网络存储服务器缓存替换策略研究
|
摘要
随着因特网的蓬勃发展和社会的数字化变革,数据爆炸式增长对存储系统提出了巨大的挑战,传统的直连式存储难以满足日益严峻的数据存储需求,促使人们不断探索新型的存储系统。在这种背景下,存储技术与网络技术逐渐融合,产生了网络存储技术。网络存储具有高性能、大容量、可扩展、易管理等特点,已经越来越多地被应用于金融、石油、电力、通信等高性能计算领域中。
作为解决I/O瓶颈问题的主要软件方法,缓存技术始终是存储系统的一个研究热点。缓存技术通过将数据暂存在相对高速的存储器中,可以提高后续的重复访问速度。由于缓存的容量通常远远小于I/O路径中下一级存储器的容量,当缓存满了以后,需要在一个恰当的时机选择恰当的数据进行淘汰,回收缓存空间以存储新的数据。这种选择的依据就是缓存替换策略,是影响缓存性能的关键因素。目前,网络存储服务器中使用的缓存策略大多是从直连式存储中移植过来的,由于没有充分考虑网络存储中特殊的缓存层次结构和多客户机访问模式,从而使得网络存储系统中的缓存性能在实际应用中表现不佳。
本文从网络存储的缓存层次结构和多客户机访问模式出发,对适应于网络存储服务器的缓存替换策略进行了探讨和研究。着重对网络存储服务器自身、网络存储服务器-单客户机、网络存储服务器-多客户机三种应用架构,由简单到复杂,由集中到分布展开研究,提出了一系列具有低失效开销、高命中率的缓存替换策略,分别适用于不同的工作负载和应用模式,从而可以提高整个网络存储系统的性能。本文取得了如下的主要研究成果:
1.提出了一种基于顺序检测的缓存替换算法SABER
传统的缓存替换策略忽略了磁盘I/O特性对缓存性能的影响。本文提出的SABER算法通过对缓存块磁盘地址的连续性进行分析,确定缓存块在磁盘上分布的顺序程度,优先淘汰磁盘地址顺序程度高的缓存块,充分利用磁盘I/O所具有的顺序局部性特征,可以减少缓存失效引起的随机访问磁盘次数,避免不必要的磁头寻道和旋转,在时间局部性很弱的网络存储中,以较低的失效开销达到了高性能。
2.提出了一种文件系统元信息感知的缓存替换算法FIMAR
传统的缓存替换策略工作于文件系统之下,块设备驱动之上,文件系统元信息对于缓存是透明的。本文提出的FIMAR算法把文件系统元信息inode引入到缓存中,以此确定缓存块归属的文件,并预测缓存块在磁盘上分布的顺序程度,然后做出替换选择,使磁盘可以尽可能工作在顺序访问模式下。文件在磁盘上一般是顺序存储的,且具有很高的空间局部性,因此这种替换算法是有效的。
3.提出了一种基于驻存时间的排他缓存替换算法RED
网络存储中的缓存层次结构带来了数据冗余问题。传统的缓存替换策略在消除数据冗余的同时,往往引入了专用的通信协议,无法兼顾对客户机的友好和高效。本文提出的RED算法利用I/O接口的语义信息,监视客户机缓存的内容,使用数据块在客户机缓存中的驻存时间作为服务器缓存中的替换依据。RED算法不仅可以提供高性能,同时不需要改变客户机软件,具有很高的可用性。
4.提出了一种多客户机自适应缓存替换算法MACOR
在网络存储中,多客户机工作负载的数据相关性严重影响着服务器缓存的性能,传统的缓存策略往往只能适应于相关性很低或者很高的情况,无法兼顾。本文提出的MACOR算法,在不同缓存层次之间实现了排他缓存,在相同缓存层次之间实现了协作缓存,可以动态自适应多客户机工作负载相关性的变化。MACOR算法还提出了一种动态的缓存划分机制,解决了多客户机对服务器缓存的竞争问题。
With the vigorous development of Internet and digital society, the traditional direct attached storage systems are difficult to meet the challenge of explosive growth of data, leading to constant investigation on new storage system architecture. As the integration technology of storage and network, networked storage systems have many good characteristics, such as high performance, high capacity, ease of management and scalability, and have been increasingly used in many high performance computing fields, such as finance, oil, electricity, telecommunication, etc.
As a major software solution to I/O bottlenecks, caching is a very important research issue for storage systems, no exception for networked storage systems. Cache is actually a relatively high speed memory buffer for holding data, to allow fast re-access of subsequent request. Because cache is usually much smaller than the storage on the next level of I/O path, when cache is full, an appropriate data block needs to be discarded to reclaim space for new data blocks at an appropriate time. A replacement policy is the basis for this choice, which is a key factor to affect the cache performance. Currently, most of replacement policies are derived from researches on direct attached storage systems, which are not aware of multi-client cache hierarchy and access pattern, so they perform poorly when used in the networked storage servers.
This thesis focuses on the research of cache replacement policies to solve the negative impact of multi-client cache hierarchy and access pattern in the networked storage servers. The work of this thesis mainly involves three aspects: isolated server, single client and single server, multi-client and single server, in which four replacement policies with low miss penalty and high hit rate are proposed to enhance the cache performance for various workloads and applications. Specifically, the thesis makes the following contributions:
1. Since disk access has sequential locality, that is, sequential access is much faster than random access, we propose a Sequential Access detection Based cachE Replacement algorithm called SABER, which obtains LBA of cache blocks to detect sequential blocks for making a replacement decision. SABER can reduce the number of random disk access induced by cache miss, to avoid unnecessary seek and rotation, so it can achieve high performance by reducing miss penalty in networked storage servers which have weak locality.
2. Most of cache replacement policies work at the block level, so file system metadata is totally transparent to the cache. In fact, because files are stored and accessed sequentially in most storage systems, metadata can help to identify sequentiality of cache blocks. We present a FIle-system Metadata Aware cache Replacement algorithm called FIMAR, in which inode is attached to each cache blocks for estimating sequentiality. FIMAR assigns blocks of large inode high priority to be discarded, so that disks can work under sequential mode as much as possible.
3. To eliminate data redundancy among cache hierarchy in the networked storage systems, traditional cache replacement policies often introduce a dedicated communication protocol, and can not take into account both the client-friendly and efficiency. We propose a REsident Distance based cache replacement algorithm for exclusive storage servers called RED, which tracks the contents of client caches by obtaining semantic information from standard I/O interface, and makes a replacement decision using the time a block stays in the client cache, so it can attain high performance without changes to clients.
4. In the networked storage systems, data correlation of multi-client applications seriously affects server cache performance. The traditional cache replacement policies are usually suitable to either low data correlation applications or high data correlation applications, but not both. We present a Multi-client Adaptive COoperative cache Replacement algorithm called MACOR, which enforces exclusive caching among different cache levels and cooperative caching at the same level, so it can dynamically adapt to changes of data correlation. MACOR also proposes a dynamic cache partition mechanism to solve server cache conflict problems induced by multi-clients.
