Lessons learned from the ATLAS performance studies of the Iberian Cloud for the first LHC running period

20th International Conference on Computing in High Energy and Nuclear Physics

物理学;计算机科学

Sánchez-Martínez, V.^1 ; Borges, G.^2 ; Borrego, C.^3 ; Del Peso, J.^4 ; Delfino, M.^5,6 ; Gomes, J.^2 ; De La Hoz, S. González^1 ; Pages, A. Pacheco^3,5 ; Salt, J.^1 ; Sedov, A.^3,5 ; Villaplana, M.^1 ; Wolters, H.^7

Instituto de Física Corpuscular (IFIC), University of Valencia, CSIC, Valencia, Spain^1

Laboratório de Instrumentação e Fisica Experimental de Partículas-LIP, Lisboa, Portugal^2

Institut de Física d'Altes Energies, Universitat Autònoma de Barcelona, Spain^3

Departamento de Física Teorica C-15, Universidad Autonoma de Madrid, Madrid, Spain^4

Port d'Informació Científica (PIC), Campus UAB, Bellaterra, Spain^5

Departament de Física, Universitat Autònoma de Barcelona, Barcelona, Spain^6

Laboratório de Instrumentação e Física Experimental de Partículas, Coimbra, Portugal^7

关键词: Cloud performance;    Data distribution;    Distributed analysis;    Distributed computing systems;    Future challenges;    Performance study;    Physics analysis;    Simulation and analysis;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/513/3/032082/pdf
DOI  :  10.1088/1742-6596/513/3/032082

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

In this contribution we describe the performance of the Iberian (Spain and Portugal) ATLAS cloud during the first LHC running period (March 2010-January 2013) in the context of the GRID Computing and Data Distribution Model. The evolution of the resources for CPU, disk and tape in the Iberian Tier-1 and Tier-2s is summarized. The data distribution over all ATLAS destinations is shown, focusing on the number of files transferred and the size of the data. The status and distribution of simulation and analysis jobs within the cloud are discussed. The Distributed Analysis tools used to perform physics analysis are explained as well. Cloud performance in terms of the availability and reliability of its sites is discussed. The effect of the changes in the ATLAS Computing Model on the cloud is analyzed. Finally, the readiness of the Iberian Cloud towards the first Long Shutdown (LS1) is evaluated and an outline of the foreseen actions to take in the coming years is given. The shutdown will be a good opportunity to improve and evolve the ATLAS Distributed Computing system to prepare for the future challenges of the LHC operation.