Method for correlating processor usage to customer billing in an on-demand server with real-time allocation/deallocation of processing resources

1. A method for selectively allocating and deallocating processing resources, comprising:

providing a plurality of processors, each processor having thermal control circuit (TCC) logic;

determining a processing requirement for the plurality of processors;

dynamically controlling a processing capability of the plurality of processors to provide the determined processing requirement by selectively enabling or disabling the TCC logic of each processor, the dynamic controlling comprising:

selectively enabling the TCC logic of a processor to reduce a processing capability of that processor; and

selectively disabling the TCC logic of a processor to increase a processing capability of that processor;

and

billing a customer based on the dynamically controlled processing capability of the plurality of processors, wherein the customer is billed for an on-demand processing resource cost according to:

on-demand processing resource cost=(a cost factor (CF))*(a number of inactive TCC logic signals)*(a time elapsed while a TCC logic signal is inactive), wherein the CF comprises: (a price of additional processors installed)+(a predetermined amount of profit generated from the additional processors)/(a time to reach a predetermined revenue).

2. The method of claim 1 , wherein providing a plurality of processors further comprises:

determining a processing requirement of a customer; and

providing more processors than needed to satisfy the processing requirement of the customer.

3. The method of claim 1 , wherein a reboot of a server system comprising the plurality of processors is not required in order to dynamically control the processing capability of the plurality of processors.

4. The method of claim 1 , wherein all of the plurality of processors are enabled upon an initial system boot.

5. The method of claim 4 , wherein all of the plurality of processors are enabled to operate at 1/N of a maximum execution rate at the initial system boot, wherein N is an integer greater or equal to 2.

6. The method of claim 5 , wherein dynamically controlling the processing capability of the plurality of processors further comprises:

selectively reducing or increasing a processing capability of at least one of the plurality of processors by 1/N of the maximum execution rate at a time.

7. A system for selectively allocating and deallocating processing resources, comprising:

a server system comprising a plurality of processors, each processor having thermal control circuit (TCC) logic;

a system for determining a processing requirement for the plurality of processors;

a system for dynamically controlling a processing capability of the plurality of processors to provide the determined processing requirement by selectively enabling or disabling the TCC logic of each processor, the dynamic controlling comprising:

selectively enabling the TCC logic of a processor to reduce a processing capability of that processor; and

selectively disabling the TCC logic of a processor to increase a processing capability of that processor;

and

a system for billing a customer based on the dynamically controlled processing capability of the plurality of processors, wherein the customer is billed for an on-demand processing resource cost according to:

on-demand processing resource cost=(a cost factor (CF))*(a number of inactive TCC logic signals)*(a time elapsed while a TCC logic signal is inactive), wherein the CF comprises: (a price of additional processors installed)+(a predetermined amount of profit generated from the additional processors)/(a time to reach a predetermined revenue).

8. The system of claim 7 , wherein a reboot of the server system is not required in order to dynamically control the processing capability of the plurality of processors.