Case of fault-tolerant memory for transaction processing

Abstract

In this paper, for database transaction processing, we compare the relative price-performance of storing data in volatile memory (V-mem), fault-tolerant non-volatile memory (FT-mem) and disk. First, we extend Gray's 5-minute rule, which compares the relative cost of storing data in volatile memory as against disk for read-only data, to read-write data. Second, we show that because of additional write overhead, FT-mem has a higher advantage over V-mem than previously thought. Previous studies comparing volatile and non-volatile memories have focussed on the response time advantages of putting log data in non-volatile memory. We show that there is a direct reduction in disk I/O, which leads to a much larger savings in cost using an FT-mem buffer. Third, the 5-minute model is a simple model that assumes knowledge of inter-access times for data items. We present a more realistic model that assumes an LRU buffer management policy. We combine this with the recovery time constraint and study the resulting price-performance. We show that the use of an FT-mem buffer can lead to a significant benefit in terms of overall price-performance.