CPPC-G: Fault-Tolerant Parallel Applications on the Grid

Abstract. With the maturity of the Grid, the community has made an important effort in developing middleware and tools to provide differ-ent functionalities, such as resource discovery, resource management, job submission, execution monitoring. Unfortunately, not so much attention has been paid in developing mechanism to provide fault-tolerance to ex-ecution of applications on a Grid. This paper addresses the design and implementation of an architecture based on services (CPPC-G) to man-age the execution of fault tolerant parallel applications on Grids. The CPPC (Controller/Precompiler for Portable Checkpointing) framework is used to insert checkpoint instrumentation into the application code. Designed services will be in charge of submission and monitoring of the execution of the parallel application, management of checkpoint files and detection and automatic restart of failed executions.