检索结果-内蒙古大学图书馆

International Conference on Machine Learning and Cybernetics (ICMLC)

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

Traditional RAID has the characteristics that location of stripe unit in each disk is stochastic and static, and that the outer zone of the disk has higher data transfer rate as compared to the inner one. Facing this situation, to exploit RAID I/O performance fully, this paper proposes a new algorithm PMSH (placement and migration based on stripe unit heat) for RAID stripe unit data to be placed optically and migrate dynamically. Based on the heat of RAID stripe unit, PMSH keeps migrating the frequently accessed stripe unit to the disk zone with higher data transfer rate, thus optimize the location of data in RAID disks, and make the data distribution adapt to the evolution of file access pattern dynamically as well. Simulation results demonstrate significant RAID I/O performance improvement using PMSH.

关键词： File systems Heat transfer Disk drives Disk recording Angular velocity Performance analysis Laboratories data storage systems Computer science Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

The approximate parameters analysis of mS/spl ***/RAID

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

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

In order to overcome the problem of making choice configuration parameters of RAID, we bring out mS/spl ***/RAID. A key problem for it is how to choose the optimal stripe unit size. However, till now this issue is not solved, especially under synchronous workload, because of the complexity about read-write of RAID and closed fork-join queue network. In this paper, we first present a read-write model of disk array under little and large I/O requests based on closed fork-join queue network model and analyze read-write action in RAID, and then deduce a approximately analytical expression to predict disk array's the mean response time under variety workload parameters designed to emulate real world condition. According to the analytical expression, we can get optimal stripe unit size under minimum mean response time. Finally, a large number of simulations have been carried out to validate our analytical result.

关键词： Predictive models Delay Queueing analysis Analytical models Laboratories data storage systems Computer science Bandwidth Parallel processing data communication

来源：评论

学校读者我要写书评

暂无评论

Object replication and migration policy based on OSS

Object replication and migration policy based on OSS

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Ling-Fang Zeng Dan Feng Fang Wang Ke Zhou Key Laboratory of Data Storage System Ministry of Education School of Computer Huazhong University of Science and Technology Wuhan Hubei China

It obviously gets limited advantage in massive storage system that all the management works are done by the servers, such as file server and metadata server of traditional storage area network (SAN). Moreover, storage device with deficient intelligence leads to lack of supporting local policy and does not scale well in performance and functionality when the number of storage device is added. At the same time, servers, e.g. metadata servers, are easy turned into bottlenecks when load balancing policies only depend on servers to scheme. This paper studied object storage system (OSS) which is a novel solution for massive storage. And the whole object storage system is divided into some domains. Each domain has its own metadata server, object storage controllers and clients (or application servers). Load balancing policies, involved three facets: metadata server (based on globe), object storage controller (based on local) and object, are presented.

关键词： File servers Network servers Load management Peer to peer computing Computer networks Scalability storage area networks Intelligent networks Proposals Laboratories

来源：评论

学校读者我要写书评

暂无评论

A Strategy of Load Balancing in Object storage system

A Strategy of Load Balancing in Object Storage System

引用

International Conference on Computer and Information Technology (CIT)

作者： Lingfang Zeng Dan Feng Fang Wang Ke Zhou Key Laboratory of Data Storage System Ministry of Education School of Computer Huazhong University of Science and Technology Wuhan Hubei China

ISBN: (纸本)076952432X

Most of traditional load balancing strategies are based on servers or applications architecture. storage subsystem, as the back tier, provides file or block interface to server or application tier, is often ignored when the bottleneck of service is studied. Our load balancing strategy is based on storage object, which provides object interface for the up tier. We concentrate on storage objects with massive dynamic processing. The characteristics of storage object in object storage system (OSS) enable us to apply our load balancing strategy at the back end of servers or applications in order to deal with bottlenecks at the storage tier in data-intensive applications

关键词： Load management Application software File servers Network servers Back Biology computing Distributed computing Biological system modeling Predictive models data storage systems

来源：评论

学校读者我要写书评

暂无评论

An intelligent prefetching strategy for a data grid prototype system

An intelligent prefetching strategy for a data grid prototyp...

引用

International Conference on Wireless Communications, Networking and Mobile Computing (WiCom)

作者： Jianxi Chen Dan Feng Key Laboratory of Data Storage System Ministry of Education College of Computer Science & Technology Huazhong University of Science and Technology Wuhan China

An amount of data-intensive applications pay more attention to the performance of storage system. Prefetching is an efficient approach to improve the I/O performance. The present algorithms of prefetching have some limitations and cannot suit for some kinds of access patterns. Intelligent prefetching strategy can recognize the current access pattern by analyzing the access trace independently. Prefetching based on the pattern recognized is more effective than blindly prefetching. Using this algorithm in a VI-based data grid prototype system (VI-DGPS), the storage nodes is divided into groups by the relation of the data, only one node judges the pattern and all other nodes just receive the pattern info in a group. All nodes in a group prefetch synchronously based on the access pattern to reduce the request response time. Test result shows that the strategy has a good performance in our system.

