HOLMES: a tool for monitoring heterogeneous architectures

Monitoring tools are necessary components in the support of distributed applications and can be used to provide dependability, debugging and testing, to enhance the performance and to make possible the run-time steering of applications. These tools are needed to exploit in the best way all the available high performance computing resources of a heterogeneous environment. The paper describes HOLMES, an on-line monitoring system designed to support dynamic management of resources that requires run-time measurement. HOLMES identifies the evolving system state and provides the necessary information to any dynamic policy to assign resources by following application evolution. HOLMES makes possible to control and steer an application even distributed across heterogeneous architectures, from parallel machines to clusters of workstations and PCs