Data snapshot method, device, computer equipment and storage medium

Abstract

The present application relates to a data snapshot method, device, computer equipment and storage medium. The method includes: acquiring the capacity of the data to be written after the snapshot, and comparing the capacity of the data to be written with a preset capacity; if the capacity of the data to be written is greater than or equal to the preset capacity, using the The data to be written is written to the snapshot volume in the redirection method; if the capacity of the data to be written is smaller than the preset capacity, the data to be written is written to the solid-state disk by means of the write redirection method If the background write-back thread detects that there is data writing in the SSD, the copy-on-write method is used to write the corresponding data in the source volume to the snapshot volume, and the data to be written in the SSD is written to the source volume. roll. The scheme of the present invention not only ensures the random write performance of large blocks of data, but also ensures the read performance of small blocks of data after random writing.

Description

technical field [0001] The present invention relates to the field of storage technologies, and in particular, to a data snapshot method, device, computer equipment and storage medium. Background technique [0002] Snapshot is a data protection technology commonly used in distributed storage systems. The essence of a snapshot is a mirror image of data at a certain point in time, which can be a copy of the data or a reference to the data. In existing production applications, snapshots can regularly backup and restore online data. When a user accidentally deletes data, the data can be rolled back to the previous timed snapshot to ensure normal business operations. Snapshot technology is becoming more and more important in applications, and data copying in several processing stages of the snapshot process is the core of the snapshot technology. [0003] At present, there are two main ways to copy data after a snapshot. The first method of copying data after snapshot is Copy On...

AI Technical Summary

Problems solved by technology

The first method of copying data after a snapshot is copy-on-write (COW for short). Go to the snapshot storage location, and then write the newly written data to the original storage location. The advantage of this method is that the read performance after the snapshot will not decrease, but the disadvantage is that the write performance after the snapshot will drop more due to the copying of the write location data; The second method of copying data after a snapshot is Redirect On Write (ROW for short). The principle is that the first write of the data after the snapshot is written directly to the new storage location, but the index of the write location data requires Point to the new storage location. The advantage of this technology is that the write performance will not decrease after the snapshot. The disadvantage is that a large number of random writes after the snapshot will cause the overall data read performance to drop significantly.

It can be seen that there are deficiencies in the post-snapshot data copy methods using COW or ROW in the prior art, so improvement is urgently needed

Images