簡易檢索 / 詳目顯示

回結果列表
研究生： 沈冠霖
Shen, Guann-Ling
論文名稱： 邊緣節點中快速輕量記憶體去重複化技術
FLOMD: Fast and Low Overhead Memory Deduplication for Edge Nodes
指導教授： 李哲榮
Lee, Che-Rung
口試委員: 周志遠
鍾一新
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 資訊工程學系
Computer Science
論文出版年： 2021
畢業學年度： 109
語文別： 英文
論文頁數： 38
中文關鍵詞： 記憶體去重複化 、邊緣運算
相關次數： 點閱：2  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 對於大量的IoT裝置和5G平台而言，邊緣運算成為在提供實時服務上必要的架構。為了減化在邊緣節點部屬和管理各種應用程式的工作，人們通常將他們的應用程式打包在容器裡。

    然而，在計算資源有限的節點上同時平順的執行大量容器運算仍然是一個挑戰。這篇論文中，我們調查了在邊緣節點中，利用記憶體去重複化來減緩記憶體壓力的技術。其中主要的困難點為在減少CPU使用量下，如何快速的發現以及合併重複的記憶體頁面。觀察容器記憶體的使用特性後，我們提出了記憶體去重複化技術名為「FLOMD」。

    FLOMD建立在四個新技術：零頁面蒐集、搜尋樹最佳化、易變頁面分辨以及掃描速度調整。在邊緣節點和伺服器上，我們做各種應用程式負載來比較 KSM、UKSM 和 FLOMD 頁面合併效率的實驗。
    結果表明，FLOMD的頁面合併效率平均比KSM以及UKSM高兩倍以上。

    Edge computing has become an indispensable architecture to provide real-time services for massive number of IoT devices and 5G platforms. To ease the effort of deploying and managing various applications on edge nodes, people usually pack their applications in containers for edge environment. However, the smooth execution of large amount of containers simultaneously on the nodes with limited computing resources remains a challenge. In this thesis, we investigate the memory deduplication technology to relieve the memory pressure for edge nodes. The major difficulty is to quickly discover and merge duplicated memory pages with less CPU consumption. Based on the observed properties of memory usages for containers, we proposed a memory deduplication algorithm, called FLOMD (Fast and Low Overhead Memory Deduplication), which is based on KSM (Kernel Same-page Merging) with four novel techniques: zero page collection, search tree optimization, volatile page identification, and scanning velocity adjustment. Experiments are conducted to compare the sharing efficiency of KSM, UKSM, and FLOMD on edge nodes and on servers with various
    workloads. The results show that the sharing efficiency of FLOMD is more than two times higher than that of others in average.

    摘要 目錄 1.Introduction----------------------------------------1 2.Background------------------------------------------4 3.Design and Implementation of FLOMD------------------9 4.Experiments----------------------------------------18 5.Conclusion and Future Work-------------------------35

