分布式磁盘阵列的结构及冗余策略

分布式磁盘阵列对于提高数据存储的可靠性、带宽和容量，具有十分重要的意义。本文介绍了分布式磁盘阵列的两种连接方式，磁盘分布连接到计算机和磁盘阵列连接到网络，以及在分布式磁盘阵列中得到应用的两种冗余策略，Chained declustering和RAID-x。     

Flexible Strategies for Disk Scheduling in Multimedia Presentation Servers

Multimedia presentations (e.g., lectures, digital libraries) normally include discrete media objects such as text and images along with continuous media objects such as video and audio. Objects composing a multimedia presentation need to be delivered based on the temporal relationships specified by the author(s). Hence, even discrete media objects (that do not normally have any real-time characteristics) have temporal constraints on their presentations. Composition of multimedia presentations may be light (without any accompanying video or large multimedia data) or heavy (accompanied by video for the entire presentation duration). The varying nature of the composition of multimedia presentations provides some flexibility for scheduling their retrieval. In this paper, we present a min-max skip round disk scheduling strategy that can admit multimedia presentations in a flexible manner depending on their composition. We also outline strategies for storage of multimedia presentations on an array of disks as well as on multi-zone recording disks.Emilda Sindhu received the B.Tech degree in Electrical & Electronics from University of Calicut, India, in 1995 and the M.S. degree in Computer Science in 2003 from National University of Singapore. This paper comprises part of her master thesis work. She is presently employed as Senior Research Officer at the A-star Institute of High Performance Computing (IHPC), Singapore. Her current research interests include distributed computing particulary Grid computing. She is involved in the development of tools and components for distributed computing applications.Lillykutty Jacob obtained her B.Sc (Engg.) degree in electronics and communication from the Kerala University, India, in 1983, M.Tech. degree in electrical engineering (communication) from the Indian Institute of Technology at Madras in 1985, and PhD degree in electrical communication engineering from the Indian Institute of Science, in 1993. She was with the department of computer science, Korea Advanced Institute of Science and Technology, S. Korea, during 1996–97, for post doctoral research, and with the department of Computer Science, National University of Singapore, during 1998–2003, as a visiting faculty. Since 1985 she has been with the National Institute of Technology at Calicut, India, where she is currently a professor. Her research interests include wireless networks, QoS issues, and performance analysis.Ovidiu Daescu received the B.S. in computer science and automation from the Technical Military Academy, Bucharest, Romania, in 1991, and the M.S. and Ph.D. degrees from the University of Notre Dame, in 1997 and 2000. He is currently an Assistant Professor in the Department of Computer Science, University of Texas at Dallas. His research interests are in algorithm design, computational geometry and geometric optimization.B. Prabhakaran is currently with the Department of Computer Science, University of Texas at Dallas. Dr. B. Prabhakaran has been working in the area of multimedia systems: multimedia databases, authoring & presentation, resource management, and scalable web-based multimedia presentation servers. He has published several research papers in prestigious conferences and journals in this area.Dr. Prabhakaran received the NSF CAREER Award FY 2003 for his proposal on Animation Databases. Dr. Prabhakaran has served as an Associate Chair of the ACM Multimedia2003 (November 2003, California), ACM MM 2000 (November 2000, Los Angeles), and ACM Multimedia99 conference (Florida, November 1999). He has served as guest-editor (special issue on Multimedia Authoring and Presentation) for ACM Multimedia Systems journal. He is also serving on the editorial board of Multimedia Tools and Applications journal, Kluwer Academic Publishers. He has also served as program committee member on several multimedia conferences and workshops. Dr. Prabhakaran has presented tutorials in several conferences on topics such as network resource management, adaptive multimedia presentations, and scalable multimedia servers.B. Prabhakaran has served as a visiting research faculty with the Department of Computer Science, University of Maryland, College Park. He also served as a faculty in the Department of Computer Science, National University of Singapore as well as in the Indian Institute of Technology, Madras, India.     

一种灵活的使用控制授权语言框架研究

首先提出一种单限制变元Datalog^乛,sc的概念,并对单限制变元Datalog^乛,sc的评价（evaluation）及其元组识别问题做了分析．然后提出使用控制授权语言框架LUC,该框架基于具有单一稳态结构的单限制变元分层Active-U-Datalog^乛,sc语法和语义,具有逻辑上的一致性、完备性和可行性,最后对LUC框架的表达力、灵活性及其实现和应用做了说明．     

在PC机上对磁盘阵列的仿真

本文介绍了一种用Ｃ语言在ＰＣ机上通过修改时钟中断处理程序和系统８２５３定时／计数器的设置来进行磁盘阵列仿真的新方法，利用它可以很好地编制仿真程序，而且程序结构清晰，仿真过程直观，结果稳定可靠。     

基于多模块的可配置阵列存储系统的模拟实现

给出一个基于多模块的可配置磁盘阵列存储系统的框架设计与编程实现,软件支持RAID0、RAID1、RAID3、RAID5、RAID6等主流阵列级别,另外还添加了RAID5x阵列.采用多线程技术,能较真实地模拟客户与存储系统的动态交互过程,能根据用户的配置进行阵列正常、降级的读写性能测试.经实验验证,该软件能对阵列存储系统进行较为真实的模拟,进一步优化后,其可以作为磁盘阵列的性能、可靠性以及阵列优化方法的一个模拟研究平台.     

固态盘阵列构建方法研究综述

单个固态盘存在随机写性能较差和擦写次数有限等缺陷,使用廉价盘冗余阵列(redundant arrays of inexpensive disks, RAID)技术将多块固态盘组织在一起有助于满足存储系统的高可靠、大容量、高性能的要求.然而,将RAID算法简单应用于固态盘阵列会遇到一些问题.首先分析了基于Flash的固态盘和RAID技术存在的缺陷,选取性能、可靠性和价格作为阵列构建方法的评价标准,并将随机写、小写、垃圾回收、负载均衡、擦除次数、磨损均衡、冗余度等问题作为分析重点;然后,从固态盘和Flash芯片2种构建粒度出发,分别论述了不同的构建方法并分析了各自的优缺点;最后,总结了不同构建方法并指出未来可能的研究方向.     

优化的存储模式-VBR视频安置在MZ磁盘组上

研究了大量视频在磁盘组上的安置和接纳计算方法。基于视频的特性、视频的流行性及磁盘的特性,提出了一个优VBRMZVBRMZ化的存储模式及相应的接纳算法,和其它现存算法相比,结果显示它能支持更多的流数、在作品流行性变化的情况下有更好的适应能力。     

用于视觉假体的柔性生物微电极阵列的设计和制作

提出了一种用于视网膜假体的基于Parylene的柔性微电极阵列的设计和制作.微电极阵列为5×5,通过光刻胶热熔回流技术形成的电极点为半球形凸起,底部直径为60 μm,高度大约为24 μm.整个电极具有很好的柔韧性,能够更好的适应视网膜表面轮廓,提高刺激效果.同时,电极具有很好的透明性,便于手术时电极的植入和手术后对生物组织的观察.     

MT2RAID:一种高可靠大规模磁盘阵列结构

传统的磁盘阵列一般采用集中式控制结构,其连接的底层磁盘数受系统总线的制约,容易出现性能瓶颈,且不能容两个以上磁盘出错。从模块化系统的组织方法出发,提出一种采用标准模块化存储单元组成的通过胖树结构互连的大规模磁盘阵列结构MT2RAID,分别就其各种数据分布的性能和可靠性进行了分析和讨论。原型系统测试结果表明,相比集中式磁盘阵列结构,MT2RAID也具有较高的性能。     

基于镍尖锥阵列的柔性超薄超级电容器

本研究采用电化学沉积的方法在金属钛板上制备出镍尖锥的规则阵列,然后将二氧化锰直接沉积到镍尖锥阵列上。这种沉积有二氧化锰的镍尖锥能够直接从基板上剥落下来形成自支撑的、柔性、超薄电极片。结果显示该电极的最高比电容达到325 F/g,并且具有出色的倍率性能。用这种电极组装成的柔性超薄超级电容器呈现出良好的电化学性能,有望在可穿戴消费电子领域得到应用。     

Integration of Au Nanorods With Flexible Thin-Film Microelectrode Arrays for Improved Neural Interfaces

In neural prosthetic systems, a low-impedance electrode–tissue interface is important for maintaining signal quality for recording, as well as effective charge transfer for stimulation. However, neural microelectrodes often have high impedance due to their small surface areas. In this paper, we present a simple method of increasing their effective surface areas by introducing nanostructures on the electrode sites. The method combines photolithography and electron-beam evaporation with a locally patterned anodized porous alumina template to integrate Au-nanorod arrays on the flexible thin-film microelectrode, which can significantly increase the effective surface area and decrease impedance due to its 3-D and compact nanostructures. Moreover, the geometrical and electrical properties of Au-nanorod electrodes were demonstrated and compared with conventional planar microelectrodes by using a scanning electron microscope and an impedance spectroscopy system. Experimental results showed that approximately 25 times lower interface impedance was achieved for this nanostructured microelectrode. Such Au-nanorod integrated microelectrode arrays will be a promising tool for neural engineering. $hfill$[2008-0136]      

Fabrication of Flexible Transducer Arrays With Through-Wafer Electrical Interconnects Based on Trench Refilling With PDMS

Flexible transducer arrays are desired to wrap around catheter tips for side-looking intravascular ultrasound imaging. We present a technique for constructing flexible capacitive micromachined ultrasonic transducer (CMUT) arrays by forming polymer-filled deep trenches in a silicon substrate. First, we etch deep trenches between the bottom electrodes of CMUT elements on a prime silicon wafer using deep reactive ion etching. Second, we fusion-bond a silicon-on-insulator (SOI) wafer to the prime silicon wafer. Once the silicon handle and buried oxide layers are removed from the back side of the SOI wafer, the remaining thin silicon device layer acts as a movable membrane and top electrode. Third, we fill the deep trenches with polydimethylsiloxane, and thin the wafer down from the back side. The 16 by 16 flexible 2-D arrays presented in this paper have a trench width that varies between 6 and 20 ; the trench depth is 150 ; the membrane thickness is 1.83 ; and the final substrate thickness is 150 . We demonstrate the flexibility of the substrate by wrapping it around a needle tip with a radius of 450 (less than catheter size of 3 French). Measurements in air validate the functionality of the arrays. The 250- by 250- transducer elements have a capacitance of 2.29 to 2.67 pF, and a resonant frequency of 5.0 to 4.3 MHz, for dc bias voltages ranging from 70 to 100 V.     

命题逻辑公式中的冗余子句及冗余文字

主要研究命题逻辑公式中的冗余子句和冗余文字。针对子句集中必需的、有用的、无用的子句,分别给出了一些等价描述方法,进而讨论子句集的无冗余等价子集。另外,得到了子句集中冗余文字的判别方法,借助可满足性给出了冗余子句的一种等价条件。上述结果为命题逻辑公式的化简奠定了一些理论基础。     

双头镜像磁盘的SSTF调度算法

首先简要介绍了双头镜像磁盘系统的研究现状,然后针对双头镜像磁盘系统中传统的先来先服务（ＦＣＦＳ）调度算法提出一种新的调度算法：短寻道时间优先算法（Ｓｈｏｒｔ Ｓｕｅｅｋ－Ｔｉｍｅ Ｆｉｒｓｔ－ＳＳＴＦ）。根据蒙特卡罗模拟实验方法,对双头镜像磁盘系统下的这两种调度算法进行模拟,从模拟实验的结果中定量分析出ＳＳＴＦ调 度算法大大提高了系统的性能。本文还讨论了在该调度算法下,系统的平均寻道时间与Ｉ／Ｏ请     

Gartner 报告显示戴尔居于中端企业级磁盘阵列产品市场领导地位

近日,戴尔公司宣布,根据权威市场研究公司Gartner发表的《Magic Quadrant for Midrange Enterprise Disk Arravs,2H06》报告,戴尔在中端企业级磁盘阵列产品市场中居于领导地位.     

容许两个盘故障的磁盘阵列数据布局与图分解的条件和存在性研究

从一个新的途径讨论容许两个盘故障的磁盘阵列数据布局：把由数据单元和通过“异或”运算得到的校验单元组成的校验组用一个图表示，把校验组容许两个盘故障的阵列布局归结为校验组的单元集合的划分，进而转化为校验组的图的顶点和边组成集合的满足一定条件的分解．证明了校验组容许两个盘故障的单元集合划分的充分必要条件及存在性；讨论了优化阵列布局方案性能的条件；给出了阵列布局的步骤．从而为设计具有最优性能的容许两个盘故障的磁盘阵列数据布局方案提供了有效的途径．     

磁盘缓存技术在硬盘写操作中的应用

本文从软件高速缓存和硬件高速缓存两方面阐述了微机系统中的磁盘缓存技术，特别提出了利用常规硬盘的小部分区域作为Cache磁盘的磁盘缓存技术的应用，将会大幅度的改善硬盘写操作的性能，从而在几乎不增加成本的基础上进一步提高了计算机系统的工作效率。