Power supply unit (PSU) right-sizing that supports power transients, with mechanism for dynamic curtailment of power transients during a PSU failure

1. A computer-implementable method of controlling power allocation in an information handling system having multiple power supply units (PSUs), the method comprising:

configuring a power controller to control power allocation to components within the system by:

identifying a sustained power state in which the system is powered by a redundant PSU configuration comprising a primary PSU and a secondary PSU, which are both rated to independently support a thermal design power (TDP) of the information handling system during normal operation, wherein, during the normal operation, a sustained power state is implemented where a maximum power utilized by the system is not greater than an amount of power capable of being provided by either one of the primary PSU and the secondary PSU to allow either of the primary PSU and the secondary PSU to individually support 100% TDP of the system during normal operation, and wherein the redundant PSU configuration provides an unused operating margin of backup reserve power from the combined power of both the first PSU and second PSU, which combined power provides 200% TDP of the system;

identifying an enhanced power state during which a maximum power required by the information handling system (IHS) is greater than the amount of power capable of being provided by the primary PSU;

allocating a portion of the unused operating margin of backup reserve power from the combined power of both the first PSU and second PSU to support intermittent power transients that can occur during system operation in the enhanced power state; and

in response to a detection of a condition that reduces an amount of unused operating margin of backup reserve power to less than an amount of additional power required to support a maximum value of the intermittent power transients, autonomously limiting access by the system to the enhanced power state to prevent an occurrence of at least a portion of the intermittent power transients.

2. The computer-implementable method of claim 1 , further comprising:

detecting a change in system operation from a sustained mode to an enhanced mode that respectively correlates to the sustained power mode and the enhanced power mode; and

in response to detecting the change, automatically configuring the redundant PSU configuration to provide access to the unused operating margins of the reserve backup power in order to support the power transients that can be generated during system operation in the enhanced mode, wherein the power transients includes intermittent spikes in overall system power consumption.

3. The computer-implementable method of claim 1 , wherein the information handling system comprises a processor that is capable of operating for a fixed period of time in an enhanced processor mode in which the processor operates at a higher than normal frequency and consumes more power than consumed during sustained processor operation, wherein the enhanced processor mode correlates to the enhanced power mode and causes the power transients.

4. The computer-implementable method of claim 3 , wherein the enhanced processor mode comprises the processor operating within a dynamic power range that is larger than a thermal design power (TDP) of the processor and requiring additional amounts of power to support power transients above the maximum amount of power provided by a primary PSU within the redundant PSU configuration.

5. The computer-implementable method of claim 3 , wherein autonomously limiting access to the enhanced power state comprises:

detecting a pending reduction of maximum power available to the system; and

calculating a maximum power that will be available following the detected pending reduction; and

reconfiguring an operating state of the components of the system that generate the power transients to prevent any operation that increases the amount of required power to above the maximum power.

6. The computer-implementable method of claim 4 , wherein:

detecting the pending reduction comprises: detecting a pending loss of the redundant PSU configuration which results in only one primary PSU being available; and in response to detecting the pending loss, while the processor is in the enhanced processing state, resetting the processor to the normal processing state;

calculating a maximum power that will be available comprises adding a first power rating of any remaining PSU(s) with a second power rating of any backup power device provided within the system to generate a maximum power value, wherein the backup power device can be one or more of a battery backup and a universal power supply (UPS); and

reconfiguring the operating state of the components comprises limiting the enhanced processing state until the redundant PSU configuration is restored.

7. The computer-implementable method of claim 1 , further comprising:

monitoring for an occurrence of a trigger condition from among (i) detecting a PSU fault condition in which the reserve backup power is no longer available, (ii) detecting a failure of at least one primary PSU of the redundant PSU configuration, (iii) detecting a pending PSU shutdown, (iv) detecting a removal of one primary PSU from the system, and (v) detecting an increase in the amount of power transients generated above a pre-set threshold of usable reserve backup power, during operation in the enhanced processor mode; and

in response to detecting the trigger condition:

asserting re-active hardware and software throttling mechanisms to reduce the system power consumption; and

reducing access to an enhanced processor mode responsible for the power transients in order to prevent processor-triggered power transients from occurring, wherein reducing access to the enhanced power mode ranges from (i) allowing some access that is scaled to correlate to an amount of total power consumption that is not more than an available amount of power to (ii) disabling access completely, and wherein the system power consumption extends only up to the TDP value while the enhanced processor mode is disabled.