    [1] D. Evans, “The internet of things: How the next evolution of the internet is changing everything,” White Paper, pp. 1–11, 2011.
    [2] C. Avasalcai, C. Tsigkanos, and S. Dustdar, “Decentralized resource auctioning for latency­sensitive edge computing,” in 2019 IEEE International Conference on Edge Com­puting (EDGE), pp. 72–76, 2019.
    [3] N. Hassan, S. Gillani, E. Ahmed, I. Yaqoob, and M. Imran, “The role of edge computing in internet of things,” IEEE Communications Magazine, vol. 56, no. 11, pp. 110–115, 2018.
    [4] M. Mohammadi, A. Al­Fuqaha, S. Sorour, and M. Guizani, “Deep learning for iot big data and streaming analytics: A survey,” IEEE Communications Surveys Tutorials, vol. 20, no. 4, pp. 2923–2960, 2018.
    [5] Z. Tao, Q. Xia, Z. Hao, C. Li, L. Ma, S. Yi, and Q. Li, “A survey of virtual machine management in edge computing,” Proceedings of the IEEE, vol. 107, no. 8, pp. 1482–1499, 2019.
    [6] A. Celesti, D. Mulfari, M. Fazio, M. Villari, and A. Puliafito, “Exploring container vir­tualization in iot clouds,” in 2016 IEEE International Conference on Smart Computing (SMARTCOMP), pp. 1–6, 2016.
    [7] A. Arcangeli, I. Eidus, and C. Wright, “Increasing memory density by using ksm,” 01 2009.
    [8] L. Chen, Z. Wei, Z. Cui, M. Chen, H. Pan, and Y. Bao, “Cmd: Classification­based mem­ory deduplication through page access characteristics,” vol. 49, pp. 65–76, 03 2014.
    [9] D. L. Yeji Nam and Y. I. Eom, “Self: Improving the memory­sharing opportunity us­ing virtual­machine self­hints in virtualized systems,” APSys ’15: Proceedings of the 6th Asia­Pacific Workshop on Systems, vol. 10, 2015.
    [10] K. Miller, F. Franz, M. Rittinghaus, M. Hillenbrand, and F. Bellosa, “XLH: More effec­tive memory deduplication scanners through cross­layer hints,” in 2013 USENIX Annual Technical Conference (USENIX ATC 13), (San Jose, CA), pp. 279–290, USENIX Asso­ciation, June 2013.
    [11] T. Veni and S. M. S. Bhanu, “Mdedup++: Exploiting temporal and spatial page­sharing behaviors for memory deduplication enhancement,” The Computer Journal, vol. 59, no. 3, pp. 353–370, 2016.
    [12] P. P. Ray, “A survey of iot cloud platforms,” Future Computing and Informatics Journal, vol. 1, no. 1, pp. 35–46, 2016.
    [13] N. Xia, C. Tian, Y. Luo, H. Liu, and X. Wang, “Uksm: Swift memory deduplication via hierarchical and adaptive memory region distilling,” 16th USENIX Conference on File and Storage Technologies (FAST 18), p. 325–340, 2018.
    [14] J. Chen and X. Ran, “Deep learning with edge computing: A review,” Proceedings of the IEEE, vol. 107, no. 8, pp. 1655–1674, 2019.
    [15] F. Paraiso, S. Challita, Y. Al­Dhuraibi, and P. Merle, “Model­driven management of docker containers,” in 2016 IEEE 9th International Conference on Cloud Computing (CLOUD), pp. 718–725, 2016.
    [16] M. Shiba, “An examination method of mergeable memory page distribution for memory deduplication,” in 2019 IEEE 8th Global Conference on Consumer Electronics (GCCE), pp. 1027–1031, 2019.
    [17] S. Jia, C. Wu, and J. Li, “Loc­k: A spatial locality­based memory deduplication scheme with prediction on k­step locations,” in 2017 IEEE 23rd International Conference on Par­allel and Distributed Systems (ICPADS), pp. 310–317, 2017.
    [18] L. You, Y. Li, F. Guo, Y. Xu, J. Chen, and L. Yuan, “Leveraging array mapped tries in ksm for lightweight memory deduplication,” in 2019 IEEE International Conference on Networking, Architecture and Storage (NAS), pp. 1–8, 2019.
    [19] M. Raoufi, Q. Deng, Y. Zhang, and J. Yang, “Pagecmp: Bandwidth efficient page dedu­plication through in­memory page comparison,” in 2019 IEEE Computer Society Annual Symposium on VLSI (ISVLSI), pp. 82–87, 2019.
    [20] S. A. Vakil Ghahani, M. T. Kandemir, and J. B. Kotra, “Dsm: A case for hardware­assisted merging of dram rows with same content,” vol. 4, no. 2, 2020.
    [21] S. Krishnaswamy and R. Sharma, “Tuning ksm for dual core automotive systems,” in 2018 International Conference on Networking, Embedded and Wireless Systems (ICNEWS), pp. 1–3, 2018.
    [22] S. Rachamalla, D. Mishra, and P. Kulkarni, “All page sharing is equal , but some sharing is more equal than others,” 2013.
    [23] A. Damien, “Linear regression example.” https://github.com/aymericdamien/TensorFlow-Examples/blob/master/tensorflow_v1/notebooks/2_BasicModels/logistic_regression.ipynb.
    [24] C. Sonmez, A. Ozgovde, and C. Ersoy, “Edgecloudsim: An environment for performance evaluation of edge computing systems,” in 2017 Second International Conference on Fog and Mobile Edge Computing (FMEC), pp. 39–44, 2017.
    [25] A. software, “Meabo.” https://github.com/ARM-software/meabo.
    [26] R. Krishnakumar, “Hugetlb­large page support in the linux kernel,” Linux Gazette, vol. 155, 2008.

    QR CODE