CAGC: A Content-aware Garbage Collection Scheme for Ultra-Low Latency Flash-based SSDs

被引:6
作者
Wu, Suzhen [1 ]
Du, Chunfeng [1 ]
Li, Haijun [1 ]
Jiang, Hong [2 ]
Shen, Zhirong [1 ]
Mao, Bo [1 ]
机构
[1] Xiamen Univ, Sch Informat, Xiamen, Fujian, Peoples R China
[2] Univ Texas Arlington, Arlington, TX 76019 USA
来源
2021 IEEE 35TH INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM (IPDPS) | 2021年
基金
中国国家自然科学基金;
关键词
Ultra-Low Latency Flash-based SSDs; Garbage Collection; Data Reduplication; Reference Count; Data Placement;
D O I
10.1109/IPDPS49936.2021.00025
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
With the advent of new flash-based memory technologies with ultra-low latency, directly applying inline data deduplication in flash-based storage devices can degrade the system performance since key deduplication operations lie on the shortened critical write path of such devices. To address the problem, we propose a Content-Aware Garbage Collection scheme (CAGC), which embeds the data deduplication into the data movement workflow of the Garbage Collection (GC) process in ultra-low latency flash-based SSDs. By parallelizing the operations of valid data pages migration, hash computing and flash block erase, the deduplication-induced performance overhead is alleviated and redundant page writes during the GC period are eliminated. To further reduce data writes and write amplification during GC, CAGC separates and stores data pages in different regions based on their reference counts. The performance evaluation of our CAGC prototype implemented in FlashSim shows that CAGC significantly reduces the number of flash blocks erased and data pages migrated during GC, leading to improved user I/O performance and reliability of ultra-low latency flash-based SSDs.
引用
收藏
页码:162 / 171
页数:10
相关论文
共 38 条
  • [1] Agrawal N, 2008, P USENIX ANN TECHN C, P57, DOI DOI 10.1109/ISSCC.2012.6177101
  • [2] [Anonymous], 2011, P 9 USENIX C FIL STO
  • [3] Cheong W, 2018, ISSCC DIG TECH PAP I, P338, DOI 10.1109/ISSCC.2018.8310322
  • [4] Chien A., 2017, P 15 USENIX C FILE S
  • [5] Colgrove John, 2015, P 2015 ACM SIGMOD IN
  • [6] The Tail at Scale
    Dean, Jeffrey
    Barroso, Luiz Andre
    [J]. COMMUNICATIONS OF THE ACM, 2013, 56 (02) : 74 - 80
  • [7] Algorithms and data structures for flash memories
    Gal, E
    Toledo, S
    [J]. ACM COMPUTING SURVEYS, 2005, 37 (02) : 138 - 163
  • [8] Gupta A., 2011, FAST, P91
  • [9] Hao MZ, 2016, 14TH USENIX CONFERENCE ON FILE AND STORAGE TECHNOLOGIES (FAST '16), P263
  • [10] Harris Bryan, 2020, P 12 USENIX WORKSH H