Adaptive Software Caching for Efficient NVRAM Data Persistence

Non-volatile main memory (NVRAM) enables data persistence in memory. However, the existence of transient CPU caches in modern computer architectures brings a serious performance issue. In particular, cache lines have to be flushed frequently to guarantee consistent persistent program states. Hence, persistence and performance cannot be easily obtained simultaneously. In this paper, we optimize data persistence by proposing a software cache. The software cache first buffers lines that need to be flushed, and then flushes them out at an appropriate later time. The software cache aims to maximize the combination of cache line flushes. We designed a new linear-time algorithm to calculate cache miss ratio curve (MRC) so as to adaptively select the best cache capacity at run-time based on program behavior. We evaluated the software cache on a real-world memory-based database benchmark, the SPLASH2 benchmark suite and four micro-benchmarks. Results indicate that the software cache solution reduces cache write backs to persistent memory by 12× and improves performance over the state-of- the-art methods by 2.1× on average, measured on a real system emulator.