| Issue |
EPJ Web Conf.
Volume 337, 2025
27th International Conference on Computing in High Energy and Nuclear Physics (CHEP 2024)
|
|
|---|---|---|
| Article Number | 01337 | |
| Number of page(s) | 8 | |
| DOI | https://doi.org/10.1051/epjconf/202533701337 | |
| Published online | 07 October 2025 | |
https://doi.org/10.1051/epjconf/202533701337
Advancements and Operations for LHC Run-3 and beyond
CERN
* e-mail: amadio@cern.ch
Published online: 7 October 2025
This paper presents recent advancements in the EOS project– the large-scale data storage system developed at CERN–during the preparation and execution of LHC Run-3. Key developments include further simplification of the service architecture, enhancements to metadata performance, and the introduction of new storage device inventory and cost/value interfaces. Additionally, we introduce a new scheduler implementation, a generated REST API derived from the gRPC protocol, and improved integration of features such as SciTags and SciTokens. We report on operational experiences, including the large-scale migration from CentOS 7 to AlmaLinux 9 across over 1000 storage nodes, and significant improvements in EOS file system check (fsck) for erasure coded files.
Looking ahead to Run-4 and the High-Luminosity LHC (HL-LHC) era, we outline the planned evolution of EOS, including ongoing software R&D and storage technology evaluations. We discuss performance testing of hard disks using shingled magnetic recording (SMR) technology, the projected HDD capacity roadmap toward 50TB drives by 2030, and the potential role of SSDs in addressing storage performance challenges at CERN and beyond.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.