Flexible computing

A system comprising:

• one or more processors of a machine;
• and
• a memory storing instructions that, when executed by the one or more processors, cause the machine to perform operations comprising:
• receiving, by a first server, query request information from a plurality of query coordinators;
• generating a current local demand based on the received query request information;
• transmitting the current local demand to a global background service over a network;
• receiving a first allocation of a first number of computing resources from the global background service;
• assigning the first number of computing resources to the plurality query coordinators;
• receiving updated information relating to query requests from the plurality of query coordinators;
• updating the current local demand for computing resources;
• receiving a second allocation of a second number of computing resources from the global background service, the second number of computing resources being fewer than the first number of computing resources;
• transmitting an instruction to a query coordinator of the plurality of coordinators to release one of its assigned computing resources based on the second allocation;
• receiving notification from the query coordinator regarding the release of one of its assigned computing resource;
• and
• communicating identification information of the released computing resource to the global background service.

A non-transitory computer readable storage media storing instructions that, when executed by one or more processors, cause the one or more processors to:

• receiving, by a first server, query request information from a plurality of query coordinators;
• generating a current local demand based on the received query request information;
• transmitting the current local demand to a global background service over a network;
• receiving a first allocation of a first number of computing resources from the global background service;
• assigning the first number of computing resources to the plurality query coordinators;
• receiving updated information relating to query requests from the plurality of query coordinators;
• updating the current local demand for computing resources;
• receiving a second allocation of a second number of computing resources from the global background service, the second number of computing resources being fewer than the first number of computing resources;
• transmitting an instruction to a query coordinator of the plurality of coordinators to release one of its assigned computing resources based on the second allocation;
• receiving notification from the query coordinator regarding the release of one of its assigned computing resource;
• and
• communicating identification information of the released computing resource to the global background service.