本文選題：網(wǎng)絡(luò)計(jì)算環(huán)境 + 分布式COW盤�。� 參考：《湖南大學(xué)》2013年碩士論文

【摘要】：人類社會(huì)進(jìn)入信息時(shí)代以來，對(duì)計(jì)算性能的要求不斷提高，網(wǎng)絡(luò)計(jì)算模式能充分的整合計(jì)算資源，滿足人們對(duì)計(jì)算性能的高要求，成為當(dāng)前研究的熱點(diǎn)。網(wǎng)絡(luò)計(jì)算模式將計(jì)算任務(wù)分配給各種分布的計(jì)算資源（各客戶主機(jī)），而將數(shù)據(jù)（系統(tǒng)數(shù)據(jù)和用戶數(shù)據(jù)）部署在相應(yīng)的網(wǎng)絡(luò)存儲(chǔ)設(shè)備中，實(shí)現(xiàn)了存儲(chǔ)與計(jì)算的分離，即存儲(chǔ)在存儲(chǔ)設(shè)備的系統(tǒng)數(shù)據(jù)不再屬于某一特定的主體，而是被網(wǎng)絡(luò)計(jì)算環(huán)境中所有主機(jī)共享。在這種模式下，網(wǎng)絡(luò)計(jì)算環(huán)境中存儲(chǔ)結(jié)構(gòu)及存儲(chǔ)優(yōu)化變得極為關(guān)鍵。 本文主要針對(duì)大規(guī)模網(wǎng)絡(luò)計(jì)算環(huán)境的分布式計(jì)算和數(shù)據(jù)集中存儲(chǔ)的特點(diǎn)，結(jié)合COW(copy-on-write)寫時(shí)復(fù)制技術(shù),提出了一種分布式COW網(wǎng)絡(luò)盤的存儲(chǔ)體系結(jié)構(gòu)。在這種存儲(chǔ)體系下,客戶主機(jī)的共享數(shù)據(jù)以只讀的方式集中存儲(chǔ)在共享源盤中,各客戶主機(jī)對(duì)共享數(shù)據(jù)的改寫塊被保存在其相應(yīng)的分布式COW盤中，在實(shí)現(xiàn)存儲(chǔ)與計(jì)算分離的基礎(chǔ)上進(jìn)一步優(yōu)化了對(duì)共享數(shù)據(jù)的讀寫操作。 本文的主要研究工作如下： 首先，基于COW技術(shù)提出了分布式COW網(wǎng)絡(luò)盤的存儲(chǔ)模型,同時(shí)結(jié)合磁盤記錄改寫塊的稀疏和突發(fā)特性，詳細(xì)描述了分布式COW網(wǎng)絡(luò)盤體系結(jié)構(gòu)及讀寫模式，將服務(wù)器處理所有客戶主機(jī)相應(yīng)COW盤的聚合開銷分?jǐn)偟礁鱾�(gè)客戶主機(jī)自身，以加速網(wǎng)絡(luò)計(jì)算環(huán)境系統(tǒng)的構(gòu)建速度。 其次，設(shè)計(jì)了一種改進(jìn)的64位位圖壓縮算法以有效減少COW盤位圖文件大小，節(jié)省服務(wù)器磁盤空間和降低分布式COW盤網(wǎng)絡(luò)傳輸開銷；提出一種適合COW盤改寫塊突發(fā)特性的預(yù)取算法，以提高分布式COW盤Cache的命中率。 最后，通過實(shí)驗(yàn)驗(yàn)證，，采用COW網(wǎng)絡(luò)盤成功的實(shí)現(xiàn)了網(wǎng)絡(luò)計(jì)算環(huán)境下多主機(jī)數(shù)據(jù)的共享訪問，同時(shí)實(shí)驗(yàn)證明基于改進(jìn)的COW盤位圖壓縮和預(yù)取算法實(shí)現(xiàn)的分布式COW盤降低了多客戶主機(jī)網(wǎng)絡(luò)計(jì)算環(huán)境的構(gòu)建延遲。
[Abstract]:Since the human society has entered the information age, the demand for computing performance has been continuously improved. The network computing model can fully integrate computing resources to meet the high demand for computing performance, which has become the focus of current research. The network computing model allocates computing tasks to all kinds of distributed computing resources (each client host computer), while the data (system data and user data) are deployed in the corresponding network storage device, which realizes the separation of storage and calculation. That is, the system data stored in the storage device no longer belongs to a particular subject, but is shared by all hosts in the network computing environment. In this mode, storage structure and storage optimization in network computing environment become critical. In this paper, according to the characteristics of distributed computing and data centralized storage in large-scale network computing environment, a storage architecture of distributed COW network disk is proposed in combination with COWcopy-on-write copy technology. In this storage system, the shared data of the client host is stored in the shared source disk in a read-only manner, and the rewriting blocks of the shared data of each client host are stored in the corresponding distributed COW disk. Based on the separation of storage and computation, the read and write operation of shared data is further optimized. The main work of this paper is as follows: Firstly, based on COW technology, the storage model of distributed COW network disk is proposed. At the same time, combining the sparse and burst characteristics of disk record rewriting block, the architecture of distributed COW network disk and the mode of reading and writing are described in detail. In order to accelerate the construction speed of the network computing environment, the aggregation overhead of the server processing the corresponding COW disk of all the client hosts is distributed to each client host itself. Secondly, an improved 64-bit map compression algorithm is designed to effectively reduce the size of COW disk bitmap file, save server disk space and reduce the transmission overhead of distributed COW disk network. A prefetching algorithm suitable for burst characteristics of COW rewriting block is proposed to improve the hit rate of distributed COW disk Cache. Finally, through the experiment verification, the COW network disk has successfully realized the multi-host data sharing access under the network computing environment. At the same time, it is proved that the distributed COW disk based on the improved COW disk bitmap compression and prefetching algorithm can reduce the construction delay of multi-client host network computing environment.
【學(xué)位授予單位】：湖南大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2013
【分類號(hào)】：TP333

