Search For:

Displaying 1-50 out of 141 total
Implementation and Evaluation of a Dynamic Schedule Policy for Multi-user Request in Network-Attached Disk Array
Found in: Young Computer Scientists, International Conference for
By Jieqiong Li, Dan Feng
Issue Date:November 2008
pp. 166-171
In the storage system, the bottom layer I/O schedule strategy is very important which decides the efficiency of the system. A good schedule policy can improve system performance obviously. This paper proposes an innovational solution that traces net users’...
 
Implementing and Evaluating Security Controls for an Object-Based Storage System
Found in: Mass Storage Systems and Technologies, IEEE / NASA Goddard Conference on
By Zhongying Niu, Ke Zhou, Dan Feng, Hong Jiang, Frank Wang, Hua Chai, Wei Xiao, Chunhua Li
Issue Date:September 2007
pp. 87-99
This paper presents the implementation and performance evaluation of a real, secure object-based storage system compliant to the T10 OSD standard. In contrast to previous work, our system implements the entire three security methods of the OSD security pro...
 
A Protocol vSCSI for Ethernet-based Network Storage
Found in: Advanced Information Networking and Applications, International Conference on
By Dan Feng, Jun Ye, Zhan Shi
Issue Date:May 2007
pp. 258-265
Ethernet-based network storage protocols such as iSCSI have become increasingly common in today?s storage network. In this paper, we propose and implement another new protocol vSCSI (VI-attached SCSI) for competing with iSCSI in LAN environment, and experi...
 
Storage Active Service: Model, Method and Practice
Found in: Frontier of Computer Science and Technology, Japan-China Joint Workshop on
By Lingfang Zeng, Dan Feng, Fang Wang, Lei Tian, Zhan Shi
Issue Date:November 2006
pp. 46-53
For current storage system, data service only passively response data consumer?s requests. With the increasing requirements of mass data storage and the development of the hardware technology of computer architecture, storage active service becomes a cruci...
 
I/O Scheduling in Huge Object-based Storage System
Found in: Frontier of Computer Science and Technology, Japan-China Joint Workshop on
By Dan Feng, Hanbo Liu
Issue Date:November 2006
pp. 39-45
Huge Object-based Storage System (HOSS), using objects which possess their own attributes and methods as storage interface, absorbs the advantages of both blocks and files interface. HOSS adopts the interaction among clients, metadata servers and object-ba...
 
A Strategy of Load Balancing in Object Storage System
Found in: Computer and Information Technology, International Conference on
By Lingfang Zeng, Dan Feng, Fang Wang, Ke Zhou
Issue Date:September 2005
pp. 310-314
<p>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 i...
 
Adaptive Policy Trigger Mechanism for OBSS
Found in: Advanced Information Networking and Applications, International Conference on
By Dan Feng, Lingfang Zeng, Fang Wang, Lingjun Qin, Qun Liu
Issue Date:March 2005
pp. 591-595
Traditional storage systems, such as NAS, SAN, are largely unaware of the users and applications actually using the storage, because block-based storage devices manage opaque data blocks. But, with OBSS (object-based storage system), the attributes and met...
 
Improved Read Performance in a Cost-Effective, Fault-Tolerant Parallel Virtual File System (CEFT-PVFS)
Found in: Cluster Computing and the Grid, IEEE International Symposium on
By Yifeng Zhu, Hong Jiang, Xiao Qin, Dan Feng, David R. Swanson
Issue Date:May 2003
pp. 730
Due to the ever-widening performance gap between processors and disks, I/O operations tend to become the major performance bottleneck of data-intensive applications on modern clusters. If all the existing disks on the nodes of a cluster are connected toget...
 
SANE: Semantic-Aware Namespacein Ultra-Large-Scale File Systems
Found in: IEEE Transactions on Parallel and Distributed Systems
By Yu Hua,Hong jiang,Yifeng Zhu,Dan Feng,Lei Xu
Issue Date:May 2014
pp. 1328-1338
The explosive growth in data volume and complexity imposes great challenges for file systems. To address these challenges, an innovative namespace management scheme is in desperate need to provide both the ease and efficiency of data access. In almost all ...
 
