Provisioning CSD-based Storage Systems with Erasure-coding Offloaded to the CSD

被引:0
作者
Byun, Hongsu [1 ]
Jamil, Safdar [1 ]
Ryu, Junghyun [1 ]
Park, Sungyong [1 ]
Lee, Myungcheol [2 ]
Park, Sung-Soon [3 ,4 ]
Kim, Youngjae [1 ]
机构
[1] Sogang Univ, Dept Comp Sci & Engn, Seoul 04107, South Korea
[2] ETRI, Smart Data Res Sect, Daejeon 34129, South Korea
[3] GlueSys, Seoul 34129, South Korea
[4] Anyang Univ, Seoul 34129, South Korea
关键词
Storage system; computational storage drive; erasure coding; analytical modeling and simulation;
D O I
10.5573/JSTS.2024.24.1.8
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
While commercially available Computational Storage Drives (CSD) have appeared, it is challenging to build a CSD array -based storage system due to the lack of storage provisioning tools determining the performance and cost-effectiveness of a storage system with CSDs. Therefore, C SD P LAN , a storage provisioning tool to find the number of performance -efficient CSDs when building a storage system with CSD, has been proposed. However, the effectiveness of C SD P LAN has only been evaluated using specific big data analysis workloads, which are not computationally intensive. In this work, we extend C SD P LAN to propose C SD P LAN -EC, a CSD provisioning tool for building storage systems with computationally intensive erasure coding offloaded to CSDs. Our evaluation shows that the optimal number of CSDs running erasure coding in a storage system is 5 and that it decreases to 1 when the computational power of the CSDs is improved by a factor of 5.
引用
收藏
页码:8 / 17
页数:10
相关论文
共 35 条
  • [1] [Anonymous], 2022, Los Alamos National Laboratory and SK hynix to demonstrate first-of-a-kind ordered Key-value Store Computational Storage Device
  • [2] ARM Xilinx, 2023, Vitis Accel Examples
  • [3] ARM Xilinx, 2023, Vitis Unified Software Platform
  • [4] ARM Xilinx, 2023, UG1399-Vitis-HLS
  • [5] ARM Xilinx, 2022, UG1416-Vitis-Documentation
  • [6] ARM Xilinx, 2021, P2P bandwidth Example
  • [7] Axboe J, 2021, Github-axboe/fio: Flexible i/o tester
  • [8] Erasure coding for distributed storage: an overview
    Balaji, S. B.
    Krishnan, M. Nikhil
    Vajha, Myna
    Ramkumar, Vinayak
    Sasidharan, Birenjith
    Kumar, P. Vijay
    [J]. SCIENCE CHINA-INFORMATION SCIENCES, 2018, 61 (10)
  • [9] Ben-Yair S., 2020, The Keyword Google Blog
  • [10] Optimizing the cost of DBaaS object placement in hybrid storage systems
    Boukhelef, Djillali
    Boukhobza, Jalil
    Boukhalfa, Kamel
    Ouarnoughi, Hamza
    Lemarchand, Laurent
    [J]. FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2019, 93 : 176 - 187