本文選題：分布式文件系統(tǒng) + 元數(shù)據(jù)副本�。� 參考：《華中科技大學(xué)》2016年碩士論文

【摘要】：在分布式文件系統(tǒng)中,元數(shù)據(jù)服務(wù)器是整個系統(tǒng)的核心,副本技術(shù)是提高系統(tǒng)可用性和性能的主要方法之一。而現(xiàn)有的元數(shù)據(jù)副本技術(shù)大多只是簡單的對元數(shù)據(jù)進(jìn)行復(fù)制保存,忽視了元數(shù)據(jù)訪問具有的局部性和相關(guān)性,已經(jīng)無法滿足大數(shù)據(jù)時代對低延遲、高性能的存儲訪問需求。因此,非常有必要研究新的元數(shù)據(jù)副本技術(shù),來滿足這些需求。通過對分布式文件系統(tǒng)的元數(shù)據(jù)訪問特征的分析和總結(jié),提出了一種基于訪問熱度分類的元數(shù)據(jù)副本生成方案,首先利用k-means聚類算法對元數(shù)據(jù)的訪問熱度進(jìn)行分類,將具有相似訪問熱度的元數(shù)據(jù)分類到一起,然后生成元數(shù)據(jù)副本,并將元數(shù)據(jù)副本發(fā)送到其他元數(shù)據(jù)服務(wù)器,當(dāng)客戶端再次發(fā)送元數(shù)據(jù)請求時,元數(shù)據(jù)服務(wù)器可以直接將包含該元數(shù)據(jù)的元數(shù)據(jù)副本發(fā)送給客戶端,客戶端可以不需要與元數(shù)據(jù)服務(wù)器交互,直接從副本中查找所需要的元數(shù)據(jù),從而大大減少元數(shù)據(jù)服務(wù)器的響應(yīng)時間,提高系統(tǒng)性能。同時元數(shù)據(jù)服務(wù)器還能根據(jù)副本的命中率動態(tài)地調(diào)整和更新元數(shù)據(jù)副本,保證元數(shù)據(jù)副本的高利用率。通過對所提出的副本生成方案的對比測試,得出以下結(jié)論:基于訪問熱度分類的副本技術(shù)能顯著提高元數(shù)據(jù)讀操作的IOPS;隨著文件目錄深度的增加,改進(jìn)后系統(tǒng)響應(yīng)時間要比未改進(jìn)前的系統(tǒng)響應(yīng)時間短,并且擁有兩個元數(shù)據(jù)副本服務(wù)器的系統(tǒng)響應(yīng)時間要比擁有單個元數(shù)據(jù)副本服務(wù)器的系統(tǒng)響應(yīng)時間更短。
[Abstract]:In distributed file system, metadata server is the core of the whole system, and replica technology is one of the main methods to improve the availability and performance of the system.However, most of the existing metadata replica technologies simply copy and preserve metadata, ignoring the locality and relevance of metadata access, and can not meet the low latency and high performance storage access requirements of big data era.Therefore, it is necessary to study new metadata replica technology to meet these requirements.Based on the analysis and summary of metadata access features of distributed file systems, a metadata replica generation scheme based on access heat classification is proposed. Firstly, k-means clustering algorithm is used to classify metadata access heat.Categorizes metadata with similar access heat, generates a metadata copy, and sends a metadata copy to another metadata server, when the client sends the metadata request again,The metadata server can directly send a copy of the metadata containing the metadata to the client, which can find the required metadata directly from the copy without having to interact with the metadata server.Therefore, the response time of metadata server is greatly reduced and the system performance is improved.At the same time the metadata server can dynamically adjust and update the metadata replica according to the hit ratio of the replica to ensure the high utilization of the metadata replica.By comparing and testing the proposed replica generation scheme, the following conclusions are drawn: the replica technology based on access heat classification can significantly improve the IOPSs of metadata reading operation, and with the increase of file directory depth,The response time of the improved system is shorter than that of the unimproved system, and the response time of the system with two metadata replica servers is shorter than that with a single metadata replica server.
【學(xué)位授予單位】：華中科技大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2016
【分類號】：TP311.13

【參考文獻(xiàn)】

相關(guān)期刊論文 前3條

1 董繼光;陳衛(wèi)衛(wèi);田浪軍;吳海佳;;大規(guī)模云存儲系統(tǒng)副本布局研究[J];計算機(jī)應(yīng)用;2012年03期

2 姚玉欽;李金廣;;一種基于網(wǎng)格的層次聚類算法[J];河南師范大學(xué)學(xué)報(自然科學(xué)版);2009年04期

3 龐麗萍,陳勇;網(wǎng)格環(huán)境下數(shù)據(jù)副本創(chuàng)建策略[J];計算機(jī)工程與科學(xué);2005年02期

相關(guān)博士學(xué)位論文 前2條

1 譚支鵬;對象存儲系統(tǒng)副本管理研究[D];華中科技大學(xué);2008年

2 熊勁;大規(guī)模機(jī)群文件系統(tǒng)的關(guān)鍵技術(shù)研究[D];中國科學(xué)院研究生院（計算技術(shù)研究所）;2006年

相關(guān)碩士學(xué)位論文 前2條

1 吳森;分布式文件系統(tǒng)小文件性能優(yōu)化技術(shù)研究[D];華中科技大學(xué);2014年

2 鄧自立;云計算中的網(wǎng)絡(luò)拓?fù)湓O(shè)計和Hadoop平臺研究[D];中國科學(xué)技術(shù)大學(xué);2009年

，

本文編號：1751553