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 張堯?qū)W;透明計(jì)算:概念、結(jié)構(gòu)和示例[J];電子學(xué)報(bào);2004年S1期

2 謝學(xué)軍;葉以正;邱善勤;喻明艷;;基于馬爾可夫模型的數(shù)據(jù)值預(yù)取方案[J];電子學(xué)報(bào);2007年02期

3 張堯?qū)W;周悅芝;;一種云計(jì)算操作系統(tǒng)TransOS:基于透明計(jì)算的設(shè)計(jì)與實(shí)現(xiàn)[J];電子學(xué)報(bào);2011年05期

4 馬一力,傅湘林,韓曉明,許魯;存儲(chǔ)與計(jì)算的分離[J];計(jì)算機(jī)研究與發(fā)展;2005年03期

5 夏楠;張堯?qū)W;楊善林;王曉輝;;IOMan:一種支持多操作系統(tǒng)遠(yuǎn)程啟動(dòng)和運(yùn)行的I/O管理方法[J];計(jì)算機(jī)研究與發(fā)展;2007年02期

6 肖連兵,黃林鵬;網(wǎng)格計(jì)算綜述[J];計(jì)算機(jī)工程;2002年03期

7 吳斌,史忠植;一種基于蟻群算法的TSP問題分段求解算法[J];計(jì)算機(jī)學(xué)報(bào);2001年12期

8 徐光yP ,史元春 ,謝偉凱;普適計(jì)算[J];計(jì)算機(jī)學(xué)報(bào);2003年09期

9 劉振軍,許魯,尹洋;藍(lán)鯨SonD動(dòng)態(tài)服務(wù)部署系統(tǒng)[J];計(jì)算機(jī)學(xué)報(bào);2005年07期

10 陳彬;肖儂;蔡志平;王志英;;基于優(yōu)化的COW虛擬塊設(shè)備的虛擬機(jī)按需部署機(jī)制[J];計(jì)算機(jī)學(xué)報(bào);2009年10期

本文編號(hào)：1883677