A Method for Distributed Storage Snapshots

Abstract

The invention discloses a snapshot method for distributed storage. For a distributed storage system, original volumes and snapshot volumes are described by using independent virtual view objects, andthe snapshot volumes have complete physical copies, so that the dependency of the snapshot volumes on the existence of the original volumes is released. All the virtual view objects, namely VDIs, andsnapshots thereof share the whole distributed storage resource pool, and the snapshot volumes do not need independent reserved storage space any more, so that the dependency of the snapshot volumes onthe original volumes is released. On the basis of the copy-on-write (COW) and redirection-on-write (ROW) mechanisms, a log mode is introduced, the problems, caused by the snapshots, of great reduction of the read and write performance of the original volumes and the consistence of performance are solved, and meanwhile, the bottleneck that the number of the snapshots is limited is broken through.The efficiency and the availability of the snapshots in the distributed storage system are obviously improved, and therefore, the availability of the system is enhanced.

Description

technical field [0001] The invention belongs to the technical field of snapshots, in particular to a method for distributed storage of snapshots. Background technique [0002] A snapshot (Snapshot) is a mirror image of a data set at a specific moment, also known as an instant copy, which is a complete and available copy of the data set. The storage network industry association SNIA defines a snapshot as: a fully available copy of a specified data set, which includes an image of the corresponding data at a certain point in time. A snapshot can be either a copy or a replica of the data it represents. [0003] At the storage system level, snapshots usually use logical units as snapshot entities, and replicate data at the granularity of data blocks. In distributed storage, snapshots use logical volumes as snapshot entities, and logical units as granularity for data replication. The snapshot generated is a logical copy of the original storage system, and the original storage s...

AI Technical Summary

Problems solved by technology

[0017] (2) The snapshot cannot be independent of the original volume

The snapshot volume only stores the updated data of the original volume, and cannot get a complete physical copy

If a full physical copy is required, it must rely on the data of the original volume, and the snapshot volume cannot exist independently of the original volume

[0019] (3) The number of snapshots is limited

The second is storage capacity. The snapshot volume needs to reserve a certain percentage of storage space. For the original volume that is frequently read and written, if there are too many snapshots, the amount of updated data will inevitably be large, which may lead to insufficient reserved storage space and cause the snapshot to fail.

Images