Data Similarity-Aware Computation Infrastructure for the Cloud
Found in: IEEE Transactions on Computers
By Yu Hua,Xue Liu,Dan Feng
Issue Date:January 2014
pp. 3-16
The cloud is emerging for scalable and efficient cloud services. To meet the needs of handling massive data and decreasing data migration, the computation infrastructure requires efficient data placement and proper management for cached data. In this paper...
 
Exploring and Exploiting the Multilevel Parallelism Inside SSDs for Improved Performance and Endurance
Found in: IEEE Transactions on Computers
By Yang Hu,Hong Jiang,Dan Feng,Lei Tian,Hao Luo,Chao Ren
Issue Date:June 2013
pp. 1141-1155
Given the multilevel internal SSD parallelism at the different four levels: channel-level, chip-level, die-level, and plane-level, how to exploit these levels of parallelism will directly and significantly impact the performance and endurance of SSDs, whic...
 
Reducing the De-linearization of Data Placement to Improve Deduplication Performance
Found in: 2012 SC Companion: High Performance Computing, Networking, Storage and Analysis (SCC)
By Yujuan Tan,Zhichao Yan,Dan Feng,E. H.-M. Sha,Xiongzi Ge
Issue Date:November 2012
pp. 796-800
Data deduplication is a lossless compression technology that replaces the redundant data chunks with pointers pointing to the already-stored ones. Due to this intrinsic data elimination feature, the deduplication commodity would delinearize the data placem...
 
A High Performance and High Reliability Storage Server for Parallel File System
Found in: 2012 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC)
By Liang Ming,Dan Feng,Fang Wang,Haifeng Sun,Sen Wu
Issue Date:October 2012
pp. 66-72
To meet the increasingly demand of massive storage system, we have designed and implemented a parallel file system called Cappella. It consists of Client, Object Storage Server (OSS) and Metadata Server (MDS). Its I/O performance and data reliability mostl...
 
HerpRap: A Hybrid Array Architecture Providing Any Point-in-Time Data Tracking for Datacenter
Found in: 2012 IEEE International Conference on Cluster Computing (CLUSTER)
By Lingfang Zeng,Dan Feng,Bo Mao,Jianxi Chen,Qingsong Wei,Wenguo Liu
Issue Date:September 2012
pp. 311-319
Both physical disk failure and logical errors such as software error, user abuse and virus attacks may cause data lose. The risk of logical errors is far greater than physical disk failure. Moreover, existing RAID solution cannot satisfy the reliability re...
 
Analogical Reasoning for Answer Ranking in Social Question Answering
Found in: IEEE Intelligent Systems
By Xudong Tu,Dan Feng,Xin-Jing Wang,Lei Zhang
Issue Date:September 2012
pp. 28-35
Answer ranking is important to social question-answering services. An analogical reasoning approach measures the similarity between new question-answer pairs and existing positive examples.
 
MERCURY: A Scalable and Similarity-Aware Scheme in Multi-level Cache Hierarchy
Found in: 2012 IEEE 20th International Symposium on Modelling, Analysis & Simulation of Computer and Telecommunication Systems (MASCOTS)
By Yu Hua,Xue Liu,Dan Feng
Issue Date:August 2012
pp. 371-378
The management of multi-level caching hierarchy is a critical and challenging task. Although there exist many hardware and OS-based schemes, they are difficult to be adopted in practice since they incur non-trivial overheads and high complexity. In order t...
 
P-Dedupe: Exploiting Parallelism in Data Deduplication System
Found in: 2012 IEEE 7th International Conference on Networking, Architecture, and Storage (NAS)
By Wen Xia,Hong Jiang,Dan Feng,Lei Tian,Min Fu,Zhongtao Wang
Issue Date:June 2012
pp. 338-347
Data deduplication, an efficient space reduction method, has gained increasing attention and popularity in data-intensive storage systems. Most existing state-of-the-art deduplication methods remove redundant data at either the file level or the chunk leve...
 
