LAC: A Workload Intensity-Aware Caching Scheme for High-Performance SSDs

被引:0
|
作者
Sun, Hui [1 ]
Tong, Haoqiang [1 ]
Yue, Yinliang [2 ]
Qin, Xiao [3 ]
机构
[1] Anhui Univ, Sch Comp Sci & Technol, Hefei 230201, Peoples R China
[2] Zhongguancun Lab, Beijing 100049, Peoples R China
[3] Auburn Univ, Dept Comp Sci & Software Engn, Auburn, AL 36849 USA
基金
中国国家自然科学基金;
关键词
Flash memories; Time factors; Costs; Tail; Writing; Random access memory; Delays; Caching scheme; I/O-intensity awareness; parallel write; die-level monitor; solid state disk; NAND flash; BUFFER MANAGEMENT SCHEME; GARBAGE COLLECTION; FLASH; LRU;
D O I
10.1109/TC.2024.3385290
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Inside an NAND Flash-based solid-state disk (SSD), utilizing DRAM-based write-back caching is a practical approach to bolstering the SSD performance. Existing caching schemes overlook the problem of high user I/Os intensity due to the dramatic increment of I/Os accesses. The hefty I/O intensity causes access conflict of I/O requests inside an SSD: a large number of requests are blocked to impair response time. Conventional passive update caching schemes merely replace pages upon access misses in event of full cache. Tail latency occurs facing a colossal I/O intensity. Active write-back caching schemes utilize idle time among requests coupled with free internal bandwidth to flush dirty data into flash memory in advance, lowering response time. Frequent active write-back operations, however, cause access conflict of requests - a culprit that expands write amplification (WA) and degrades SSD lifetime. We address the above issues by proposing a workLoad intensity-aware and Active parallel Caching scheme - LAC - that is powered by collaborative-load awareness. LAC fends off user I/Os' access conflict under high-I/O-intensity workloads. If the I/O intensity is low - intervals between consecutive I/O requests are large - and the target die is free, LAC actively and concurrently writes dirty data of adjacent addresses back to the die, cultivating clean data generated by the active write-back. Replacing clean data in priority can reduce response time and prevent flash transactions from being blocked. We devise a data protection method to write back cold data based on various criteria in the cache replacement and active write-backs. Thus, LAC reduces WA incurred by actively writing back hot data and extends SSD lifetime. We compare LAC against the six caching schemes (LRU, CFLRU, GCaR-LRU, MQSim, VS-Batch, and Co-Active) in the modern MQSim simulator. The results unveil that LAC trims response time and erase count by up to 78.5% and 47.8%, with an average of 64.4% and 16.6%, respectively.
引用
收藏
页码:1738 / 1752
页数:15
相关论文
共 50 条
  • [41] High-Performance Linguistics Scheme for Cognitive Information Processing
    Suryanarayana, D.
    Kanakam, Prathyusha
    Hussain, S. Mahaboob
    Gupta, Sumit
    PROGRESS IN INTELLIGENT COMPUTING TECHNIQUES: THEORY, PRACTICE, AND APPLICATIONS, VOL 1, 2018, 518 : 369 - 378
  • [42] An evolutionary management scheme in high-performance packet switches
    Ascia, G
    Catania, V
    Panno, D
    IEEE-ACM TRANSACTIONS ON NETWORKING, 2005, 13 (02) : 262 - 275
  • [43] A cascaded scheme for high-performance estimation of vehicle states
    Chen, Jianfeng
    Hu, Shulin
    Ye, Yicai
    Huang, Haoqian
    Langari, Reza
    Tang, Chuanye
    PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART D-JOURNAL OF AUTOMOBILE ENGINEERING, 2021, 235 (08) : 2101 - 2113
  • [44] A mesochronous pipelining scheme for high-performance digital systems
    Tatapudi, Suryanarayana B.
    Delgado-Frias, Jos G.
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2006, 53 (05) : 1078 - 1088
  • [45] High-performance docker integration scheme based on OpenStack
    Yang, Sijie
    Wang, Xiaofeng
    Wang, Xiaoxue
    An, Lun
    Zhang, Guizhu
    WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS, 2020, 23 (04): : 2593 - 2632
  • [46] A high-performance priority scheme for ATM switching systems
    Chen, WT
    Hwang, WY
    JOURNAL OF HIGH SPEED NETWORKS, 1997, 6 (01) : 1 - 14
  • [47] A high-performance calculation scheme for stochastic dynamic problems
    Huang, Dongwei
    Wu, Feng
    Zhang, Sheng
    Chen, Biaosong
    Zhang, Hongwu
    MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2023, 189
  • [48] A scheme for high-performance data delivery in the Web environment
    Jung, GS
    Malluhi, QM
    Brown, WG
    1998 INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED SYSTEMS, PROCEEDINGS, 1998, : 210 - 217
  • [49] Fault-Aware Runtime Strategies for High-Performance Computing
    Li, Yawei
    Lan, Zhiling
    Gujrati, Prashasta
    Sun, Xian-He
    IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2009, 20 (04) : 460 - 473
  • [50] Energy-aware job scheduler for high-performance computing
    Mammela, Olli
    Majanen, Mikko
    Basmadjian, Robert
    De Meer, Hermann
    Giesler, Andre
    Homberg, Willi
    COMPUTER SCIENCE-RESEARCH AND DEVELOPMENT, 2012, 27 (04): : 265 - 275