Search

Transparent file encryption is an important means to protect file data security. However, for the traditional file encryption system based on file filter driver, constant cache cleaning is required to ensure the correctness of the data in the cache, which greatly reduces the efficiency of file operations. In the paper, a transparent file encryption system based on FUSE (File System in User Space) is proposed to overcome the shortcomings of the traditional transparent file encryption systems. To avoid cleaning the system file cache frequently, file redirection is adopted to transfer file operations to FUSE, which processes the file operations initiated by the trusted processes and non-trusted processes differently, with respect to cache. This system can not only be used for local file protection, but can also be applied to secure the files on cloud storages.

A new backup method, which achieves on-demand restore as part of file system backup to object storage, is proposed. On-demand restore is a function that restores only a certain directory or file according to the request from an end user. The proposed method backs up relationships between a file and an object on a directory basis in order to efficiently handle the relationships in the restore. It is experimentally shown that the proposed method reduces the response time of file access involving restore by over an order of magnitude.

The performance of a distributed file system is defined by its hardware components, as well as its operational parameters. Even a slight change on a working condition may induce the major impact, for instance, on service response times. In this paper, we propose a set of experiments on the Babel file system using a client that sends requests for either file storage or retrieval, with two file sizes (512 MB and 1 GB). The aim is to achieve the best working conditions. To measure the performance of the Babel system we took the throughput and the response time when any of two operations (storage or retrieval) was running. The analysis of results showed that, for a given set of operational parameters, there is an optimal file size that gets the best out of the system's performance.

Inspired by D2D communication which is regarded as one of the potential technology in the next generation of wireless communication, we propose a novel framework in which cluster head might update cache file and the user acquire a file under the eNB guidance. The content cluster update deployment method is based on device-to-device (D2D) system, where the devices have cached video files from a media cloud. Moreover, each device downloads file from some other devices nearby through a direct link or multi-hop without going through eNB. In particular, we describe the physical layer as a simple "protocol-model", without interference. The highlights of this work lie in defining the cluster selecting, update file methods and shortest multi-hop problem and analyzing this method according simulation result.

With the further development of the Internet, the amount of data on the network grows exponentially in recent years. While the fastest increasing objects are the mass small files from blogs, forums, etc. Master/Slave structure distributed file systems have some shortcomings, such as the poor access performance with small files, single-point bottlenecks, etc. Although these problems have been solved in the P2P structure distributed file system to some extent, there is still some improvement room of accessing performance for small files in the P2P structure distributed file system, so a small file merging strategy(SFMS) is proposed in this paper. The throughput rate of reading small files is increased significantly. Experiments show that the throughput rate of reading small files is increased by 90% compared with the original system, and 25 times higher than the TFS which is based on Master/Slave structure.

This paper proposes a massive Remote sensing tile data organization and management strategy based on file tree. The storage rule of tree-structured file directory is: root directory\ tile pyramid hierarchy\subdirectory\tile file data. Here, subdirectory is dynamically created by the strategy of alternating growth. The strategy can maintenance a dynamic balance between subdirectory numbers and file numbers under tile directory hierarchy. However, there are some problems need to be elaborated.

This paper describes a strategy to optimize small file's reading and writing performance on traditional distributed file system. Traditional distributed file system like GlusterFS stores data within local file system (XFS, EXT3, EXT4, etc.), which shows a significant bottleneck on file metadata lookup. We try to re-design metadata structure by merging small file into large file, thus to reduce size of metadata, so we can store the whole files' metadata inside main memory. We design and implement the whole strategy on GlusterFS, test results show a great performance optimization on small file operation.

The File Allocation Table (FAT) file system is widely used file system in tablet personal computers, mobile phones, digital cameras and other embedded devices for data storage and multi-media applications such as video imaging, audio/video playback and recording. The FAT file system is not power fail-safe. This means that, the uncontrolled power loss or abrupt removal of storage device from computer/embedded system causes the file system corruption. The TFAT (Transaction safe FAT) file system is an extension of FAT file system to provide power fail-safe feature to the FAT file system. This paper explores the design methodologies of cluster allocation algorithms of TFAT file system by conducting various combinations of file system operations in Windows CE (Compact Embedded) 6.0 Operating System (OS). This paper also records the performance bench-marking of TFAT file system in comparison with FAT File system.

