Cargando…

Monitoring CMS experiment data and infrastructure for LHC Run3 and beyond

The CMS experiment at CERN is a scientific endeavor that requires the coordinated efforts of thousands of researchers and engineers from around the world. To process and store the petabytes of data produced by CMS, the experiment relies on a distributed computing infrastructure. The CMS Offline and...

Descripción completa

Detalles Bibliográficos
Autor principal: Uzunoglu, Ceyhun
Lenguaje:eng
Publicado: 2023
Materias:
Acceso en línea:http://cds.cern.ch/record/2853680
Descripción
Sumario:The CMS experiment at CERN is a scientific endeavor that requires the coordinated efforts of thousands of researchers and engineers from around the world. To process and store the petabytes of data produced by CMS, the experiment relies on a distributed computing infrastructure. The CMS Offline and Computing group is responsible for workflow and data management, to ensure that critical datasets are processed and made available for the physics community in a timely manner. Scalable and reliable monitoring services are essential to ensure the efficient usage and performance of the computing infrastructure. This note presents the CMS Monitoring infrastructure, services, and applications, along with the improvements made in data management monitoring over the past few years. By adopting open-source technologies such as Kubernetes and Prometheus, and by relying on the CERN IT and MONIT services, the CMS Monitoring group has established a reliable and scalable monitoring infrastructure and services which are essential for computing operations of the CMS collaboration.