发明名称 Classifying data for deduplication and storage
摘要 In a method of classifying data for deduplication, data to be classified is accessed. The data is classified into a deduplication classification in accordance with a data content aware data classification policy such that classified data is created. The data classification policy includes a plurality of deduplication classifications.
申请公布号 US9176978(B2) 申请公布日期 2015.11.03
申请号 US200912366563 申请日期 2009.02.05
申请人 发明人 Wideman Roderick B.
分类号 G06F17/30 主分类号 G06F17/30
代理机构 代理人
主权项 1. A non-transitory computer-readable storage medium storing computer-executable instructions that when executed by a computer cause the computer to perform a method, the method comprising: accessing data to be classified; classifying the data into a deduplication classification based, at least in part, on a classification policy where the classification policy explicitly indicates at least a blocklet size for the data, where classifying the data into a deduplication classification based, at least in part, on the classification policy includes classifying the data based, at least in part, on an access requirement associated with the data; controlling a processor to selectively perform a whole file deduplication methodology on an item upon determining that the deduplication classification associated with the item is a whole file deduplication policy; and controlling the processor to perform a sub-file blocklet level deduplication methodology on the item upon determining that the deduplication classification associated with the item is a sub-file blocklet level deduplication policy, where the sub-file blocklet level deduplication methodology is controlled, at least in part, by the deduplication classification associated with the item, where the item comprises a file or a data stream, and where the different deduplication methodologies deduplicate with respect to average blocklet size, minimum blocklet size, or maximum blocklet size as controlled by the deduplication classification.
地址