Efficient Memory Mapped File I/O for In-Memory File Systems
Efficient Memory Mapped File I/O for In-Memory File Systems
复制标题
适用于内存文件系统的高效内存映射文件 I/O
DOI：
--
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
Hwansoo Han
中科院分区：
文献类型：
--
作者：
Jungsik Choi;Jiwon Kim;Hwansoo Han
最近，随着低延迟NVM存储的出现，软件开销已经成为比存储延迟更大的瓶颈，并且存储器映射文件I/O作为避免软件开销的手段已经获得关注。然而，根据我们的分析，内存映射文件I/O会产生大量额外的开销。为了充分利用内存映射文件I/O的潜力，应该减轻这种开销。我们提出了映射提前，映射缓存，和扩展madvise技术，以最大限度地提高性能的内存映射文件I/O低延迟NVM存储系统。该解决方案可以避免页错误开销和页表项构造开销。我们的实验结果表明，吞吐量提高了38-70%，在微基准测试和性能提高了6-18%，在真实的应用程序相比，现有的内存映射I/O机制。
Recently, with the emergence of low-latency NVM storage, software overhead has become a greater bottleneck than storage latency, and memory mapped file I/O has gained attention as a means to avoid software overhead. However, according to our analysis, memory mapped file I/O incurs a significant amount of additional overhead. To utilize memory mapped file I/O to its true potential, such overhead should be alleviated. We propose map-ahead, mapping cache, and extended madvise techniques to maximize the performance of memory mapped file I/O on low-latency NVM storage systems. This solution can avoid both page fault overhead and page table entry construction overhead. Our experimental results show throughput improvements of 38-70% in microbenchmarks and performance improvements of 6-18% in real applications compared to existing memory mapped I/O mechanisms.