由於近年來的CPU、儲存裝置、main memory，和網路頻寬的發展，使得虛擬化技術的研究越來越熱門，虛擬化技術提供了一個抽象化的硬體資源。虛擬化技術可在一台實體機器上能同時運行多個虛擬機器(Virtual machine)，每個虛擬機器可以獨立運行，並擁有其作業系統，並且有效利用有限的硬體資源， 當運行多台虛擬機器時，其儲存裝置的I/O的效能將會是虛擬化技術需要探討的一個重要因素。目前流行的儲存裝置有傳統硬碟(traditional hard-disk drives)和固態硬碟(solid-stat drives)，雖然傳統硬碟比固態硬碟更便宜且容量更大，但是固態硬碟擁有更高的I/O效能且更加省電。我們將在Xen Hypervisor建立一個虛擬儲存環境並使用SSD和HDD，我們會分析多個虛擬機器的I/O請求和SSD容量的使用情況，將I/O請求分配到適當的儲存裝置，總體而言，我們所提出的方法可以利用固態硬碟效能的優勢提供對於那些需要高I / O性能的VM，提升整體效能。

Nowadays, virtualization is a popular technology to provide an abstract hardware emulation due to the increasing hardware speed and capabilities such as multi-core CPUs, large-size main memory, and high-bandwidth networking. Virtualization technology enables multiple virtual machines to run on a physical machine, where each virtual machine can run independently and own its operating system. In particular, I/O performance will be an important factor of virtualization technology. Current popular storage devices contain traditional hard-disk drives (HDDs) and solid-state drives (SSDs). Although HDDs can provide a more economical solution than SSDs, SSDs can provide high I/O performance and power saving, especially for random I/O accesses. In the thesis, we will build a virtual storage system for SSDs and HDDs in Xen hypervisor. With the proposed virtual storage systems, we can receive and analyze I/O requests from multiple virtual machines, and perform I/O requests to any physical storage devices. According to the experimental results, the proposed method can combine and utilize the advantages of SSDs (i.e., fast access) and HDDs (i.e, low cost). Overall, the proposed method can provide an adjustment on I/O performance for those applications that require high I/O performance in virtualization environment.

[1] "VMware Homepage," [Online]. Available: http://www.vmware.com.
[2] "Virtual Box," [Online]. Available: https://www.virtualbox.org/.
[3] "Windows Hyper-V server," [Online]. Available: http://www.microsoft.com/en-us/server-cloud/hyper-v-server/default.aspx.
[4] "Xensource Homepage," [Online]. Available: http://www.xen.org/.
[5] "KVM," [Online]. Available: http://www.linux-kvm.org/page/Main_Page.
[6] Feng Chen, Song Jiang, Xiaodong Zhang, “SmartSaver: Turning flash drive into a disk energy saver for mobile computers,” ACM ISLPED, 2006.
[7] Li-Pin Chang , “Hybrid solid-state disks: combining heterogeneous NAND flash in large SSDs,” ASP-DAC, 2008.
[8] G. Soundararajan, V. Prabhakaran, M. Balakrishnan and T. Wobber, “Extending SSD lifetimes with disk-based write caches,” USENIX, 2010.
[9] Guangyu Sun , Yongsoo Joo , Yibo Chen, Dimin Niu, Yuan Xie, Yiran Chen and Hai Li, “A Hybrid solid-state storage architecture for the performance, energy consumption, and lifetime improvement,” IEEE HPCA, 2010.
[10] B. Mao, H. Jiang, S. Wu, L. Tian, D. Feng, J. Chen and L. Zeng, “HPDA: A hybrid parity-based disk array for enhanced performance and reliability,” ACM TOC, 2012.
[11] "Iometer Filesystem Benchmark," [Online]. Available: http://www.iometer.org/.
[12] Adam Leventhal , “Flash storage memory,” Communications of the ACM, 2008.
[13] Jeanna Matthews, Sanjeev Trika, Debra Hensgen, Rick Coulson and Knut Grimsrud, “Intel Turbo Memory: Nonvolatile disk caches in the storage hierarchy of mainstream computer systems,” ACM Transactions on Storage, 2008.
[14] Taeho Kgil, David Roberts and Trevor Mudge, “Improving NAND Flash Based Disk Caches,” ACM ISCA, 2008.
[15] Timothy Pritchett and Mithuna Thottethodi, “SieveStore: a highly-selective, ensemble-level disk cache for cost-performance,” ACM ISCA, 2010.
[16] Chai-Hao Tsai, Jerry Chou, Yeh-Ching Chung, “Value-Based Tiering Management on Heterogeneous Block-Level Storage System,” IEEE 4th International Conference on Cloud Computing Technology and Science, 2012.
[17] Youngjae Kim, Aayush Gupta, Bhuvan Urgaonkar, Piotr Berman, and Anand Sivasubramaniam, “HybridStore A Cost-Efficient, High-Performance Storage System Combining SSDs and HDDs,” 19th Annual IEEE International Symposium on Modelling, Analysis, and Simulation of Computer and Telecommunication Systems, 2011.
[18] Xiaojian Wu and A. L. Narasimha Reddy, “Managing storage space in a flash and disk hybrid storage system,” Modeling, Analysis & Simulation of Computer and Telecommunication Systems, 2009.
[19] Su-Fang Hsiao, Pi-Cheng Hsiu and Tei-Wei Kuo , “A Reconfigurable Virtual Storage Device,” IEEE ISORC, 2009.
[20] Mustafa Canim, George A. Mihaila, Bishwaranjan Bhattacharjee, Kenneth A. Ross and Christian A. Lang, “An object placement advisor for DB2 using solid state storage,” Proceedings of the VLDB Endowment, 2009.
[21] Hannes Payer, Marco A.A. Sanvido,Zvonimir Z. Bandic and Christoph M. Kirsch, “Combo Drive: Optimizing Cost and Performance in a Heterogeneous Storage Device,” WISH, 2009.
[22] Qing Yang and Jin Ren, “I-CASH: Intelligently Coupled Array of SSD and HDD,” IEEE HPCA, 2011.
[23] Feng Chen, David A. Koufaty, Xiaodong Zhang, “Hystor: making the best use of solid state drives in high performance storage systems,” ACM ICS, 2011.
[24] Shih-Yu Liu, “An Efficient Data Management Method for SSD-Based Storage Systems,” National Taiwan University of Science and Technology Master Thesis, 2012.
[25] Chih-Kai Kang, “A Hybrid Storage Access Framework for Virtual Machines,” National Taiwan University of Science and Technology Master Thesis, 2012.
[26] "Xen blktap2 driver," [Online]. Available: http://wiki.xen.org/wiki/Blktap2.
[27] "Storage Performance Council," [Online]. Available: http://www.storageperformance.org/home/.