臺灣博碩士論文加值系統

　　隨著科技日新月異的發展，固態硬碟已被預期為下一期將被廣泛使用的儲存裝置。而本篇論文最主要的目的，就是希望能在固態硬碟的架構下完成虛擬硬碟的方法，並達到每個使用者皆擁有獨立性表現的目標。因為固態硬碟的硬體特性和傳統硬碟的特性是大不相同的，而使得過去虛擬硬碟方法在固態硬碟的架構下失去了獨立表現的特性。固態硬碟的三種特性：回收機制、內部平行以及裝置內部的排隊延遲時間，造成了過去的虛擬硬碟方法難以去預測每個使用者的儲存裝置資源的使用量，進而失去了公平表現的特性。
　　本篇論文提出了一個新穎的方法並設計在固態硬碟的轉譯層上，去解決以上所提及的問題。在我們的實驗表示，我們的虛擬硬碟方法和過去虛擬硬碟方法比較下，固態硬碟的處理能力擁有最為公平的表現，並且能夠根據不同使用者的資料特性，將回收機制的硬體資源花費完全分開。

With updating development of modern technology, the solid-state drives (SSDs) have been expected as the next generation storage device. This paper wants to achieve virtual storage method in NAND-flash based SSD and isolation performance for every user. But the SSD’s device characteristic is very different from Hard Disk Drive (HDD), which caused past virtual storage method is hard to achieve performance isolation in SSD. The SSD’s GC overhead, internal parallelism and the device queuing delay caused that past virtual storage methods have unfair performance because their storage resource accounting of per user is hard to predict.
VSSD brings up a novel virtual storage method and is designed in the Flash Translation Layer (FTL) of SSD to solve these problems. Our experiment shows that VSSD has best fair throughput performance, which can easily separate the GC overhead for every user with their data characteristic.

摘要 i
Abstract ii
誌謝 iii
Contents iv
List of Tables vi
List of Figures vii
Chapter 1 Introduction 1
Chapter 2 Background 3
2.1 SSD Architecture 3
2.2 Flash Translation Layer (FTL) 4
2.3 Virtual storage method 5
Chapter 3 Related Works 6
3.1 Façade 6
3.2 Argon 6
3.3 FIOS 7
Chapter 4 Motivation 9
4.1 GC overhead Problem 10
4.2 Channel Occupation Problem 12
4.3 Device Queuing Delay Problem 13
Chapter 5 Design and Implementation 14
5.1 Fair-charging Flash Translation Layer 15
5.1.1 Per User Allocation method 15
5.1.2 Local GC 21
5.2 Fair charging IO Scheduling (FACO) 22
5.2.1 Considering Channel Occupation 22
5.2.2 Excluding Queuing Delay 23
Chapter 6 Experiment 24
6.1 Experimental Setup 25
6.2 Synthetic Workloads 26
6.2.1 Effectiveness of Local GC 26
6.2.2 Effectiveness of Considering Channel Occupation 29
6.2.3 Effectiveness of Excluding Queuing Delay 31
6.3 Application Workloads 33
6.4 Work Conserving 48
6.5 Selection of Isolation Allocation methods 48
Chapter 7 Conclusion 50
Reference 51

[1] N. Agrawal, V. Prabhakaran, T. Wobber, J. Davis, M. Manasse, and R. Panigrahy, “Design tradeoffs for SSD performance, in USENIX Annual Technical Conference, 2008, pp. 57–70.
[2] A. Gupta, Y. Kim, and B. Urgaonkar. DFTL: A Flash Translation Layer Employing Demand-based Selective Caching of Page-level Address MUserings. In ASPLOS’09, Washington, DC, USA, March 2009.
[3] C. R. Lumb, A. Merchant, and G. A. Alvarez. Façade: virtual storage devices with performance guarantees. Conference on File and Storage Technologies, pages 131–144. USENIX Association, 2003.
[4] M. Wachs, M. Abd-El-Malek, E. Thereska, and G. R. Ganger. Argon: performance insulation for shared storage servers. In FAST, 2007.
[5] PARK, S., AND SHEN, K. FIOS: A fair, efficient flash i/o sched-uler. In FAST (2012).
[6] Intel Corporation and Seagate Technology. Serial ATA Native Command Queuing. July, 2003
[7] Microsoft, SSD Extension for DiskSim Simulation Environment
http://research.microsoft.com/en-us/downloads/b41019e2-1d2b-44d8-b512-ba35ab814cd4/
[8] M. Mesnier. Intel open storage toolkit.
http://www.sourceforge.org/projects/intel-iscsi.
[9] SPC Trace File Format Specification
http://traces.cs.umass.edu/index.php/Storage/Storage
[10] M. L. Chiao and D. W. Chang ROSE: A novel flash translation layer for NAND flash memory based on hybrid address translation, IEEE Trans. Comput., vol. 60, no. 6, pp.753 -766 2011
[11] Dau-Jieu Yang “BLAS: A Block-Level and Adaptive Stripping Policy for Solid-State Drives
[12] D. Skourtis, S. Kato, and S. Brandt. QBox: Guaranteeing I/O Performance on Black Box Storage Systems, In Proceedings of the 21st ACM Symposium on High-Performance Parallel and Distributed Computing (HPDC'12), pp. 73-84, 2012.
[13] A. Povzner et al. Efficient guaranteed disk request scheduling with Fahrrad. SIGOPS Oper. Syst. Rev., 42(4):13–25, 2008
[14] S. W. Lee, D. J. Park, T. S. Chung, D. H. Lee, S. Park, and H. J. Song, “A Log Buffer-Based Flash Translation Layer Using Fully-Associative Sector Translation, ACM Trans. Embedded Computing Systems, vol. 6, no. 3, pp. 436-453, 2007.
[15] D. Jung, J.-U. Kang, H. Jo, J.-S. Kim, and J. Lee, “Superblock FTL: A superblock-based flash translation layer with a hybrid address translation scheme, ACM Trans. Embedded Computing Systems, vol. 9, no. 4, pp. 1-41, 2010.
[16] M.-L. Chiang, P. C. H. Lee, and R.-C. Chang, “Cleaning Policies in Mobile Computers Using Flash Memory, Journal of Systems and Software, vol. 48, no. 3, pp. 213-231, 1999.
[17] M. Chiang, P. Lee, and R. Chang, “Using data clustering to improve cleaning performance for flash memory, Software-Practice and Experience, vol. 29, no. 3, pp. 267-290, 1999.