Checkpointing strategy for multiple real-time tasks

We analyze checkpointing strategy for multiple realtime tasks with deadlines. Real-time tasks usually have deadlines associated with them. For multiple real-time tasks, checkpointing strategy considering deadlines of all tasks is very difficult to derive. We analyze the problem of checkpoint placement for such multiple tasks. In our strategy, the interval between checkpoints are determined for each task. An approximated failure probability over a specified interval is derived. Then the number of checkpoints for each task is selected to minimize the approximated failure probability. To show the usefulness of our strategy, error bound between the exact and the approximated failure probability is estimated, which is revealed to be quite small.