Integrating multiple scientific computing needs via a Private Cloud infrastructure

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

物理学;计算机科学

Bagnasco, S.^1 ; Berzano, D.^1,2,3 ; Brunetti, R.^1,4 ; Lusso, S.^1 ; Vallero, S.^1,2

Istituto Nazionale di Fisica Nucleare, Via Pietro Giuria 1, Torino

10125, Italy^1

Dipartimento di Fisica, Università Degli Studi di Torino, Via Pietro Giuria 1, Torino

10125, Italy^2

CERN-European Organization for Nuclear Research, Geneva 23

CH-1211, Switzerland^3

COLT Engine Srl, Pianezza, Italy^4

关键词: Building blockes;    Contextualization;    Diverse applications;    Interactive analysis;    Interactive data analysis;    Linux distributions;    Network virtualization;    Scientific computing applications;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/513/3/032100/pdf
DOI  :  10.1088/1742-6596/513/3/032100

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

In a typical scientific computing centre, diverse applications coexist and share a single physical infrastructure. An underlying Private Cloud facility eases the management and maintenance of heterogeneous use cases such as multipurpose or application-specific batch farms, Grid sites catering to different communities, parallel interactive data analysis facilities and others. It allows to dynamically and efficiently allocate resources to any application and to tailor the virtual machines according to the applications' requirements. Furthermore, the maintenance of large deployments of complex and rapidly evolving middleware and application software is eased by the use of virtual images and contextualization techniques; for example, rolling updates can be performed easily and minimizing the downtime. In this contribution we describe the Private Cloud infrastructure at the INFN-Torino Computer Centre, that hosts a full-fledged WLCG Tier-2 site and a dynamically expandable PROOF-based Interactive Analysis Facility for the ALICE experiment at the CERN LHC and several smaller scientific computing applications. The Private Cloud building blocks include the OpenNebula software stack, the GlusterFS filesystem (used in two different configurations for worker- and service-class hypervisors) and the OpenWRT Linux distribution (used for network virtualization). A future integration into a federated higher-level infrastructure is made possible by exposing commonly used APIs like EC2 and by using mainstream contextualization tools like CloudInit.