Concurrent Shadow Paging

摘要

In this paper we present several new ideas about concurrent shadow paging as a crash recovery method in databases. We show how to use shadow paging in a multi-user environment and describe several optimizations and ideas which significantly improve the performance and general usability of shadow paging, making it very competitive to other methods in crash recovery. Shadow paging with our optimizations appears to be much faster than log-based solutions, and it would seem to be very generally applicable. We also present some new, potentially very useful ideas, which can be efficiently implemented with shadow paging but not with logging.