MUSE: a software oscilloscope for clusters and grids

Oscilloscopes and their cousins, logic analyzers, are the tools of choice for difficult electronic hardware problems. In the hands of a skilled engineer or technician, these tools can be used to solve stubborn problems. The key to the utility of oscilloscopes is the depth of detail they provide and their flexibility, which allows the level of detail to be adjusted to fit the task at hand. Distributed applications, which run on computing clusters and computational grids, are also complex and difficult to tame. We need tools to understand their complexities and the ability to choose the level of detail to fit the task, whether the task be debugging, tuning, monitoring or controlling. The MAGNET User-Space Environment (MUSE) has been designed as a "software oscilloscope" for computing clusters and computational grids. It is a toolkit for applications and developers to obtain detailed information about the environment on the host. The information can be used on-line or saved for off-line analysis. It has low overhead and allows the level of detail to be adjusted. Furthermore, MUSE monitors without requiring the modification or relinking of applications. It has been designed to make it easy to develop "adaptive applications" - applications that are aware of their environment and can adapt to changes.