An I/O Isolation Scheme for Key-Value Store on Multiple Solid-State Drives

被引:3
作者
Kim, Hwajung [1 ]
Yeom, Heon Young [1 ]
Son, Yongseok [2 ]
机构
[1] Seoul Natl Univ, Dept Comp Sci & Engn, Seoul, South Korea
[2] Chung Ang Univ, Sch Software, Seoul, South Korea
来源
2019 IEEE 4TH INTERNATIONAL WORKSHOPS ON FOUNDATIONS AND APPLICATIONS OF SELF* SYSTEMS (FAS*W 2019) | 2019年
基金
新加坡国家研究基金会;
关键词
High-Performance Storage Device; LSM-tree; Key-Value Store;
D O I
10.1109/FAS-W.2019.00049
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
High-performance storage devices, such as Non-Volatile Memory express Solid-State Drives (NVMe SSDs), have widely adopted in data centers. Especially, multiple storage devices improve higher I/O performance compared with a single device. However, the performance can be reduced in the case of workloads with mixed read and write requests (e.g., key-value stores) even though multiple storage devices are adopted. The reason is that read requests can be blocked until the processing for write requests is finished. In this paper, we propose an I/O isolation scheme to improve the performance of key-value store for multiple SSDs. In our scheme, we separate read and write operations for multiple files. For example, we classify generated files of key-value store and perform read/write operations in the separated storage devices according to the characteristics of each file. To do this, we deploy files by considering their characteristics on multiple SSDs. We implement our scheme in RocksDB and evaluate its performance with six NVMe SSDs compare with RAID-0 configuration. In the experimental results, we demonstrate that our scheme improves performance compared with an existing scheme (i.e., RAID-0).
引用
收藏
页码:170 / 175
页数:6
相关论文
共 17 条
  • [1] [Anonymous], FLASH MEM SUMM
  • [2] [Anonymous], 2019, Rocksdb benchmarking tools
  • [3] [Anonymous], 2015, P 8 ACM INT SYSTEMS
  • [4] FIOS: Feature Based I/O Stream Identification for Improving Endurance of Multi-Stream SSDs
    Bhimani, Janki
    Mi, Ningfang
    Yang, Zhengyu
    Yang, Jingpei
    Pandurangan, Rajinikanth
    Choi, Changho
    Balakrishnan, Vijay
    [J]. PROCEEDINGS 2018 IEEE 11TH INTERNATIONAL CONFERENCE ON CLOUD COMPUTING (CLOUD), 2018, : 17 - 24
  • [5] Bjorling M, 2017, PROCEEDINGS OF FAST '17: 15TH USENIX CONFERENCE ON FILE AND STORAGE TECHNOLOGIES, P359
  • [6] Chen F, 2011, INT S HIGH PERF COMP, P266, DOI 10.1109/HPCA.2011.5749735
  • [7] Gonzalez J., 2016, NVMW
  • [8] Jo K., 2014, FLASH MEM SUMM
  • [9] Kang J.-U., 2014, HotStorage
  • [10] Durable Write Cache in Flash Memory SSD for Relational and NoSQL Databases
    Kang, Woon-Hak
    Lee, Sang-Won
    Moon, Bongki
    Kee, Yang-Suk
    Oh, Moonwook
    [J]. SIGMOD'14: PROCEEDINGS OF THE 2014 ACM SIGMOD INTERNATIONAL CONFERENCE ON MANAGEMENT OF DATA, 2014, : 529 - 540