HEPiX Benchmarking Solution for WLCG Computing Resources

The increasing computational demand in High Energy Physics (HEP) as well as increasing concerns about energy efficiency in highperformance/high-throughput computing are driving forces in the search for more efficient ways to utilise available resources. Since avoiding idle resources is key in achieving high efficiency, an appropriate measure is sharing of idle resources of underutilised sites with fully occupied sites. The software COBalD/TARDIS can automatically, transparently, and dynamically (dis)integrate such resources in an opportunistic manner. Sharing resources however also requires accounting. In this work we introduce AUDITOR (AccoUnting DatahandlIng Toolbox for Opportunistic Resources), a flexible and extensible accounting system that is able to cover a wide range of use cases and infrastructures. AUDITOR gathers accounting data via so-called collectors which are designed to monitor batch systems, COBalD/TARDIS, cloud schedulers, or other sources of information. The data is stored in a database and provided to so-called plugins, which act based on accounting records. An action could for instance be creating a bill of utilised resources, computing the CO2 footprint, adjusting parameters of a service, or forwarding accounting information to other accounting systems. Depending on the use case, a suitable collector and plugin can be chosen from a growing ecosystem of collectors and plugins. Libraries for interacting with AUDITOR are provided to facilitate the development of collectors and plugins by the community.

Section: The Auditor Core Componentmentioning

confidence: 87%

AUDITOR: Accounting for opportunistic resources

Boehler,

Gamel,

Kroboth

et al. 2024

“…Therefore, the HEPiX benchmark working group designed a new benchmark based on current HEP workloads to measure the computing performance of a system for HEP software. [3] The current HEP benchmark released in April 2023, the so-called HEPScore23 [4], will be used for the pledges of the Grid sites in the coming years.…”

Section: Cpu Benchmarks In High Energy Physicsmentioning

confidence: 99%

CPU Performance Study for HEP Workloads with Respect to the Number of Single-core Slots

Schnepf,

Fischer,

Petzold

2024

Many common CPU architectures provide simultaneous multithreading (SMT). The operating system sees multiple logical CPU cores per physical CPU core and can schedule several processes to one physical CPU core. This overbooking of physical cores enables a better usage of parallel pipelines and doubled components within a CPU core. On systems with several applications running in parallel, such as batch jobs on worker nodes, the usage of SMT can increase the overall performance. In high energy physics (HEP) batch/Grid jobs are accounted for in units of single-core jobs. One single-core job is designed to utilize one logical CPU core fully. As a result, Grid sites often configure their worker nodes to provide as many single-core slots as physical or logical CPU cores. However, due to memory and disk space constraints, not all logical CPU cores can be used. Therefore, it can be useful to configure more single-core slots than physical CPU cores but fewer than logical CPU cores per worker node. We have extensively used and studied this strategy at the GridKa Tier 1 center. In this contribution, we show benchmark results for different overbooking factors of physical cores on various CPU models for different HEP workflows and Benchmarks.

“…This led to the creation of the HEP Benchmarks project and the development of a software framework to benchmark the performance of computing servers using HEP applications [9]. The Working Group developed the HEP Benchmark Suite that provides a simple way to run containerized HEP applications and other benchmarks, and record the results in an Elasticsearch database at CERN [10].…”

Section: Motivation For a New Cpu Benchmarkmentioning

confidence: 99%

“…Each container includes a configuration file with a parameter for the number of events that allows one to adjust the duration of the execution (more details can be found in ref. [10]). Each workload is run three times and the geometric mean is taken as the benchmark (typically in units of events per second); this is identical to the method used for each workload component in HS06.…”

Section: Hep Workloadsmentioning

confidence: 99%

HEPScore: A new CPU benchmark for the WLCG

Giordano,

Barbet,

Boccali

et al. 2024

Self Cite

HEPScore is a new CPU benchmark created to replace the HEPSPEC06 benchmark that is currently used by the WLCG for procurement, computing resource pledges, usage accounting and performance studies. The development of the new benchmark, based on HEP applications or workloads, has involved many contributions from software developers, data analysts, experts of the experiments, representatives of several WLCG computing centres and WLCG site managers. In this contribution, we review the selection of workloads and the validation of the new HEPScore benchmark.