19–25 Oct 2024
Europe/Zurich timezone

Exploring Client-Server Scalability with RNTuple & EOS: Comparative Analysis of Physics Data Formats for Analysis

Not scheduled
30m
Talk Plenary

Speakers

Dr Andrea Sciabà (CERN) Jakob Blomer (CERN)Dr Vincenzo Eduardo Padulano (CERN)

Description

Collaboratively, the IT and EP departments have launched a formal project within the Research and Computing sector to evaluate a novel data format for physics analysis data utilized in LHC experiments and other fields. The objective of this initiative is to substitute the current TTree data format of ROOT with a more efficient format known as RNTuple, which provides superior support for multi-threading and enhanced compression capabilities. This aspect of the project focuses on verifying the scalability of the storage back-end EOS during the migration from the old to the new format, utilizing replicated and erasure coded profiles.

Primary authors

Co-authors

Alaettin Serhan Mete (Argonne National Laboratory (US)) Danilo Piparo (CERN) Florine de Geus (CERN/University of Twente (NL)) Matti Kortelainen (Fermi National Accelerator Lab. (US)) Philippe Canal (Fermi National Accelerator Lab. (US))

Presentation materials

There are no materials yet.