In this research, we designed and implemented Real-World File System (RWFS), which can manage files as if we can put them onto or pick them up from the places of the real world. RWFS regards the places of the real world as directories of the file system by associating a directory with a place. We create directories called Real-World Directory (RWD) which forms a hierarchical structure to reflect the natural property of places. In addition to the conventional access rights of read, write, and execute as implemented in other file systems, RWFS accommodates utilizing location information of the target user in access rights; RWFS can decide whether or not the user can access to a particular file or directory based on the user's location. Therefore, accessible files for a user change depending on the user's location. This mechanism enables creating information that can be read or written by users who physically stay at a particular place. We evaluated this system by measuring turnaround time to operate the file system together with simulation.

Distributed storage systems have greatly evolveddue to cloud computing upsurge in the past several years. Thedistributed file systems inherit many components fromcentralized ones and use them in a distributed manner. There aretwo ways to grow the storage capacity: by scaling-up or byscaling-out and growing the number of storage devices in astorage system. The growth of storage devices impose manychallenges related to interconnection protocols and topologies,error handling, data consistency, security and so on. In thisarticle we have studied how distributed and parallel storageshave evolved from direct connected storages in terms ofarchitecture, data management and organization and how thenew challenges imposed by data distribution have been solved.We have selected for studying several of the most representativedistributed storages solutions: Andrew File System, Google FileSystem, General Parallel File System, Lustre and Ceph. First, weemphasize how a generic distributed storage layout has inspiredfrom structured disk layout (Berkeley Fast File System). Second,we describe the evolution path of distributed storages from awide variety of perspectives, including: distributed units whichare moving from blocks to objects due to their undeniableadvantages or distribution methods that have evolved from listsmuch like inode mapping to deterministic hash functions likeRUSH or CRUSH. Third, the networks are evolving very fast interms of topologies and protocols. Using graph theory,researchers are continuously improving different aspects ofcluster networks. Fourth, storage security is a critical componentdue to the demand of storing sensitive data for long term, sharingit in a secure way and impacting as little as possible the systemperformance.

In this paper, we propose the architecture of a wide area file service infrastructure, called I-Shadow. I-Shadow can provide both short delay file access and dependable file management for mobile users by using a set of active rules. We also show that average file access time of I-Shadow is shorter than that of cache based Coda distributed file system through a simulation study.

MemFS is a fully-symmetrical, in-memory distributed runtime file system. Its design is based on uniformly distributing file stripes across the storage nodes belonging to an application by means of a distributed hash function, purposefully sacrificing data locality for balancing both network traffic and memory consumption. This way, reading and writing files can benefit from full network bisection bandwidth, while data distribution is balanced across the storage servers.

A file system is used for the organization, storage, retrieval, naming, sharing, and protection of files. Distributed file system has certain degrees of transparency to the user and the system such as access transparency, [2] location transparency, failure transparency, heterogeneity, replication transparency etc. [1][2] NFS (Network File System), RFS (Remote File Sharing), Andrew File System (AFS) are examples of Distributed file system. Distributed file systems are generally used for cloud computing applications based on [4] the MapReduce programming model. A MapReduce program consist of a Map () procedure that performs filtering and a Reduce () procedure that performs a summary operation. However, in a cloud computing environment, sometimes failure is occurs and nodes may be upgraded, replaced, and added in the system. Therefore load imbalanced problem arises. To solve this problem, load rebalancing algorithm is implemented in this paper so that central node should not overloaded. The implementation is done in hadoop distributed file system. As apache hadoop is used, security issues are arises. To solve these security issues and to increase security, [17]Kerberos authentication protocol is implemented to handle multiple nodes. This paper shows real time implementation experiment on cluster.

The processing of massive small files is a challenge in the design of distributed file systems. Currently, the combined-block-storage approach is prevalent. However, the approach employs traditional file systems like ExtFS and may cause inefficiency for random access to small files. This paper focuses on optimizing the performance of data servers in accessing massive small files. We present a Flat Lightweight File System (iFlatLFS) to manage small files, which is based on a simple metadata scheme and a flat storage architecture. iFlatLFS aims to substitute the traditional file system on data servers that are mainly used to store small files, and it can greatly simplify the original data access procedure. The new metadata proposed in this paper occupies only a fraction of the original metadata size based on traditional file systems. We have implemented iFlatLFS in CentOS 5.5 and integrated it into an open source Distributed File System (DFS), called Taobao FileSystem (TFS), which is developed by a top B2C service provider, Alibaba, in China and is managing over 28.6 billion small photos. We have conducted extensive experiments to verify the performance of iFlatLFS. The results show that when the file size ranges from 1KB to 64KB, iFlatLFS is faster than Ext4 by 48% and 54% on average for random read and write in the DFS environment, respectively. Moreover, after iFlatLFS is integrated into TFS, iFlatLFS-based TFS is faster than the existing Ext4-based TFS by 45% and 49% on average for random read access and hybrid access (the mix of read and write accesses), respectively.

