Cargando…

Exploring Object Stores for High-Energy Physics Data Storage

Over the last two decades, ROOT TTree has been used for storing over one exabyte of High-Energy Physics (HEP) events. The TTree columnar on-disk layout has been proved to be ideal for analyses of HEP data that typically require access to many events, but only a subset of the information stored for e...

Descripción completa

Detalles Bibliográficos
Autores principales: López-Gómez, Javier, Blomer, Jakob
Lenguaje:eng
Publicado: 2021
Materias:
Acceso en línea:https://dx.doi.org/10.1051/epjconf/202125102066
http://cds.cern.ch/record/2775940
_version_ 1780971605449506816
author López-Gómez, Javier
Blomer, Jakob
author_facet López-Gómez, Javier
Blomer, Jakob
author_sort López-Gómez, Javier
collection CERN
description Over the last two decades, ROOT TTree has been used for storing over one exabyte of High-Energy Physics (HEP) events. The TTree columnar on-disk layout has been proved to be ideal for analyses of HEP data that typically require access to many events, but only a subset of the information stored for each of them. Future colliders, and particularly HL-LHC, will bring an increase of at least one order of magnitude in the volume of generated data. Therefore, the use of modern storage hardware, such as low-latency high-bandwidth NVMe devices and distributed object stores, becomes more important. However, TTree was not designed to optimally exploit modern hardware and may become a bottleneck for data retrieval. The ROOT RNTuple I/O system aims at overcoming TTree’s limitations and at providing improved effciency for modern storage systems. In this paper, we extend RNTuple with a backend that uses Intel DAOS as the underlying storage, demonstrating that the RNTuple architecture can accommodate high-performance object stores. From the user perspective, data can be accessed with minimal changes to the code, that is by replacing a filesystem path by a DAOS URI. Our performance evaluation shows that the new backend can be used for realistic analyses, while outperforming the compatibility solution provided by the DAOS project.
id cern-2775940
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2021
record_format invenio
spelling cern-27759402023-01-31T09:51:18Zdoi:10.1051/epjconf/202125102066http://cds.cern.ch/record/2775940engLópez-Gómez, JavierBlomer, JakobExploring Object Stores for High-Energy Physics Data Storagehep-exParticle Physics - Experimentcs.DBComputing and ComputersOver the last two decades, ROOT TTree has been used for storing over one exabyte of High-Energy Physics (HEP) events. The TTree columnar on-disk layout has been proved to be ideal for analyses of HEP data that typically require access to many events, but only a subset of the information stored for each of them. Future colliders, and particularly HL-LHC, will bring an increase of at least one order of magnitude in the volume of generated data. Therefore, the use of modern storage hardware, such as low-latency high-bandwidth NVMe devices and distributed object stores, becomes more important. However, TTree was not designed to optimally exploit modern hardware and may become a bottleneck for data retrieval. The ROOT RNTuple I/O system aims at overcoming TTree’s limitations and at providing improved effciency for modern storage systems. In this paper, we extend RNTuple with a backend that uses Intel DAOS as the underlying storage, demonstrating that the RNTuple architecture can accommodate high-performance object stores. From the user perspective, data can be accessed with minimal changes to the code, that is by replacing a filesystem path by a DAOS URI. Our performance evaluation shows that the new backend can be used for realistic analyses, while outperforming the compatibility solution provided by the DAOS project.Over the last two decades, ROOT TTree has been used for storing over one exabyte of High-Energy Physics (HEP) events. The TTree columnar on-disk layout has been proved to be ideal for analyses of HEP data that typically require access to many events, but only a subset of the information stored for each of them. Future colliders, and particularly HL-LHC, will bring an increase of at least one order of magnitude in the volume of generated data. Therefore, the use of modern storage hardware, such as low-latency high-bandwidth NVMe devices and distributed object stores, becomes more important. However, TTree was not designed to optimally exploit modern hardware and may become a bottleneck for data retrieval. The ROOT RNTuple I/O system aims at overcoming TTree's limitations and at providing improved efficiency for modern storage systems. In this paper, we extend RNTuple with a backend that uses Intel DAOS as the underlying storage, demonstrating that the RNTuple architecture can accommodate high-performance object stores. From the user perspective, data can be accessed with minimal changes to the code, that is by replacing a filesystem path by a DAOS URI. Our performance evaluation shows that the new backend can be used for realistic analyses, while outperforming the compatibility solution provided by the DAOS project.arXiv:2107.07304oai:cds.cern.ch:27759402021
spellingShingle hep-ex
Particle Physics - Experiment
cs.DB
Computing and Computers
López-Gómez, Javier
Blomer, Jakob
Exploring Object Stores for High-Energy Physics Data Storage
title Exploring Object Stores for High-Energy Physics Data Storage
title_full Exploring Object Stores for High-Energy Physics Data Storage
title_fullStr Exploring Object Stores for High-Energy Physics Data Storage
title_full_unstemmed Exploring Object Stores for High-Energy Physics Data Storage
title_short Exploring Object Stores for High-Energy Physics Data Storage
title_sort exploring object stores for high-energy physics data storage
topic hep-ex
Particle Physics - Experiment
cs.DB
Computing and Computers
url https://dx.doi.org/10.1051/epjconf/202125102066
http://cds.cern.ch/record/2775940
work_keys_str_mv AT lopezgomezjavier exploringobjectstoresforhighenergyphysicsdatastorage
AT blomerjakob exploringobjectstoresforhighenergyphysicsdatastorage