Method for improving usability of disk and disk array controller

Abstract

The invention discloses a method for improving the usability of a disk and a disk array controller. The method comprises the following steps of: arranging a main data memory space in a disk array; arranging more than one backup data memory spaces; determining a first main data memory space on the damaged track when detecting the damage of part track of the disk in the disk array; selecting an idle first backup data memory space; establishing a corresponding relationship between the block addresses contained by the first main data memory space and the block addresses contained by the first backup data memory space; receiving the visiting instructions of the block contained by the first main data memory space; querying the blocks contained by the first backup data memory space according to the block address in the visiting instructions and the corresponding relationship; and visiting the block contained by the first backup data memory space. The method and the disk array controller can improve the usability of the disk in the disk array.

Description

technical field [0001] The invention relates to network communication technology, in particular to a method for improving disk availability and a disk array controller. Background technique [0002] At present, in order to improve the storage performance and data security of the hard disk, a Redundant Array of Independent Disks (RAID, Redundant Array of Independent Disks,) is called a disk array for short. Disk array technology is to use the combination of multiple hard disks to form an array, and selectively distribute data on multiple disks in an array, and use the parallel access and parallel transmission of the multiple disks to match the bandwidth and improve the performance. Access speed, for the host, it is equivalent to a fast and large-capacity disk, thereby improving the availability and storage capacity of network data. [0003] In a disk array, data is organized using extents, strips, and stripes. figure 1 It is a schematic diagram of the partition structure in...

AI Technical Summary

Problems solved by technology

[0005] However, in actual business, in many cases, not all tracks in a disk will be damaged, but only some of the tracks will be damaged. The existing technology also considers that the entire disk is unusable when some tracks are damaged, and replaces it with a new one. This method greatly reduces the availability of disks in the disk array and greatly wastes disk resources.

[0006] Furthermore, for a disk array with a fault-tolerant mechanism, when only some tracks in the disk are damaged and the rest of the tracks are normal, the data in the stripes on the normal tracks can actually be read normally, but the existing technology is due to replacement The new disk, therefore, needs to rebuild the data on all the tracks on the replaced disk, that is, not only the data in the stripes on the damaged track, but also the data in the stripes on the normal tracks that could have been read normally. The data for also needs to be reconstructed, resulting in excessively long data reconstruction times and a large amount of processing power

[0007] Further, due to the too long time for data reconstruction in the prior art, it is easy to damage the tracks of other disks during the reconstruction period, which easily exceeds the number of unusable disks that the disk array can tolerate, causing the entire disk array to be damaged. Unavailable, resulting in loss of all data in the entire disk array

Images