The present invention discloses a method and system for carrying out IO deduplication on non-homologous data of a storage system in the operation process, and relates to the field of data processing. The method comprises: S1, by a virtual machine, reading data and acquiring a characteristic code of the data; S2, determining whether the characteristic code of the data exists in a dedicated cache, proceeding to S3 if yes, and if not, proceeding to S4; S4, calling data which is stored in the dedicated cache and corresponds to the characteristic code of the data, and proceeding to S5; S4, calling data in an image file, which corresponds to the characteristic code of the data, and proceeding to S5; and S5, enabling the virtual machine to work by using the acquired data. The system comprises: a physical machine system module, a physical machine caching module, a virtual machine image file module and a virtual machine system module. The method and system provided by the present invention solve the problem that when a plurality of virtual machines simultaneously read respective image files, a server system cache is easy to reach a bottleneck.