作为解决I/O瓶颈问题的主要软件方法,缓存技术始终是存储系统的一个研究热点。缓存技术通过将数据暂存在相对高速的存储器中,可以提高后续的重复访问速度。由于缓存的容量通常远远小于I/O路径中下一级存储器的容量,当缓存满了以后,需要在一个恰当的时机选择恰当的数据进行淘汰,回收缓存空间以存储新的数据。这种选择的依据就是缓存替换策略,是影响缓存性能的关键因素。目前,网络存储服务器中使用的缓存策略大多是从直连式存储中移植过来的,由于没有充分考虑网络存储中特殊的缓存层次结构和多客户机访问模式,从而使得网络存储系统中的缓存性能在实际应用中表现不佳。
本文从网络存储的缓存层次结构和多客户机访问模式出发,对适应于网络存储服务器的缓存替换策略进行了探讨和研究。着重对网络存储服务器自身、网络存储服务器-单客户机、网络存储服务器-多客户机三种应用架构,由简单到复杂,由集中到分布展开研究,提出了一系列具有低失效开销、高命中率的缓存替换策略,分别适用于不同的工作负载和应用模式,从而可以提高整个网络存储系统的性能。本文取得了如下的主要研究成果:
1.提出了一种基于顺序检测的缓存替换算法SABER
传统的缓存替换策略忽略了磁盘I/O特性对缓存性能的影响。本文提出的SABER算法通过对缓存块磁盘地址的连续性进行分析,确定缓存块在磁盘上分布的顺序程度,优先淘汰磁盘地址顺序程度高的缓存块,充分利用磁盘I/O所具有的顺序局部性特征,可以减少缓存失效引起的随机访问磁盘次数,避免不必要的磁头寻道和旋转,在时间局部性很弱的网络存储中,以较低的失效开销达到了高性能。
2.提出了一种文件系统元信息感知的缓存替换算法FIMAR
传统的缓存替换策略工作于文件系统之下,块设备驱动之上,文件系统元信息对于缓存是透明的。本文提出的FIMAR算法把文件系统元信息inode引入到缓存中,以此确定缓存块归属的文件,并预测缓存块在磁盘上分布的顺序程度,然后做出替换选择,使磁盘可以尽可能工作在顺序访问模式下。文件在磁盘上一般是顺序存储的,且具有很高的空间局部性,因此这种替换算法是有效的。
3.提出了一种基于驻存时间的排他缓存替换算法RED
网络存储中的缓存层次结构带来了数据冗余问题。传统的缓存替换策略在消除数据冗余的同时,往往引入了专用的通信协议,无法兼顾对客户机的友好和高效。本文提出的RED算法利用I/O接口的语义信息,监视客户机缓存的内容,使用数据块在客户机缓存中的驻存时间作为服务器缓存中的替换依据。RED算法不仅可以提供高性能,同时不需要改变客户机软件,具有很高的可用性。
4.提出了一种多客户机自适应缓存替换算法MACOR
在网络存储中,多客户机工作负载的数据相关性严重影响着服务器缓存的性能,传统的缓存策略往往只能适应于相关性很低或者很高的情况,无法兼顾。本文提出的MACOR算法,在不同缓存层次之间实现了排他缓存,在相同缓存层次之间实现了协作缓存,可以动态自适应多客户机工作负载相关性的变化。MACOR算法还提出了一种动态的缓存划分机制,解决了多客户机对服务器缓存的竞争问题。
With the vigorous development of Internet and digital society, the traditional direct attached storage systems are difficult to meet the challenge of explosive growth of data, leading to constant investigation on new storage system architecture. As the integration technology of storage and network, networked storage systems have many good characteristics, such as high performance, high capacity, ease of management and scalability, and have been increasingly used in many high performance computing fields, such as finance, oil, electricity, telecommunication, etc.
As a major software solution to I/O bottlenecks, caching is a very important research issue for storage systems, no exception for networked storage systems. Cache is actually a relatively high speed memory buffer for holding data, to allow fast re-access of subsequent request. Because cache is usually much smaller than the storage on the next level of I/O path, when cache is full, an appropriate data block needs to be discarded to reclaim space for new data blocks at an appropriate time. A replacement policy is the basis for this choice, which is a key factor to affect the cache performance. Currently, most of replacement policies are derived from researches on direct attached storage systems, which are not aware of multi-client cache hierarchy and access pattern, so they perform poorly when used in the networked storage servers.
This thesis focuses on the research of cache replacement policies to solve the negative impact of multi-client cache hierarchy and access pattern in the networked storage servers. The work of this thesis mainly involves three aspects: isolated server, single client and single server, multi-client and single server, in which four replacement policies with low miss penalty and high hit rate are proposed to enhance the cache performance for various workloads and applications. Specifically, the thesis makes the following contributions:
1. Since disk access has sequential locality, that is, sequential access is much faster than random access, we propose a Sequential Access detection Based cachE Replacement algorithm called SABER, which obtains LBA of cache blocks to detect sequential blocks for making a replacement decision. SABER can reduce the number of random disk access induced by cache miss, to avoid unnecessary seek and rotation, so it can achieve high performance by reducing miss penalty in networked storage servers which have weak locality.
2. Most of cache replacement policies work at the block level, so file system metadata is totally transparent to the cache. In fact, because files are stored and accessed sequentially in most storage systems, metadata can help to identify sequentiality of cache blocks. We present a FIle-system Metadata Aware cache Replacement algorithm called FIMAR, in which inode is attached to each cache blocks for estimating sequentiality. FIMAR assigns blocks of large inode high priority to be discarded, so that disks can work under sequential mode as much as possible.
3. To eliminate data redundancy among cache hierarchy in the networked storage systems, traditional cache replacement policies often introduce a dedicated communication protocol, and can not take into account both the client-friendly and efficiency. We propose a REsident Distance based cache replacement algorithm for exclusive storage servers called RED, which tracks the contents of client caches by obtaining semantic information from standard I/O interface, and makes a replacement decision using the time a block stays in the client cache, so it can attain high performance without changes to clients.
4. In the networked storage systems, data correlation of multi-client applications seriously affects server cache performance. The traditional cache replacement policies are usually suitable to either low data correlation applications or high data correlation applications, but not both. We present a Multi-client Adaptive COoperative cache Replacement algorithm called MACOR, which enforces exclusive caching among different cache levels and cooperative caching at the same level, so it can dynamically adapt to changes of data correlation. MACOR also proposes a dynamic cache partition mechanism to solve server cache conflict problems induced by multi-clients.
引文
[1] Morris R J T, Truskowski B J. The evolution of storage systems [J]. IBM Systems Journal, 2003, 42(2):205~207.
[2] Ealan J S, Satran J, Henis E, Vortman P. Trends in Storage Infrastructure [R]. IBM Corporation, 2002:23~34.
[3] Xie C S. Trends of information store in digital era [J]. The Computer World, 2001, 34:4~5.
[4]肖侬,舒继武,刘芳,李明强.存储技术的研究发展现状与趋势[R].2008年度中国计算机科学技术发展报告,中国计算机学会文集,2009.
[5]马一力,傅湘林,韩晓明,许鲁.存储与计算的分离[J].计算机研究与发展,2005,42(3):520~530.
[6] Gray J. What Next? A Few Remaining Problems in Information Technology [EB/OL]. http://research.microsoft.com/~gray/talks/Gray_Turing_FCRC.pdf, 1998.
[7]舒继武,薛巍,付长冬.网络存储系统与技术的现状与发展趋势[J].中国计算机学会通讯,2004.
[8] IDC, EMC. The Digital Universe Decade– Are You Ready? [EB/OL]. http:// canada.emc.com/collateral/analyst-reports/idc-digital-universe-are-you-ready.pdf,2010.
[9]王胜航等.容灾白皮书[EB/OL].IBM中国信息支持中心. http://www-900. ibm.com/cn/support/guide/whitebooks/Disaster_recovery/Disaster_recovery6_1.shtml.
[10]吴杰平.用容错=买保险[J].信息系统工程,2004.
[11] Xin Q, Miller E L, Schwarz T, Long D D E, Brandt S A, Litwin W. Reliability Mechanisms for Very Large Storage Systems [C]. The 20th IEEE/11th NASA Goddard conference on Mass Storage Systems and Technologies (MSST 2003), 2003:146~ 156.
