Accounting and monitoring tools enhancement for Run 3 in the ATLAS distributed computing

Abstract

The ATLAS experiment at the LHC utilizes complex multicomponent distributed systems for processing (PanDA WMS) and managing (Rucio) data. The complexity of the relationships between components, the amount of data being processed and the continuous development of new functionalities of the critical systems are the main challenges to consider when creating monitoring and accounting tools able to adapt to this dynamic environment in a short time. To overcome these challenges, ATLAS uses the unified monitoring infrastructure (UMA) provided by CERN-IT since 2018, which accumulates information from distributed data sources and then makes it available for different ATLAS distributed computing user groups. The information is displayed using Grafana dashboards. Based on the information provided, they can be grouped as “data transfers”, “site accounting”, “jobs accounting” and so on. These monitoring tools are used daily by ATLAS members to spot and fix issues. In addition, LHC Run 3 required the implementation of significant changes in the monitoring and accounting infrastructure to collect and process data collected by ATLAS during the LHC run. This paper describes the recent enhancements to the UMA-based monitoring and accounting dashboards.