Integrating FTS in the Fenix HPC Infrastructure

Long, Shiting; Carpene, Michele; Carpio, Miguel; More, Sergi; Padrin, Cristiano; Pleiter, Dirk; Patrascoiu, Mihai

doi:10.1051/epjconf/202429501037

Journal Article/Contribution to a conference proceedings

FZJ-2025-00800

Integrating FTS in the Fenix HPC Infrastructure

Long, S. (Corresponding author)FZJ* ; Pleiter, D. ; Patrascoiu, M. ; Padrin, C. ; Carpene, M. ; More, S. ; Carpio, M.

2024
EDP Sciences Les Ulis

26th International Conference on Computing in High Energy and Nuclear Physics, CHEP 2023, Norfolk, VA, USA, 8 May 2023 - 12 May 2023 The European physical journal / Web of Conferences 295, 01037 (2024) [10.1051/epjconf/202429501037]

This record in other databases:

Please use a persistent id in citations: doi:10.1051/epjconf/202429501037 doi:10.34734/FZJ-2025-00800

Abstract: As compute requirements in experimental high-energy physicsare expected to significantly increase, there is a need for leveraging high-performance computing (HPC) resources. However, HPC systems are currentlyorganised and operated in a way that this is not easily possible. Here we willfocus on a specific e-infrastructure that incorporates HPC resources, namelyFenix, which is based on a consortium of 6 leading European supercomput-ing centres. Fenix was initiated through the Human Brain Project (HBP) butalso provides resources to other research communities in Europe. The Fenixsites are integrated into a common AAI and provide a so-called Archival DataRepository that can be accessed through a Swift API.In this paper, we report on our efforts to realise a data transfer service that allowto exchange data with the Fenix e-infrastructure. This has been enabled by im-plementing support of Swift in FTS3 and related software components. We will,in particular, discuss how FTS3 has been integrated into the Fenix AAI, whichlargely follows the architectural principles of the European Open Science Cloud(EOSC). Furthermore, we show how end-users can use this service through aWebFTS service that has been integrated into the science gateway of the HBP,which is also known as the HBP Collaboratory. Finally, we discuss how trans-fer commands can be automatically distributed over several FTS3 instances tooptimise transfer between different Fenix sites.

Classification: