检索结果-内蒙古大学图书馆

Japan-China Joint Workshop on Frontier of Computer Science and Technology (FCST)

作者： Liang Xiao Qiang Cao Changsheng Xie Chuanwen Wu Key Laboratory of Data Storage System Ministry of Education Wuhan National Laboratory for Optoelectronics Huazhong University of Science and Technology Wuhan China

I/O performance is always the traditional criterion for the evaluation of storage system. Many researches have been being carried on how to improve the storage system performance, mainly focusing on the storage architecture and I/O optimization for the storage devices. In many application systems, the phenomenon of replicating batch small files between two locations widely exists and always represents poor performance in systems. This paper analyzes and optimizes replication process for batch small files in Linux file system. In local case, six algorithms are achieved by using parallel, consecutive and aggregating polices in different stages of the whole process. In network case, achieve and compress strategies are also introduced and compared with aggregating algorithm. Moreover, the average latency of basic operations in each stage of file I/O can be estimated accurately, which is helpful for future research of file system. The experiment shows that the algorithm of consecutive reading source files and parallel writing target files have the best performance in local replication, and aggregating algorithm also do in network replication.

关键词： Delay File systems Educational technology data communication system performance Computer science data storage systems Computer science education Application software Geography

来源：评论

学校读者我要写书评

暂无评论

Scalability Support for SMI-S with Chord

Scalability Support for SMI-S with Chord

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Ze Deng Dan Feng Zhan Shi Chao Luo Key Laboratory of Data Storage System Ministry of Education School of Computer Huazhong University of Science and Technology Wuhan Hubei China

The storage management initiative specification (SMI-S) has been proposed for years to standardize the management of storage resources in storage area network (SAN). However, current management architecture mainly focuses on local area management. In this paper, we propose a scalable management architecture based on the integration of SMI-S and Chord. Meanwhile, Chord can only deal with exact query, the query of storage resources is significantly more complex. To deal with this problem, we further improve our architecture with a scalable blind search method - recursive partition search (RPS). Experiments show RPS is an effective approach for storage resource range query in the case that the Chord overlay network is not very large.

关键词： Computer architecture Computer integrated manufacturing XML databases Scalability storage area networks Partitioning algorithms

来源：评论

学校读者我要写书评

暂无评论

TSPSCDP: A Time-Stamp Continuous data Protection Approach Based on Pipeline Strategy

TSPSCDP: A Time-Stamp Continuous Data Protection Approach Ba...

引用

Japan-China Joint Workshop on Frontier of Computer Science and Technology (FCST)

作者： Jingning Liu Tianming Yang Zuoheng Li Ke Zhou School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Key Laboratory of Data Storage System Ministry of Education China

Traditional cold backup technology can not fight against data loss between two consecutive backups which usually has a time span of 24 hours. Hot backup technology, such as snapshot decreases the amount of potential data loss, but still cannot completely prevent data loss. More recently, a new technology called continuous data protection (CDP) is emerging to provide more powerful data protection. CDP captures every change to the data volume hence can provide any point-in-time data views and enable timely recovery to any point-in-time of user data. However, existing implementations of CDP usually suffer from poor write performance and cannot meet the data protection demand of some high performance application environments. How to improve the CDP performance in terms of write throughput and response time is one of the most important considerations in implementing CDP. This paper presents a time-stamp pipeline strategy continuous data protection approach called TSPSCDP which uses pipeline strategy in write operation of CDP to improve data processing capability. Our experiments demonstrated that TSPSCDP can not only recover data to any point-in-time upon a failure but also improve the CDP performance in terms of write throughput and respond time upon the ordinary CDP by a factor of 2 and about 25% respectively.

关键词： Protection Pipelines File systems Educational technology Throughput Availability Computer science Delay data storage systems Computer science education

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of IP-SAN Based on Third Party Transfer Protocols

Design and Implementation of IP-SAN Based on Third Party Tra...

