媒體存儲(chǔ)技術(shù)-6存儲(chǔ)測(cè)評(píng)技術(shù)(完整版)
【正文】 0x56A – Rolling 0’s and Rolling 1’s – 0001 0010 0100 1000 0X1248 ? One type of test does not represent all applications. ? One type of application does not represent all uses for a storage product. ? Common types of application simulation testing: ? Test storage latency for messaging or other singlethreaded applications. ? Test peak storage bandwidth for data acquisition or data streaming environments. ? Test peak storage IOPS for databases. 1 1 Outstanding I/O simulates a single threaded application. Note: Single threaded applications are extremely sensitive to latency (server, HBA, switch and storage device). 25 25 Outstanding I/Os simulates a multithreaded application. 8 Small transfer request size simulates database transfers. Match the application’s read/write distribution. Database activity is mostly random. 512 Big transfer request size tests peak bandwidth. Match the application’s read/write distribution. A mostly sequential setting is best. ? Testing with the actual application is the best way to measure storage performance. ? Productionlike environment that can stress storage limits is desirable. ? Measure performance of different solutions: ? Compare OLTP response times. ? Compare batch run times. ? Compare sustained streaming rates. ? Operating system and application tools can help monitor storage performance. ? Risk vs. Reward. ? Risk: taking an unsupported, welltraveled evaluation unit and putting it in a production environment could promise application availability and expose unexpected system problems. ? Reward: sometimes this is the only way to know for certain that storage performance is acceptable for an application. ? Testing storage performance with file copy mands. ? Comparing storage devices backtoback without clearing server cache. ? Testing where the data set is so small the benchmark rarely goes beyond server cache. ? Testing peak device performance with one outstanding I/O. ? Testing peak bandwidth of storage with a PCI 32/33 PCI slot. ? Fetting to monitor processor utilization during testing. ? 網(wǎng)絡(luò)存儲(chǔ)的綜合評(píng)測(cè)指標(biāo)系統(tǒng)，不僅僅強(qiáng)調(diào)存儲(chǔ)的性能指標(biāo)，同時(shí)還包括功能、可用性和功耗等指標(biāo)，更科學(xué)地揭示不同結(jié)構(gòu)存儲(chǔ)系統(tǒng)的長(zhǎng)處和短處，便于進(jìn)行不同設(shè)備與系統(tǒng)之間的全面對(duì)比，為存儲(chǔ)產(chǎn)業(yè)的快速發(fā)展提供技術(shù)指導(dǎo)，為用戶購(gòu)買最合適應(yīng)用需求的存儲(chǔ)系統(tǒng)提供決策支持。 39。 39。 39。對(duì)于并發(fā)存取訪問(wèn)模式，每個(gè)進(jìn)程擁有一個(gè)屬于自己的操作文件，因此很容易實(shí)現(xiàn)按操作隊(duì)列進(jìn)行讀寫操作，進(jìn)程只需按照操作隊(duì)列循環(huán)讀寫相應(yīng)文件即可。 ? Reiserfts用于測(cè)試 Use新聞服務(wù)器上高速增加刪除文件性能測(cè)試； ? Postmark主要用于測(cè)試文件系統(tǒng)在郵件系統(tǒng)或電子商務(wù)系統(tǒng)中性能。 ? SGI開(kāi)發(fā)的 Webstone主要用于評(píng)測(cè)系統(tǒng)在不同環(huán)境、不同負(fù)載模式下的 Web服務(wù)性能 2. 事務(wù)處理性能型 ? 其中 Oracle公司的 ORION基準(zhǔn)測(cè)試主要用于對(duì)比不同層面和類型的磁盤用于 Oracle數(shù)據(jù)庫(kù)時(shí)的性能和吞吐量，是一款比較全面的針對(duì)數(shù)據(jù)庫(kù)應(yīng)用的 IO測(cè)試工具 ? 由 TPC(Transaction Processing Performance Council，事務(wù)處理性能委員會(huì) )負(fù)責(zé)定義了諸如 TPCC、 TPCH和 TPCW基準(zhǔn)測(cè)試之類的事務(wù)處理與數(shù)據(jù)庫(kù)性能基準(zhǔn)測(cè)試，并依據(jù)這些基準(zhǔn)測(cè)試項(xiàng)目發(fā)布客觀性能數(shù)據(jù)。 這類典型程序包括 IOmeter、 I/Ozone、IOGen和 Bonnie++等 。 2023年 10月 ， TPC推出了功耗測(cè)評(píng)基準(zhǔn) TPCEne
環(huán)評(píng)公示相關(guān)推薦
鄂ICP備17016276號(hào)-1