8. The computer-implementable method of claim 7 , further comprising:

in response to detecting a pending PSU shutdown:

issuing a notification of the pending PSU shutdown; and

reconfiguring one or more components that trigger the power transients when in an enhanced operating mode to only operate in one of (i) a sustained operating mode and (ii) a limited enhanced operating mode to prevent an occurrence of peak power transients that are not within a normal TDP budget.

9. The computer-implementable method of claim 7 , further comprising:

detecting a de-assertion of a power good signal prior to a shutdown of the PSU; and

performing one of (a) de-activating and (b) limiting the enhanced operating mode in response to detecting the de-assertion of the power good signal in order to respectively eliminate or reduce a magnitude of the power transients generated by operation in the enhanced processing state; and

in response to detecting a later re-assertion of the power good signal, which indicates that restoration of the redundant PSU configuration has occurred, re-activating the full enhanced operating mode in response to detecting the re-assertion of the power good signal.

10. The computer-implementable method of claim 1 , wherein:

the primary PSU includes N PSUs where N is an integer number greater than or equal to 1, and the N PSUs that comprise the primary PSU collectively provide the power necessary to support the IHS;

the secondary PSU includes M PSUs that operate as backup PSUs to the primary PSU and which collectively provide additional redundant power capacity; and

the redundant configuration of PSUs comprises N primary PSUs and M secondary PSUs in an N+M configuration.

11. An information handling system comprising:

multiple power supply units (PSUs), including a primary PSU and a secondary PSU comprising one or more of a second PSU, an internal battery, and a universal power supply (UPS);

one or more functional components including a processor that executes program instructions; and

a power controller communicatively coupled to the multiple PSUs and to the processor and which controls power allocation to the one or more functional components within the system, the power controller comprising firmware that causes the controller to:

identify a sustained power state in which the system is powered by a redundant PSU configuration comprising a primary PSU and a secondary PSU, which are both rated to independently support a thermal design power (TDP) of the information handling system during normal operation, wherein, during the normal operation, a sustained power state is implemented where a maximum power utilized by the system is not greater than an amount of power capable of being provided by either one of the primary PSU and the secondary PSU to allow either of the primary PSU and the secondary PSU to individually support 100% TDP of the system during normal operation, and wherein the redundant PSU configuration provides an unused operating margin of backup reserve power from the combined power of both the first PSU and second PSU, which combined power provides 200% TDP of the system;

identify an enhanced power state during which a maximum power required by the information handling system is greater than the amount of power capable of being provided by the primary PSU;

allocate a portion of the unused operating margin of backup reserve power from the combined power of both the first PSU and second PSU to support intermittent power transients that can occur during system operation in the enhanced power state; and

in response to a detection of a condition that reduces an amount of unused operating margin of backup reserve power to less than an amount of additional power required by the system to support a maximum value of the intermittent power transients, autonomously limiting access to the enhanced power state to prevent an occurrence of at least some of the intermittent power transients.

12. The information handling system of claim 11 , wherein the firmware further causes the controller to:

detect a change in system operation from a normal mode to an enhanced mode that respectively correlates to the sustained power mode and the enhanced power mode; and

in response to detecting the change, automatically configure the redundant PSU configuration to provide access to the unused operating margins of the reserve backup power in order to support the power transients that can be generated during system operation in the enhanced mode, wherein the power transients includes intermittent spikes in overall system power consumption.

