ZENTURIO: An Experiment Management System for Cluster and Grid Computing
Thomas Fahringer, Radu Prodan
Over the last decade, a dramatic increase has been observed in the ability to generate and store data in the course of parameter studies, performance analysis, and software testing. In this paper, we introduce ZENTURIO, a sophisticated experiment management environment that greatly alleviates parameter studies, performance analysis, and software testing for a wide variety of target architectures, including cluster and Grid architectures. ZENTURIO uses a novel directive-based language named ZEN in combination with a user portal to specify arbitrary complex program executions. Among others, ZEN enables to substitute strings, to request for performance information, and to control the number of experiments.
ZENTURIO has been designed as a collection of Grid services, which comprise the following:
(1) a registry service which supports registering and locating Grid services;
(2) an experiment generator that parses files with ZEN directives and instruments applications for performance analysis and parameter studies;
(3) an experiment manager that compiles and controls the execution of experiments on the target machine. A graphical user portal allows the user to control and monitor the experiments and to automatically visualize performance and output data across multiple experiments.
ZENTURIO has been implemented by employing Java/Jini technologies and supports experiments on cluster architectures via PBS and on Grid infrastructures through Globus schedulers. We report results of using ZENTURIO with an actual performance analysis and parameter study for a Globus site and a cluster architecture, respectively.