Automatic Parallel Program Checkpointing in Message-Passing Environments
Andrey Smirnov · Proceedings of the Spring/Summer young researchers' colloquium on software engineering · 2007
Problem of efficient cluster resources usage is very important, because of high demand for parallel computations.Checkpointing allows to manage cluster computing time more efficiently.In this article parallel programs checkpointing problems are discussed and implementation of automatic parallel checkpointing systems for MPI programs is presented.It is based on simple user-space portable checkpointing library with two different parallel program analysis approaches to checkpoint consistency.