File Transfer Protocol is the most popular file transfer standard. This FTP can let a computer system connect to the internet via a communication network, and it can also access the system resources from the internet. File server is being downloaded now by TCP/IP protocol, while before it was downloaded by signal server. Due to the limited flow control, the old method could not use download time efficiently. In order to solve the flow control problem, some researchers came up with a distributed file transfer method that can share the document with other users, thus allowing the shortest transfer time using neighboring servers. Although the distributed file transfer can reduce the file transfer time, it was not concerned with the quality of the transfer between two servers, and was inappropriate for file segmentation and transfer, so the file transfer could not attain the optimal transfer efficacy. Based on our research, we propose a new method called Distributed Parallelized File Transfer Protocol (DPFTP). This method is based on Parallelized File Transfer Protocol (P-FTP) and is beneficial to multi-users, as it utilizes server loading and reduces the download time.

The Network File System (NFS) is one of the most popular remote file system protocols for accessing directories and files over the network. If NFS mount point has thousands of files (e.g. a directory containing 5000 files), there is a significant performance drop in directory browsing (traverse, open(), stat() and read()) time as compared to local file system browsing (traverse, open(), stat() and read()) time. In order to reduce the file browsing time in the NFS with single client system, this paper presents the modification of a conventional NFS protocol usage with multiple client systems. Experimental results show the proposed implementation gives 44.6% performance improvement over a conventional one.

As a consequence of voluminous growth and proliferation of digital data, the file system size and count limitations have become problematic. The fact is that file systems use fixed length fields within their metadata structures to keep track of volume size, file size and file count, and hence need design (and source) modification to cope up with this growth. In this paper, we propose a Scalable User-space Virtual File System, namely suvfs, which when mounted on top of any file system extends its capability to store and process large files not natively supported by the file system. It works by exploiting the concept of virtual unification to present a large virtual file that spans over a number of legitimate sized physical files. It does so without modifying user applications, system libraries, system calls and even file systems. We implemented it using FUSE framework & evaluated it for performance overhead added by layering it over FAT32 file system. The results indicate that there is a very minimal performance hit encountered by FAT32 with suvfs mounted on top for sequential reading, while as for sequential writing & deletion the performance hit increases with file size but is largely due to FUSE framework & not by suvfs.

To deal with the challenge of the storage of mass data, we provide a kind of distributed file system to store the small images which size are under 100KB. For these huge amounts of data, a centralized file system can't meet the storage requirement. It is necessary to ensure the storage efficiency and fault-tolerant rate. Nowadays, most images which stored on the internet are very small. For these images, an efficient storage system and a management method are also crying needs. Similarly, how to retrieve the image effectively and how to classify the images are also challenges. So we aim at design a proprietary small images storage system based on distributed file system. Meanwhile, we contrast our distribution file system with HDFS and show the effectiveness's promotion.

Understanding the inherent system characteristics is crucial to the design and optimization of cloud storage system, and few studies have systematically investigated its data characteristics and access patterns. This paper presents an analysis of file system snapshot and five-month access trace of a campus cloud storage system that has been deployed on Tsinghua campus for three years. The system provides online storage and data sharing services for more than 19,000 students and 500 student groups. We report several data characteristics including file size and file type, as well as some access patterns, including read/write ratio, read-write dependency and daily traffic. We find that there are many differences between cloud storage system and traditional file systems: our cloud storage system has larger file sizes, lower read/write ratio, and smaller set of active files than those of a typical traditional file system. With a trace-driven simulation, we find that the cache efficiency can be improved by 5 times using the guidance from our observations.