引用

ISECS International Colloquium on Computing, Communication, Control, and Management, CCCM

作者： MingHua Jiang Ming Hu Jingli Zhou Tao Peng College of Computer Science Wuhan University of Science and Engineering Wuhan China Key Laboratory of Data Storage System Huazhong University of Science and Technology Wuhan China

The IP-SAN based on third party transfer protocols comprises host(s), controller(s) and stores by extending the SCSI-3 transport layer to support distribution application. In the implemented architecture data may be sent directly between host and stores, passing all commands through the controller retains simplicity, relieving the controller communication bottleneck. A prototype IP-SAN using Ethernet and Linux OS with the system implemented in the iSCSI transport layer protocol and in the controller's SCSI application layer, has been constructed. The theoretical analyses indicated that the factors affecting the iSCSI-based storage system including network performance, CRC computation in iSCSI protocol and the performance of the server. The performance test proves that the analysis is right.

关键词： Protocols storage area networks Servers Bandwidth IP networks Ethernet networks Performance evaluation

来源：评论

学校读者我要写书评

暂无评论

Availability Analysis and Evaluation of Flexible Supply Chain system

Availability Analysis and Evaluation of Flexible Supply Chai...

引用

ISECS International Colloquium on Computing, Communication, Control, and Management, CCCM

作者： MingHua Jiang Shuqing Ma Jingli Zhou Ming Hu College of Computer Science Wuhan University of Science and Engineering Wuhan China Key Laboratory of Data Storage System Ministry of Education Huazhong University of Science and Technology Wuhan China

As complexity and demand for new products grow, companies are realizing that their supply chains need to be more flexible. Currently, in supply chain system, users' reliance has driven a universal user expectation that all the information be readily availability whenever and wherever they want. Evaluating and thinking about managing such availability are therefore becoming one of the important factors to improve the performance of the supply chain system. So, how to effectively analyze and evaluate service availability of supply chain system is a challenging problem for investigators. In this paper, the architecture of web-based services of flexible supply chain system is interpreted elaborately, and then an imperfect coverage service model for this system is designed and analyzed exhaustively. The result achieved from this model can help designers find the right tradeoffs for achieving availability of users required while providing acceptable levels of performance.

关键词： Supply chains Availability Servers databases Web server Business Computer architecture

来源：评论

学校读者我要写书评

暂无评论

Research of GFS based digital TV storage system

引用

Wuhan Ligong Daxue Xuebao/Journal of Wuhan University of Technology 2008年第7期30卷 138-140页

作者： Zhang, Kun Xie, Chang-Sheng Key Laboratory of Data Storage System Huazhong University of Science and Technology Wuhan 430074 China

To meet the current digital video storage subsystems on the demand, the paper by analyzing global file system (GFS) of the architecture and proposed to build a file system based on the GFS SAN strategy and implementation, as a video server and storage subsystem performance test. Tests showed that the storage system enhances the sharing of resources and overall performance, video server to meet the high-capacity, high-performance storage requirements.

关键词： Digital video GFS SAN

来源：评论

学校读者我要写书评

暂无评论

EvoRAID: Adaptation to Dynamic Change of Disks in storage system

EvoRAID: Adaptation to Dynamic Change of Disks in Storage Sy...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Yan Liu Chang-Sheng Xie Huai-Yang Li Zhao-bin Liu Key Laboratory of Data Storage System School of Computer Science and Technology Huazhong University of Science and Technology Wuhan Hubei China School of Computer Science and Technology Dalian Maritime University China

The system architecture cannot adapt to the dynamic change of system disks, which is a general problem in traditional storage system. While EvoRAID system, a dynamic storage system we proposed, applies DAA algorithm to cope with three kinds of storage system disk changes - homogeneous disk adding, heterogeneous disk adding, and heterogeneous disk replacement. Simulation results demonstrate that without stopping system I/O service, EvoRAID system can assimilate the adding/replacing homogeneous/heterogeneous disks gradually with little extra system overhead, and achieve optimized storage capacity and I/O performance.