[12] Adya Atul, et al. FARSITE: Federated, Available, and Reliable Storage for an Incompletely Trusted Environment [C]. The 5th Symposium on Operating Systems Design and Implementation (OSDI 2002), 2002.
[13] Clark T. Designing Storage Area Networks [M]. Addison-Wesley, 1999.
[14] Jin Hai, Cortes Toni, Buyya Rajkumar. High Performance Mass Storage and Parallel I/O: Technologies and Applications [M]. New Jersey, IEEE Press, 2001.
[15] Kulawik A K, Seitz C L, Seizovic J N, Su W K. Myrinet: A Gigabit–per- Second Local Area Network [J]. IEEE Micro, 1995, 15(1):29~36.
[16]付长冬,舒继武,沈美明等.网络存储体系结构的发展和研究[J].小型微型计算机系统,2004, 25(4):485~489.
[17]仇德成,李向伟,王安,王继伟.网格存储关键技术综述[J].兰州工业高等专科学校学报,2006.
[18]赵文辉,徐俊,周加林.李晨.网络存储技术[M].北京:清华大学出版社,2005.
[19] Gibson G A, Meter R V. Network attached storage architecture [J]. Communications of the ACM, 2002, 43(11): 37~45.
[20] Sandberg R, Goldberg D, Kleiman S, Walsh D, Lyon Bob. Design and Implementation of the Sun Network Filesystem [C]. Proceedings of the Summer 1985 USENIX Conference, 1985:119~130.
[21] Brent Callaghan. NFS Illustrated [M]. Addison-Wesley, 2000.
[22] Christopher R. Hertel. Implementing CIFS: The Common Internet File System [M]. IEEE Press, 2004.
[23] Khttar R, Murphy M, Tarella G, et al. Introduction to Storage Area Network [M]. IBM Redbooks Publications, 1999.
[24] Peter W, Robert E G, Henry G, et al. IP SAN-from iSCSI to IP-addressable Ethernet Disks [C]. The 20th IEEE/11th NASA Goddard Conference on Mass Storage Systems and Technologies (MSST 2003), 2003:189~194.
[25] Dan McConnell. IP Storage: A Technology Overview [R]. Storage Architecture and Technology Evaluation Rnterprise Systems Group, 2001.
[26] Hernandez R, Kion C. IP Storage Networking: IBM NAS and iSCSI Solutions [M]. IBM Redbooks Publications, 2001.
[27] He X B, Praveen B, Dan Z. Performance Evaluation of Distributed iSCSI RAID [C]. The 2003 International workshop on Storage Network Architecture and Parallel I/Os (SNAPI 2003), 2003:1~8.
[28] Palekar A. Design and Implementation of the SCSI target Mid-level for the Linux Operating System [R], University of New Hampshire, 2001.
[29] Kalman Meth, Julian Satran. Design of the iSCSI protocol [C]. The 20th IEEE/11th NASA Goddard Conference on Mass Storage Systems and Technologies (MSST 2003), 2003:116~122.
[30] Kalman Meth. iSCSI initiator design and implementation experience [C]. The 19th IEEE/10th NASA Goddard Conference on Mass Storage Systems and Technologies (MSST 2002), 2002:10~21.
[31] Aiken S, Grunwald. A performance analysis of the iSCSI protocol [C]. The 20th IEEE/11th NASA Goddard Conference on Mass Storage Systems and Technologies (MSST 2003), 2003:123~134.
[32] Gordon Moore. Cramming more components onto integrated circuits [J]. Electronics Magazine, 1965, 38(8):114~117.
[33] Gordon Moore. Progress in digital integrated electronic [C]. IEEE ElectronicDevices Meeting, 1975:11~13.
[34] Gordon Moore. Lithography and the Future of Moore's Law [J]. Proc. of SPIE, 1995.
[35] Gordon Moore. Intel Drives Moore's Law Forward With 65 Nanometer Process Technology [J]. Intel Press, 2004.
[36] Gordon Moore. Innovation More Important Than Ever in Platform Era [J], Intel Press, 2005.
[37] Schaller R R. Moore's law: past, present and future [J]. IEEE Spectrum, 1997, 34 (6):52~59.
[38] Adee S. the data: 37 Years of Moore's Law [J]. IEEE Spectrum, 2008, 45 (5):56~56.
[39] Randal E B, David R O. Computer Systems: A Programmer’s Perspective [M]. Prentice Hall, 2003.
[40] Amdahl G M. Validity of the Single Processor Approach to Achieving Large- Scale Computing Capabilities [C]. AFIPS Conference Proceedings, 1967, 30:483~485.
[41] David P. Improvements in multiprocessor system design [J]. ACM SIGARCH Computer Architecture News archive, 1985, 13 (3): 225~231.
[42] Riedel E, Gibson G. Understanding customer dissatisfaction with underutilized distributed file servers [C]. The 5th Goddard Space Flight Center Conf. on MSST, 1996.
[43] Sun Xianhe. Remove the memory wall: from performance modeling to architecture MINimization [C]. The 20th IEEE International Parallel and Distributed Processing Symposium (IPDPS 2006), 2006.
[44] Liu C, Anand S, Kandemir M. Organizing the last line of defense before hitting the memory wall for CMPs [C]. The 10th International Symposium on High Performance Computer Architecture (HPCA 2004), 2004:176~185.
[45] Zhang Xiaodong. Research Issues and Challenges to Advance System Software for Multicore Processors and Data-Intensive Applications [C]. The 2008 IEEE/IFIP International Conference on Embedded and Ubiquitous Computing (EUC 2008), 2008:4~4.
[46] Stallings W. Operating Systems, Internals and Design Principles, Fifth Edition [M]. Prentice Hall, 2005.
[47] Hwang Kai. Advanced Computer Architecture: Parallelism, Scalability, Programmability [M]. McGraw-Hill, 1992.
[48] Wilkes M, Stringer J. Microprogramming and the Design of the Control Circuits in an Electronics Digital Computer [J]. Proceedings of the Cambridge Philosophical Society, 1953.
[49] Denning P. The Working Set Model for Program Behavior [J]. Communicationsof the ACM, 1968.
[50] Knuth D. An Empirical Stuy of FORTRAN Programs [J]. Software Practice and Experience [J], 1971.
[51] Tanenbaum A. Implications of Structured Programming for Machine Architecture [J]. Communications of the ACM, 1978.
[52] Patterson D, Sequin C. A VLSI RISC [J]. Computer, 1982.
[53] Huck T. Comparative Analysis of Computer Architectures [R]. Stanford University Technical Report, 1983:83~243.
[54] Patterson D. Reduced Instruction Set Computers [J]. Communications of the ACM, 1985.
[55] Tamir Y, Sequin C. Strategies for Managing the Register File in RISC [J]. IEEE Transactions on Computers, 1983.
[56] Bovet D P, Cesati M. Understanding the Linux Kernel [M]. O’Reilly, 2005.
[57] Lian S, Jiang S, Zhang X D. STEP: Sequentiality and Thrashing Detection Based Prefetching to Improve Performance of Networked Storage Servers [C]. The 27th IEEE International Conference on Distributed Computing Systems (ICDCS 2007), 2007:64~64.
[58] Brown A D, Mowry T C, Krieger O. Compiler-based I/O prefetching for out-of-core applications [J]. ACM Transactions on Computer Systems, 2001, 19(2):111~170.
[59] Cao P, Felten E W, Karlin A R, Li K. Implementation and performance of integrated application-controlled file caching, prefetching, and disk scheduling [J]. ACM Transactions on Computer Systems, 1996, 14(4):311~343.
[60] Ding X, Jiang S, Chen F, Davis K, Zhang X D. DiskSeen: Exploiting Disk Layout and Access History to Enhance I/O Prefetch [C]. Proceedings of USENIX 2007 Annual Technical Conference, 2007.