With the development of network storage systems, distributed file system has become more and more important. In the storage of the large and medium-sized websites, requirement of storage with mass small file is of extremely importance, especially the small pictures, electronic documents and some other kind of small files. Considering the extremely large number of small files, if we choose the traditional distributed file system without additional improvement, the efficiency will be greatly reduced. QFS is such a distributed file system that focuses on storage of massive small files. The file system has made great improvements in many aspects such as the metadata management, high concurrency access, storage efficiency. Moreover, its design is simple and efficient.

File sharing is a common basic requirement when the users work on a particular domain or area of interest. We have designed and implemented an application that utilizes the concepts of distributed computing and provides with the necessary functionality of remote file sharing and accessing where the files of interest are distributed across the network but the users have an illusion of a centralized file system and access them accordingly. The overall focus is on location and access transparency along with the utilization of a fault tolerance mechanism.

Modern distributed file systems can store huge amounts of information while retaining the benefits of high reliability and performance. Many of these systems are prototyped with FUSE, a popular framework for implementing user-level file systems. Unfortunately, when these systems are mounted on a client that uses FUSE, they suffer from I/O overhead caused by extra memory copies and context switches during local file access. Overhead imposed by FUSE on file systems is not small and becomes more pronounced during local file access. This overhead may significantly degrade the performance of data-intensive applications running with distributed file systems that aggressively use local storage. In this paper, we propose a mechanism that achieves rapid local file access in FUSE-based distributed file systems by reducing the number of memory copies and context switches. We then incorporate the mechanism into the FUSE framework and demonstrate its effectiveness through experiments, using the Gfarm distributed file system.

We have investigated the workload of a campus wide distributed file service. The observation is that hot files are downloaded many times within a short period of time. To reduce the server overhead, we employed a client side cooperation module in the system. The client side cooperation module can get file data from other clients instead of directly download data from data servers. The applied mechanism can significantly reduce server load that is critical to system scalability. Thus, this distributed file service can support more users with the same amount of servers while keeping or improving user experiences. We verified the proposed mechanism in the file service system with over 5000 registered users. Results show that, in the environment of campus network, server load can be reduced by up to 30%. The chunk response latency can be reduced by 90% percent and gives a significant boost to the client side download speed.

Cloud storage is one of the underlying services in cloud computing. However, there are some critical issues in file storage which should be resolved urgently, such as the blocking file storage. In order to solve the shortages of hot file storage and parallel computing support issues in fixed-blocking storage, we propose a smart-blocking file storage method in this paper. By setting up 6 grouping factors, the method can determine whether the file should be blocked or not automatically depending on the size of the file and the client bandwidth. The proposed method can block the file into similar size sub-blocks as large as possible when the file is judged to be blocked. Normally the size of the last sub-block is smaller than other similar sub-blocks. But the gap maintains within the size of the next smaller grouping factor. The Metadata server can address the hot files when the file is blocked. In addition, the proposed method also defines the file uniformity and the system uniformity to quantitatively describe the uniformity of sub-blocks in the file and in the whole system. Analysis and simulation demonstrate the proposed method has better system uniformity in file storage, the node load balance caused by hot file, and a large number of file fragments reduction.

We have developed a mobility prediction algorithm that reflects in a customized AODV designed for k-hop dominating set file sharing scenario. Mobility of a node is detected based on the received signal strength (RSS) measurements. This measurement serve as a basis for a client to associate with nearest dominating node (file server) to always have access to the files. Our proposed mechanism ensures file availability, reduces the latency to access the shared files hence suitable for time critical applications.

This paper proposes Block Link(BL) file system which provides high-speed multimedia files editing and storing technique. When editing and storing large-scale multimedia files, the BL file system does not need data I/O, needs only modification of the metadata. In addition, by sharing data blocks among multimedia files, the BL file system can save storage space. The BL file system is based on Ext3 file system and implemented in a Linux environment, and the usefulness of the BL file system is validated by applying the Linux multimedia file-editing tool ‘Avidemux’.

Recently, the concept of distributed file system has been widely used in many Internet applications. A distributed file system integrates many file servers on the network and becomes an efficiency file system with large storage space. Users can access their files anytime and anywhere. However, the cost for building and maintaining these storage systems is high for many small enterprises and organizations. Thus, a reliable file system with low cost and large storage space is necessary for many users. In this paper, we proposed a low cost distributed file system. The proposed file system stores the file replications in different network area. We also design a load detection module in the proposed system. The module will detect the load of each file servers and improve the overall system performance.