A Parity Scheme to Enhance Reliability for SSDs
Found in: 2012 IEEE 7th International Conference on Networking, Architecture, and Storage (NAS)
By Yi Qin,Dan Feng,Jingning Liu,Wei Tong,Yang Hu,Zhiming Zhu
Issue Date:June 2012
pp. 293-297
Recent years, the application of solid-state disks (SSDs) increases explosively. All SSDs have to employ error correcting code (ECC) technique to ensure the reliability of flash memory at page level. However, data loss may be caused by bad block or chip fa...
 
An In-Depth Analysis of TCP and RDMA Performance on Modern Server Platform
Found in: 2012 IEEE 7th International Conference on Networking, Architecture, and Storage (NAS)
By Yong Wan,Dan Feng,Fang Wang,Liang Ming,Yulai Xie
Issue Date:June 2012
pp. 164-171
Traditional analysis on the TCP performance attributes the overhead of TCP mainly on these aspects: many times of memory access and copy, much data transmission on bus and a large number of CPU cycles required by the protocol processing. Compared to TCP, t...
 
SUV: A Novel Single-Update Version-Management Scheme for Hardware Transactional Memory Systems
Found in: 2012 IEEE International Symposium on Parallel & Distributed Processing (IPDPS)
By Zhichao Yan,Hong Jiang,Dan Feng,Lei Tian,Yujuan Tan
Issue Date:May 2012
pp. 131-143
In order to maintain the transactional semantics, Transactional Memory (TM) must guarantee isolated read and write operations in each transaction, meaning that it must spend a non-negligible and potentially significant amount of time on keeping track of th...
 
Metadata Performance Optimization in Distributed File System
Found in: Computer and Information Science, ACIS International Conference on
By Quan Zhang,Dan Feng,Fang Wang
Issue Date:June 2012
pp. 476-481
Nowadays distributed file systems have to manage billions of small files for applications, and face with more metadata operations than data. So how to provide high metadata performance with such tremendous number of files and such large scale directories i...
 
PCAR: Parallelism Based Cache Replacement Scheme to Exploit Inter-disks Parallelism and Intra-disk Spatial Locality in Parallel Disk Array
Found in: Parallel Architectures, Algorithms and Programming, International Symposium on
By Xiaodong Shi,Dan Feng
Issue Date:December 2011
pp. 218-222
For parallel disk array systems, the parallelism among disks is the key factor influencing the performance and the scale of systems. Unfortunately, the parallelism of cached blocks is largely ignored by cache management schemes that focus on reducing the n...
 
A Case Study of the Interplay between Conflict Management and Version Management in Hardware Transactional Memory Systems
Found in: Parallel Architectures, Algorithms and Programming, International Symposium on
By Zhichao Yan,Dan Feng,Yujuan Tan
Issue Date:December 2011
pp. 334-339
As one of the most potential solution to parallel programming on the future many-core platforms, Transactional Memory (TM) systems have attracted a great deal of attention from both the industry and academic since the first TM was proposed in 1993. Various...
 
DiscPOP: Power-aware buffer management for disk accesses
Found in: International Green Computing Conference and Workshops
By Xiongzi Ge, Dan Feng,David H. C. Du
Issue Date:July 2011
pp. 1-6
Much research has been conducted on energy efficient cache buffer management for disk based storage systems. Some of them use greedy prefetching technique to artificially increase disk idle intervals if there are a large number of known future requests. Ho...
 
DBA: A Dynamic Bloom Filter Array for Scalable Membership Representation of Variable Large Data Sets
Found in: Modeling, Analysis, and Simulation of Computer Systems, International Symposium on
By Jiansheng Wei,Hong Jiang,Ke Zhou,Dan Feng
Issue Date:July 2011
pp. 466-468
This paper proposes a Dynamic Bloom filter Array (DBA) to represent membership for variable large data sets in storage systems in a scalable way. DBA consists of dynamically created groups of space-efficient Bloom Filters (BFs) to accommodate changes in se...
 