[61] Gill B S, Bathen L A D. AMP: Adaptive Multi-stream Prefetching in a Shared Cache [C]. The Fifth USENIX Symposium on File and Storage Technologies (FAST 2007), 2007:185~198.
[62] Gill B S, Modha D S. Sarc: Sequential prefetching in adaptive replacement cache [C]. Proceedings of the General Track: USENIX 2005 Annual Technical Conference (USENIX 2005), 2005:293~308.
[63] Lei H, Duchamp D. An analytical approach to file prefetching [C]. Proceedings of the USENIX 1997 Annual Technical Conference (USENIX 1997), 1997:275~288.
[64] Papathanasiou A E,Scott M L. Aggressive prefetching: An idea whose time has come [C]. The 10th Workshop on Hot Topics in Operating Systems (HotOS 2005), 2005.
[65] Patterson R H, Gibson G A, Ginting E, Stodolsky D, Zelenka J. Informedprefetching and caching [C]. Proceedings of the 15th ACM symposium on Operating systems principles (SOSP 1995), 1995:79~95.
[66] Shriver E, Small C, Smith K A. Why does file system prefetching work? [C] The USENIX 1999 Annual Technical Conference (USENIX 1999), 1999:71~84.
[67] Smith A J. Sequentiality and prefetching in database systems [J]. ACM Transactions on Database Systems, 1978, 3(3):223~247.
[68] Handy J. The Cache Memory Book [M]. Academic Press, 1993.
[69] Smith A. Cache Memories [J]. ACM Computer Surveys, 1992.
[70] Chen Z, Zhang Y, Zhou Y, Scott H, Schiefer B. Empirical Evaluation of Multi-level Buffer Cache Collaboration for Storage Systems [C]. Proc. ACM Int'l Conf. Measurement and Modeling of Computing Systems (SIGMETRICS '05), 2005.
[71] Dan A, Dias D M, Yu P S. Analytical modelling of a hierarchical buffer for a data sharing environment [C]. Proceedings of the 1991 ACM SIGMETRICS Conference on Measurement and Modeling of Computer Systems (SIGMETRICS 1991), 1991:156~167.
[72] Franklin M J, Carey M J, Livny M. Global memory management in client-server database architectures [C]. Proceedings of the 18th International Conference on Very Large Data Bases (VLDB 1992), 1992:596~609.
[73] Muntz D, Honeyman P. Multi-level caching in distributed file systems -or- your cache ain’t nuthin’but trash [C]. Proceedings of the Winter 1992 USENIX Conference, 1992:305~314.
[74] Chen Z, Zhou Y, Li K. Eviction-based cache placement for storage caches [C]. Proceedings of the 2003 USENIX Annual Technical Conference, 2003:269~282.
[75] Jiang S, Zhang X. ULC: A file block placement and replacement protocol to effectively exploit hierarchical locality in multi-level buffer caches [C]. Proceedings of the 24th International Conference on Distributed Computing Systems (ICDCS 2004), 2004.
[76] Wong T and Wilkes J. My cache or yours? Making storage more exclusive [C]. Proceedings of the 2002 USENIX Annual Technical Conference, 2002:161~175.
[77] Williamson C. On Filter Effects in Web Caching Hierarchies [J]. ACM Trans on Internet Technology, 2002, 2(1):47~77.
[78] Froese K W, Bunt R B. The effect of client caching on file server workloads [C]. HICSS (1), 1996:150~159.
[79] Hsu W W, Smith A J, Young H C. The automatic improvement of locality in storage systems [J]. ACM Transtion on Computer System, 2005:23(4):424~473.
[80] Lishing Liu. Issues in multi-level cache designs [C]. Proceedings of the1994 IEEE International Conference on Computer Design: VLSI in Computer & Processors (ICCS 1994), 1994:46~52.
[81] Przybylski S, Horowitz M, Hennessy J. Characteristics of performance- MINimal multi-level cache hierarchies [C]. Proceedings of the 16th annual international symposium on Computer architecture (In ISCA 1989), 1989:114~121.
[82] Bairavasundaram L N, Sivathanu M, Arpaci-Dusseau A C, Arpaci-Dusseau R H. X-RAY: A non-invasive exclusive caching mechanism for RAIDs [C]. Proceedings of the 31th Annual International Symposium on Computer Architecture (ISCA 2004), 2004: 176~187.
[83] Binny S Gill. On Multi-level Exclusive Caching: Of?ine MINimality and Why promotions are better than demotions [C]. The 6th USENIX Conference on File and Storage Technologies (FAST 2008), 2008:49:~65.
[84] Xin Liu, Ashraf Aboulnaga, Kenneth Salem, Xuhui Li. CLIC: CLient-Informed Caching for Storage Servers [C]. The 7th USENIX Conference on File and Storage Technologies (FAST 2009), 2009:297~310.
[85] Gala Yadgar, Michael Factor, Assaf Schuster. Karma: Know-it-All Replacement for a Multilevel cAche [C]. The 5th USENIX Conference on File and Storage Technologies (FAST 2007), 2007.
[86] Xubin He, Li Ou, Martha Kosa, Stephen Scott, Christian Engelmann. A Unified Multiple-Level Cache for High Performance Cluster Storage Systems [J]. International Journal of High Performance Computing and Networking, 2007, 5(1): 97~109.
[87] MatthewWachs, Michael Abd-El-Malek, Eno Thereska, Gregory R Ganger. Argon: performance insulation for shared storage servers [C]. The 5th USENIX Conference on File and Storage Technologies (FAST 2007), 2007.
[88] Gala Yadgar, Michael Factor, Kai Li ,Assaf Schuster. MC2: Multiple Clients on a Multilevel Cache [C]. The 28th International Conference on Distributed Computing Systems (ICDCS 2008), 2008:722~730.
[89] Sivathanu M, Bairavasundaram L N, Arpaci-Dusseau A C, Arpaci-Dusseau R H. Database-aware semantically-smart storage [C]. The 3th USENIX Conference on File and Storage Technologies (FAST 2005), 2005.
[90] Belady L A. A study of replacement algorithms for a virtual-storage computer [J]. IBM Systems Journal, 1966, 5(2):78~101.
[91] Kruse R L, Joan L S. Data Structures & Program Design [M]. Prentice-Hall, 1987.
[92] Belady L A, Nelson R A, Shedler G S. An anomaly in space-time characteristics of certain programs running in a paging machine [J]. Communications of the ACM, 1969, 12(6):349~353.
[93] Mattson R L, Gecsei J, Slutz D R, Traiger I L. Evaluation techniques for storage hierarchies [C]. IBM System Journals, 1970, 9(2):78~117.
[94] Denning P J. Working sets past and present [J]. IEEE Trans on Software Engineeing, 1980, 6(1):64~84.
[95] Coffman J E G, Denning P J. Operating Systems Theory [M]. Prentice-Hall, 1973.
[96] Aho A V, Denning P J, Ullman J D. Principles of optimal page replacement [J]. Journal of the ACM, 1971, 18(1):80~93.
[97] Robinson J T, Devarakonda M V. Data cache management using frequency-based replacement [C]. Proceedings of the 1990 ACM SIGMETRICS Conference on Measurement and Modeling of Computer Systems (SIGMETRICS 1990), 1990:134~142.
[98] O’Neil E J, O’Neil P E, Weikum G. The LRU-K page replacement algorithm for database disk buffering [C]. Proceedings of the ACM SIGMOD Conference (SIGMOD 1993), 1993:297~306.
[99] Johnson T, Shasha D. 2Q: A low overhead high performance buffer management replacement algorithm [C]. Proceedings of the 20th International Conference on Very Large Data Bases (VLDB 1994), 1994:439~450.
