Data preservation significantly increases the scientific output of high-energy physics experiments during and after data acquisition. For new and ongoing experiments, the careful consideration of long-term data preservation in the experimental design contributes to improving computational efficiency and strengthening the scientific activity in HEP through Open Science methodologies. This contribution is based on 15 years of experience of the DPHEP collaboration in the field of data preservation and focuses on aspects relevant for the strategic programming of particle physics in Europe: the preparation of future programs using data sets preserved from previous similar experiments (e.g. HERA for EIC), and the use of LHC data long after the end of the data taking. The lessons learned from past collider experiments and recent developments open the way to a number of recommendations for the full exploitation of the investments made in large HEP experiments.

The recent evolutions of the analysis frameworks and physics data formats of the LHC experiments provide the opportunity of using central analysis facilities with a strong focus on interactivity and short turnaround times, to complement the more common distributed analysis on the Grid. In order to plan for such facilities, it is essential to know in detail the performance of the combination of a given analysis framework, of a specific analysis and of the installed computing and storage resources. This contribution describes performance studies performed at CERN, using the EOS disk-based storage, either directly or through an XCache instance, from both batch resources and highperformance compute nodes which could be used to build an analysis facility. A variety of benchmarks, both synthetic and based on real-world physics analyses and their corresponding input datasets, are utilized. In particular, the RNTuple format from the ROOT project is put to the test and compared to the latest version of the TTree format, and the impact of caches is assessed. In addition, we assessed the difference in performance between the use of storage system specific protocols, like XRootd, and FUSE. The results of this study are intended to be a valuable input in the design of analysis facilities, at CERN and elsewhere.

The recent evolutions of the analysis frameworks and physics data formats of the LHC experiments provide the opportunity of using central analysis facilities with a strong focus on interactivity and short turnaround times, to complement the more common distributed analysis on the Grid. In order to plan for such facilities, it is essential to know in detail the performance of the combination of a given analysis framework, of a specific analysis and of the installed computing and storage resources. This contribution describes performance studies performed at CERN, using the EOS disk-based storage, either directly or through an XCache instance, from both batch resources and highperformance compute nodes which could be used to build an analysis facility. A variety of benchmarks, both synthetic and based on real-world physics analyses and their corresponding input datasets, are utilized. In particular, the RNTuple format from the ROOT project is put to the test and compared to the latest version of the TTree format, and the impact of caches is assessed. In addition, we assessed the difference in performance between the use of storage system specific protocols, like XRootd, and FUSE. The results of this study are intended to be a valuable input in the design of analysis facilities, at CERN and elsewhere.

Data preservation is a mandatory specification for any present and future experimental facility and it is a cost-effective way of doing fundamental research by exploiting unique data sets in the light of the continuously increasing theoretical understanding. This document summarizes the status of data preservation in high energy physics. The paradigms and the methodological advances are discussed from a perspective of more than ten years of experience with a structured effort at international level. The status and the scientific return related to the preservation of data accumulated at large collider experiments are presented, together with an account of ongoing efforts to ensure long-term analysis capabilities for ongoing and future experiments. Transverse projects aimed at generic solutions, most of which are specifically inspired by open science and FAIR principles, are presented as well. A prospective and an action plan are also indicated.

Caching can effectively reduce the cost of serving content and improve the user experience. In this paper, we explore the benefits of caching for existing scientific workloads, taking the Worldwide LHC (Large Hadron Collider) Computing Grid as an example. It is a globally distributed system that stores and processes multiple hundred petabytes of data and serves the needs of thousands of scientists around the globe. Scientific computation differs from other applications like video streaming as file sizes vary from a few bytes to terabytes and logical links between the files affect user access patterns. These factors profoundly influence caches' performance and, therefore, should be carefully analyzed to select which caching policy to deploy or to design new ones. In this work, we study how the hierarchical organization of the LHC physics data into files and groups of files called datasets affects the request patterns. We then propose new caching policies that exploit dataset-specific knowledge and compare them with file-based ones. Moreover, we show that limited connectivity between the computing and storage sites leads to the delayed hits phenomenon and estimate the consequent reduction in the potential benefits of caching.

Today, cloud systems provide many key services to development and production environments; reliable storage services are crucial for a multitude of applications ranging from commercial manufacturing, distribution and sales up to scientific research, which is often at the forefront of computing resource demands. In large-scale computer centers, the storage system requires particular attention and investment; usually, a large number of diverse storage devices need to be deployed in order to match the varying performance and volume requirements of changing user applications. As of today, magnetic drives still play a dominant role in terms of deployed storage volume and of service outages due to device failure. In this paper, we study methods to facilitate automated proactive disk replacement. We propose a method to identify disks with media failures in a production environment and describe an application of supervised machine learning to predict disk failures. In particular, a proper stage to automatically label (healthy/at-risk) the disks during the training and validation stage is presented along with tuning strategy to optimize the hyperparameters of the associated machine learning classifier. The approach is trained and validated against a large set of 65,000 hard drives in the CERN computer center, and the achieved results are discussed.

The increase in the scale of LHC computing during Run 3 and Run 4 (HL-LHC) will certainly require radical changes to the computing models and the data processing of the LHC experiments. The working group established by WLCG and the HEP Software Foundation to investigate all aspects of the cost of computing and how to optimise them has continued producing results and improving our understanding of this process. In particular, experiments have developed more sophisticated ways to calculate their resource needs, we have a much more detailed process to calculate infrastructure costs. This includes studies on the impact of HPC and GPU based resources on meeting the computing demands. We have also developed and perfected tools to quantitatively study the performance of experiments workloads and we are actively collaborating with other activities related to data access, benchmarking and technology cost evolution. In this contribution we expose our recent developments and results and outline the directions of future work.

