Methods, apparatus, and systems to aggregate partitioned computer database data

A non-transitory computer-readable storage medium comprising instructions that, when executed, cause a machine to at least:

• identify a set of nodes from a plurality of nodes for use in preparing response to a request to query database data, the database data distributed across the plurality of nodes irrespective of a data content, the request received from an application;
• decompose the request to query the database data into a plurality of sub-queries;
• provide the plurality of sub-queries to queriers associated with respective ones of the identified set of nodes for execution;
• store, in response to a determination that a timeout has occurred, a hinted handoff notice for a node associated with the timeout;
• and
• combine results of execution of the respective ones of the plurality of sub-queries from the queriers of the identified set of nodes not associated with the timeout to generate a response to the request to query the database data.

A method for aggregation of partitioned data, the method comprising:

• identifying a set of nodes from a plurality of nodes for use in preparing response to a request to query database data, the database data distributed across the plurality of nodes irrespective of a data content, the request received from an application;
• decomposing the request to query the database data into a plurality of sub-queries;
• providing the plurality of sub-queries to queriers associated with respective ones of the identified set of nodes for execution;
• storing, in response to a determination that a timeout has occurred, a hinted handoff notice for a node associated with the timeout;
• and
• combining results of execution of the respective ones of the plurality of sub-queries from the queriers of the identified set of nodes not associated with the timeout to generate a response to the request to query the database data.