Experience in CMS with the common analysis framework project

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

物理学;计算机科学

Mascheroni, Marco^1 ; Spiga, Daniele^2 ; Boccali, Tommaso^3 ; Bonacorsi, Daniele^4 ; Cinquilli, Mattia^2 ; Giordano, Domenico^2 ; Fanzago, Federica^5 ; Fisk, Ian^6 ; Girone, Maria^2 ; Hernandez, Jose^7 ; Konstantinov, Preslav^8 ; Magini, Niccolo^2 ; Mancinelli, Valentina^2 ; Riahi, Hassen^9 ; Santos, Lola Saiz^10 ; Vaandering, Eric W.^6

Universita e INFN, Sezione di Milano-Bicocca, Italy^1

CERN, European Organization for Nuclear Research, Switzerland^2

INFN Sezione di Pisa, Italy^3

Universita e INFN, Sezione di Bologna, Italy^4

Universita e INFN Sezione di Padova, Italy^5

Fermi National Accelerator Laboratory, United States^6

CIEMAT, Madrid, Spain^7

INRNE, Sofia, Bulgaria^8

Universita e INFN, Sezione di Perugia, Italy

(10) University of California San Diego, United States^9

关键词: Analysis frameworks;    Analysis workflow;    Computing infrastructures;    Feasibility studies;    Job scheduling;    Proof of concept;    Resource provisioning;    Workflow tools;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/513/3/032064/pdf
DOI  :  10.1088/1742-6596/513/3/032064

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

ATLAS, CERN-IT, and CMS embarked on a project to develop a common system for analysis workflow management, resource provisioning and job scheduling. This distributed computing infrastructure was based on elements of PanDA and prior CMS workflow tools. After an extensive feasibility study and development of a proof-of-concept prototype, the project now has a basic infrastructure that supports the analysis use cases of both experiments via common services. In this paper we will discuss the state of the current solution and give an overview of all the components of the system.