Method and device for writing data

Abstract

The invention discloses a device for writing data. The device for writing data includes: a first obtaining module, used for redirecting a snapshot while writing. When writing an operation command, obtain the size information of the write data contained in the write operation command; the write operation module is used to apply for storage matching the size information from a preset storage area according to the size information of the write data space, and perform write operations in the requested storage space. The invention also discloses a method for writing data. The invention realizes the purpose of efficiently writing data without reading the data of the original storage block in the process of redirecting the snapshot while writing.

Description

technical field [0001] The invention relates to the technical field of data storage, in particular to a method and device for writing data. Background technique [0002] With the development of information technology, there are more and more digital resources, and data security and backup are becoming more and more important. At present, snapshot technology is usually used to back up data. According to the definition of the Storage Networking Industry Association (SNIA), a snapshot is a fully available copy of a set of data, including an image of the corresponding data at the moment of copy initialization. There are two types of existing snapshot mainstream technologies, one is copy on first write (Copy On First Write, COFW), and the other is redirect on write (Redirect On Write, ROW). [0003] In the distributed storage scenario, data is stored with a block (Chunk) as the smallest unit. However, when writing operations in the redirected-on-write snapshot technology, a new ...

AI Technical Summary

Problems solved by technology

[0003] In the distributed storage scenario, data is stored with a block (Chunk) as the smallest unit. However, when writing operations in the redirected-on-write snapshot technology, a new chunk space of a chunk size is usually allocated for writing operations. , when the data written in the write operation is smaller than the chunk size, first read the data of the old chunk in the source volume, then merge the data and write to the new chunk space, because this method of writing data needs to read the data first, merge The data is written into the chunk again, and the writing operation process is cumbersome, especially when the writing operation is frequent, a large number of reading and merging operations reduce the performance of writing data

Images