Raid overlapping
AssigneeInternational Business Machines Corporation
InventorsSeiji Kobayashi, Toshiyuki Sanuki
Life of this patent
Estimating the term…
Abstract
A first array of disk drives overlaps with a second array of disk drives in a Redundant Array of Inexpensive Drives (RAID) system, in which the first and second arrays share at least one disk drive. A first stripe of data from a first client is stored in the first array, and a second stripe of data from a second client is stored in the second array. The shared disk drives are less than the number of drives needed to reconstruct a full stripe. Thus, in the event of a drive failure in the first array, the first client can reconstruct the first data stripe, but is never able to reconstruct the second stripe. Likewise, in the event of a drive failure in the second array, the second client can reconstruct the second data stripe, but is never able to reconstruct the first stripe.
Claims7
A disk storage server for providing a storage area of a storage device to a client, the disk storage server comprising:
- a storage device group composed of multiple storage devices, wherein the multiple storage devices are divided into a first array that is assigned to a first client and a second array that is assigned to a second client;
- and
- a data processing unit for dividing a write data in a write request so that concatenating the divided data is able to restore the original information, and for writing the data so that said plural storage devices storing the write data of each client partly overlap with each other, and wherein a quantity of shared storage devices, that are shared between the first and second clients, is equal to n−(t+1), wherein n is a total number of storage devices assigned to both the first and second clients, and wherein t is a total number of storage devices that can fail within a storage device array while still allowing data in the storage device array to be restored, wherein said data processing unit changes a method for dividing the write data for each client.
A computer apparatus comprising:
- a storage device group composed of multiple storage devices, wherein the multiple storage devices are divided into a first array that is assigned to a first client and a second array that is assigned to a second client;
- and
- a data processing unit for reading or writing data from or into said storage devices, wherein said data processing unit, when writing data into said storage devices, divides each data file into multiple pieces of divided data so that concatenating the divided data may restore the original information, and wherein the data processing unit writes the data so that storage devices storing the divided data of a certain data file and storage devices storing the divided data of another data file partly overlap, and wherein a quantity of shared storage devices, that are shared between the first and second clients, is equal to n−(t+1), wherein n is a total number of storage devices assigned to both the first and second clients, and wherein t is a total number of storage devices that can fail within a storage device array while still allowing data in the storage device array to be restored, wherein said data processing unit changes the number of pieces of divided data for each data file.
A computer apparatus comprising:
- a storage device group composed of multiple storage devices, wherein the multiple storage devices are divided into a first array that is assigned to a first client and a second array that is assigned to a second client;
- and
- a data processing unit for reading or writing data from or into said storage devices, wherein said data processing unit, when writing data into said storage devices, divides each data file into multiple pieces of divided data so that concatenating the divided data may restore the original information, and wherein the data processing unit writes the data so that storage devices storing the divided data of a certain data file and storage devices storing the divided data of another data file partly overlap, and wherein a quantity of shared storage devices, that are shared between the first and second clients, is equal to n−(t+1), wherein n is a total number of storage devices assigned to both the first and second clients, and wherein t is a total number of storage devices that can fail within a storage device array while still allowing data in the storage device array to be restored, wherein said data processing unit changes the size of divided data for each data file or each divided data.
Dependencies are inferred from the claim text.