计算机科学
延迟(音频)
隐藏物
德拉姆
闪光灯(摄影)
工作量
SCSI
操作系统
嵌入式系统
计算机硬件
软件
电信
艺术
视觉艺术
作者
Qihui Chen,Shuai Wang,You Zhou,Fei Wu,Shu Li,Zhengyong Wang,Conghua Xie
标识
DOI:10.1109/iccd56317.2022.00019
摘要
QLC flash-based SSDs are gaining increasing attention and are expected to be widely used in read-intensive application scenarios, since they provide high density and low cost but suffer from poor write endurance and performance. QLC flash has four types of pages, between which read latency variation is as large as 1.6 to 4.8 times. This raises a critical concern for QLC SSDs to provide adequate and stable read performance. Notice that the SSD-internal cache (built with DRAM or non-volatile RAM) has long been utilized to improve write performance and lifetime. In this paper, we argue that the cache also plays an important role in read performance optimization of QLC SSDs. We design a novel flash page type aware read cache scheme, called PACA. It exploits read latency variation of QLC pages to prioritize caching data stored in high-latency QLC pages in a workload-adaptive manner. We verified PACA in FEMU, a popular SSD emulator. Experimental results show that PACA can reduce the average SSD read latency by up to 44.5%, compared with a baseline read cache scheme being unaware of flash page types.
科研通智能强力驱动
Strongly Powered by AbleSci AI