Tiered Storage

Tiered storage is the assignment of different categories of data to different types of storage media in order to reduce total storage cost. Categories may be based on levels of protection needed, performance requirements, frequency of use, and other considerations. Since assigning data to particular media may be an ongoing and complex activity, some vendors provide software for automatically managing the process based on a company-defined policy. As an example of tiered storage, tier 1 data (such as mission-critical, recently accessed, or top secret files) might be stored on expensive and high-quality media such as double-parity RAIDs (redundant arrays of independent disks). Tier 2 data (such as financial, seldom-used, or classified files) might be stored on less expensive media in conventional storage area networks (SANs). As the tier number increased, cheaper media could be used. Thus, tier 3 in a 3-tier system might contain event-driven, rarely used, or unclassified files on recordable compact discs (CD-Rs) or tapes.

Grid Storage

Grid storage is a general term for any approach to storing data that employs multiple self-contained storage nodes interconnected so that any node can communicate with any other node without the data having to pass through a centralized switch. Each storage node contains its own storage medium, microprocessor, indexing capability, and management layer. Several topologies have been designed and tested, including the interconnection of nodes in a hypercube configuration, similar to the way nodes are interconnected in a mesh network. Grid storage offers at least three advantages over older storage methods: higher fault-tolerance and redundancy, better performance under conditions of fluctuating load and lower cost.

分級(jí)存儲(chǔ)

分級(jí)存儲(chǔ)是把不同類(lèi)別的數(shù)據(jù)分配給不同類(lèi)型的存儲(chǔ)介質(zhì)，以減少存儲(chǔ)成本。(數(shù)據(jù))類(lèi)別可以基于所需保護(hù)的等級(jí)、性能要求、使用頻度以及其他考慮。由于將數(shù)據(jù)分配給特定介質(zhì)可能是一個(gè)在行進(jìn)中完成的復(fù)雜動(dòng)作，有些供應(yīng)商提供軟件，依據(jù)(用戶)公司制定的策略自動(dòng)管理這個(gè)過(guò)程。下面是分級(jí)存儲(chǔ)的例子，1級(jí)數(shù)據(jù)(如關(guān)鍵任務(wù)、最近訪問(wèn)過(guò)的或絕密級(jí)文件)可以存儲(chǔ)在昂貴的、高質(zhì)量介質(zhì)(如雙奇偶檢測(cè)磁盤(pán)陣列)RAID(獨(dú)立磁盤(pán)冗余陣列)上。2級(jí)數(shù)據(jù)(如財(cái)務(wù)、很少用的、或保密文件)可以存儲(chǔ)在常規(guī)的存儲(chǔ)區(qū)域網(wǎng)絡(luò)中不太貴的介質(zhì)上。隨著級(jí)數(shù)的增加，可以使用更便宜的介質(zhì)。因而，在分3級(jí)的系統(tǒng)中第3級(jí)可以包括那些事件驅(qū)動(dòng)的、極少用的、或不保密的文件，它們被存儲(chǔ)在可刻錄的光盤(pán)或磁帶上。

網(wǎng)格存儲(chǔ)

網(wǎng)格存儲(chǔ)是一個(gè)普通術(shù)語(yǔ)，指任何使用多個(gè)互連的自給自足的存儲(chǔ)節(jié)點(diǎn)存儲(chǔ)數(shù)據(jù)的方法，其數(shù)據(jù)不必通過(guò)中央交換機(jī)一個(gè)節(jié)點(diǎn)就能與任何節(jié)點(diǎn)通信。每個(gè)存儲(chǔ)節(jié)點(diǎn)包含自己的存儲(chǔ)介質(zhì)、微處理器、編制索引的能力以及管理層。已經(jīng)有幾種拓?fù)浣Y(jié)構(gòu)被設(shè)計(jì)出來(lái)并做過(guò)試驗(yàn)，其中一個(gè)是以超級(jí)立方配置互連節(jié)點(diǎn)，與網(wǎng)狀網(wǎng)絡(luò)中節(jié)點(diǎn)互連的方式類(lèi)似。網(wǎng)格存儲(chǔ)比起老一些的存儲(chǔ)方法至少有三大優(yōu)點(diǎn)：更高的容錯(cuò)與冗余度、在負(fù)載波動(dòng)的情況下有更好的性能、以及更低的成本。