Transitioning CMS to Rucio Data Managment

Author:

Vaandering Eric

Abstract

Following a thorough review in 2018, the CMS experiment at the CERN LHC decided to adopt Rucio as its new data management system. Rucio is emerging as a community software project and will replace an aging CMSonly system before the start-up of LHC Run 3 in 2021. Rucio was chosen after an evaluation determined that Rucio could meet the technical and scale needs of CMS. The data management system for CMS needs to manage the current data sample of approximately 200 PB of data with 1 PB of transfers per day. The data management system must also have a development path suitable for LHC Run 4 (2026) data rates, which are expected to be 50 times larger. This contribution details the ongoing CMS adoption process as we replace our legacy system with Rucio, focusing on the challenges of integrating Rucio into an established set of experimental tools and procedures. This will include the migration of metadata, the construction of interfaces to the rest of the CMS computing tools, scale tests, operations, monitoring, and the plan to gradually turn over primary responsibility for the management of data to Rucio. A description of CMS user data management with Rucio will also be provided.

Publisher

EDP Sciences

Reference16 articles.

1. Rehn J., et al. “PhEDEx high-throughput data transfer management system”, Proc. CHEP06, Computing in High Energy Physics, Mumbai, India, (2006).

2. Iiyama Y., Paus C., Goncharov M., “Dynamo — The dynamic data management system for the distributed CMS computing system’, Proc. CHEP16, Computing in High Energy Physics, San Francisco, USA, (2016).

3. Apollinari G., Béjar Alonso I., Brüning O., Lamont M. and Rossi L., doi:10.5170/CERN2015-005

4. Rucio: Scientific Data Management

Cited by 3 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Prototyping a ROOT-based distributed analysis workflow for HL-LHC: The CMS use case;Computer Physics Communications;2024-02

2. CMS Tier-0 data processing during the detector commissioning in Run 3;EPJ Web of Conferences;2024

3. Optimizing large data transfers for the ALICE experiment in Run 3;2023 22nd RoEduNet Conference: Networking in Education and Research (RoEduNet);2023-09-21

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3