Optimizing method for storing virtual machine mirror images based on CAS (content addressable storage)

The invention relates to an optimizing method for storing virtual machine mirror images based on CAS (content addressable storage). The method specifically comprises the following steps of adopting a CAS method to divide a virtual machine mirror image file into blocks, calculating fingerprint sequences, and judging the repetitive data through the fingerprint sequences. Only one data block is reserved for the data blocks with the same content, and the number of corresponding share times is stored in each block file. The original file is actually stored with the finger sequences (as shown in Figure 3), and the data part is stored in a shared storage system. To ensure the transparent storage of a virtual machine monitor and the portability of the shared storage system, the operation process of the virtual machine mirror images is packaged into the realizing process of a corresponding system calling and response interface by a FUSE (filesystem in user space)-based framework, so as to service a FUSE inner module to obtain an I/O (input/output) request generated by an upper-layer user operating a virtual machine, and convert the direct storage of the virtual machine mirror image files into the storage based on the CAS method. The method for eliminating the repetitive data based on the CAS has the advantages that the occupation amount of disks of the vertical machine mirror images is reduced by more than 50%, and the application prospect is wide for the current states of the large-scale application of the existing virtual machine.