[100] Jiang S, Zhang X. LIRS: an efficient low inter-reference recency set replacement policy to improve buffer cache performance [C]. Proceedings of the 2002 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems (SIGMETRICS 2002), 2002:31~42.
[101] MySQL AB. What is MySQL? MySQL 5.1 Reference Manual [Z], 2010.
[102] Megiddo N, Modha D S. ARC: A self-tuning, low overhead replacement cache [C]. Proceedings of the 2nd USENIX Conference on File and Storage Technologies (FAST 2003), 2003:115~130.
[103] Sun Microsystems. ZFS: the last word in file systems [Z], 2004.
[104] Zhou Y, Philbin J, Li K. The multi-queue replacement algorithm for second level buffer caches [C]. Proceedings of the 2001 USENIX Annual Technical Conference, 2001:91~104.
[105] Dahlin M D, Wang R Y, Anderson T E, Patterson D A. Cooperative caching: Using remote client memory to improve file system performance [C]. Proceedings of the 1st Symposium on Operating Systems Design and Implementation (OSDI 1994), 1994:267~280.
[106] Sarkar P, Hartman J. Efficient cooperative caching using hints [C]. Proceedings of the 2nd USENIX symposium on Operating Systems Design and Implementation (OSDI 1996), 1996:35~46.
[107] Mulvany R B. Engineering Design of a Disk Storage Facility with Data Modules [J]. IBM Systems Journal, 1974, 18(6):489~505.
[108] Seagate Technology. Product Manual: Barracuda 7200.11 Serial ATA [Z]. http://www.seagate.com.
[109] Wood R, Hsu Y, Schultz Ma. Perpendicular Magnetic Recording Technology [R], 2007.Cache for High Performance Storage Systems [J]. IEEE Transactions on Parallel and Distributed Systems, 2002, 13(3): 290~307.
[111] Jiang S, Ding X, Chen F, Tan E, Zhang X. DULO: An Effective Buffer Cache Management Scheme to Exploit Both Temporal and Spatial Locality [C]. The 4th USENIX Conference on File and Storage Technologies (FAST 2005), 2005:101~104.
[112] Donald Knuth. The Art of Computer Programming, Volume 3: Sorting and Searching, Third Edition [M]. Addison-Wesley, 1997:458~475.
[113] Casmira J P, Kaeli D R. Modeling cache pollution [J]. International Journal of Modeling and Simulation, 1998, 19(2):132~138.
[114] Adelson-Veslkii G M, Landis Y M. An Algorithm for the Organization of Information [J]. Doklady Akademi Nauk, 1962, 146:263~266.
[115] Chang L, Kuo T. An Adaptive Stripping Architecture for Flash Memory Storage Systems of Embedded Systems [C]. IEEE Eighth Real-Time and Embedded Technology and Applications Symposium (RTAS 2002), 2002.
[116] Wu C, Chang L, Kuo T. An Efficient R-Tree Implementation over Flash-Memory Storage Systems [C]. The 11th International Symposium on Advances in Geographic Information Systems (ACM-GIS 2003), 2003.
[117] IBM System Storage DS8000 Turbo. http://www-900.ibm.com/storage/cn/ disk/ds8000/.
[118] Gregory R G, Bruce L W, Yale N P. The DiskSim simulation environment version 2.0 reference manual [Z], 1999.
[119] Rémy C, Theodore T, Stephen T. Design and implementation of the second extended filesystem [C]. Proceedings of the First Dutch International Symposium on Linux, 1994.
[120] Tanenbaum A S, Woodhull A S. Operating Systems Design and Implementation [M]. Prentice Hall, 2006.
[121] Helen Custer. Inside the Windows NT File System [M]. Microsoft Press, 2006.
[122] Roy Duncan. Design goals and implementation of the new High Performance File System [J]. Microsoft Systems Journal, 1989, 4(5):1~13.
[123] Sammes A J, Jenkinson B. Forensic Computing: A Practitioner's Guide [M]. Springer, 2000.
[124] McKusick M K, Joy W N, Leffler S J, Fabry R S. A Fast File System for UNIX" [J]. ACM Transactions on Computer Systems, 1984, 2 (3):181~197.
[125] Theodore Ts'o, The Linux ext2/3/4 Filesystem: Past, Present, and Future [R], 2006.
[126] Zhu Yifeng, Jiang Hong. RACE: A Robust Adaptive Caching Strategy for Buffer Cache [J]. IEEE Transactions on Computers, 2007, 57(1):25~40.
[127] Gniady C, Butt A R, Hu Y C. Program-counter-based pattern classification inbuffer caching[C]. Proceedings of 6th Symposium on Operating System Design and Implementation (OSDI 2004), 2004:395~408.
[128] Steffen J L. Interactive examination of a C program with Cscope [C]. Proceedings of Winter USENIX Technical Conference, 1985.
[129] Stallman R. Using and porting the GNU compiler collection [M]. Iuniverse Inc, 1989.
[130] Howard JH. An Overview of the Andrew File System [C]. Winter 1988 USENIX Conference, 1988: 23~26.
[131] Lee D, Choi J, Kim J H, Noh S H, Min S L, Cho Y, Kim C S. LRFU: A spectrum of policies that subsumes the least recently used and least frequently used policies [J]. IEEE Trans on Computers, 2001, 50(12):1352~1361.
[132] Lumb C, Schindler J, Ganger G R, Riedel E, Nagle D F. Towards higher disk head utilization: Extracting“free”bandwidth from busy disk drives [C]. Symposium on Operating Systems Design and Implementation (OSDI 2000), 2000.
[133] Zipf G K. Human Behavior and the Principle of Least Effort [M]. Addison Wesley, 1949.
[134] Crovella Mark E, Bestavros A. Self-similarity in World Wide Web traffic: evidence and possible causes [J]. IEEE /ACM Transactions on Networking, 1997 5(6):835~846.
[135] Breslau L, Cao P, Fan L, Phillips G, Shenker S. Web caching and Zipf-like distributions: Evidence and implications [C]. INFOCOM, 1999:126~134.
[136] TPC benchmark H standard specification [Z], Revision 2.1.0.
[137] Rui Chu, Nong Xiao, Yongzhen Zhuang, Yunhao Liu, Xicheng Lu. A distributed paging RAM grid system for wide-area memory sharing [C]. Proceedings of the IPDPS Conference, 2006:10~17.
[138] Dahlin M, Wang R, Anderson T, Patterson S. Cooperative Caching: Using remote client memory to improve file system performance [C]. Operating Systems Design and Implementation (OSDI), 1994.
[139] Katz E D, Butler M, McGrath R. A scalable HTTP server: The NCSA prototype [J]. Computer networks and ISDN systems, 1994, 27(2):155~164.
[140] Uysal M, Acharya A, Saltz J. Requirements of I/O Systems for Parallel Machines: An Application-driven Study [R], University of Maryland, 1997.
[2] Ealan J S, Satran J, Henis E, Vortman P. Trends in Storage Infrastructure [R]. IBM Corporation, 2002:23~34.
[3] Xie C S. Trends of information store in digital era [J]. The Computer World, 2001, 34:4~5.
[4]肖侬,舒继武,刘芳,李明强.存储技术的研究发展现状与趋势[R].2008年度中国计算机科学技术发展报告,中国计算机学会文集,2009.
[5]马一力,傅湘林,韩晓明,许鲁.存储与计算的分离[J].计算机研究与发展,2005,42(3):520~530.
[6] Gray J. What Next? A Few Remaining Problems in Information Technology [EB/OL]. http://research.microsoft.com/~gray/talks/Gray_Turing_FCRC.pdf, 1998.
[7]舒继武,薛巍,付长冬.网络存储系统与技术的现状与发展趋势[J].中国计算机学会通讯,2004.
