Data center power management

Patent metadata

Field	Value
Publication number	US-11301020-B2
Application number	US-201715601296-A
Country	US
Kind code	B2
Filing date	May 22, 2017
Priority date	May 22, 2017
Publication date	Apr 12, 2022
Grant date	Apr 12, 2022

Abstract

In an example, there is disclosed a demand scaling engine, including: a processor interface to communicatively couple to a processor; a network controller interface to communicatively couple to a network controller and to receive network demand data; a scaleup criterion; a current processor frequency scale datum; and logic, provided at least partly in hardware, to: receive the network demand data; compare the network demand data to the scaleup criterion; determine that the network demand data exceeds the scaleup criterion; and instruct the processor via the processor interface to scaleup processor frequency.

First claim

What is claimed is:

1. A demand scaling engine, comprising:
a processor hardware interface to communicatively couple to a processor;
a network controller hardware interface to communicatively couple to a network controller and to receive network demand data; and
a processing circuit, comprising an application-specific integrated circuit (ASIC) or field-programmable gate array (FPGA) configured to:
receive a scaleup criterion comprising a processing cost for processing packet demand;
compute a current processor frequency scale datum; and
receive the network demand data via the network controller hardware interface;
compare the network demand data to the scaleup criterion;
determine that the network demand data exceeds the scaleup criterion; and
instruct the processing circuit via the processor hardware interface to scaleup processor frequency.

2. The demand scaling engine of claim 1 , wherein the network demand data are real-time network demand data.

3. The demand scaling engine of claim 1 , wherein the scaleup criterion comprises a size increment.

4. The demand scaling engine of claim 3 , wherein the size increment is between 100 and 500 megahertz.

5. The demand scaling engine of claim 1 , further comprising a data interface for receiving a policy from an orchestrator.

6. The demand scaling engine of claim 1 , further comprising a policy specifying a maximum processor frequency.

7. The demand scaling engine of claim 1 , further comprising a policy specifying a minimum processor frequency.

8. The demand scaling engine of claim 1 , further comprising a policy specifying an activation parameter.

9. The demand scaling engine of claim 1 , further comprising a policy specifying a deactivation parameter.

10. The demand scaling engine of claim 1 , further comprising a policy specifying a frequency scaling granularity.

11. The demand scaling engine of claim 1 , further comprising an interface for receiving feedback for calculating a cost per packet arriving at the processor.

12. A computing system, comprising:
a processor;
a network interface;
and a demand scaling engine, comprising:
a processor hardware interface to communicatively couple to the processor;
a network interface hardware controller to communicatively couple to the network interface and to receive network demand data; and
a processing circuit, comprising an application-specific integrated circuit (ASIC) or field-programmable gate array (FPGA) configured to:
receive a scaleup criterion comprising a processing cost for current packet demand;
compute a current processor frequency scale datum; and
compare the network demand data to the scaleup criterion;
determine that the network demand data exceeds the scaleup criterion; and
instruct the processing circuit via the processor hardware interface to scaleup processor frequency.

13. The computing system of claim 12 , wherein the network demand data are real-time network demand data.

14. The computing system of claim 12 , wherein the scaleup criterion comprises a size increment.

15. The computing system of claim 14 , wherein the size increment is between 100 and 500 megahertz.

16. The computing system of claim 12 , further comprising a data interface for receiving a policy from an orchestrator.

17. The computing system of claim 12 , further comprising a policy specifying a maximum processor frequency.

18. The computing system of claim 12 , further comprising a policy specifying a minimum processor frequency.

19. The computing system of claim 12 , further comprising a policy specifying an activation parameter.

20. The computing system of claim 12 , further comprising a policy specifying a deactivation parameter.

21. The computing system of claim 12 , further comprising a policy specifying a frequency scaling granularity.

22. A computer-implemented method of providing power management, comprising:
communicatively coupling to a processor;
communicatively coupling to a network controller and receiving network demand data; and
operate a processing circuit, comprising an application-specific integrated circuit (ASIC) or field-programmable gate array (FPGA) to:
receiving a scaleup criterion comprising a compute processing cost for current packet demand;
computing a current processor frequency scale datum;
comparing the network demand data to the scaleup criterion;
determining that the network demand data exceeds the scaleup criterion; and
instructing the processing circuit to scaleup processor frequency.

23. The method of claim 22 , wherein the network demand data are real-time network demand data.

24. The method of claim 22 , wherein the scaleup criterion comprises a size increment.

25. The method of claim 24 , wherein the size increment is between 100 and 500 megahertz.

26. One or more tangible, non-transitory computer-readable media having stored thereon instructions to:
provide early detection of a network traffic burst based at least partly on received network data identifying an amount of network traffic in a network receive queue for a core and a processor P-state, send an instruction to increase a clocking frequency of the core.

27. The one or more tangible, non-transitory media of claim 26 , wherein the network data are real-time network demand data.

28. The one or more tangible, non-transitory media of claim 26 , further comprising receiving a demand scaling policy from an orchestrator.

29. The one or more tangible, non-transitory media of claim 28 , wherein the policy comprises a scaleup granularity.

Assignees

• Intel Corp

Inventors

• Macnamara Christopher
• Browne John J
• Bowhill William J
• Nolan Christopher
• Marjanovic Nemanja
• Sexton Rory
• Agnew Padraic
• Hanily Colin

Classifications

• H04L43/08

  Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters · CPC title

• H04L41/0893

  Assignment of logical groups to network elements · CPC title

• H04L43/20

  the monitoring system or the monitored elements being virtualised, abstracted or software-defined entities, e.g. SDN or NFV · CPC title

• H04L41/0894

  Policy-based network configuration management · CPC title

• H04L41/0895

  Configuration of virtualised networks or elements, e.g. virtualised network function or OpenFlow elements · CPC title