摘要：In this paper, we present a high performance recovery algorithm for distributed systems in which checkpoints are taken asynchronously. It offers fast determination of the recent consistent global checkpoint (maximum consistent state) of a distributed system after the system recovers from a failure. The main feature of the proposed recovery algorithm is that it avoids to a good extent unnecessary comparisons of checkpoints while testing for their mutual consistency. The algorithm is executed simultaneously by all participating processes, which ensures its fast execution. Moreover, we have presented an enhancement of the proposed recovery idea to put a limit on the dynamically growing lengths of the data structures used. It further reduces the number of comparisons necessary to determine a recent consistent state and thereby reducing further the time of completion of the recovery algorithm. Finally, it is shown that the proposed algorithm offers better performance compared to some related existing works that use asynchronous checkpointing.
关键词：asynchronous checkpointing; recovery; maximum consistent state
