公开(公告)号：US5504858A

公开(公告)日：1996-04-02

申请号：US385227

申请日：1995-02-08

申请人： Robert A. Ellis ,  Clark E. Lubbers ,  Steven J. Malan ,  Peter Rivera ,  Sid Snyder ,  David W. Thiel ,  Richard B. Wells

发明人： Robert A. Ellis ,  Clark E. Lubbers ,  Steven J. Malan ,  Peter Rivera ,  Sid Snyder ,  David W. Thiel ,  Richard B. Wells

IPC分类号： G06F11/10 ,  G06F11/00

CPC分类号： G06F11/1076

摘要： A data storage system using a RAID array and a logging process and apparatus that identifies a parity block that may not contain the proper parity for its associated data blocks and which prevents such inconsistent parity information from being used in the regeneration of unavailable data. A small fraction of the blocks of each disk are dedicated to storing parity metadata bits. The parity metadata is associated with the parity blocks and identifies whether or not each parity block contains the proper parity information for its associated data blocks or may contain invalid information. The data integrity of the RAID array is preserved by preventing the generation of undetected corrupt data.

摘要翻译： 一种使用RAID阵列的数据存储系统以及记录过程和装置，其识别可能不包含其关联数据块的正确奇偶校验的奇偶校验块，并且防止这种不一致的奇偶校验信息被用于不可用数据的再生。 每个磁盘的一小部分块专用于存储奇偶校验元数据位。 奇偶校验元数据与奇偶校验块相关联，并且识别每个奇偶校验块是否包含其相关数据块的适当奇偶校验信息，或者可能包含无效信息。 通过防止产生未检测到的损坏的数据来保护RAID阵列的数据完整性。

公开(公告)号：US5519849A

公开(公告)日：1996-05-21

申请号：US329046

申请日：1994-10-25

申请人： Steven J. Malan ,  Sid Snyder ,  David W. Thiel ,  Alan Rollow

发明人： Steven J. Malan ,  Sid Snyder ,  David W. Thiel ,  Alan Rollow

IPC分类号： G06F3/06 ,  G06F9/00

CPC分类号： G06F3/0601 ,  G06F2003/0697

摘要： Data storage systems using a RAID-4 or RAID-5 organization divide an application I/O request into a number of individual I/O requests, each of which is contained within the boundaries of a single strip. The data blocks of each chunk on a strip responsive to an I/O request can form a complex geometric pattern requiring complicated operations to perform the I/O request. To simplify the necessary operations, each individual I/O request to a strip is divided into at most three requests targeted to data blocks forming a rectangle and each of these rectangles are processed as a unit. If a data block within a rectangle is unavailable, then the request to that rectangle is further subdivided into at most two requests targeted to data blocks forming smaller, non-overlapping rectangles which collectively are the original rectangle. The recursive decomposition of rectangles into smaller rectangles isolates the data block with an error and permits the selection of fewer and less complicated operation algorithms to complete the I/O request.

摘要翻译： 使用RAID-4或RAID-5组织的数据存储系统将应用程序I / O请求划分为多个单独的I / O请求，每个I / O请求都包含在单个条带的边界内。 响应于I / O请求的条上的每个块的数据块可以形成需要复杂操作以执行I / O请求的复杂几何图案。 为了简化必要的操作，对条带的每个单独的I / O请求被分成最多三个针对形成矩形的数据块的请求，并且这些矩形中的每一个作为一个单元被处理。 如果矩形内的数据块不可用，则对该矩形的请求进一步细分为最多两个针对数据块的请求，这两个请求形成较小的非重叠矩形，它们是原始矩形。 将矩形递归分解成较小的矩形将数据块与错误隔离，并允许选择越来越少复杂的操作算法来完成I / O请求。