EPJ Web Conf.
Volume 245, 202024th International Conference on Computing in High Energy and Nuclear Physics (CHEP 2019)
|Number of page(s)||6|
|Section||2 - Offline Computing|
|Published online||16 November 2020|
ATLAS Event Store and I/O developments in support for Production and Analysis in Run 3
Brookhaven National Laboratory, Upton, New York 11973, USA
2 Argonne National Laboratory, Argonne, Illinois 60439, USA
* Corresponding author: firstname.lastname@example.org
† Copyright 2020 CERN for the benefit of the ATLAS Collaboration. Reproduction of this article or parts of it is allowed as specified in the CC-BY-4.0 license.
Published online: 16 November 2020
During the long LHC shutdown, ATLAS experiment is preparing several fundamental changes to its offline event processing framework and analysis model. These include moving to multi-threaded reconstruction and simulation and reducing data duplication during derivation analysis by producing a combined mini-xAOD stream. These changes will allow ATLAS to take advantage of the higher luminosity at Run 3 without overstraining processing and storage capabilities. They also require significant improvements to the underlying event store and the I/O framework to support them. These improvements include: 1) an overhaul of the Run 2 I/O framework to be thread-safe and minimize serial bottlenecks, 2) introduction of new immutable references for object navigation, which don’t rely on storage container entry number so data can be merged in-memory, 3) using filter decisions to annotate combined output stream to allow for fast event selection on input and 4) selecting optimized compression algorithms and settings to allow efficient reading of event selections.
© The Authors, published by EDP Sciences, 2020
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.