| 摘要 |
A Redundant Array of Independent Disks (RAID) system that is adaptable to host Input/Output traffic, wherein the RAID configuration is hidden from the host computer, and wherein the system uses various methods for striping and organizing data across the array when disks are added or removed. The system dynamically determines the RAID configuration used to store host data. To maximize response time and avoid a write penalty, small write operations are mapped into RAID 1 configurations, and medium and large write operations are mapped into RAID 3 configurations. The data are migrated into RAID 5 configurations as a background operation, to minimize the disk space lost. The system hides configuration changes necessary for the addition and/or removal of disks to/from the disk array by unstriping data, adding or deleting (removing) a disk and then restriping data over all the disks. The methods may include steps of dividing data blocks into a plurality of square portions, and exchanging data in sets of blocks of each of the square portions, with the exchanging step including locating a diagonal set of blocks within a selected square portion, and exchanging all sets of blocks equidistant from the diagonal, on opposite sides of the diagonal, and in a line perpendicular to the diagonal. While these changes are in progress, the disk array remains on-line and most host data is available for access and modification. |