This paper introduces the technology of transparent file encryption based on network file system filtering driver and how it works. The method can be used for confidential data of network File System transparent encryption and decryption, and ensure the information security of Network File System. File protected system software based on file system filter driver is security, efficacious, easycost, extensible, maintenance-free and device-independent. A method is given based on the operating system:windows 2000/xp.

We propose a random-walk-based file search for unstructured P2P networks. In the proposal, each node keeps two pieces of information, one is on the hop-limited shortest path tree rooted at itself and the other is on the indexes of files owned by neighbor nodes, referred to as the file list. A random-walk search is conducted along the concatenation of hop limited shortest path trees. To find a file, a node first checks its file list. If the requested file is found in the list, the node sends the file request message to the file owner, otherwise, it sends a file-search message to a randomly-selected leaf node on the hop-limited shortest path trees. Numerical examples show that our proposal is much more efficient than the normal random-walk search, while it waists much less network bandwidth than the flooding (network-broadcast) based search.

In the paper, a system known as FTWN (File Transfer in Wireless Networks Environment) is developed. In wireless networks, sending a large file above 100 MB is a big issue. The problem is solved by the system developed using JAVA. In this system FTP is used to transfer file. The transfer time is recorded and found to be very useful in wireless system.

As storage capacity in CE devices has been increased, the number and type of files has been increased accordingly. But traditional file systems generally use hierarchical directory/file structure to organize files. When we want to store and retrieve a file, we should know the name and location of the file exactly. And only one access path can be allowed to users. These file systems are not adequate to manage files of portable storage. We present WebFS to effectively manage files stored in mobile storage and to provide users with a convenient way to retrieve files. WebFS represents complicated information of files by using extended file metadata and provides various and effective way to access files by using inter-file relationships among files.

Peer-to-peer networks are a popular means of obtaining large files. Network coding has been shown as an efficient means of sharing large files in a P2P network. With network coding, all file blocks have the same relative importance. This paper presents Deluge, which uses network coding to share large files in a P2P overlay running on a MANET. Peers request file blocks from multiple server nodes and servers multicast blocks to multiple receivers, providing efficient multipoint-to-multipoint communication. Simulation results show that compared to other common download techniques, Deluge performs very well, having low download time and low energy consumption. Further, more peers participate in uploading the file and the performance of Deluge varies little with increasing overlay size, indicating good scalability.

This paper designed and realized a P2P file sharing system (FSP2P) by using Java network programming. An adapter was contained in FSP2P. By using the adapter, FSP2P not only can be array to pure IPv4 or IPv6 network, but also can be array to IPv4/IPv6 coexistent network. So, it realized transparent connect between IPv4 and IPv6 in P2P file sharing system.

In 1989, the RAID (Redundant Arrays of Inexpensive Disks) group at U. C. Berkeley built a prototype disk array called RAID-I. The bandwidth achieved by RAID-I was severely limited by the memory system bandwidth of the disk array's host workstation. As a result, most of the bandwidth available from the disks could not be delivered to clients of the RAID-I file server. We designed our second prototype, RAID-II, to deliver more of the disk array bandwidth to file server clients. A custom-built crossbar memory system called the XBUS board connects the disks directly to the high-speed network, allowing data for large requests to bypass the server workstation. A single workstation can control several XBUS boards for increased bandwidth. RAID-II runs the Log-Structured File System (LFS) software to optimize performance for bandwidth-intensive applications. The RAID-II hardware with a single XBUS controller board delivers 20 megabytes/second of raw I/O between 24 disks and the high-speed network for large, random read operations and up to 31 megabytes/second for sequential read operations. This is an order of magnitude better than our first prototype, but lower than our performance goal of 40 megabytes/second because of lower-than-expected performance of the commercial disk controller boards and our disk system interfaces. A preliminary implementation of LFS software on RAID-II configured with 24 disks delivers 13.4 megabytes/second on large read requests.

This paper presents VIRGO_DFS, a framework of distributed file system based on virtual hierarchical tree Grid organizations(VIRGO) p2p network. The directory servers(DS) construct n-tuple virtual hierarchical overlay network. Because of the cached addresses of directory servers, the overload of traffic in tree structure canbe avoided. This strategy can construct virtually huge volumes of file storage by connecting billions of computers. It may enhance stability against file servers' crash down. It also makes file operation totally transparent.

