Impact of checkpoint latency on overhead ratio of a checkpointing scheme
Nitin H. Vaidya · IEEE Transactions on Computers · 1997
Checkpointing reduces loss of computation in the presence of failures. Two metrics characterize a checkpointing scheme: checkpoint overhead and checkpoint latency. The paper shows that a large increase in latency is acceptable if it is accompanied by a relatively small reduction in overhead. Also, for equidistant checkpoints, optimal checkpoint interval is shown to be typically independent of checkpoint latency.