Performance evaluation of parallel systems employing roll-forward checkpoint schemes

High performance and reliability are the main goals of parallel and distributed computing systems. To increase the performance and reliability of the systems, various checkpoint schemes have been proposed in the literature for decades. However, the lack of general analytical models has been an obstacle to compare the performance of systems employing different checkpoint schemes. This paper develops an analytical model to evaluate the relative response time of systems employing checkpoint schemes. The model has been applied to evaluate the relative response time of systems employing RFC (Roll-Forward Checkpoint), DMR-F (Double Modular Redundancy for Forward recovery), and DST (Duplex with Self-Test) schemes. The result shows the feasibility of the model developed in the paper.