[8] IDC, EMC. The Digital Universe Decade– Are You Ready? [EB/OL]. http:// canada.emc.com/collateral/analyst-reports/idc-digital-universe-are-you-ready.pdf,2010.
[9]王胜航等.容灾白皮书[EB/OL].IBM中国信息支持中心. http://www-900. ibm.com/cn/support/guide/whitebooks/Disaster_recovery/Disaster_recovery6_1.shtml.
[10]吴杰平.用容错=买保险[J].信息系统工程,2004.
[11] Xin Q, Miller E L, Schwarz T, Long D D E, Brandt S A, Litwin W. Reliability Mechanisms for Very Large Storage Systems [C]. The 20th IEEE/11th NASA Goddard conference on Mass Storage Systems and Technologies (MSST 2003), 2003:146~ 156.
[12] Adya Atul, et al. FARSITE: Federated, Available, and Reliable Storage for an Incompletely Trusted Environment [C]. The 5th Symposium on Operating Systems Design and Implementation (OSDI 2002), 2002.
[13] Clark T. Designing Storage Area Networks [M]. Addison-Wesley, 1999.
[14] Jin Hai, Cortes Toni, Buyya Rajkumar. High Performance Mass Storage and Parallel I/O: Technologies and Applications [M]. New Jersey, IEEE Press, 2001.
[15] Kulawik A K, Seitz C L, Seizovic J N, Su W K. Myrinet: A Gigabit–per- Second Local Area Network [J]. IEEE Micro, 1995, 15(1):29~36.
[16]付长冬,舒继武,沈美明等.网络存储体系结构的发展和研究[J].小型微型计算机系统,2004, 25(4):485~489.
[17]仇德成,李向伟,王安,王继伟.网格存储关键技术综述[J].兰州工业高等专科学校学报,2006.
[18]赵文辉,徐俊,周加林.李晨.网络存储技术[M].北京:清华大学出版社,2005.
[19] Gibson G A, Meter R V. Network attached storage architecture [J]. Communications of the ACM, 2002, 43(11): 37~45.
[20] Sandberg R, Goldberg D, Kleiman S, Walsh D, Lyon Bob. Design and Implementation of the Sun Network Filesystem [C]. Proceedings of the Summer 1985 USENIX Conference, 1985:119~130.
[21] Brent Callaghan. NFS Illustrated [M]. Addison-Wesley, 2000.
[22] Christopher R. Hertel. Implementing CIFS: The Common Internet File System [M]. IEEE Press, 2004.
[23] Khttar R, Murphy M, Tarella G, et al. Introduction to Storage Area Network [M]. IBM Redbooks Publications, 1999.
[24] Peter W, Robert E G, Henry G, et al. IP SAN-from iSCSI to IP-addressable Ethernet Disks [C]. The 20th IEEE/11th NASA Goddard Conference on Mass Storage Systems and Technologies (MSST 2003), 2003:189~194.
[25] Dan McConnell. IP Storage: A Technology Overview [R]. Storage Architecture and Technology Evaluation Rnterprise Systems Group, 2001.
[26] Hernandez R, Kion C. IP Storage Networking: IBM NAS and iSCSI Solutions [M]. IBM Redbooks Publications, 2001.
[27] He X B, Praveen B, Dan Z. Performance Evaluation of Distributed iSCSI RAID [C]. The 2003 International workshop on Storage Network Architecture and Parallel I/Os (SNAPI 2003), 2003:1~8.
[28] Palekar A. Design and Implementation of the SCSI target Mid-level for the Linux Operating System [R], University of New Hampshire, 2001.
[29] Kalman Meth, Julian Satran. Design of the iSCSI protocol [C]. The 20th IEEE/11th NASA Goddard Conference on Mass Storage Systems and Technologies (MSST 2003), 2003:116~122.
[30] Kalman Meth. iSCSI initiator design and implementation experience [C]. The 19th IEEE/10th NASA Goddard Conference on Mass Storage Systems and Technologies (MSST 2002), 2002:10~21.
[31] Aiken S, Grunwald. A performance analysis of the iSCSI protocol [C]. The 20th IEEE/11th NASA Goddard Conference on Mass Storage Systems and Technologies (MSST 2003), 2003:123~134.
[32] Gordon Moore. Cramming more components onto integrated circuits [J]. Electronics Magazine, 1965, 38(8):114~117.
[33] Gordon Moore. Progress in digital integrated electronic [C]. IEEE ElectronicDevices Meeting, 1975:11~13.
[34] Gordon Moore. Lithography and the Future of Moore's Law [J]. Proc. of SPIE, 1995.
[35] Gordon Moore. Intel Drives Moore's Law Forward With 65 Nanometer Process Technology [J]. Intel Press, 2004.
[36] Gordon Moore. Innovation More Important Than Ever in Platform Era [J], Intel Press, 2005.
[37] Schaller R R. Moore's law: past, present and future [J]. IEEE Spectrum, 1997, 34 (6):52~59.
[38] Adee S. the data: 37 Years of Moore's Law [J]. IEEE Spectrum, 2008, 45 (5):56~56.
[39] Randal E B, David R O. Computer Systems: A Programmer’s Perspective [M]. Prentice Hall, 2003.
[40] Amdahl G M. Validity of the Single Processor Approach to Achieving Large- Scale Computing Capabilities [C]. AFIPS Conference Proceedings, 1967, 30:483~485.
[41] David P. Improvements in multiprocessor system design [J]. ACM SIGARCH Computer Architecture News archive, 1985, 13 (3): 225~231.
[42] Riedel E, Gibson G. Understanding customer dissatisfaction with underutilized distributed file servers [C]. The 5th Goddard Space Flight Center Conf. on MSST, 1996.
[43] Sun Xianhe. Remove the memory wall: from performance modeling to architecture MINimization [C]. The 20th IEEE International Parallel and Distributed Processing Symposium (IPDPS 2006), 2006.
[44] Liu C, Anand S, Kandemir M. Organizing the last line of defense before hitting the memory wall for CMPs [C]. The 10th International Symposium on High Performance Computer Architecture (HPCA 2004), 2004:176~185.
[45] Zhang Xiaodong. Research Issues and Challenges to Advance System Software for Multicore Processors and Data-Intensive Applications [C]. The 2008 IEEE/IFIP International Conference on Embedded and Ubiquitous Computing (EUC 2008), 2008:4~4.
[46] Stallings W. Operating Systems, Internals and Design Principles, Fifth Edition [M]. Prentice Hall, 2005.
[47] Hwang Kai. Advanced Computer Architecture: Parallelism, Scalability, Programmability [M]. McGraw-Hill, 1992.
[48] Wilkes M, Stringer J. Microprogramming and the Design of the Control Circuits in an Electronics Digital Computer [J]. Proceedings of the Cambridge Philosophical Society, 1953.
[49] Denning P. The Working Set Model for Program Behavior [J]. Communicationsof the ACM, 1968.
[50] Knuth D. An Empirical Stuy of FORTRAN Programs [J]. Software Practice and Experience [J], 1971.
[51] Tanenbaum A. Implications of Structured Programming for Machine Architecture [J]. Communications of the ACM, 1978.
[52] Patterson D, Sequin C. A VLSI RISC [J]. Computer, 1982.
[53] Huck T. Comparative Analysis of Computer Architectures [R]. Stanford University Technical Report, 1983:83~243.
[54] Patterson D. Reduced Instruction Set Computers [J]. Communications of the ACM, 1985.
[55] Tamir Y, Sequin C. Strategies for Managing the Register File in RISC [J]. IEEE Transactions on Computers, 1983.
[56] Bovet D P, Cesati M. Understanding the Linux Kernel [M]. O’Reilly, 2005.
