Modification Operation Buffering : A Low-Overhead Approach to Checkpoint User Files

Checkpointing and recovery is a technique for saving process state during normal execution and restoring the saved state after a failure to reduce the amount of lost work. One of its important capabilities is to save and restore the state of user files of the process. This paper presents an approach called Modification Operation Buffering to support this capability. MOB approach buffers all the modification operations after a checkpoint until the next one, making all the operations between two checkpoints atomic as a whole. By choosing a suitable size dynamically for memory buffer, and by hiding the latency of flushing the buffer, the MOB approach achieves an overhead lower than other approaches.