Evolution of the use of relational and NoSQL databases in the ATLAS experiment

The ATLAS experiment used for many years a large database infrastructure based on Oracle to store several different types of non-event data: time-dependent detector configuration and conditions data, calibrations and alignments, configurations of Grid sites, catalogues for data management tools, job...

Full description

Saved in:
Bibliographic Details
Published inPhysics of particles and nuclei letters Vol. 13; no. 5; pp. 613 - 617
Main Author Barberis, D.
Format Journal Article
LanguageEnglish
Published Moscow Pleiades Publishing 01.09.2016
Springer Nature B.V
Subjects
Computer Technologies in Physics
Data management
Data storage
Evolution
Infrastructure
Metadata
Particle and Nuclear Physics
Performance enhancement
Physics
Physics and Astronomy
Relational data bases
Servers
Storage systems
ATLAS
CERN LHC
Hadoop
Database
Metadata
Oracle
Conditions
Online AccessGet full text

Cover

More Information
Summary:The ATLAS experiment used for many years a large database infrastructure based on Oracle to store several different types of non-event data: time-dependent detector configuration and conditions data, calibrations and alignments, configurations of Grid sites, catalogues for data management tools, job records for distributed workload management tools, run and event metadata. The rapid development of “NoSQL” databases (structured storage services) in the last five years allowed an extended and complementary usage of traditional relational databases and new structured storage tools in order to improve the performance of existing applications and to extend their functionalities using the possibilities offered by the modern storage systems. The trend is towards using the best tool for each kind of data, separating for example the intrinsically relational metadata from payload storage, and records that are frequently updated and benefit from transactions from archived information. Access to all components has to be orchestrated by specialised services that run on front-end machines and shield the user from the complexity of data storage infrastructure. This paper describes this technology evolution in the ATLAS database infrastructure and presents a few examples of large database applications that benefit from it.
ISSN:1547-4771
1531-8567
DOI:10.1134/S1547477116050083