Join queries in data virtualization-based architecture

A non-transitory computer-readable medium having program instructions stored thereon that are capable of causing a compute cluster to perform operations comprising:

• maintaining a plurality of virtual data sources (VDSs) based on a set of corresponding origins, wherein a given VDS of the plurality of VDSs includes a bitmap index representative of a portion of data stored at the set of origins;
• receiving a request for data stored across at least first and second bitmap indexes of the plurality of VDSs, wherein the first bitmap index is distributed across at least two compute nodes of the compute cluster such that a first portion of the first bitmap index is maintained by a first compute node and a second portion of the first bitmap index is maintained by a second compute node;
• performing a join operation to generate a join result having data from the first and second bitmap indexes, wherein the join operation is collectively performed by the first and second compute nodes that store respective portions of the first and second bitmap indexes;
• and
• returning a response that includes the join result.

A distributed compute cluster system, comprising:

• at least one processor;
• and
• memory having program instructions stored thereon that are executable by the at least one processor to perform operations comprising:
• maintaining, by the distributed compute cluster system, a plurality of virtual data sources (VDSs) based on a set of corresponding origins, wherein a given VDS of the plurality of VDSs includes a bitmap index representative of a portion of data stored at the set of origins;
• receiving, by the distributed compute cluster system, a request for data stored across at least first and second bitmap indexes of the plurality of VDSs, wherein the first bitmap index is distributed across at least two compute nodes such that a first portion of the first bitmap index is maintained by a first compute node and a second portion of the first bitmap index is maintained by a second compute node;
• performing, by the distributed compute cluster system, a join operation to generate a join result having data from the first and second bitmap indexes, wherein the join operation is collectively performed by the first and second compute nodes that store respective portions of the first and second bitmap indexes;
• and
• returning, by the distributed compute cluster system, a response that includes the join result.