一种持久性内存文件系统数据页的混合管理机制

A Hybrid Approach for Managing Data Pages in Persistent Memory File Systems

英特尔于2019年4月正式发布基于3D-Xpoint技术的傲腾持久性内存(Optane DC persistent memory),这为构建高效的持久性内存存储系统提供了新的机遇.然而,现有的存储系统软件并不能很好地利用其字节寻址特性,持久性内存性能很难充分发挥.提出一种文件系统数据页的混合管理机制HDPM,通过选择性使用写时复制机制和日志结构管理文件数据,充分发挥持久性内存字节可寻址特性,从而避免了传统单一模式在非对齐写或者小写造成的写放大问题.为避免影响读性能,HDPM引入逆向扫描机制,实现日志结构重构数据页时不引入额外数据拷贝.HDPM还提出一种多重垃圾回收机制进行日志清理.当单个日志结构过大时,通过读写流程主动回收日志结构;当持久性内存空间受限时,则通过后台线程使用免锁机制异步释放日志空间.实验显示,HDPM相比于NOVA文件系统,单线程写延迟降低达58%,且读延迟不受影响;Filebench多线程测试显示,HDPM相比于NOVA提升吞吐率33%.

Intel has officially released the Optane DC Persistent Memory based on 3D-Xpoint technology in April 2019,which provides new opportunities for building efficient persistent memory storage systems.However,existing software is far from fully exploiting the hardware performance,due to the ignorance of utilizing the byte-addressable feature of persistent memory.This paper proposes a hybrid data page management(HDPM)mechanism.It manages file data by selectively using the copy-on-write technique and log-structure,so as to fully utilize the byte-addressable feature of persistent memory.It can avoid the redundant copy overhead as in traditional approaches when processing un-aligned or small-sized writes.To guarantee the read performance unaffected,HDPM introduces reverse-scanning mechanism,which avoids the additional data copying when rebuilding data pages from the log.HDPM also introduces a multi-stage garbage collection mechanism for log cleaning.When a single log is too large,it s automatically reclaimed by read write system calls.When the persistent memory space is limited,a background thread asynchronously reclaims the log space with a lock-free approach,without affecting the normal read write performance.Experiments show that HDPM provides high write performance.Compared with NOVA,a state-of-the-art persistent memory file system,HDPM exhibits 58%lower write latency at most with the small-sized and write-intensive workload,and provides comparable performance for read operations.Our evaluation with Filebench shows that HDPM outperforms NOVA by 33%at most with 10 concurrent threads.