing.. Quantitatively, we’re ~9% of the way there in terms of CPU (9,000 ex 100,000) and disk (3 ex 12-14*3 years)… In production terms, we’ve made base camp We are here (1 km) Importance of step-by-step planning… Pre-plan your trip, carry an ice axe and crampons and arrange for a guide…

28 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee Grid and e-Science Support in 2008 What areas require support? IV Running the Tier-1 Data Centre IVHardware annual upgrade IVContribution to Tier-2 Sysman effort  (non-PPARC) hardware IVFrontend Tier-2 hardware IVContribution to Tier-0 support IIIOne M/S/N expert in each of 6 areas IIIProduction manager and four Tier-2 coordinators IIApplication/Grid experts (UK support) IATLAS Computing MoU commitments and support ICMS Computing MoU commitments and support ILHCb Core Tasks and Computing Support IALICE Computing support IFuture experiments adopt e-Infrastructure methods No GridPP management: (assume production mode established + devolved management to Institutes) III. Grid Middleware I. Experiment Layer II. Application Middleware IV. Facilities and Fabrics

29 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee Priorities in context of a financial snapshot in 2008 Grid (£5.6m p.a.) and e-Science (£2.7m p.a.) Assumes no GridPP project management Savings? –EGEE Phase 2 ( ) may contribute –UK e-Science context is 1.NGS (National Grid Service) 2.OMII (Open Middleware Infrastructure Institute) 3.DCC (Digital Curation Centre) Timeline? Grid and e-Science funding requirements To be compared with Road Map: Not a Bid - Preliminary Input

30 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee Grid and e-Science Exploitation Timeline? PPAP initial inputOct 2004 Science Committee initial input PPARC call assessment ( )2005 Science Committee outcomeOct 2005 PPARC call Jan 2006 PPARC close of call May 2006 Assessment Jun-Dec 2006 PPARC outcome Dec 2006 Institute Recruitment/RetentionJan-Aug 2007 Grid and e-Science Exploitation Sep …. Note if the assessment from PPARC internal planning differs significantly from this preliminary advice from PPAP and SC, then earlier planning is required.

31 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee Executive Summary GRIDPP-PMB-40-EXEC The Grid is a reality A project was/is needed Under control LCG2 support: SC case being written 16 UK sites are on the Grid –MoUs, planning, deployment, monitoring –each underway as part of GridPP2 Developments estd.,R-GMA deployed Glite designed inc. web services Interfaces developed, testing phase Area transformed Initial ideas.. consultation reqd. Introduction Project Management Resources LCG Deployment –Tier-1/A production + Tier-2 resources M/S/N EGEE Applications Dissemination Beyond GridPP2

32 Tony Doyle - University of Glasgow 10 January 2005Oversight Committee OSC actions Plan for support of physics analysis community in 2007 Better understanding of capacity limits at Tier1 and strategic priorities £1M bid for LCG2 to go to PPARC Science Committee Plan to raise job completion efficiency Statement on gLite OSC views project as excellently managed and very successful


Download ppt "Tony Doyle - University of Glasgow 10 January 2005Oversight Committee GridPP: status report Andy Parker (Taken from GridPP report at OSC by Tony Doyle)"

Similar presentations


Ads by Google