本文關(guān)鍵詞：基于數(shù)據(jù)塊的數(shù)據(jù)保護(hù)技術(shù)研究　出處：《華中科技大學(xué)》2013年博士論文　論文類(lèi)型：學(xué)位論文

  更多相關(guān)文章： 連續(xù)數(shù)據(jù)保護(hù) 緩存機(jī)制 元數(shù)據(jù)管理 熱啟動(dòng) 固態(tài)盤(pán) 輸入輸出性能

【摘要】：隨著社會(huì)對(duì)信息化依賴程度越來(lái)越高,數(shù)據(jù)丟失往往會(huì)造成巨大的損失。數(shù)據(jù)丟失的原因主要可以分為兩類(lèi),一類(lèi)是系統(tǒng)的軟硬件故障,另一類(lèi)則是人為誤刪除或非法篡改。系統(tǒng)的意外停機(jī)會(huì)直接導(dǎo)致系統(tǒng)緩存中數(shù)據(jù)丟失。即便部分緩存采用的是非易失性存儲(chǔ)器,也可能因其緩存映射表和狀態(tài)信息異常失效而依然導(dǎo)致整個(gè)緩存不可使用。為了抵抗這種風(fēng)險(xiǎn)需要緩存有可持續(xù)性。人為操作失誤或篡改則會(huì)直接改變當(dāng)前數(shù)據(jù)存儲(chǔ)狀態(tài),為了抵抗這一風(fēng)險(xiǎn)也需要存儲(chǔ)系統(tǒng)有在時(shí)間軸上向前回滾的能力。 首先為解決緩存系統(tǒng)發(fā)生意外時(shí)數(shù)據(jù)丟失的問(wèn)題,設(shè)計(jì)了一個(gè)基于固態(tài)盤(pán)(SSD)的緩存系統(tǒng)PFC (Persistent Flash Cache)。PFC采用改進(jìn)的組相聯(lián)映射地址映射方式,在節(jié)省元數(shù)據(jù)開(kāi)銷(xiāo)的同時(shí),利用局部性原理加快了數(shù)據(jù)寫(xiě)回硬盤(pán)的速度。同時(shí)PFC通過(guò)將部分存在易失性主存(RAM)中的緩存系統(tǒng)元數(shù)據(jù)映射到非易失性的固態(tài)盤(pán)中并實(shí)時(shí)更新的方式,保證緩存中的數(shù)據(jù)在經(jīng)歷計(jì)劃停機(jī)或意外停機(jī)時(shí)都不丟失。 其次提出了低開(kāi)銷(xiāo)高可用元數(shù)據(jù)更新方法LUFUW(Lazy-Update Following an Update-Write)。LUFUW通過(guò)借鑒計(jì)算機(jī)網(wǎng)絡(luò)技術(shù)中TCP協(xié)議確認(rèn)幀是通過(guò)數(shù)據(jù)幀捎回這一策略,使某個(gè)元數(shù)據(jù)條目的更新可以通過(guò)同一個(gè)元數(shù)據(jù)塊中的其它元數(shù)據(jù)條目的更新捎帶回固態(tài)盤(pán)緩存的元數(shù)據(jù)區(qū)。從而在只增加少量元數(shù)據(jù)更新開(kāi)銷(xiāo)的情況下,保證系統(tǒng)重啟后,固態(tài)盤(pán)中絕大部分緩存數(shù)據(jù)可用。實(shí)驗(yàn)結(jié)果表明在非正常關(guān)機(jī)啟動(dòng)時(shí),相對(duì)于傳統(tǒng)的只有14%緩存數(shù)據(jù)可用元數(shù)據(jù)更新方式,新的元數(shù)據(jù)更新策略使99%以上緩存數(shù)據(jù)可用。從而使系統(tǒng)重啟后緩存的性能是原始Flashcache的兩倍。 最后設(shè)計(jì)了一個(gè)在時(shí)間軸上有向前回滾能力的高效連續(xù)數(shù)據(jù)保護(hù)系統(tǒng)ST-CDP (Snapshot in TRAP Continuous Data Protection)。傳統(tǒng)的連續(xù)數(shù)據(jù)保護(hù)系統(tǒng)為了保存系統(tǒng)中每一次修改,會(huì)產(chǎn)生大量的記錄數(shù)據(jù)。ST-CDP通過(guò)引入異或運(yùn)算提高了數(shù)據(jù)的壓縮比,有效的節(jié)省存儲(chǔ)空間。通過(guò)結(jié)合傳統(tǒng)的快照技術(shù)和現(xiàn)有的連續(xù)數(shù)據(jù)保護(hù)技術(shù),在記錄數(shù)據(jù)變化的校驗(yàn)鏈中周期性的插入快照,使系統(tǒng)能確保在發(fā)生故障時(shí)進(jìn)行快速、可靠的數(shù)據(jù)恢復(fù)。通過(guò)建立如何插入、何時(shí)插入快照的數(shù)學(xué)模型,優(yōu)化存儲(chǔ)空間和恢復(fù)時(shí)間。基于此數(shù)學(xué)模型,在Linux內(nèi)核上設(shè)計(jì)并實(shí)現(xiàn)了此連續(xù)數(shù)據(jù)保護(hù)系統(tǒng)。實(shí)現(xiàn)表明,ST-CDP和傳統(tǒng)的連續(xù)數(shù)據(jù)保護(hù)技術(shù)在運(yùn)行時(shí)開(kāi)銷(xiāo)相似,但其連續(xù)數(shù)據(jù)保護(hù)日志空間非常開(kāi)銷(xiāo)小,接近于即時(shí)任意點(diǎn)數(shù)據(jù)恢復(fù)(TRAP)。
[Abstract]:With the increasing dependence of society on information technology, data loss will often cause huge losses. The reasons for data loss can be divided into two categories, one is the system software and hardware failures. The other is human error deletion or illegal tampering. The unexpected shutdown of the system will directly lead to the loss of data in the system cache, even if part of the cache uses non-volatile memory. It is also possible that the entire cache is not usable because its cache mapping table and state information are not working. To resist this risk, cache sustainability is required. Human error or tampering directly changes the current data. Storage status. To resist this risk, storage systems are also required to roll back on the timeline. First of all, to solve the cache system unexpected data loss problem. A cache system, PFC persistent Flash Cache).PFC, based on SSD, is designed in this paper. It uses improved group associative mapping address mapping method. While saving metadata overhead. The local principle is used to speed up the speed of data being written back to the hard disk. At the same time, PFC uses part of the volatile main memory (RAM) to write the data back to the hard disk. The way in which cache system metadata is mapped to a non-volatile solid-state disk and updated in real time. Ensure that data in the cache is not lost during scheduled or unexpected downtime. Secondly, LUFUW(Lazy-Update Following an Update-Write-based method with low overhead and high availability is proposed. LUFUW uses the TCP protocol in computer network technology to confirm that frames are sent back by data frames. An update of a metadata entry can be piggyback to a cached metadata area of a solid-state disk through an update of other metadata entries in the same metadata block, thereby adding only a small amount of metadata update overhead. After the system is restarted, most of the cache data are available in the solid state disk. The experimental results show that only 14% cache data can be updated by metadata in the abnormal shutdown startup. The new metadata update strategy makes more than 99% cache data available, making the cache performance twice as good as the original Flashcache after the system restarts. Finally, an efficient continuous data protection system, ST-CDP, which has the ability to roll back forward on the time axis, is designed. Snapshot in TRAP Continuous Data protection. Traditional continuous data protection system to save every change in the system. ST-CDP will produce a large amount of recorded data. ST-CDP can improve the compression ratio of data by introducing XOR operation and save storage space effectively by combining the traditional snapshot technology and the existing continuous data protection technology. The periodic insertion of snapshots in the check chain that records changes of data enables the system to ensure rapid and reliable data recovery in the event of failure. A mathematical model of how to insert and when to insert a snapshot is established. Based on this mathematical model, the continuous data protection system is designed and implemented on the Linux kernel. The overhead of ST-CDP is similar to that of the traditional continuous data protection technology, but its continuous data protection log space is very small, which is close to the real-time data recovery at any point.
【學(xué)位授予單位】：華中科技大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2013
【分類(lèi)號(hào)】：TP333