Detecting Duplicates over Sliding Windows with RAM-Efficient Detached Counting Bloom Filter Arrays
Found in: Networking, Architecture, and Storage, International Conference on
By Jiansheng Wei,Hong Jiang,Ke Zhou,Dan Feng,Hua Wang
Issue Date:July 2011
pp. 382-391
Detecting duplicates over sliding windows is an important technique for monitoring and analysing data streams. Since recording the exact information of elements in a sliding window can be RAM-resource-intensive and introduce an unacceptable search complexi...
 
TMTLS: Combine TM with TLS to Limit the Memory Contentions and Exploit the Parallelism in the Long-Running Transactions
Found in: Networking, Architecture, and Storage, International Conference on
By Zhichao Yan,Dan Feng,Yujuan Tan
Issue Date:July 2011
pp. 140-148
As more threads added to execute the multi-threaded applications in the many-core era, memory contentions among different threads impose a severe challenge to both the programmability and performance. Existing studies show that Transactional Memory (TM) is...
 
A Comprehensive Study on RAID-6 Codes: Horizontal vs. Vertical
Found in: Networking, Architecture, and Storage, International Conference on
By Chao Jin,Dan Feng,Hong Jiang,Lei Tian
Issue Date:July 2011
pp. 102-111
The RAID-6 architecture is playing an increasingly important role in modern storage systems. There are generally two kinds of RAID-6 codes, horizontal codes and vertical codes. Horizontal codes have been extensively studied and widely implemented, while ve...
 
Locality-Sensitive Bloom Filter for Approximate Membership Query
Found in: IEEE Transactions on Computers
By Yu Hua,Bin Xiao,Bharadwaj Veeravalli,Dan Feng
Issue Date:June 2012
pp. 817-830
In many network applications, Bloom filters are used to support exact-matching membership query for their randomized space-efficient data structure with a small probability of false answers. In this paper, we extend the standard Bloom filter to Locality-Se...
 
Semantic-Aware Metadata Organization Paradigm in Next-Generation File Systems
Found in: IEEE Transactions on Parallel and Distributed Systems
By Yu Hua,Hong Jiang,Yifeng Zhu,Dan Feng,Lei Tian
Issue Date:February 2012
pp. 337-344
Existing data storage systems based on the hierarchical directory-tree organization do not meet the scalability and functionality requirements for exponentially growing data sets and increasingly complex metadata queries in large-scale, Exabyte-level file ...
 
CABdedupe: A Causality-Based Deduplication Performance Booster for Cloud Backup Services
Found in: Parallel and Distributed Processing Symposium, International
By Yujuan Tan,Hong Jiang,Dan Feng,Lei Tian,Zhichao Yan
Issue Date:May 2011
pp. 1266-1277
Due to the relatively low bandwidth of WAN (Wide Area Network) that supports cloud backup services, both the backup time and restore time in the cloud backup environment are in desperate need for reduction to make cloud backup a practical and affordable se...
 
RAID6L: A log-assisted RAID6 storage architecture with improved write performance
Found in: Mass Storage Systems and Technologies, IEEE / NASA Goddard Conference on
By Chao Jin,Dan Feng,Hong Jiang,Lei Tian
Issue Date:May 2011
pp. 1-6
The RAID6 architecture is playing an increasingly important role in modern storage systems due to its provision of very high reliability. However, its high write penalty, because of the double-parity-update overheads upon each write operation, has been a p...
 
Design and evaluation of Oasis: An active storage framework based on T10 OSD standard
Found in: Mass Storage Systems and Technologies, IEEE / NASA Goddard Conference on
By Yulai Xie,Kiran-Kumar Muniswamy-Reddy,Dan Feng,Darrell D. E. Long, Yangwook Kang,Zhongying Niu, Zhipeng Tan
Issue Date:May 2011
pp. 1-12
In this paper, we present the design and performance evaluation of Oasis, an active storage framework for object-based storage systems that complies with the current T10 OSD standard. In contrast with previous work, Oasis has the following advantages. Firs...
 
Availability-Aware Cache Management with Improved RAID Reconstruction Performance
Found in: Computational Science and Engineering, IEEE International Conference on
By Suzhen Wu, Bo Mao, Dan Feng, Jianxi Chen
Issue Date:December 2010
pp. 229-236
The RAID reconstruction performance has a significant impact on the availability of RAID-structured storage systems due to the high disk failure rate. Most existing cache managements for RAID-structured storage systems focus on improving the performance or...
 