13. The information handling system of claim 11 , wherein the information handling system comprises a processor that is capable of operating for a fixed period of time in an enhanced processor mode in which the processor operates at a higher than normal frequency and consumes more power than consumed during normal processor operation, wherein the enhanced processor mode correlates to the enhanced power mode and causes the power transients.

14. The information handling system of claim 13 , wherein the enhanced processor mode comprises the processor operating within a dynamic power range that is larger than a thermal design power (TDP) of the processor and requiring additional amounts of power to support power transients above the maximum amount of power provided by a single one of the PSUs within the redundant PSU configuration.

15. The information handling system of claim 14 , wherein the firmware configuring the controller to autonomously limit access to the enhanced power state comprises the firmware configuring the controller to:

detect a pending reduction of maximum power available to the system; and

calculate a maximum power that will be available following the detected pending reduction; and

reconfigure an operating state of the components of the system that generate the power transients to prevent any operation that increases the amount of required power to above the maximum power.

16. The information handling system of claim 15 , wherein:

configuring the controller to detect the pending reduction comprises configuring the controller to: detect a pending loss of the redundant PSU configuration which results in only one PSU being available; and in response to detecting the pending loss, while the processor is in the enhanced processing state, reset the processor to the sustained processing state;

configuring the controller to calculate a maximum power that will be available comprises configuring the controller to add a first power rating of any remaining PSU(s) with a second power rating of any backup power device provided within the system to generate a maximum power value, wherein the backup power device can be one or more of a battery backup and a universal power supply (UPS); and

configuring the controller to reconfigure the operating state of the components comprises configuring the controller to limit the enhanced processing state until the redundant PSU configuration is restored.

17. The information handling system of claim 11 , wherein the firmware further configures the controller to:

monitor for an occurrence of a trigger condition from among (i) detecting a PSU fault condition in which the reserve backup power is no longer available, (ii) detecting a failure of at least one PSU of the redundant PSU configuration, (iii) detecting a pending PSU shutdown, (iv) detecting a removal of a PSU from the system, and (v) detecting an increase in the amount of power transients generated above a pre-set threshold of usable reserve backup power, during operation in the enhanced processor mode; and

in response to detecting the trigger condition:

assert re-active hardware and software throttling mechanisms to reduce the system power consumption; and

reducing access to an enhanced processor mode responsible for the power transients in order to prevent processor-triggered power transients from occurring, wherein reducing access to the enhanced power mode ranges from (i) allowing some access that is scaled to correlate to an amount of total power consumption that is not more than an available amount of power to (ii) disabling access completely, and wherein the system power consumption extends only up to the TDP value while the enhanced processor mode is disabled.

18. The information handling system of claim 17 , wherein the firmware further configures the controller to:

in response to detecting a pending PSU shutdown;

issue a notification of the pending PSU shutdown; and

reconfigure one or more components that trigger the power transients when in an enhanced operating mode to only operate in one of (i) a normal operating mode and (ii) a limited enhanced operating mode to prevent an occurrence of peak power transients that are not within a normal TDP budget.

19. The information handling system of claim 18 , wherein the firmware further configures the controller to:

detecting a de-assertion of a power good signal prior to a shutdown of the PSU; and

performing one of (a) de-activating and (b) limiting the enhanced operating mode in response to detecting the de-assertion of the power good signal in order to respectively eliminate or reduce a magnitude of the power transients generated by operation in the enhanced processing state; and

in response to detecting a later re-assertion of the power good signal, which indicates that restoration of the redundant PSU configuration has occurred, re-activating the full enhanced operating mode in response to detecting the re-assertion of the power good signal.

20. The information handling system (IHS) of claim 11 , wherein:

the primary PSU includes N PSUs where N is an integer number greater than or equal to 1, and the N PSUs that comprise the primary PSU collectively provide the power necessary to support the IHS;

the secondary PSU includes M PSUs that operate as backup PSUs to the primary PSU and which collectively provide additional redundant power capacity; and

the redundant configuration of PSUs comprises N primary PSUs and M secondary PSUs in an N+M configuration.