To share and exchange the files among Internet users, peer-to-peer (P2P) applications build another layer of overlay networks on top of the Internet infrastructure. In P2P file sharing systems, a file request takes two steps. First, a routing message is generated by the client (request initiator) and spread to the overlay network. After the process finishes, the location information of the requested file is returned to the client. In the second step, the client establishes direct connection(s) with the peer(s) who store a copy of that file to start the retrieving process. While numerous research projects have been conducted to design efficient, high-performance routing algorithms, few work concentrated on file retrieving performance. In this paper, we propose a novel and efficient algorithm - PROD to improve the file retrieving performance in DHT based overlay networks. In PROD, when a file or a portion of a file is transferred from a source peer to the client, instead of creating just one direct link between these two peers, we build an application level connection chain. Along the chain, multiple network links are established. Each intermediate peer on this chain uses a store-and-forward mechanism for the data transfer. PROD also introduces a novel topological based strategy to choose these peers and guarantees the transmission delay of each intermediate link is much lower than the direct link. We conducted extensive simulation experiments and the results shown that PROD can greatly reduce the transfer time per file in DHT base P2P systems.

This paper presents a new probabilistic model which describes the way data blocks belonging to a certain file are distributed along the disk in general purpose systems. The distribution type is classified depending on the kind of file system, the file size and the disk occupancy ratio. The resulting algorithm will be used to simulate the access time to the data stored on a disk of an I/O node, where the position of data blocks determines the access time. In order to perform the modeling, some parameters have been estimated using some stress tests with different degrees of disk occupancy and file sizes on Ext2 and ReiserFS file systems.

Most traditional cluster file systems replicate whole files to support the data availability. However, considering that the access patterns of file systems have high localities, replicating whole files is not an efficient strategy to improve the data availability. This paper presents the design and the implementation of HA-PVFS, a PVFS supporting high data availability, in which the replication is performed partially based on the locality information. Our performance results show that HA-PVFS is dynamic with little overhead over various access patterns.

We designed and implemented MSFSS, a scalable and flexible distributed file system for storage and retrieval of mass small files. MSFSS is a platform built upon the existing commodity file systems. It automatically stores files onto the best-fit commodity file systems according their access patterns. To avoid central bottleneck, it optimizes metadata size, separates metadata operations from file data transfer, and implements batch metadata operations. The system provides data migration, hot file caching, and replication, which are essential for large scale, reliable storage systems. It has successfully been deployed as storage system for our Web application which has about 50 TB of small files. Experimental results show that MSFSS provides high scalability and throughput in file operation services.

We propose a fluid model for eMule-like file sharing systems. The analytical analysis of a two file system is presented followed by the numerical analysis of a n-file system. We show the influence of the parameters such as the storage probability of a file and the request rate for a file on the system performance, i.e., on average downloading times. Our results reveal that the uploading policy, which equally treats each request, is not appropriate and that it introduces unfairness in the system. Afterwards, we discuss the optimal uploading policy on peers, i.e., which part of the uploading bandwidth should be dedicated to each shared file on a peer in order to improve the fairness in the system

According to the development of the object based storage device (OSD) and networking technologies, some OSD based clustering file systems, for example, the ActiveScale storage cluster of the Panasas Corp. and the Lustre file system of the Cluster File System Corp., are emerging in the marketplace. Typically, these systems connect multiple OSDs on the fast network. When a large number of OSDs are connected as a linear style configuration, a client machine stores a file in its local memory first and then flushes it into an OSD. However, the file stored temporarily in the client's memory may not be completely stored in the selected OSD because the size of the file can be bigger than that of the OSD's available space. In this paper, we propose a detailed algorithm and system structure for solving this problem occurring in the cluster file system using OSDs.

The EXT3NS is a file system based on a special HIW device, called NS card for multimedia data. In general, normal computer has high level of CPU utilization for networking operations with gigabit level and several copy operations. Therefore, we have developed the NS card to alleviate this overhead. EXT3NS provides the standard API's to read and write files in storage unit of NS card. The performance measurements on our system show obvious performance improvements. Especially, the system shows much less server's CPU utilization and less fluctuation of client bitrate, hence more reliable streaming service is possible.

