Virtual machine image access de-duplication

A system for de-duplicating virtual machine image accesses, comprising:

• at least one distinct software module, each distinct software module being embodied on a tangible computer-readable medium;
• a memory;
• and
• at least one processor coupled to the memory and operative for:
• identifying two or more blocks having identical content in two or more images in a virtual machine image repository;
• generating a block map for mapping the two or more blocks having identical content into a same block, wherein each entry in the block map points one of the two or more blocks to a destination address in a local disk cache associated with one or more blocks based on block content;
• deploying a virtual machine image by reconstituting an image from the block map and fetching any unique blocks remotely on-demand;
• de-duplicating virtual machine image accesses by storing the deployed virtual machine image in the local disk cache;
• and
• redirecting a read request for one of the two or more blocks to the corresponding destination address in a local disk cache based on the block map upon receiving the read request at a cache device.

A distributed storage system, comprising:

• distinct software modules, wherein each distinct software module is embodied on a tangible computer-readable memory and executing on a hardware processor, the software modules comprising:
• a metadata module which identifies two or more blocks having identical content in two or more images in a virtual machine image repository and generates a block map for mapping the two or more blocks having identical content into a same block, wherein each entry in the block map points one of the two or more blocks to a destination address in a local disk cache associated with one or more blocks based on block content;
• an access mapping module which redirects virtual machine an image read request for one of the two or more blocks to the corresponding destination address in a local disk cache according to the block map upon receiving the read request at a cache device;
• and
• a local disk cache management module which fetches blocks remotely on-demand, and stores virtual machine images in a local disk cache.

A method for de-duplicating virtual machine image accesses, the method comprising:

• identifying two or more blocks having identical content in two or more images in a virtual machine image repository;
• generating a block map for mapping the two or more blocks having identical content into a same block, wherein each entry in the block map points one of the two or more blocks to a destination address in a local disk cache associated with one or more blocks based on block content;
• deploying a virtual machine image by reconstituting an image from the block map and fetching any unique blocks remotely on-demand;
• de-duplicating virtual machine image accesses by storing the deployed virtual machine image in the local disk cache;
• and
• redirecting a read request for one of the two or more blocks to the corresponding destination address in a local disk cache based on the block map upon receiving the read request at a cache device;
• wherein said identifying, said generating, said deploying, said de-duplicating and said redirecting are carried out by a computer device.