1 Multi-threaded, discrete event simulation of distributed computing system

The LHC experiments have envisaged unprecedented complex computing sys-tems, for which is necessary to provide a realistic description and modelling of data access patterns and of many jobs running concurrently on large scale distrib-uted systems and exchanging very large amounts of data. A process oriented approach for discrete event simulation is well suited to describe various activities running concurrently as well the stochastic arrival pat-terns, specific for such type of simulation. Threaded objects or “Active Objects” can provide a natural way to map the specific behavior of distributed data pro-cessing into the simulation program. The simulation tool developed within MONARC[1] is based on Java(TM) [2] technology which provides adequate tools for developing a flexible and distrib-uted process oriented simulation. Proper graphics tools, and ways to analyze data interactively, are essential in any simulation project. The design elements, status and features of the MONARC simulation tool are presented. The program allows realistic modelling of complex data access pat-terns by multiple concurrent users in large scale computing systems in a wide range of possible architectures, from centralized to highly distributed. Compari-son between queueing theory and realistic client-server measurements are also presented. 1