The ARDA Project Massimo Lamanna CERN LCG ARDA

The ARDA Project Massimo Lamanna CERN LCG ARDA Project

Summary • Historical background and highlights – – NA 4 -related LCG activities ARDA working group (ARDA LCG RTAG) ARDA working group recommendations ARDA workshop • ARDA project LCG ARDA Project

HEP requirement • HEP (mainly LHC) requirements have been gathered and discussed since the early stages of the projects • GAG is the long-lived forum – Hepcal • Systematic descriptions of HEP Grid Use Cases • CERN-LCG-2002 -020 (29 May 2002) lcg. web. cern. ch/LCG/sc 2/RTAG 4/finalreport. doc • Hepcal-prime: cern. ch/fca/HEPCAL-prime. doc – Hepcal 2 • Analysis Use Cases • CERN-LCG-2003 -032 (29 October 2003) lcg. web. cern. ch/LCG/SC 2/GAG/HEPCAL-II. doc LCG ARDA Project

GAG membership • • • Chair: F. Carminati ALICE: P. Buncic, PG. Cerello ATLAS: L. Perini, [D. Quarrie & C. Tull & D. Barberis] CMS: R. Cavanaugh, C. Grandi LHCb: A. Tsaregorodtsev, N. Brook GDA: F. Donno, A. Sciabà, I. Bird GTA: D. Foster App Area: J. Beringer, [O. Smirnova, ] A. Pfeiffer Relations with EU Projects: F. Harris Relations with US Projects: R. Pordes Experiment Independent expert & co-editor: J. Templon LCG ARDA Project

ARDA working group (A Roadmap to Distributed Analysis) • • LCG project (initiated by the LCG SC 2) Lead by L. Bauerdick (FNAL) All 4 LHC experiments involved Summer/Fall 2003 – Final report: November 2004 – CERN-LCG-2003 -33 • www. uscms. org/s&c/lcg/ARDA-report-final. pdf LCG ARDA Project

ARDA working group mandate • To review the current DA activities and to capture their architectures in a consistent way • To confront these existing projects to the HEPCAL II use cases and the user's potential work environments in order to explore potential shortcomings. • To consider the interfaces between Grid, LCG and experiment specific services – Review the functionality of experiment-specific packages, state of advancement and role in the experiment – Identify similar functionalities in the different packages – Identify functionalities and components that could be integrated in the generic GRID middleware • To confront the current projects with critical GRID areas • To develop a roadmap specifying wherever possible the architecture, the components and potential sources of deliverables to guide the medium term (2 year) work of the LCG and the DA planning in the experiments. LCG ARDA Project

ARDA working group recommendations • New service decomposition EG – Alien EE Mi dd lew ar e • Role of experience, existing technology… – Web service framework AR D • Interfacing to existing middleware to enable their A pr oje use in the experiment frameworks ct • Early deployment of (a series of) prototypes to ensure functionality and coherence LCG ARDA Project

ARDA workshop (January 2003) agenda. cern. ch/full. Agenda. php? ida=a 036745 LCG ARDA Project Miron Livny ARDA Workshop January 2004

End-to-end prototypes • Provide a fast feedback to the EGEE MW development team • Guarantee the experiments are ready to benefit from the new MW as soon it becomes available • – Avoid uncoordinated evolution – Coherence between users expectations and final product – Expose the experiments (and the community in charge of the deployment) to the current evolution of the whole system, to be prepared to use it in the best and quickest way The experience gathered in the last years (EDG, LCG, LHC experiments data challenges and distributed analysis systems, …) suggests that the prototype could be also useful to enable some production and physics analysis – Might be too ambitious. On the other hand, the prototypes should be exercised with realistic workload and conditions (experiments absolutely required for that!) – A lot of work (and useful software) is involved in current experiments data challenges: this will be used as a starting point LCG ARDA Project

ARDA Project • LCG: – Project leader (Massimo Lamanna/CERN) – 4 LCG staff (100% at CERN) matching the 4 EGEE staff – About 2 FTEs from other sources (not always at CERN) • EGEE: – 4 NA 4 staff (Already selected. Reasonable hope to start on April 1 st) LCG ARDA Project

ARDA Project • Stakeholders: – EGEE MW team – Experiment interface • • – HEP tools providers • • (ALICE) David Adams (ATLAS) Lucia Silvestris (CMS) Ulrik Egede (LHCb) – “E 2 E integration team” – Users from the 4 experiments! GAE GANGA POOL PROOF ROOT SEAL … – Service providers 4 EGEE + CERN matching LCG ARDA Project

ALICE CMS ATLAS ALICE LHCb Distr. analysis Specifications ……. . SEAL POOL ARDA Project ……. . Collaboration Coordination Integration PROOF Specifications Planning Regional Centres GDB Security Group GAG GAE Priorities Resource Providers– Experience Generic Middleware Project EGEE/VDT/. . LCG ARDA Project Requirements Guidelines

Coordination with NA 4 • Frank and Massimo have already started to work together • Naturally ARDA will provide useful input within NA 4 for the HEP part – HEP is one of the two EGEE pilot applications – The interaction ARDA – GAG is expected to provide more useful input – The Hepcal documents are already interesting document to let emerge a common application layer. The experience on the prototype will be a contribution in this direction LCG ARDA Project

Conclusions • Project plan being prepared – Converge within LCG before the end of March • Good response from the experiments so far – Very constructive attitude • Good coordination with NA 4 LCG ARDA Project