FFCCD: fence-free crash-consistent concurrent defragmentation for persistent memory
FFCCD: fence-free crash-consistent concurrent defragmentation for persistent memory
复制标题
DOI：
10.1145/3470496.3527406
复制
发表时间：
2022-06
期刊：
影响因子：
--
通讯作者：
Yuanchao Xu;Chencheng Ye;Yan Solihin;Xipeng Shen
中科院分区：
文献类型：
--
作者：
Yuanchao Xu;Chencheng Ye;Yan Solihin;Xipeng Shen
持续的内存（PM）越来越多地补充或代替DRAM作为主要内存。先前的工作集中在持续记忆的可重复性和内存泄漏上，但没有解决因持久性，持久记忆碎片的扩大问题，这是指在整个用法中持续的持续记忆的碎片持续恶化。本文揭示了挑战，并提出了第一个系统的碰撞解决方案，即无栅栏一致的并发碎片化（FFCCD）。 FFCCD强调了持续的指针格式，根节点和由持续内存编程模型提供的键入分配，以启用PM上的并发碎片。 FFCCD引入了架构支持，以进行并发碎片化，从而实现无围栏的设计和快速读取障碍，从而减少了两个碎片持续的持久内存的主要开销。这些技术是有效的（减少28--73％的碎裂）和快速（4.1％的执行时间开销）。
Persistent Memory (PM) is increasingly supplementing or substituting DRAM as main memory. Prior work have focused on reusability and memory leaks of persistent memory but have not addressed a problem amplified by persistence, persistent memory fragmentation, which refers to the continuous worsening of fragmentation of persistent memory throughout its usage. This paper reveals the challenges and proposes the first systematic crash-consistent solution, Fence-Free Crash-consistent Concurrent Defragmentation (FFCCD). FFCCD resues persistent pointer format, root nodes and typed allocation provided by persistent memory programming model to enable concurrent defragmentation on PM. FFCCD introduces architecture support for concurrent defragmentation that enables a fence-free design and fast read barrier, reducing two major overheads of defragmenting persistent memory. The techniques is effective (28--73% fragmentation reduction) and fast (4.1% execution time overhead).