[57] Lian S, Jiang S, Zhang X D. STEP: Sequentiality and Thrashing Detection Based Prefetching to Improve Performance of Networked Storage Servers [C]. The 27th IEEE International Conference on Distributed Computing Systems (ICDCS 2007), 2007:64~64.
[58] Brown A D, Mowry T C, Krieger O. Compiler-based I/O prefetching for out-of-core applications [J]. ACM Transactions on Computer Systems, 2001, 19(2):111~170.
[59] Cao P, Felten E W, Karlin A R, Li K. Implementation and performance of integrated application-controlled file caching, prefetching, and disk scheduling [J]. ACM Transactions on Computer Systems, 1996, 14(4):311~343.
[60] Ding X, Jiang S, Chen F, Davis K, Zhang X D. DiskSeen: Exploiting Disk Layout and Access History to Enhance I/O Prefetch [C]. Proceedings of USENIX 2007 Annual Technical Conference, 2007.
[61] Gill B S, Bathen L A D. AMP: Adaptive Multi-stream Prefetching in a Shared Cache [C]. The Fifth USENIX Symposium on File and Storage Technologies (FAST 2007), 2007:185~198.
[62] Gill B S, Modha D S. Sarc: Sequential prefetching in adaptive replacement cache [C]. Proceedings of the General Track: USENIX 2005 Annual Technical Conference (USENIX 2005), 2005:293~308.
[63] Lei H, Duchamp D. An analytical approach to file prefetching [C]. Proceedings of the USENIX 1997 Annual Technical Conference (USENIX 1997), 1997:275~288.
[64] Papathanasiou A E,Scott M L. Aggressive prefetching: An idea whose time has come [C]. The 10th Workshop on Hot Topics in Operating Systems (HotOS 2005), 2005.
[65] Patterson R H, Gibson G A, Ginting E, Stodolsky D, Zelenka J. Informedprefetching and caching [C]. Proceedings of the 15th ACM symposium on Operating systems principles (SOSP 1995), 1995:79~95.
[66] Shriver E, Small C, Smith K A. Why does file system prefetching work? [C] The USENIX 1999 Annual Technical Conference (USENIX 1999), 1999:71~84.
[67] Smith A J. Sequentiality and prefetching in database systems [J]. ACM Transactions on Database Systems, 1978, 3(3):223~247.
[68] Handy J. The Cache Memory Book [M]. Academic Press, 1993.
[69] Smith A. Cache Memories [J]. ACM Computer Surveys, 1992.
[70] Chen Z, Zhang Y, Zhou Y, Scott H, Schiefer B. Empirical Evaluation of Multi-level Buffer Cache Collaboration for Storage Systems [C]. Proc. ACM Int'l Conf. Measurement and Modeling of Computing Systems (SIGMETRICS '05), 2005.
[71] Dan A, Dias D M, Yu P S. Analytical modelling of a hierarchical buffer for a data sharing environment [C]. Proceedings of the 1991 ACM SIGMETRICS Conference on Measurement and Modeling of Computer Systems (SIGMETRICS 1991), 1991:156~167.
[72] Franklin M J, Carey M J, Livny M. Global memory management in client-server database architectures [C]. Proceedings of the 18th International Conference on Very Large Data Bases (VLDB 1992), 1992:596~609.
[73] Muntz D, Honeyman P. Multi-level caching in distributed file systems -or- your cache ain’t nuthin’but trash [C]. Proceedings of the Winter 1992 USENIX Conference, 1992:305~314.
[74] Chen Z, Zhou Y, Li K. Eviction-based cache placement for storage caches [C]. Proceedings of the 2003 USENIX Annual Technical Conference, 2003:269~282.
[75] Jiang S, Zhang X. ULC: A file block placement and replacement protocol to effectively exploit hierarchical locality in multi-level buffer caches [C]. Proceedings of the 24th International Conference on Distributed Computing Systems (ICDCS 2004), 2004.
[76] Wong T and Wilkes J. My cache or yours? Making storage more exclusive [C]. Proceedings of the 2002 USENIX Annual Technical Conference, 2002:161~175.
[77] Williamson C. On Filter Effects in Web Caching Hierarchies [J]. ACM Trans on Internet Technology, 2002, 2(1):47~77.
[78] Froese K W, Bunt R B. The effect of client caching on file server workloads [C]. HICSS (1), 1996:150~159.
[79] Hsu W W, Smith A J, Young H C. The automatic improvement of locality in storage systems [J]. ACM Transtion on Computer System, 2005:23(4):424~473.
[80] Lishing Liu. Issues in multi-level cache designs [C]. Proceedings of the1994 IEEE International Conference on Computer Design: VLSI in Computer & Processors (ICCS 1994), 1994:46~52.
[81] Przybylski S, Horowitz M, Hennessy J. Characteristics of performance- MINimal multi-level cache hierarchies [C]. Proceedings of the 16th annual international symposium on Computer architecture (In ISCA 1989), 1989:114~121.
[82] Bairavasundaram L N, Sivathanu M, Arpaci-Dusseau A C, Arpaci-Dusseau R H. X-RAY: A non-invasive exclusive caching mechanism for RAIDs [C]. Proceedings of the 31th Annual International Symposium on Computer Architecture (ISCA 2004), 2004: 176~187.
[83] Binny S Gill. On Multi-level Exclusive Caching: Of?ine MINimality and Why promotions are better than demotions [C]. The 6th USENIX Conference on File and Storage Technologies (FAST 2008), 2008:49:~65.
[84] Xin Liu, Ashraf Aboulnaga, Kenneth Salem, Xuhui Li. CLIC: CLient-Informed Caching for Storage Servers [C]. The 7th USENIX Conference on File and Storage Technologies (FAST 2009), 2009:297~310.
[85] Gala Yadgar, Michael Factor, Assaf Schuster. Karma: Know-it-All Replacement for a Multilevel cAche [C]. The 5th USENIX Conference on File and Storage Technologies (FAST 2007), 2007.
[86] Xubin He, Li Ou, Martha Kosa, Stephen Scott, Christian Engelmann. A Unified Multiple-Level Cache for High Performance Cluster Storage Systems [J]. International Journal of High Performance Computing and Networking, 2007, 5(1): 97~109.
[87] MatthewWachs, Michael Abd-El-Malek, Eno Thereska, Gregory R Ganger. Argon: performance insulation for shared storage servers [C]. The 5th USENIX Conference on File and Storage Technologies (FAST 2007), 2007.
[88] Gala Yadgar, Michael Factor, Kai Li ,Assaf Schuster. MC2: Multiple Clients on a Multilevel Cache [C]. The 28th International Conference on Distributed Computing Systems (ICDCS 2008), 2008:722~730.
[89] Sivathanu M, Bairavasundaram L N, Arpaci-Dusseau A C, Arpaci-Dusseau R H. Database-aware semantically-smart storage [C]. The 3th USENIX Conference on File and Storage Technologies (FAST 2005), 2005.
[90] Belady L A. A study of replacement algorithms for a virtual-storage computer [J]. IBM Systems Journal, 1966, 5(2):78~101.
[91] Kruse R L, Joan L S. Data Structures & Program Design [M]. Prentice-Hall, 1987.
[92] Belady L A, Nelson R A, Shedler G S. An anomaly in space-time characteristics of certain programs running in a paging machine [J]. Communications of the ACM, 1969, 12(6):349~353.
[93] Mattson R L, Gecsei J, Slutz D R, Traiger I L. Evaluation techniques for storage hierarchies [C]. IBM System Journals, 1970, 9(2):78~117.
[94] Denning P J. Working sets past and present [J]. IEEE Trans on Software Engineeing, 1980, 6(1):64~84.
[95] Coffman J E G, Denning P J. Operating Systems Theory [M]. Prentice-Hall, 1973.