This paper proposes an efficient algorithm for P2P file sharing systems based on WiMAX mesh mode and Wi-Fi technologies. Wireless networks in our system are hierarchically divided into three layers: Wi-Fi based wireless local area networks under a subscriber station; the mesh network of subscriber stations under a base station; the network of base stations. File lookup procedure may go through three steps: the requesting end host firstly looks up for the requested file within it's neighbor end hosts under the same subscribe station; if fails, then it sends lookup messages to the nearest subscriber stations in the mesh network following to a changed dynamic source routing protocol; if both the steps fail, then the requesting end host searches the requested file through the Chord-based base stations' overlay. By statistical analysis and simulations, we prove that our layered P2P file sharing system can reduce the number of lookup messages in physical networks and prevent over expenses of precious bandwidth in wireless metropolitan area networks.

We are going to demonstrate two functionalities about the shared rapid file system on Ethernet. One is throughput and the other is "user ID mapping ". Shared rapid file system was originally implemented on our HPC system named numerical simulator 111 that has crossbar interconnection network. During this demonstration, we would like to discuss about a file server allocation concept, namely what is the difference between "central file system " and "distributed file system", and what kind of application and HPC system fit these file systems and so on.

With the increasing number of applications and their variety, the need to prevent unauthorized disclosure of data and to ensure data integrity in distributed systems has led to a heavy reliance on encryption. Typically, the encryption process operates at file or directory level and applies indiscriminately one algorithm to all the data in a file. In this paper, a distributed scheme is proposed whereby secrecy is achieved through file data concealment and file location concealment, within a network of nodes. This involves first the division of a file into fragments, which are encrypted by applying different algorithms; second the random distribution of these fragments to connected nodes, third the generation of metadata for reconstructing the original file and its commitment to a physical medium and finally the deletion of both the original file and its metadata from the local node. Access to the metadata is the only way of retrieving the original file. An evaluation of the scheme is presented with some performance results.

An efficient and distributed scheme for file mapping or file lookup scheme is critical in decentralizing metadata management within a group of metadata servers. This work presents a technique called HBA (hierarchical Bloom filter arrays) to map file names to the servers holding their metadata. Two levels of probabilistic arrays, i.e., Bloom filter arrays, with different accuracies are used on each metadata server. One array, with lower accuracy and representing the distribution of the entire metadata, trades accuracy for significantly reduced memory overhead, while the other array, with higher accuracy, caches partial distribution information and exploits the temporal locality of file access patterns. Extensive trace-driven simulations have shown our HBA design to be highly effective and efficient in improving performance and scalability of file systems in clusters with 1,000 to 10,000 nodes (or superclusters).

We have designed a stackable file system called Redundant Array of Independent Filesystems (RAIF). It combines the data survivability properties and performance benefits of traditional RAIDs with the unprecedented flexibility of composition, improved security, and ease of development of stackable file systems. RAIF can be mounted on top of any combination of other file systems including network, distributed, disk-based, and memory-based file systems. Existing encryption, compression, antivirus, and consistency checking stackable file systems can be mounted above and below RAIF, to efficiently cope up with slow or unsecure branches. Individual files can be distributed across branches, replicated, stored with parity, or stored with erasure correction coding to recover from failures on multiple branches. Per-file incremental recovery, storage type migration, and load-balancing are especially well suited for grid storages. In this paper, we describe the current RAIF design, provide preliminary performance results and discuss current status and future directions.

The design of a persistent peer-to-peer (P2P) network storage application is presented in the paper. SNS separates the application from the underlying P2P network, i.e. the serverless layer. The serverless layer is responsible for routine networking tasks such as self-organisation and maintaining the network state information. The application specific functions are implemented through the file information protocol e.g. maintaining and synchronizing file and disk space information by using lightweight XML-formatted messages. The distributed storage is made to appear as a single large network drive, with all the main features of a conventional file system being made available to the client nodes.

The explosive growth of the Web contents has led to increasing attention on two major challenges: scalability and high availability of network file system. We introduced the concept of intermediate file handling to improve the availability of the NFS-based file system and proposed a new data consistency scheme to improve our design of a reliable file system, which had been implemented as an example of the software replication approach. By using a minor sequence in token getting, the total number of getting-token requests is reduced along with the data-requested size for each write operation. We also proposed a simple load-sharing mechanism for the NFS client to switch to a lightly-load server based on the number of NFS client's RPC requests for a period of time. Such an approach is easy to derive the load information, which each client generated. Finally, we analysed the proposed data consistency scheme. It shows truly that the scheme is able to reduce the overhead of write requests of our network file system.