Data operating method of redundant arrays of independent disk and device

Abstract

The invention provides a data operating method of redundant arrays of an independent disk and a device; wherein the method comprises the following steps: creating a logic unit based on RAID and dividing the logic unit into multiple grain size intervals, and carrying out striping processing based on the grain size intervals; before carrying out write operation on the logic unit, judging whether the sizes of the strips to be written into the grain size intervals are matched with the current values of strip parameters; if not, adjusting the sizes of the strips to be written into the grain size intervals according to the current values of the strip parameters and carrying out write operation according to the adjusted sizes of the strips; or, directly carrying out write operation according to the sizes of the strips to be written into the grain size intervals; wherein the strip parameter has an initial value and is updated according to the writing data quantity of write operation on the logic unit. According to the data operating method, the data read / write performance of the RAID can be improved.

Description

technical field [0001] The present invention relates to the technical field of redundant array of independent disks (RAID, Redundant Array of Independent Disks), in particular to a data operation method and device of redundant array of independent disks. Background technique [0002] RAID is aggregated by multiple disks, which can provide higher access speed, better availability, and data redundancy protection while providing large capacity. Wherein, the disks in the RAID may be referred to as member disks of the RAID. The following briefly introduces the related concepts of RAID: [0003] A partition (Extent) is a storage block with consecutive addresses on a disk. A disk can be divided into multiple partitions, and each partition can be of equal size. Partitions are also sometimes called logical disks. [0004] Block (Strip), divide a partition into multiple blocks of equal size and adjacent addresses. These blocks are called blocks. Chunks are generally thought of as...

AI Technical Summary

Problems solved by technology

[0011] 1. After the array is created, the stripe size is fixed and cannot be changed

If the business I / O changes for special reasons and does not match the stripe size, it will appear that each write operation needs to read a large amount of unchanged data, which affects the efficiency of the write operation

[0012] 2. An array can only be suitable for a specific size of I / O business. When adding a new I / O feature business, using the free space of the existing array will affect the read and write performance of the new business

[0014] The disadvantage of the above scheme is that,

[0015] 1. When changing the stripe size, the stripes of the entire RAID array need to be adjusted, and a large amount of data is migrated. The speed is very slow, and the processing pressure of the storage device controller is huge.

[0016] 2. After the adjustment, the RAID array is still only suitable for a certain size of I / O business. When adding a new I / O feature business, using the free space of the existing array will still affect the read and write performance

Images