Checkpointing memory-resident databases

Abstract

A database system is considered in which a main-memory database system holds all data in semiconductor memory, and for recovery purposes a backup copy of the database is maintained in secondary storage. The checkpointer is the component of the crash recovery manager responsible for maintaining the backup copy. Ideally, the checkpointer should maintain an almost-up-to-date backup while interfering as little as possible with the system's transaction processing activities. Several algorithms for maintaining such a backup database are presented and compared using an analytic model. The results show some significant performance differences among the algorithms and illustrate some of the tradeoffs that are available in designing such a checkpointer.<>