Distributed data store for efficient snapshot management using collocated metadata

A non-transitory computer readable medium having stored thereon a sequence of instructions which, when executed by a processor causes a set of acts comprising:

• maintaining a cluster comprising a plurality of nodes storing a plurality of objects, each object of the objects in the plurality of objects having an associated subset of metadata such that the plurality of objects has a plurality of subsets of metadata to manage data for respective objects of the plurality of objects, wherein individual storage units correspond to individual objects of the plurality of objects;
• storing metadata for a storage unit corresponding to an object, and metadata for snapshots of the storage unit corresponding to the object, collocated within a same subset of metadata corresponding to the object;
• and
• processing access requests to data on at least one node in the plurality of nodes using the plurality of subsets of the metadata at least by, for each access request:
• accessing a corresponding subset of metadata corresponding to a requested object of the access request to obtain extent information, wherein the extent information corresponds to one or more of the metadata for the storage unit or the metadata for a snapshot of the storage unit collocated in the subset of metadata corresponding to the access request;
• and
• executing an access operation, corresponding to the access request, on one or more portions of the data corresponding to the requested object, based on the extent information.

A computing system comprising:

• a memory to hold a set of instructions;
• and
• a computer processor to execute the set of instructions, which when executed cause a set of acts comprising:
• maintaining a cluster comprising a plurality of nodes storing a plurality of objects, each object of the objects in the plurality of objects having an associated subset of metadata such that the plurality of objects has a plurality of subsets of metadata to manage data for respective objects of the plurality of objects, wherein individual storage units correspond to individual objects of the plurality of objects;
• storing metadata for a storage unit corresponding to an object, and metadata for snapshots of the storage unit corresponding to the object, collocated within a same subset of metadata corresponding to the object;
• and
• processing access requests to data on at least one node in the plurality of nodes using the plurality of subsets of the metadata at least by, for each access request:
• accessing a corresponding subset of metadata corresponding to a requested object of the access request to obtain extent information, wherein the extent information corresponds to one or more of the metadata for the storage unit or the metadata for a snapshot of the storage unit collocated in the subset of metadata corresponding to the access request;
• and
• executing an access operation, corresponding to the access request, on one or more portions of the data corresponding to the requested object, based on the extent information.