TRIP: Temporal Redundancy Integrated Performance Booster for Parity-Based RAID Storage Systems
Found in: Parallel and Distributed Systems, International Conference on
By Chao Jin, Dan Feng, Hong Jiang, Lei Tian, Jingning Liu, Xiongzi Ge
Issue Date:December 2010
pp. 205-212
Parity redundancy is widely employed in RAID-structured storage systems to protect against disk failures. However, the small-write problem has been a persistent root cause of the performance bottleneck of such parity-based RAID systems, due to the addition...
 
Design and Implementation of Object-Oriented Encryption Storage System Based on Trusted Computing Platform
Found in: Computational Intelligence and Security, International Conference on
By Junjian Chen, Jingning Liu, Dan Feng
Issue Date:December 2010
pp. 546-550
Object-oriented storage system is a distributed storage systems with a storage device directly connected to the network. In existing encryption schemes the protection of the sensitive data is achieved mainly through an encrypted data storage system, but th...
 
SafeVanish: An Improved Data Self-Destruction for Protecting Data Privacy
Found in: Cloud Computing Technology and Science, IEEE International Conference on
By Lingfang Zeng, Zhan Shi, Shengjie Xu, Dan Feng
Issue Date:December 2010
pp. 521-528
In the background of cloud, self-destructing data mainly aims at protecting the data privacy. All the data and its copies will become destructed or unreadable after a user-specified period, without any user intervention. Besides, anyone cannot get the decr...
 
Improving Availability of RAID-Structured Storage Systems by Workload Outsourcing
Found in: IEEE Transactions on Computers
By Suzhen Wu, Hong Jiang, Dan Feng, Lei Tian, Bo Mao
Issue Date:January 2011
pp. 64-79
Due to the contention for the shared disk bandwidth, the user I/O intensity can significantly impact the performance of the online low-priority background tasks, thus reducing the reliability and availability of RAID-structured storage systems. In this pap...
 
SAM: A Semantic-Aware Multi-tiered Source De-duplication Framework for Cloud Backup
Found in: Parallel Processing, International Conference on
By Yujuan Tan, Hong Jiang, Dan Feng, Lei Tian, Zhichao Yan, Guohui Zhou
Issue Date:September 2010
pp. 614-623
Existing de-duplication solutions in cloud backup environment either obtain high compression ratios at the cost of heavy de-duplication overheads in terms of increased latency and reduced throughput, or maintain small de-duplication overheads at the cost o...
 
CDRM: A Cost-Effective Dynamic Replication Management Scheme for Cloud Storage Cluster
Found in: Cluster Computing, IEEE International Conference on
By Qingsong Wei, Bharadwaj Veeravalli, Bozhao Gong, Lingfang Zeng, Dan Feng
Issue Date:September 2010
pp. 188-196
Data replication has been widely used as a mean of increasing the data availability of large-scale cloud storage systems where failures are normal. Aiming to provide cost-effective availability, and improve performance and load-balancing of cloud storage, ...
 
Reliability Modeling of Energy Efficient Logging Architectures Based on RAID10 Systems
Found in: Frontier of Computer Science and Technology, Japan-China Joint Workshop on
By Fang Wang, Yinliang Yue, Quan Zhang, Lei Tian, Dan Feng
Issue Date:August 2010
pp. 57-62
Logging is an important and commonly-used approach to improving energy efficiency and performance of storage systems. Reliability is one of the most important metrics to evaluate the storage systems. However, reliability modeling of energy-efficient loggin...
 
USP: A Lightweight File System Management Framework
Found in: Networking, Architecture, and Storage, International Conference on
By Zhan Shi, Dan Feng, Heng Zhao, Lingfang Zeng
Issue Date:July 2010
pp. 250-256
With data amount growing at an ever increasing rate, file system, as the basis of data management, its functionality and content are becoming more and more complex. Thus the file system is forced to be upgraded constantly, in order to satisfy the growing d...
 
