A. Dell'Acqua | Searcharxiv

arXiv2003

Building A High Performance Parallel File System Using Grid Datafarm and ROOT I/O

Sheer amount of petabyte scale data foreseen in the LHC experiments require a careful consideration of the persistency design and the system design in the world-wide distributed computing. Event parallelism of the HENP data analysis enables us to take maximum advantage of the high performance cluster computing and networking when we keep the parallelism both in the data processing phase, in the data management phase, and in the data transfer phase. A modular architecture of FADS/ Goofy, a versatile detector simulation framework for Geant4, enables an easy choice of plug-in facilities for persistency technologies such as Objectivity/DB and ROOT I/O. The framework is designed to work naturally with the parallel file system of Grid Datafarm (Gfarm). FADS/Goofy is proven to generate 10^6 Geant4-simulated Atlas Mockup events using a 512 CPU PC cluster. The data in ROOT I/O files is replicated using Gfarm file system. The histogram information is collected from the distributed ROOT files. During the data replication it has been demonstrated to achieve more than 2.3 Gbps data transfer rate between the PC clusters over seven participating PC clusters in the United States and in Japan.

cs.DC↗

arXiv2003

The full detector simulation for the Atlas experiment: status and outlook

The simulation of the ATLAS detector is a major challenge, given the complexity of the detector and the demanding environment of the LHC. The apparatus, one of the biggest and most complex ever designed, requires a detailed, flexible and, if possible, fast simulation which is needed already today to deal with questions related to design optimization, to issues raised by staging scenarios, and of course to enable detailed physics studies to lay the basis for the first physics discoveries. Scalability and robustness stand out as the most critical issues that are to be faced in the implementation of such a simulation. In this paper we present the status of the present simulation and the adopted solutions in terms of speed optimization, centralization of services, framework facilities and persistency solutions. Emphasis is put on the global performance when the different detector components are collected together in a full and detailed simulation. The reference tool adopted is Geant4.

physics.data-an↗