【共引文獻(xiàn)】

相關(guān)期刊論文 前7條

1 錢(qián)育蓉;于炯;王衛(wèi)源;孫華;廖彬;楊興耀;;云計(jì)算環(huán)境下軟硬件節(jié)能和負(fù)載均衡策略[J];計(jì)算機(jī)應(yīng)用;2013年12期

2 丁晨;袁良;;多核程序交互理論及應(yīng)用[J];計(jì)算機(jī)工程與科學(xué);2014年01期

3 丁晨;向曉婭;包斌;羅昊;羅英偉;汪小林;;Performance Metrics and Models for Shared Cache[J];Journal of Computer Science & Technology;2014年04期

4 韓永;姚念民;蔡紹濱;;基于局部性定量分析模型的自適應(yīng)替換算法LA-LRFU[J];計(jì)算機(jī)學(xué)報(bào);2014年07期

5 于炯;廖彬;張?zhí)?孫華;國(guó)冰磊;楊興耀;;云存儲(chǔ)系統(tǒng)節(jié)能研究綜述[J];計(jì)算機(jī)科學(xué)與探索;2014年09期

6 謝徐超;宋振龍;李瓊;魏登萍;方健;肖立權(quán);;WAPFTL:支持預(yù)測(cè)機(jī)制的負(fù)載自適應(yīng)閃存轉(zhuǎn)換層算法[J];計(jì)算機(jī)工程與科學(xué);2014年07期

7 陳釗;余鋒;陳婷婷;;基于日志結(jié)構(gòu)的閃存均衡回收策略[J];浙江大學(xué)學(xué)報(bào)(工學(xué)版);2014年01期

相關(guān)博士學(xué)位論文 前3條

1 伍江江;面向服務(wù)應(yīng)急響應(yīng)的數(shù)據(jù)保護(hù)關(guān)鍵技術(shù)研究[D];國(guó)防科學(xué)技術(shù)大學(xué);2012年

2 敬思遠(yuǎn);面向綠色虛擬數(shù)據(jù)中心資源管理的若干關(guān)鍵技術(shù)研究[D];電子科技大學(xué);2013年

3 王繼彬;磁盤(pán)陣列快速重構(gòu)，，擴(kuò)容及性能優(yōu)化研究[D];華中科技大學(xué);2013年

相關(guān)碩士學(xué)位論文 前5條

1 馮剛;面向云計(jì)算平臺(tái)的虛擬機(jī)故障注入工具研究與設(shè)計(jì)[D];哈爾濱工業(yè)大學(xué);2013年

2 余寶柱;數(shù)字視音頻技術(shù)的研究及在智能社區(qū)中的應(yīng)用[D];浙江工業(yè)大學(xué);2013年

3 劉磊;分布式塊存儲(chǔ)系統(tǒng)節(jié)能技術(shù)研究[D];華中科技大學(xué);2013年

4 吳東;一種基于SSD緩存的RAID1技術(shù)研究[D];華中科技大學(xué);2013年

5 劉玲;虛擬機(jī)內(nèi)存輕量級(jí)檢查點(diǎn)的研究[D];華中科技大學(xué);2013年

本文編號(hào)：1369042