Zweilous: A Decoupled and Flexible Memory Management Framework

被引:0
作者
Li, Guoxi [1 ]
Chen, Wenzhi [1 ]
Xiang, Yang [2 ]
机构
[1] Zhejiang Univ, Sch Comp Sci & Technol, Hangzhou 310027, Zhejiang, Peoples R China
[2] Swinburne Univ Technol, Sch Software & Elect Engn, Hawthorn, Vic 3122, Australia
关键词
Memory management; Hardware; Linux; Cloud computing; Kernel; Operating systems; memory management; memory architecture; ARCHITECTURE;
D O I
10.1109/TC.2020.3009124
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Currently, with the booming growth of cloud computing, workloads from broad ranges of functions and demands are crammed into a single physical machine. They lay considerable stress on the need of evolution of the operating system underneath, especially the memory subsystem. Even enhancing large pages with main memory compression is not intuitively straightforward due to rigid rules imposed by the state-of-the-art manager Buddy System from the beginning of the design. To relieve the aforementioned problems and provide broader design space for system designers, we propose Zweilous, a clean slate physical memory management framework. It is self-contained, highly decoupled, and thus can co-exist with the vanilla memory manager. Separate self-contained metadata/functions guarantee a flexible extension with little modification to current frameworks. To show it is easy to add enhanced functions that accelerate the evolution of the memory management subsystem, we implement Hzmem, a new large page memory manager redesign enhanced with the function of main memory compression. Our method achieves competitive performance compared with native and virtualized large page support, effective memory size increased and fewer impacts on other parts of the operating system.
引用
收藏
页码:1350 / 1362
页数:13
相关论文
共 50 条
  • [1] Reference Capabilities for Flexible Memory Management
    Arvidsson, Ellen
    Castegren, Elias
    Clebsch, Sylvan
    Drossopoulou, Sophia
    Noble, James
    Parkinson, Matthew J.
    Wrigstad, Tobias
    PROCEEDINGS OF THE ACM ON PROGRAMMING LANGUAGES-PACMPL, 2023, 7 (OOPSLA): : 1363 - 1393
  • [2] DYNAMIC MEMORY MANAGEMENT IN THE LOCI FRAMEWORK
    Zhang, Yang
    Luke, Edward A.
    SCALABLE COMPUTING-PRACTICE AND EXPERIENCE, 2006, 7 (03): : 27 - 37
  • [3] Space-address decoupled scratchpad memory management for neural network accelerators
    Zhang, Zhenxing
    Sun, Shiyan
    Chen, Xunyu
    Zhi, Tian
    Guo, Qi
    Chen, Yunji
    CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2021, 33 (06)
  • [4] A customisable memory management framework for C++
    Attardi, G
    Flagella, T
    Iglio, P
    SOFTWARE-PRACTICE & EXPERIENCE, 1998, 28 (11) : 1143 - 1183
  • [5] Flips: A Flexible Partitioning Strategy Near Memory Processing Architecture for Recommendation System
    Qiu, Yudi
    Lu, Lingfei
    Yi, Shiyan
    Jing, Minge
    Zeng, Xiaoyang
    Kong, Yang
    Fan, Yibo
    IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2025, 36 (04) : 745 - 758
  • [6] Decoupled and Explainable Associative Memory for Effective Knowledge Propagation
    Fernando, Tharindu
    Priyasad, Darshana
    Sridharan, Sridha
    Fookes, Clinton
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024,
  • [7] Early-Adaptor: An Adaptive Framework for Proactive UVM Memory Management
    Go, Seokjin
    Lee, Hyunwuk
    Kim, Junsung
    Lee, Jiwon
    Yoon, Myung Kuk
    Ro, Won Woo
    2023 IEEE INTERNATIONAL SYMPOSIUM ON PERFORMANCE ANALYSIS OF SYSTEMS AND SOFTWARE, ISPASS, 2023, : 248 - 258
  • [8] MNEMEE - A Framework for Memory Management and Optimization of Static and Dynamic Data in MPSoCs
    Mallik, Arindam
    Marwedel, Peter
    Soudris, Dimitrios
    Stuijk, Sander
    PROCEEDINGS OF THE 2010 INTERNATIONAL CONFERENCE ON COMPILERS, ARCHITECTURES AND SYNTHESIS FOR EMBEDDED SYSTEMS (CASES '10), 2010, : 257 - 258
  • [9] A Length Adaptive Memory Management Framework in High Speed Acquisition System
    Chen, Xin
    Ding, Haolun
    Li, Xinyu
    Li, Haiou
    Liu, Yajun
    Mei, Hong
    Kang, Zhiwen
    Song, Guolin
    2022 9TH INTERNATIONAL FORUM ON ELECTRICAL ENGINEERING AND AUTOMATION, IFEEA, 2022, : 349 - 352
  • [10] Maximizing Entanglement Rates via Efficient Memory Management in Flexible Quantum Switches
    Promponas, Panagiotis
    Valls, Victor
    Guha, Saikat
    Tassiulas, Leandros
    IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2024, 42 (07) : 1749 - 1762