【摘要】：隨著大規(guī)�；ヂ�(lián)網(wǎng)應(yīng)用的高速發(fā)展，給存儲(chǔ)系統(tǒng)的可擴(kuò)展性提出了更高的要求，鍵值數(shù)據(jù)庫(kù)由于其簡(jiǎn)單高效的數(shù)據(jù)模型在可擴(kuò)展性方面較傳統(tǒng)的數(shù)據(jù)庫(kù)系統(tǒng)有很大的優(yōu)勢(shì)。另一方面，隨著硬件的發(fā)展，固態(tài)盤(pán)的性?xún)r(jià)比逐步提高，已經(jīng)成為越來(lái)越多系統(tǒng)的首選，其隨機(jī)讀的優(yōu)勢(shì)與互聯(lián)網(wǎng)應(yīng)用的特征高度符合，但是其寫(xiě)性能的相對(duì)低下以及擦除次數(shù)的限制影響了它的應(yīng)用場(chǎng)景，于是將固態(tài)盤(pán)與磁盤(pán)相結(jié)合的融合存儲(chǔ)系統(tǒng)得到了大家的廣泛關(guān)注。因此針對(duì)鍵值數(shù)據(jù)庫(kù)而設(shè)計(jì)的融合存儲(chǔ)系統(tǒng)是一個(gè)有價(jià)值的結(jié)合點(diǎn)。 針對(duì)Web應(yīng)用的負(fù)載特點(diǎn)，通過(guò)日志的方式順序的記錄對(duì)鍵值數(shù)據(jù)庫(kù)的操作，所有的操作都僅僅是順序的寫(xiě)入內(nèi)存，當(dāng)內(nèi)存中的數(shù)據(jù)達(dá)到了一定閾值以后一次刷寫(xiě)到后端存儲(chǔ)上，日志的方式一定程度上是通過(guò)犧牲讀性能來(lái)優(yōu)化寫(xiě)性能，所以和固態(tài)盤(pán)有天然的互補(bǔ)關(guān)系。由于后端固態(tài)盤(pán)與磁盤(pán)的不同特性，使用層次化的方法將寫(xiě)的特點(diǎn)進(jìn)行分類(lèi)后寫(xiě)入不同的設(shè)備上，并設(shè)計(jì)實(shí)現(xiàn)了一個(gè)可定制文件放置與遷移策略的文件系統(tǒng)HybridFS，，通過(guò)監(jiān)控分析腳本可以對(duì)同一文件系統(tǒng)中不同特點(diǎn)的文件選擇不同的放置與遷移策略。針對(duì)鍵值數(shù)據(jù)庫(kù)的文件訪問(wèn)特點(diǎn)，日志類(lèi)文件多是一次寫(xiě)很少讀，所以直接寫(xiě)入磁盤(pán)。元數(shù)據(jù)類(lèi)文件讀寫(xiě)都很頻繁但是文件大小和數(shù)量偏少，因此寫(xiě)入固態(tài)盤(pán)。對(duì)數(shù)據(jù)文件由于其海量、定長(zhǎng)、一次寫(xiě)多次讀的特點(diǎn)，根據(jù)負(fù)載特點(diǎn)選擇性的寫(xiě)入磁盤(pán)或者固態(tài)盤(pán)。針對(duì)純寫(xiě)入型負(fù)載使用概率選擇的方式比Flashcache提升了5%-56%，而對(duì)于讀寫(xiě)混合行負(fù)載使用LRU的遷移方式相比Flashcache有4%-14%的性能提升。
[Abstract]:With the rapid development of large-scale Internet applications, the scalability of storage system is higher. Because of its simple and efficient data model, key-valued database has great advantages over traditional database system in scalability. On the other hand, with the development of hardware, the performance-price ratio of solid disk has been gradually improved, which has become the first choice of more and more systems, and its advantages of random reading are highly consistent with the characteristics of Internet applications. However, the relatively low writing performance and the limitation of erasure times affect its application scenario, so the fusion storage system which combines solid-state disk and disk has been paid more and more attention. Therefore, the fusion storage system designed for key-valued database is a valuable combination point. According to the load characteristics of Web application, the operation of key value database is recorded sequentially by logging, and all the operations are only written to memory sequencely. when the data in memory reaches a certain threshold, it is brushed to the back end storage once. The way of logging is to optimize writing performance at the expense of reading performance, so it is naturally complementary to solid-state disk. Because of the different characteristics of back-end solid-state disk and disk, the characteristics of writing are classified and written to different devices by hierarchical method, and a file system HybridFS, with customizable file placement and migration strategy is designed and implemented. Different placement and migration strategies can be selected for files with different characteristics in the same file system by monitoring and analyzing scripts. According to the file access characteristics of key-valued database, log class files are mostly written and rarely read at a time, so they are written directly to disk. Metadata files are read and written frequently, but the size and number of files are small, so they are written to solid-state disks. The data file is selectively written to disk or solid state disk according to the characteristics of load because of its mass, fixed length and multiple reading at a time. The choice of usage probability for pure write load is 5% 鈮

本文編號(hào)：2492413