簡易檢索 / 詳目顯示

研究生: 劉又德
Liu, Yo-de
論文名稱: 增進檔案系統效能之檔案搬移機制設計與實作
Design and Implementation of a File Migration Mechanism for File System Performance Improvement
指導教授: 張大緯
Chang, Da-Wei
學位類別: 碩士
Master
系所名稱: 電機資訊學院 - 資訊工程學系
Department of Computer Science and Information Engineering
論文出版年: 2008
畢業學年度: 96
語文別: 中文
論文頁數: 46
中文關鍵詞: 資料搬移檔案系統快閃記憶體硬碟
外文關鍵詞: Data Migraition, Hard Disk, Flash Memory, File System
相關次數: 點閱:61下載:3
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
  • 傳統硬碟是目前最常見的儲存裝置,它具有高容量和價格便宜的優點。另外,近年來以快閃記憶體(flash memory)製成的各種儲存裝置也被廣泛使用。傳統硬碟與快閃記憶體在處理不同種類的資料時會有不同的效能表現。與快閃記憶體相比,傳統硬碟處理隨機存取時較為不利,但是快閃記憶體比起傳統硬碟較不適合頻繁的資料寫入。在這篇論文中,我們設計並且實作一個新的檔案系統來結合傳統硬碟和快閃記憶體。此一檔案系統會依照資料存取的特性將資料在兩種裝置間搬移,藉此達到提升整體儲存裝置效能的目的。根據實驗顯示,新的檔案系統結合兩種不同種類的裝置之後,不但不會有額外的效能負擔,和只使用傳統硬碟相比,根據處理資料的型態,最多能提升將近50%的效能。

    Magnetic hard disk is currently the most common storage device. It has the advantages of high storage and low price. In recent years, flash-based storage devices are becoming popular. Due to the difference in hardware property, these two kinds of devices result in different performance for different kinds of data accesses. In this paper, we design and implement a new file system to combine the advantages of traditional hard disk and flash memory. It detects file access patterns and migrates the data between these two devices according to the access patterns so as to improve file system performance. The experiment results show that the new file system leads to little overhead as well as improves performance by up to 50%, while comparing with using a disk-based file system.

    第一章 論文介紹與研究動機 1 1.1 研究背景 1 1.2 研究動機 4 1.3 研究方法與目標 5 1.4 章節介紹 7 第二章 相關研究 8 2.1 Stackable File System 8 2.2 Data Migration 9 2.2.1 PDC 9 2.2.2 PB-PDC 10 2.3 Flash Memory Cache 11 2.3.1 降低電力消耗 11 2.3.2 提升I/O效能 12 第三章 檔案系統設計 13 3.1 設計目標 13 3.2 檔案系統架構 14 3.2.1 Access Manager 15 3.2.2 Policy Manager 15 3.2.3 Data Migrator 16 3.3 需考慮的事項 16 3.3.1 資料處理的單位 16 3.3.2 資料搬移機制 17 第四章 檔案系統實作 19 4.1 實作概觀 19 4.2 新增的資料結構 22 4.3 Unionfs 檔案系統函式的修改 25 4.3.1 unionfs_open 25 4.3.2 unionfs_read與unionfs_write 26 4.3.3 unionfs_file_release 27 4.3.4其它函式 27 4.4 Policy Manager實作 27 4.5 Data Migrator實作 30 第五章 實驗 32 5.1 實驗目的 32 5.2 實驗環境 32 5.3 實驗結果 33 5.3.1 額外效能負擔 33 5.3.2 Data Migration的增進效能結果 36 第六章 未來發展與結論 40 6.1 未來發展方向 40 6.1.1 整體實作改進 40 6.1.2 改進Data Migrator啟動機制 41 6.2 結論 42

    [1] M. Baker, S. Asami, E. Deprit, J. Ousterhout, and M. Seltzer, “Non-volatile Memory for Fast, Reliable File Systems”, Proceeding of the 5th International Conference on Architectural Support for Programming Languages and Operating Systems, Pages 10-22,1992.
    [2] T. Bisson, S. A. Brandt, and D. D. Long, “NVCache: Increasing the Effectiveness of Spin-down Algorithms with Caching”, Proceeding of the 14th International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems, Pages 422-432, 2006.
    [3] F.Chen, S. Jiang, X.Zhang, “SmartSaver: Turning Flash Drive into a Disk Energy Saver for Mobile Computers” Proceedings of the 2006 International Symposium on Low Power Electronics and Design, Pages 171-177, 2006.
    [4] Y. Hu, T. Nightingale, and Q. Yang, “RAPID-Cache: A Reliable and Inexpensive Write Cache for High Performance Storage Systems”, IEEE Transactions on Parallel and Distributed Systems, Volume 13 , Issue 3, Pages: 290 – 307, 2002.
    [5] N. Joukov, A. Rai, and E. Zadok, “Increasing Distributed Storage Survivability with a Stackable RAID-like File System”, Proceedings of the 5th IEEE International Symposium on Cluster Computing and the Grid, Pages 82-89, 2005.
    [6] T. Kgil and T. Mudge, “FlashCache: A NAND Flash Memory File Cache for Low Power Web Servers”, Proceedings of the 2006 International Conference on Compilers, Architecture and Synthesis for Embedded Systems, Pages 103-122, 2006.
    [7] Y. J. Kim, K. T. Kwon, and J. Kim “Energy-Efficient File Placement Techniques for Heterogeneous Mobile Storage Systems”, Proceedings of the 6th ACM & IEEE International conference on Embedded software, Pages 171-177, 2006.
    [8] B. Marsh, F. Douglis, and P. Krishnan, “Flash Memory File Caching for Mobile Computers”, Proceeding of the 27th Hawaii Conference on System Science, Pages 451-460, 1994.
    [9] E. L. Miller, S. A. Brandt, and D. D. E. Long, “HeRMES: High-Performance Reliable MRAM-Enabled Storage”, Proceedings of the 8th Workshop on Hot Topics in Operating Systems, Pages 95-99, 2001.
    [10] E. Pinheiro and R. Bianchini, “Energy Conservation Techniques for Disk Array-Based Servers”, Proceedings of the 18th International Conference on Supercomputing, Pages 88–95, 2004
    [11] G. Sivathanu and E. Zadok, “A Versatile Persistent Caching Framework for File Systems”, Stony Brook U. CS TechReport FSL-05-05, 2005.
    [12] C. P. Wright, J.Dave, P. Gupta, H. Krishnan, D. P. Quigley, E. Zadok, and M. N. Zubair, “Versatility and Unix Semantic in Namespace Unification”, ACM Transactions on Storage (TOS), Volume 2 , Issue 1, Pages: 74 – 105, 2006.
    [13] E. Zadok and J. Nieh, “FiST: ALanguage for Stackable File System”, Proceeding of USENIX Annual Technical Conference, Pages 55-70, 2000.
    [14] Microsoft, ReadyDrive and Hybrid Disk, http://www.microsoft.com/whdc/device/storage/hybrid.mspx
    [15] Bonnie++, http://www.coker.com.au/bonnie++/
    [16] http_load, http://www.acme.com/software/http_load/
    [17] Glimpse, http://webcom.com/glossary/glimpse.shtml
    [18] WebStone, http://www.webstonevalves.com/

    下載圖示 校內:2013-08-26公開
    校外:2013-08-26公開
    QR CODE