The ATLAS Readout System for LHC Runs 2 and 3

The ReadOut System (ROS) is a central part of the dataacquisition (DAQ) system of the ATLAS Experiment at the CERN LargeHadron Collider (LHC). The system is responsible for receiving andbuffering event data from all detector subsystems and serving theseto the High Level Trigger (HLT) system via a 10 GbE network,discarding or transporting data onward once the trigger hascompleted its selection process. The ATLAS ROS was completelyreplaced during the 2013–2014 experimental shutdown in order tomeet the demanding conditions expected during LHC Run 2 and Run 3(2015–2025). The ROS consists of roughly one hundred Linux-based2U-high rack-mounted servers equipped with PCIe I/O cards and10 GbE interfaces. This paper documents the system requirementsfor LHC Runs 2 and 3 and the design choices taken to meet them. Theresults of performance measurements and the re-use of ROS technologyfor the development of data sources, test platforms for othersystems, and another ATLAS DAQ system component, namely the Regionof Interest Builder (RoIB), are also discussed. Finally performanceresults for Run 2 operations are presented before looking at theupgrade for Run 3.