Reliable and scalable image transfer for data centers with low connectivity using redundancy detection

A system for transferring virtual machine images, comprising:

• one or more computer having a processor processors;
• one or more non-transitory computer-readable storage device media;
• program instructions embodied on the storage device stored on the non-transitory computer-readable storage media for execution by at least one of the one or more processor processors, the program instructions comprising:
• program instructions to analyze each of a plurality of virtual machine images present on a plurality of nodes to create image clusters corresponding to a plurality of data blocks present in the plurality of virtual machine images, the plurality of nodes including a source node and a target node, wherein each image cluster is associated with a grouping of data blocks and comprises a list of hash codes of the data blocks and further comprises an image cluster identifier;
• program instructions to generate a similarity matrix using the created image clusters;
• program instructions to select a virtual machine image present on the source node to be reconstituted on the target node;
• program instructions to identify a plurality of data block sets in the selected virtual machine image for transfer to the target node, using the similarity matrix;
• program instructions to transfer the plurality of data block sets to the target node, according to an optimal transfer plan;
• and
• program instructions to reconstitute the plurality of data block sets on the target node, using at least the transferred plurality of data block sets.

A computer program product for transferring virtual machine images, the computer program product comprising:

• a non-transitory computer-readable storage medium having program code embodied therewith, the program code readable/executable by a processor to perform a method comprising:
• analyzing each of a plurality of virtual machine images present on a plurality of nodes, by the processor, to create image clusters corresponding to a plurality of data blocks present in the plurality of virtual machine images, the plurality of nodes including a source node and a target node, wherein each image cluster is associated with a grouping of data blocks and comprises a list of hash codes of the data blocks and further comprises an image cluster identifier;
• generating a similarity matrix, by the processor, using the created image clusters;
• selecting a virtual machine image present on the source node, by the processor, to be reconstituted on the target node;
• identifying a plurality of data block sets in the selected virtual machine image, by the processor, for transfer to the target node, using the similarity matrix;
• transferring the plurality of data block sets to the target node, by the processor, according to an optimal transfer plan;
• and
• reconstituting the plurality of data block sets, by the processor, on the target node using at least the transferred plurality of data block sets.