[96] Aho A V, Denning P J, Ullman J D. Principles of optimal page replacement [J]. Journal of the ACM, 1971, 18(1):80~93.
[97] Robinson J T, Devarakonda M V. Data cache management using frequency-based replacement [C]. Proceedings of the 1990 ACM SIGMETRICS Conference on Measurement and Modeling of Computer Systems (SIGMETRICS 1990), 1990:134~142.
[98] O’Neil E J, O’Neil P E, Weikum G. The LRU-K page replacement algorithm for database disk buffering [C]. Proceedings of the ACM SIGMOD Conference (SIGMOD 1993), 1993:297~306.
[99] Johnson T, Shasha D. 2Q: A low overhead high performance buffer management replacement algorithm [C]. Proceedings of the 20th International Conference on Very Large Data Bases (VLDB 1994), 1994:439~450.
[100] Jiang S, Zhang X. LIRS: an efficient low inter-reference recency set replacement policy to improve buffer cache performance [C]. Proceedings of the 2002 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems (SIGMETRICS 2002), 2002:31~42.
[101] MySQL AB. What is MySQL? MySQL 5.1 Reference Manual [Z], 2010.
[102] Megiddo N, Modha D S. ARC: A self-tuning, low overhead replacement cache [C]. Proceedings of the 2nd USENIX Conference on File and Storage Technologies (FAST 2003), 2003:115~130.
[103] Sun Microsystems. ZFS: the last word in file systems [Z], 2004.
[104] Zhou Y, Philbin J, Li K. The multi-queue replacement algorithm for second level buffer caches [C]. Proceedings of the 2001 USENIX Annual Technical Conference, 2001:91~104.
[105] Dahlin M D, Wang R Y, Anderson T E, Patterson D A. Cooperative caching: Using remote client memory to improve file system performance [C]. Proceedings of the 1st Symposium on Operating Systems Design and Implementation (OSDI 1994), 1994:267~280.
[106] Sarkar P, Hartman J. Efficient cooperative caching using hints [C]. Proceedings of the 2nd USENIX symposium on Operating Systems Design and Implementation (OSDI 1996), 1996:35~46.
[107] Mulvany R B. Engineering Design of a Disk Storage Facility with Data Modules [J]. IBM Systems Journal, 1974, 18(6):489~505.
[108] Seagate Technology. Product Manual: Barracuda 7200.11 Serial ATA [Z]. http://www.seagate.com.
[109] Wood R, Hsu Y, Schultz Ma. Perpendicular Magnetic Recording Technology [R], 2007.Cache for High Performance Storage Systems [J]. IEEE Transactions on Parallel and Distributed Systems, 2002, 13(3): 290~307.
[111] Jiang S, Ding X, Chen F, Tan E, Zhang X. DULO: An Effective Buffer Cache Management Scheme to Exploit Both Temporal and Spatial Locality [C]. The 4th USENIX Conference on File and Storage Technologies (FAST 2005), 2005:101~104.
[112] Donald Knuth. The Art of Computer Programming, Volume 3: Sorting and Searching, Third Edition [M]. Addison-Wesley, 1997:458~475.
[113] Casmira J P, Kaeli D R. Modeling cache pollution [J]. International Journal of Modeling and Simulation, 1998, 19(2):132~138.
[114] Adelson-Veslkii G M, Landis Y M. An Algorithm for the Organization of Information [J]. Doklady Akademi Nauk, 1962, 146:263~266.
[115] Chang L, Kuo T. An Adaptive Stripping Architecture for Flash Memory Storage Systems of Embedded Systems [C]. IEEE Eighth Real-Time and Embedded Technology and Applications Symposium (RTAS 2002), 2002.
[116] Wu C, Chang L, Kuo T. An Efficient R-Tree Implementation over Flash-Memory Storage Systems [C]. The 11th International Symposium on Advances in Geographic Information Systems (ACM-GIS 2003), 2003.
[117] IBM System Storage DS8000 Turbo. http://www-900.ibm.com/storage/cn/ disk/ds8000/.
[118] Gregory R G, Bruce L W, Yale N P. The DiskSim simulation environment version 2.0 reference manual [Z], 1999.
[119] Rémy C, Theodore T, Stephen T. Design and implementation of the second extended filesystem [C]. Proceedings of the First Dutch International Symposium on Linux, 1994.
[120] Tanenbaum A S, Woodhull A S. Operating Systems Design and Implementation [M]. Prentice Hall, 2006.
[121] Helen Custer. Inside the Windows NT File System [M]. Microsoft Press, 2006.
[122] Roy Duncan. Design goals and implementation of the new High Performance File System [J]. Microsoft Systems Journal, 1989, 4(5):1~13.
[123] Sammes A J, Jenkinson B. Forensic Computing: A Practitioner's Guide [M]. Springer, 2000.
[124] McKusick M K, Joy W N, Leffler S J, Fabry R S. A Fast File System for UNIX" [J]. ACM Transactions on Computer Systems, 1984, 2 (3):181~197.
[125] Theodore Ts'o, The Linux ext2/3/4 Filesystem: Past, Present, and Future [R], 2006.
[126] Zhu Yifeng, Jiang Hong. RACE: A Robust Adaptive Caching Strategy for Buffer Cache [J]. IEEE Transactions on Computers, 2007, 57(1):25~40.
[127] Gniady C, Butt A R, Hu Y C. Program-counter-based pattern classification inbuffer caching[C]. Proceedings of 6th Symposium on Operating System Design and Implementation (OSDI 2004), 2004:395~408.
[128] Steffen J L. Interactive examination of a C program with Cscope [C]. Proceedings of Winter USENIX Technical Conference, 1985.
[129] Stallman R. Using and porting the GNU compiler collection [M]. Iuniverse Inc, 1989.
[130] Howard JH. An Overview of the Andrew File System [C]. Winter 1988 USENIX Conference, 1988: 23~26.
[131] Lee D, Choi J, Kim J H, Noh S H, Min S L, Cho Y, Kim C S. LRFU: A spectrum of policies that subsumes the least recently used and least frequently used policies [J]. IEEE Trans on Computers, 2001, 50(12):1352~1361.
[132] Lumb C, Schindler J, Ganger G R, Riedel E, Nagle D F. Towards higher disk head utilization: Extracting“free”bandwidth from busy disk drives [C]. Symposium on Operating Systems Design and Implementation (OSDI 2000), 2000.
[133] Zipf G K. Human Behavior and the Principle of Least Effort [M]. Addison Wesley, 1949.
[134] Crovella Mark E, Bestavros A. Self-similarity in World Wide Web traffic: evidence and possible causes [J]. IEEE /ACM Transactions on Networking, 1997 5(6):835~846.
[135] Breslau L, Cao P, Fan L, Phillips G, Shenker S. Web caching and Zipf-like distributions: Evidence and implications [C]. INFOCOM, 1999:126~134.
[136] TPC benchmark H standard specification [Z], Revision 2.1.0.
[137] Rui Chu, Nong Xiao, Yongzhen Zhuang, Yunhao Liu, Xicheng Lu. A distributed paging RAM grid system for wide-area memory sharing [C]. Proceedings of the IPDPS Conference, 2006:10~17.
[138] Dahlin M, Wang R, Anderson T, Patterson S. Cooperative Caching: Using remote client memory to improve file system performance [C]. Operating Systems Design and Implementation (OSDI), 1994.
[139] Katz E D, Butler M, McGrath R. A scalable HTTP server: The NCSA prototype [J]. Computer networks and ISDN systems, 1994, 27(2):155~164.
[140] Uysal M, Acharya A, Saltz J. Requirements of I/O Systems for Parallel Machines: An Application-driven Study [R], University of Maryland, 1997.