Lifetime-Leveling LSM-Tree Compaction for ZNS SSD

被引:27
|
作者
Jung, Jeeyoon [1 ]
Shin, Dongkun [1 ]
机构
[1] Sungkyunkwan Univ, Seoul, South Korea
来源
PROCEEDINGS OF THE 2022 14TH ACM WORKSHOP ON HOT TOPICS IN STORAGE AND FILE SYSTEMS, HOTSTORAGE 2022 | 2022年
基金
新加坡国家研究基金会;
关键词
Zoned Namespace; LSM-tree; Compaction; Solid-State Drives;
D O I
10.1145/3538643.3539741
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
The Log-Structured Merge (LSM) tree is considered well-suited to zoned namespace (ZNS) storage devices since the write requests to LSM-tree is sequential. However, zones can be partially invalidated and be fragmented during LSM-tree compaction. The partially-invalid zones cannot be utilized and thus space amplification becomes significant. To reclaim the invalid space, host-managed garbage collection (GC) is required, which increases the write amplification of ZNS storage and degrades I/O performance. We introduce a lifetime-leveling compaction (LL-compaction) tailored for ZNS SSD, which can alleviate space amplification without GC by making the sorted string tables in a zone have similar lifetimes. In our experiments using LevelDB, the LL-compaction achieved 1.7x better performance by removing GCs.
引用
收藏
页码:100 / 105
页数:6
相关论文
共 50 条
  • [31] Reducing Tail Latency of LSM-tree based Key-value Store via Limited Compaction
    Hu, Yongchao
    Du, Yajuan
    36TH ANNUAL ACM SYMPOSIUM ON APPLIED COMPUTING, SAC 2021, 2021, : 178 - 181
  • [32] Learning Autoregressive Model in LSM-Tree based Store
    Su, Yunxiang
    Ma, Wenxuan
    Song, Shaoxu
    PROCEEDINGS OF THE 29TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2023, 2023, : 2061 - 2071
  • [33] Improving LSM-Tree Based Key-Value Stores With Fine-Grained Compaction Mechanism
    Sun, Hui
    Chen, Guanzhong
    Yue, Yinliang
    Qin, Xiao
    IEEE TRANSACTIONS ON CLOUD COMPUTING, 2023, 11 (04) : 3778 - 3796
  • [34] Adaptive Lower-Level Driven Compaction to Optimize LSM-Tree Key-Value Stores
    Chai, Yunpeng
    Chai, Yanfeng
    Wang, Xin
    Wei, Haocheng
    Wang, Yangyang
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2022, 34 (06) : 2595 - 2609
  • [35] WA-Zone: Wear-Aware Zone Management Optimization for LSM-Tree on ZNS SSDs
    Long, Linbo
    He, Shuiyong
    Shen, Jingcheng
    Liu, Renping
    Tan, Zhenhua
    Gao, Congming
    Liu, Duo
    Zhong, Kan
    Jiang, Yi
    ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION, 2024, 21 (01)
  • [36] MDCF: Multiple Dynamic Cuckoo Filters for LSM-Tree
    Yao, Xingfei
    Xie, Taotao
    Chen, Xiaowei
    Shen, Zhaoyan
    Cai, Xiaojun
    ALGORITHMS AND ARCHITECTURES FOR PARALLEL PROCESSING, ICA3PP 2023, PT VI, 2024, 14492 : 202 - 218
  • [37] LTG-LSM: The Optimal Structure in LSM-tree Combined with Reading Hotness
    Yu, JiaPing
    Chen, HuaHui
    Qian, JiangBo
    Dong, YiHong
    2020 IEEE 26TH INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED SYSTEMS (ICPADS), 2020, : 1 - 8
  • [38] Optimization of LSM-Tree for Key-Value Stores
    Wu S.
    Xie J.
    Wang Y.
    Jisuanji Yanjiu yu Fazhan/Computer Research and Development, 2020, 57 (11): : 2432 - 2441
  • [39] D2Comp: Efficient Offload of LSM-tree Compaction with Data Processing Units on Disaggregated Storage
    Ding, Chen
    Zhou, Jian
    Lu, Kai
    Li, Sicen
    Xiong, Yiqin
    Wan, Jiguang
    Zhan, Ling
    ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION, 2024, 21 (03)
  • [40] A storage computing architecture with multiple NDP devices for accelerating compaction performance in LSM-tree based KV stores
    Sun, Hui
    Wang, Qiang
    Yue, Yin Liang
    Zhao, Yuhong
    Fu, Song
    JOURNAL OF SYSTEMS ARCHITECTURE, 2022, 130