可扩展的分布式邮件系统的研究与实现

提出了一种可扩展、分布式的邮件系统设计方案.通过远程过程调用和负载的动态分配,可以将邮件储存在多个服务器上,解决了单台服务器CPU、磁盘I/O性能不足的问题;通过邮件的同步备份实现了故障冗余.通过用户映射表结构,可以将用户分配到各个服务器上,当系统中有服务器发生故障或者新增加服务器时,能够对用户进行重新分配,动态地维持每一个服务器的管理责任.实际的测试结果表明,系统性能随着服务器数量的增加基本呈线性增长,邮件服务不会由于部分服务器发生故障而终止.     

EH＊g：一个高可用的可扩展分布式数据结构

EH＊g是一个高可用性的可扩展分布式数据结构。利用记录组技术增加系统的可利用性，并对每条要求插入的记录，在主文件和奇偶文件两个地方进行插入。当主文件中的记录发生丢失或破坏时，可利用同一记录组中其它记录的信息和保存在奇偶文件中的信息来恢复该记录，以此达到高可用性。     

分布式存储的并行串匹配算法的设计与分析

并行串匹配算法的研究大都集中在PRAM(parallel random access machine)模型上,其他更为实际的模型上的并行串匹配算法的研究相对要薄弱得多.该文采用将最优串行算法并行化的技术,利用模式串的周期性质,巧妙地将改进的KMP(Knuth-Morris-Pratt)算法并行化,提出了一个简便、高效且具有良好可扩放性的分布式串匹配算法,其计算复杂度为O(n/p+m),通信复杂度为O(ulogp相似文献   

New Rate Allocation Method for MPEG-4 FGS Video Streaming

A new rate allocation method for fine-granular scalability (FGS) coded bltstreams is presented in order to achieve smooth quality reconstruction of frames under channel conditions with a wide range of bandwidth variation and improve the average PSNR of the whole sequence. Based on a quality weighted bit allocation method, a sliding window rate allocation method is proposed for the first time so that the window can slide along the video sequence with a certain sliding step. Experimental results show that, under dynamic bandwidth conditions, the proposed method can simultaneously satisfy the requirements for improving average PSNR of the whole video sequence greatly and reducing the fluctuations between adjacent frames greatly.     

区块链分片技术综述

区块链作为分布式账本的关键技术之一,其去中心化、可匿名、不可篡改的特性受到学术界和工业界的青睐,被广泛应用于金融、数字货币、公共服务等领域。分片技术作为区块链扩容的主流方式之一,能够在不降低区块链去中心化程度的同时实现高性能的链上扩容,从而解决区块链可拓展性不足以及吞吐量较低的问题。介绍近年来出现的分片技术以及相关协议,总结分片技术的关键理论与方法,从分片配置、重配置、片内共识协议、跨片共识协议、状态存储等方面对分片技术方案进行对比,归纳不同分片方案在网络分片、交易分片、状态分片等设计中存在的优势和不足。同时,阐述一些经典分片技术在性能和实现方式上的特点,对许可区块链和无许可区块链、片内共识协议、跨片共识协议、准入性方案、状态分片方式等进行分析和概述。在此基础上,从分片内、分片间以及系统层级的角度总结分片技术当前所面临的困境和挑战,并对该领域的发展前景及未来研究方向加以展望。     

基于RDMA的区块传输机制设计与实现

随着区块链技术的不断发展,区块的传输延迟成为区块链系统可扩展性的性能瓶颈。远程直接内存访问（RDMA）技术能够支持高带宽和低时延的数据传输,为低延迟区块传输提供了新的思路。因此,结合RDMA原语的特性,设计了用于区块信息共享的区块目录结构,并在此基础上设计并实现了区块传输的基本工作过程。实验结果表明,相较于基于TCP的方案,在1 MB大小的区块上基于RDMA的区块传输机制将节点间的区块传输延迟降低了44%,全网络的区块传输延迟降低了24.4%,在10 000节点规模的区块链上,区块链发生临时分叉的数量降低了22.6%。可见,基于RDMA的区块传输机制充分发挥了高速网络的性能优势,降低了区块传输延迟及临时分叉的数量,提高了现有区块链系统的可扩展性。     

不同数据分配方式下并行系统的可扩展性

本文以高斯消去法为例,从理论和实验上给出了一般可扩展性分析步骤,分析了不同数据分配策略对并行算法和机器组合体可扩展性的影响。这对算法可扩展性分析的推广是很有意义的。     

面向头肩序列图像的质量可精细扩展视频编码方法

FGS编码方法具有细粒度的可扩展能力,能很好地适应网络带宽的动态变化,被认为是一种适合于网络视频传输的编码方案.但现有的MPEG-4 FGS编码标准效率低,限制了其进一步的推广应用.因此,本文面向视频应用中常见的头肩序列图像,实现了一种质量可精细扩展的视频编码方法.该方法采用H.26L对基本层进行编码,采用基于DCT变换的SPIHT方法对原始图像与基本层重建图像之间的残差进行编码得到增强层的码流.然后将复杂背景下的人脸检测与跟踪技术与选择性增强技术结合起来,对人脸区域优先编码.实验结果表明,该方法不仅编码效率高于现有的MPEG-4 FGS标准,码流具有可精细扩展的特性,还可以选择性地提高人脸区域重建图像的主观感受水平.     

From sequential pattern mining to structured pattern mining: A pattern-growth approach

Sequential pattern mining is an important data mining problem with broad applications. However,it is also a challenging problem since the mining may have to generate or examine a combinatorially explosivenumber of intermediate subsequences. Recent studies have developed two major classes of sequential patternmining methods: (1) a candidate generation-and-test approach, represented by (i) GSP, a horizontal format-basedsequential pattern mining method, and (ii) SPADE, a vertical format-based method; and (2) a pattern-growthmethod, represented by PrefixSpan and its further extensions, such as gSpan for mining structured patterns. In this study, we perform a systematic introduction and presentation of the pattern-growth methodologyand study its principles and extensions. We first introduce two interesting pattern-growth algorithms, FreeSpanand PrefixSpan, for efficient sequential pattern mining. Then we introduce gSpan for mining structured patternsusing the same methodology. Their relative performance in l     

Density-Independent,Scalable Search in Ad Hoc Networks

We analyze the asymptotic cost of discovering a route within a flat ad hoc network and we show that one can discover a route with cost that is proportional only to the area of the network, which is independent of the number of network nodes. Furthermore, we show that this is optimal and that bordercasting (a query propagation protocol where a node retransmits a query to a set of nodes at some hop-distance away) possesses this density-independence property. We present the design of bordercast and the associated maintenance protocols, and we evaluate their performance. In particular, we highlight that the aggregation of local information by bordercasting at each network node is a fundamental building block for the construction of scalable protocols in flat ad hoc networks.