EDOS: Employing Mini-DB for High Semantic Object Store
Found in: Networking, Architecture, and Storage, International Conference on
By Xudong Tu, Dan Feng, Zhipeng Tan
Issue Date:July 2010
pp. 420-428
Storage management server, compatible with decoupled data and meta data fashion, is being employed frantically to build large-scale distributed storage system for performance and capacity. To design this hot commodity on flexibly managing the extracted dat...
 
DAM: A DataOwnership-Aware Multi-layered De-duplication Scheme
Found in: Networking, Architecture, and Storage, International Conference on
By Yujuan Tan, Dan Feng, Zhichao Yan, Guohui Zhou
Issue Date:July 2010
pp. 403-411
Beyond the storage savings brought by chunk-level de-duplication in backup and archiving systems, a prominent challenge facing this technology is how to efficiently and effectively identify the duplicate chunks. Most of the chunk fingerprints used to ident...
 
RoLo: A Rotated Logging Storage Architecture for Enterprise Data Centers
Found in: Distributed Computing Systems, International Conference on
By Yinliang Yue, Lei Tian, Hong Jiang, Fang Wang, Dan Feng, Quan Zhang, Pan Zeng
Issue Date:June 2010
pp. 293-304
We propose RoLo (Rotated Logging), a new logging architecture for RAID10 systems for enhanced energy efficiency, performance and reliability. By spreading destaging I/O activities among short idle time slots and proactively reclaiming the stale logging spa...
 
Supporting Scalable and Adaptive Metadata Management in Ultralarge-Scale File Systems
Found in: IEEE Transactions on Parallel and Distributed Systems
By Yu Hua, Yifeng Zhu, Hong Jiang, Dan Feng, Lei Tian
Issue Date:April 2011
pp. 580-593
This paper presents a scalable and adaptive decentralized metadata lookup scheme for ultralarge-scale file systems (more than Petabytes or even Exabytes). Our scheme logically organizes metadata servers (MDSs) into a multilayered query hierarchy and exploi...
 
MAD2: A scalable high-throughput exact deduplication approach for network backup services
Found in: Mass Storage Systems and Technologies, IEEE / NASA Goddard Conference on
By Jiansheng Wei, Hong Jiang, Ke Zhou, Dan Feng
Issue Date:May 2010
pp. 1-14
Deduplication has been widely used in disk-based secondary storage systems to improve space efficiency. However, there are two challenges facing scalable high-throughput deduplication storage. The first is the duplicate-lookup disk bottleneck due to the la...
 
Achieving page-mapping FTL performance at block-mapping FTL cost by hiding address translation
Found in: Mass Storage Systems and Technologies, IEEE / NASA Goddard Conference on
By Yang Hu, Hong Jiang, Dan Feng, Lei Tian, Shuping Zhang, Jingning Liu, Wei Tong, Yi Qin, Liuzheng Wang
Issue Date:May 2010
pp. 1-12
Flash Translation Layer (FTL) is one of the most important components of SSD, whose main purpose is to perform logical to physical address translation in a way that is suitable to the unique physical characteristics of the Flash memory technology. The pure...
 
A study of self-similarity in parallel I/O workloads
Found in: Mass Storage Systems and Technologies, IEEE / NASA Goddard Conference on
By Qiang Zoll, Yifeng Zhu, Dan Feng
Issue Date:May 2010
pp. 1-6
A challenging issue in performance evaluation of parallel storage systems through trace-driven simulation is to accurately characterize and emulate I/O behaviors in real applications. The correlation study of inter-arrival times between I/O requests, with ...
 
Seesaw: Performance Guarantee for RAID Reconstruction
Found in: Computational Sciences and Optimization, International Joint Conference on
By Junping Liu, Ke Zhou, Zhikun Wang, Liping Pang, Dan Feng
Issue Date:May 2010
pp. 348-351
Today, the disk failures in large-scale storage can occur almost on a daily basis and the reconstruction process is very common. Additionally, the reconstruction process is always time-consuming. When RAID is in the reconstruction process, the performance ...
 
 1  2 Next >>