EOS is a CERN-developed storage system that serves several hundred petabytes of data to the scientific community of the Large Hadron Collider (LHC). In particular, it provides services to the four largest LHC particle detectors: LHCb, CMS, ATLAS, and ALICE. Each of these collaborations uses different workflows to process and analyse its data. EOS has a monitoring system that collects detailed information on the file accesses and can give important insights about the specifics of the physics experiments’ workflows. In our study, we analyse the monitoring information accumulated over a six months period and amounting to over 1.3 terabytes and have the goal to help the IT department and the experiments’ operations teams to better understand the EOS data flows. In this contribution, we describe a pipeline, mainly developed in R, for processing large volumes of access logs and perform a comparative analysis of the storage usage in scientific workflows. In particular, we calculate aggregated statistics over a six months period and provide a high-level overview of the experiments’ data flows. Additionally, we study how the frequency of data accesses changes over time and estimate to what extent different experiments may benefit from an additional caching layer.

The size and complexity of large storage systems, such as high-performance computing (HPC) systems, inhibit rapid effective restructuring of data layouts to maintain performance as workloads shift. To address this issue, we have developed Geomancy, a tool that models the placement of data within a distributed storage system and reacts to drops in performance. Our approach to optimizing throughput offers benefits for storage systems such as avoiding potential bottlenecks and increasing overall I/O throughput from 11% to 30%.

The increase in the scale of LHC computing expected for Run 3 and even more so for Run 4 (HL-LHC) over the next ten years will certainly require radical changes to the computing models and the data processing of the LHC experiments. Translating the requirements of the physics programmes into computing resource needs is a complicated process and subject to significant uncertainties. For this reason, WLCG has established a working group to develop methodologies and tools intended tocharacterise the LHC workloads, better understand their interaction with the computing infrastructure, calculate their cost in terms of resources and expenditure and assist experiments, sites and the WLCG project in the evaluation of their future choices. This working group started in November 2017 and has about 30 active participants representing experiments and sites. In this contribution we expose the activities, the results achieved and the future directions.

In response to the 2013 Update of the European Strategy for Particle Physics (EPPSU), the Future Circular Collider (FCC) study was launched as a world-wide international collaboration hosted by CERN. The FCC study covered an energy-frontier hadron collider (FCC-hh), a highest-luminosity high-energy lepton collider (FCC-ee), the corresponding 100km tunnel infrastructure, as well as the physics opportunities of these two colliders, and a high-energy LHC, based on FCC-hh technology. This document constitutes the third volume of the FCC Conceptual Design Report, devoted to the hadron collider FCC-hh. It summarizes the FCC-hh physics discovery opportunities, presents the FCC-hh accelerator design, performance reach, and staged operation plan, discusses the underlying technologies, the civil engineering and technical infrastructure, and also sketches a possible implementation. Combining ingredients from the Large Hadron Collider (LHC), the high-luminosity LHC upgrade and adding novel technologies and approaches, the FCC-hh design aims at significantly extending the energy frontier to 100TeV. Its unprecedented centre of-mass collision energy will make the FCC-hh a unique instrument to explore physics beyond the Standard Model, offering great direct sensitivity to new physics and discoveries.

The EOS deployment at CERN is a core service used for both scientific data processing, analysis and as back-end for general end-user storage (eg home directories/CERNBOX). The collected disk failure metrics over a period of 1 year from a deployment size of some 70k disks allows a first systematic analysis of the behaviour of different hard disk types for the large CERN usecases. In this contribution we describe the data collection and analysis, summarise the measured rates and compare them with other large disk deployments. We further describe initial steps to use the collected failure and SMART metrics to develop a machine learning model predicting imminent failures and hence avoid service degradation and repair costs.

Particle physics has an ambitious and broad experimental programme for the coming decades. This programme requires large investments in detector hardware, either to build new facilities and experiments, or to upgrade existing ones. Similarly, it requires commensurate investment in the R D of software to acquire, manage, process, and analyse the shear amounts of data to be recorded. In planning for the HL-LHC in particular, it is critical that all of the collaborating stakeholders agree on the software goals and priorities, and that the efforts complement each other. In this spirit, this white paper describes the R D activities required to prepare for this software upgrade.

Without significant changes to data organization, management, and access (DOMA), HEP experiments will find scientific output limited by how fast data can be accessed and digested by computational resources. In this white paper we discuss challenges in DOMA that HEP experiments, such as the HL-LHC, will face as well as potential ways to address them. A research and development timeline to assess these changes is also proposed.

The IT Analysis Working Group (AWG) has been formed at CERN across individual computing units and the experiments to attempt a cross cutting analysis of computing infrastructure and application metrics. In this presentation we will describe the first results obtained using medium/long term data (1 months — 1 year) correlating box level metrics, job level metrics from LSF and HTCondor, IO metrics from the physics analysis disk pools (EOS) and networking and application level metrics from the experiment dashboards. We will cover in particular the measurement of hardware performance and prediction of job duration, the latency sensitivity of different job types and a search for bottlenecks with the production job mix in the current infrastructure. The presentation will conclude with the proposal of a small set of metrics to simplify drawing conclusions also in the more constrained environment of public cloud deployments.