PROFICIENT CHECKPOINTING PROCEDURES FOR DISTRIBUTED SYSTEMS

Abstract

Checkpointing technique is applied to recover a system from fault tolerant state, whereas checkpoint is known as process state. State is said to be consistent only if doesnt contain inconsistent. In checkpointing processes take checkpoints that result in consistent global state. In case any failure, system reboots and starts its execution from a previous consistent state which should be global and finally saves on the stable storage, in final checkpointed state computation can be only done if it is needed to be redone again. In this paper, authors presented some inconsistencies in existing in checkpointing of distributed systems and suggested some guidelines for reviewing such protocols.