Improving Fairness for SSD Devices through DRAM Over-Provisioning Cache Management

被引:6
|
作者
Liu, Renping [1 ]
Tan, Zhenhua [1 ]
Long, Linbo [1 ]
Wu, Yu [2 ]
Tan, Yujuan [2 ]
Liu, Duo [2 ]
机构
[1] Chongqing Univ Posts & Telecommun, Coll Comp Sci, Chongqing 400065, Peoples R China
[2] Chongqing Univ, Coll Comp Sci, Chongqing 400044, Peoples R China
基金
中国国家自然科学基金;
关键词
Solid state drives (SSDs); multiple applications; fairness; data cache management; PERFORMANCE; SCHEME;
D O I
10.1109/TPDS.2022.3143295
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Modern NVMe SSDs have been widely deployed in multi-tenant cloud computing environments or multi-programming systems. When multiple applications concurrently access one SSD hardware, unfairness within the shared SSD will slow down the application significantly and lead to a violation of service level objectives. However, traditional data cache management within SSDs mainly focuses on improving cache hit ratio, which causes data cache contention and sacrifices fairness among multiple applications. In this paper, we propose a DRAM-based Over-Provisioning (OP) cache management mechanism, named Justitia, to reduce data cache contention and improve fairness for modem SSDs. Justitia consists of two stages including Static-OP stage and Dynamic-OP stage. Through the novel OP mechanism in the two stages, Justitia reduces the max slowdown by 4.5 x on average. At the same time, Justitia increases fairness by 20.6x and buffer hit ratio by 19.6% averagely, compared with the traditional shared mechanism.
引用
收藏
页码:2444 / 2454
页数:11
相关论文
共 7 条
  • [1] Cache Management for Video Servers by the Combined Use of DRAM and SSD
    Lee, Jungwoo
    Song, Minseok
    [J]. PROCEEDINGS OF 2016 IEEE INTERNATIONAL SYMPOSIUM ON MULTIMEDIA (ISM), 2016, : 537 - 540
  • [2] SCM Capacity and NAND Over-Provisioning Requirements for SCM/NAND Flash Hybrid Enterprise SSD
    Sun, Chao
    Miyaji, Kousuke
    Johguchi, Koh
    Takeuchi, Ken
    [J]. 2013 5TH IEEE INTERNATIONAL MEMORY WORKSHOP (IMW), 2013, : 64 - 67
  • [3] Scalable Multimedia Group Communications through the Over-Provisioning of Network Resources
    Neto, Augusto
    Cerqueira, Eduardo
    Curado, Marilia
    Mendes, Paulo
    Monteiro, Edmundo
    [J]. MANAGEMENT OF CONVERGED MULTIMEDIA NETWORKS AND SERVICES, PROCEEDINGS, 2008, 5274 : 52 - +
  • [4] Improving Performance of Parallel I/O Systems through Selective and Layout-Aware SSD Cache
    He, Shuibing
    Wang, Yang
    Sun, Xian-He
    [J]. IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2016, 27 (10) : 2940 - 2952
  • [5] Improving the Performance and Energy Efficiency of GPGPU Computing through Integrated Adaptive Cache Management
    Kim, Kyu Yeun
    Park, Jinsu
    Baek, Woongki
    [J]. IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2019, 30 (03) : 630 - 645
  • [6] Improving Performance for Flash-Based Storage Systems through GC-Aware Cache Management
    Wu, Suzhen
    Mao, Bo
    Lin, Yanping
    Jiang, Hong
    [J]. IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2017, 28 (10) : 2852 - 2865
  • [7] Improving the management of the blood supply through the use of Haemonetics' MCS-8150 automated double red cell collection devices
    Ridley, Joseph
    [J]. TRANSFUSION AND APHERESIS SCIENCE, 2009, 41 (01) : 39 - 43