分布式存儲中精確修復(fù)最小帶寬再生碼的性能研究
發(fā)布時(shí)間:2018-11-07 21:31
【摘要】:分布式存儲系統(tǒng)為保證數(shù)據(jù)可靠性,需要對數(shù)據(jù)進(jìn)行冗余存儲來應(yīng)對由于節(jié)點(diǎn)失效所帶來的數(shù)據(jù)不可靠性.基于矩陣積構(gòu)造的精確修復(fù)最小帶寬再生碼除了能夠顯著降低系統(tǒng)的存儲冗余,而且編碼的構(gòu)造參數(shù)之間沒有約束限制,還能夠顯著降低修復(fù)帶寬的開銷,具有廣闊的應(yīng)用前景.然而,基于此編碼方案所設(shè)計(jì)的分布式存儲系統(tǒng)的性能開銷并沒有得到充分的研究和分析.針對該編碼在分布式存儲系統(tǒng)中數(shù)據(jù)上傳、修復(fù)、下載3個(gè)階段,分別比較CPU使用率、文件大小、緩沖區(qū)大小以及有限域大小對上述3個(gè)階段中運(yùn)算速度的影響,發(fā)現(xiàn)通過對相關(guān)參數(shù)進(jìn)行合理配置,可以使得基于相應(yīng)編碼方案的分布式存儲系統(tǒng)能夠獲得良好的運(yùn)行性能.
[Abstract]:In order to ensure data reliability, distributed storage system needs redundant storage to deal with the data unreliability caused by node failure. In addition to reducing the storage redundancy of the system, the exact repair minimum bandwidth regenerative code based on matrix product can significantly reduce the overhead of the repair bandwidth, and there are no constraints between the coded construction parameters. It has broad application prospect. However, the performance overhead of the distributed storage system based on this coding scheme has not been fully studied and analyzed. According to the three stages of data upload, repair and download in distributed storage system, the effects of CPU usage, file size, buffer size and finite field size on the operation speed are compared. It is found that the distributed storage system based on the corresponding coding scheme can achieve good performance by reasonably configuring the relevant parameters.
【作者單位】: 智能信息處理上海市重點(diǎn)實(shí)驗(yàn)室(復(fù)旦大學(xué)計(jì)算機(jī)科學(xué)技術(shù)學(xué)院);
【基金】:國家自然科學(xué)基金項(xiàng)目(61171074) 國家“八六三”高技術(shù)研究發(fā)展計(jì)劃基金項(xiàng)目(2009AA01A348) 教育部新世紀(jì)優(yōu)秀人才支持計(jì)劃基金項(xiàng)目(NCET-11-0113)
【分類號】:TP333
[Abstract]:In order to ensure data reliability, distributed storage system needs redundant storage to deal with the data unreliability caused by node failure. In addition to reducing the storage redundancy of the system, the exact repair minimum bandwidth regenerative code based on matrix product can significantly reduce the overhead of the repair bandwidth, and there are no constraints between the coded construction parameters. It has broad application prospect. However, the performance overhead of the distributed storage system based on this coding scheme has not been fully studied and analyzed. According to the three stages of data upload, repair and download in distributed storage system, the effects of CPU usage, file size, buffer size and finite field size on the operation speed are compared. It is found that the distributed storage system based on the corresponding coding scheme can achieve good performance by reasonably configuring the relevant parameters.
【作者單位】: 智能信息處理上海市重點(diǎn)實(shí)驗(yàn)室(復(fù)旦大學(xué)計(jì)算機(jī)科學(xué)技術(shù)學(xué)院);
【基金】:國家自然科學(xué)基金項(xiàng)目(61171074) 國家“八六三”高技術(shù)研究發(fā)展計(jì)劃基金項(xiàng)目(2009AA01A348) 教育部新世紀(jì)優(yōu)秀人才支持計(jì)劃基金項(xiàng)目(NCET-11-0113)
【分類號】:TP333
【相似文獻(xiàn)】
相關(guān)期刊論文 前10條
1 孟慶偉;;云計(jì)算技術(shù)及其電信應(yīng)用[J];電信快報(bào);2010年07期
2 盧益陽;;分布式存儲系統(tǒng)調(diào)查[J];企業(yè)科技與發(fā)展;2011年16期
3 王大濤;姜月秋;;一種適用于集群的高可用存儲模型的研究[J];沈陽理工大學(xué)學(xué)報(bào);2007年02期
4 邢繼元;張義德;;計(jì)算機(jī)存儲技術(shù)的發(fā)展現(xiàn)狀和趨勢[J];科協(xié)論壇(下半月);2008年02期
5 張?zhí)煜?潘峰;楊曉元;劉鎮(zhèn);張薇;;改進(jìn)的LPCA算法[J];計(jì)算機(jī)工程與應(yīng)用;2010年09期
6 陳衛(wèi)衛(wèi);吳海佳;胥光輝;;分布式存儲中文件分割的最優(yōu)化模型[J];解放軍理工大學(xué)學(xué)報(bào)(自然科學(xué)版);2010年04期
7 王文奎;吳國新;;一種對等式存儲系統(tǒng)的設(shè)計(jì)與實(shí)現(xiàn)[J];計(jì)算機(jī)技術(shù)與發(fā)展;2008年04期
8 馬軍;鄭p,
本文編號:2317623
本文鏈接:http://sikaile.net/kejilunwen/jisuanjikexuelunwen/2317623.html
最近更新
教材專著