关键词： Computer architecture Heuristic algorithms Distributed databases Process control Software Arrays Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Metadata Management for Distributed Multimedia storage system

Metadata Management for Distributed Multimedia Storage Syste...

引用

International Symposium on Electronic Commerce and Security

作者： Ling Zhan Jiguang Wan Peng Gu Key Laboratory of Data Storage System School of Computer Science and Technology Huazhong University of Science and Technology Wuhan Hubei China School of Electrical Engineering and Computer Science University of Central Florida Orlando FL USA

ISBN: (纸本)9780769532585

As a result of the multimedia rapid growth, there has been a huge increase in the amount of information generated and shared by people all over the world. Demand for large-scale multimedia storage system is growing rapidly. This paper describes the design and implementation of the Two-level metadata server for distributed multimedia storage system (DMSS). The DMSS divides the logical view of the stored data from the physical view. The logical view is managed by the metadata server which is called GMS (global metadata server), and the physical view is managed by a component of storage servers which is called LMS (local metadata server). Adopting LMS, each storage server can maintain its own storage resources and metadata and data independently, and can offer storage service independently. The DMSS allows the application servers to access the storage servers directly and in parallel providing very high performance.

关键词： Servers Multimedia communication Multimedia systems Least squares approximation system performance File systems Heart beat

来源：评论

学校读者我要写书评

暂无评论

High TPO/TCO for data storage:policy,algorithm and early practice

引用

中国高等学校学术文摘·计算机科学 2007年第3期1卷 349-360页

作者： ZENG Lingfang FENG Dan JIANG Hong Key Laboratory of Data Storage System Ministry of EducationSchool of ComputerHuazhong University of Science and TechnologyWuhan 430074China University of Nebraska LincolnUSA

Today,the data storage industry faces a rapidly growing volume of *** more primary disk capacity to manage data growth is a costly and non-sustainable *** investing in new capacity,data managers should rationalize their existing storage infrastructure to maximize the use of existing *** is a growing need for achieving a high ratio of Total Performance of Ownership (TPO) to Total Cost of Ownership (TCO),or TPO/*** storage infrastructure can be made more efficient by assessing data usages,eliminating unnecessary data copies,moving less critical data to less expensive disk devices and repurposing allocated but unused *** existing storage assets can reduce storage costs by delaying or eliminating the need for new primary capacity to manage information *** this paper,we apply the notion of information lifecycle management (ILM) to achieve the above improved efficiencies and *** balancing data value and storage requirements,we aim to reduce the storage system's dependence on expensive high-performance disk devices and lower its cost per online gigabyte,thus resulting in a higher TPO/TCO.

关键词： storage system information lifecycle management data migration energy conservationaccepted June 20 2007

来源：评论

学校读者我要写书评

暂无评论

FPGA/ASIC based cryptographic object store system

FPGA/ASIC based cryptographic object store system

引用

3rd Internationl Symposium on Information Assurance and Security, IAS 2007

作者： Dan, Feng Lanxiang, Chen Lingfang, Zeng Zhongying, Niu Key Laboratory of Data Storage System Huazhong University of Science and Technology Ministry of Education Wuhan China

ISBN: (纸本)0769528767

To avoid re-encryption in cryptographic storage system when revoking users, Field Programmable Gate Array (FPGA) and Application Specific Integrated Circuit (ASIC) hardware module have been introduced to a cryptographic object store system, let private key never leave the hardware module and symmetric key only exist in hardware module in plaintext. Anyone doesn't know private or symmetric key, so when revoking users, it just needs to modify access control list (ACL) to delete the privileges of the users. To facilitate file sharing and key management, group is adopted. In our system, almost all computationally expensive cryptographic operations are through FPGA/ASIC hardware module. Once creator revokes some users, objects don't need re-encryption. How to use ACL and FPGA/ASIC hardware module to authenticate and authorize are described. And the procedure of object store and the distribution of meta-data are detailed. Finally, a cryptographic object store prototype system is implemented with tested and effective performance. © 2007 IEEE.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：