关键词： Prefetching Prototypes Educational technology Pattern recognition Delay system testing Laboratories data storage systems Computer science education Computer science

来源：评论

学校读者我要写书评

暂无评论

The NDMP-plus prototype design and implementation for network based data management

引用

IFIP International Conference on Network and Parallel Computing, NPC 2004

作者： Ouyang, Kai Zhou, Jingli Xia, Tao Yu, Shengsheng Key Laboratory of Data Storage System Ministry of Education Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)3540233881

Network based data management/backup/restore is the key component in the data storage centre. This paper proposes a new network based data management --- NDMP-Plus. We firstly discuss the components of the NDMP-Plus architecture. Then, we detail two new techniques in NDMP-Plus --- VSL (Virtual storage Layer) and the negotiation mechanism. VSL is the core component to implement the flexibility, which could avoid the network communication with the storage media directly. And the negotiation mechanism is the key mechanism to improve the performance. Furthermore, we carry out an experiment to evaluate the performance of NDMP-Plus. The result of it suggests that NDMP-Plus has stronger flexibility and higher performance than the original NDMP. © IFIP International Federation for Information Processing 2004.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

A scalable object-based intelligent storage device

A scalable object-based intelligent storage device

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： D. Feng Ling-Jun Qin Ling-Fang Zeng Qun Liu Key Laboratory of Data Storage System Ministry of Education School of Computer Huazhong University of Science and Technology Wuhan China

A scalable object-based intelligent storage device (SOID) is presented in this paper. A scalable way of describing the object attributes of SOID is discussed and is adaptive to many application fields. In the SOID system, the users can register and upload methods at the device and associate an object with a chain of methods. Any kind of operations on objects can be performed by the method chains which are executed by taking the object as an input stream in a SOID. The SOID has also explored two promising enhancements: object-based interface and embedded computational capabilities. It improves the scalability of storage system.

关键词： Computational intelligence Computer architecture Streaming media Computer interfaces Embedded computing Intelligent networks Laboratories data storage systems Computer science education Educational technology

来源：评论

学校读者我要写书评

暂无评论

SOSS: smart object-based storage system

SOSS: smart object-based storage system

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Ling-Fang Zeng Dan Feng Ling-Jun Qin Key Laboratory of Data Storage System Ministry of Education School of Computer Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)0780384032

Hints for storage system come from three aspects: the first is in combination with accurate file or directory attribute layout. The second is from existing file system and depends on user input. The third is from file content analysis. However in the SOSS (smart object-based storage system), object, a new fundamental storage component different from traditional storage unit (file or block), is introduced, and object provides ample hints for storage system, which can help with designing more intelligent (or smarter) storage system. This paper gives a brief introduction about SOSS, and some methods adopted in SOSS to achieve intelligence, such as pattern recognition method, predicting object properties method and an adaptive cache replacement policy (all are based on object attribute), are studied.

关键词： Pattern recognition Intelligent networks Fabrics storage automation File systems Laboratories data storage systems Computer science education Educational technology Cache storage

来源：评论

学校读者我要写书评

暂无评论

Mathematical properties of four wavelet filters and their performance in embedded image coders

Mathematical properties of four wavelet filters and their pe...

引用

International Conference on Signal Processing Proceedings (ICSP)

作者： Guo Hongxing Su Lei Yu Shengsheng Zhou Jingli Department of Computer Science and Engineering Key Laboratory of Data Storage System of Ministry of Education Huazhong University of Science and Technology Wuhan Hubei China

This paper analyses the mathematical properties of four famous wavelets and evaluates their coding performance for different kinds of images in EZW image coders. It can be found that although the 9/7 biorthogonal wavelets, which obtain better tradeoff among incompatible mathematical properties, give the best performance. But it still can't code edges and textures efficiently due to existing ringing and smearing artifacts at low bit rates. The harmonic decomposition must follow the uncertainty principle that prevents any atom perfectly, which is well localized in the space domain to retain frequency localization. It gives an opportunity to develop new paradigms to efficiently representing and coding structures very well localized in the space domain, but with large frequency band such as edges and textures.

关键词： Wavelet analysis Low pass filters Image coding Filter bank Image analysis Frequency Computer science data storage systems Computer science education Bit rate

来源：评论

学校读者我要写书评

暂无评论

Research of the Streaming Media system Architecture Based on Net-RAID

引用

Wuhan University Journal of Natural Sciences 2003年第4A期8卷 1081-1084页

作者： Deng Yu-hui, Zhang Jiang-ling, Feng Dan key laboratory of data storage system,Ministry of Education, Huazhong University of Science and Technology, Wuhan 430074,Hubei, China Huazhong University of Science and Technology Key Laboratory of Data Storage System Ministry of Education Wuhan Hubei China (GRID:grid.33199.31) (ISNI:***)

In the typical streaming media system, the streaming media server is system bottleneck with the expansion of Internet subscribers. This paper proposes an innovational high performance streaming media system architecture (HPSMS) based on the logical separation of streaming media transport protocol. The system avoids expensive store-and-forward data copies between streaming media server and storage devices, improves the system performance greatly. The system bandwidth continuously increases with the expansion of storage system capacity is the highlight. The performance of the proposed HPSMS is evaluated through a practical prototype implementation.

关键词： streaming media system RTP/RTCP system architecture Net-RAID

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：