Communication associated with multiple nodes for delivery of power

• US 10,664,034 B2
• Filed: 04/28/2014
• Issued: 05/26/2020
• Est. Priority Date: 04/28/2014
• Status: Active Grant

• Current Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Original Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Inventors: Nguyen, Hai Ngoc, Wang, Han, Raymond, Patrick A, Venugopal, Raghavan V
• Primary Examiner(s): Abbaszadeh, Jaweed A
• Assistant Examiner(s): Pandey, Keshab R
• Application Number:
  US15/119,811
• Publication Number:
  US 20170052582A1
• Time in Patent Office: 2,220 Days
• CPC Class Codes: G06F 1/263 Arrangements for using multiple switchable power supplies, e.g. battery and AC G06F1/30 takes precedence
• CPC Class Codes: G06F 1/266 Arrangements to supply power to external peripherals either directly from the computer or under computer control, e.g. supply of power through the communication port, computer controlled power-strips
• CPC Class Codes: G06F 1/30 Means for acting in the event of power-supply failure or interruption, e.g. power-supply fluctuations for resetting only G06F1/24

Abstract

Examples herein disclose receiving a communication indicating a number of loads supported by multiple nodes and determining an amount of power available at a backup power source. Based on the determination of the amount of power, the examples disclose delivering power to the multiple nodes from the backup power source.

Claims

1. A system comprising:

multiple backup power sources; and

a centralized controller external to the backup power sources and to multiple nodes, the centralized controller to;

receive a communication associated with the multiple nodes, via a communication bus, the communication indicating a number of hardware loads supported by the multiple nodes;

communicate with the backup power sources;

determine which of the backup power sources is to deliver power to the multiple nodes based on the received communication associated with the multiple nodes and the communicating with the backup power sources; and

control the backup power sources to deliver power to the multiple nodes based on the determination, the power delivery being via an electrically conductive path distinct from the communication bus;

a software-based virtual controller operating on a chassis manager external to the backup power sources, the centralized controller, and the multiple nodes, the virtual controller to communicate with each of the nodes, wherein the virtual controller transmits the communication to the centralized controller via the communication bus, and the communication includes the number of hardware loads supported by the multiple nodes; and

the centralized controller further comprising;

a register to hold a value corresponding to the number of hardware loads supported by the multiple nodes, and the centralized controller to determine charge available at the backup power sources.

2. The system of claim 1 wherein the multiple nodes includes multiple servers, each server supporting multiple hardware loads wherein the centralized controller receives communications from the virtual controller including load information at each server.

3. The system of claim 1 further comprising:

the multiple nodes, each of the multiple nodes supporting multiple hardware loads.

4. The system of claim 1, wherein each of the backup power sources is configured to deliver power to each of the nodes.

5. The system of claim 1, wherein the centralized controller to:

receive communication, via the communication bus, indicating a potential power outage at one or more of the multiple nodes; and

control the backup power sources to deliver power to the multiple nodes based on the potential power outage.

6. A method, executable by a centralized controller, the method comprising:

receiving, via a communication bus, a communication associated with multiple servers, wherein the communication includes a number of hardware loads associated with the multiple servers;

communicating with multiple backup power sources, which are external to the centralized controller and to the multiple servers, upon receiving the communication;

determining an amount of power available at each backup power source;

selecting one or more of the backup power sources to deliver power to the multiple servers, the selecting based on the received communication associated with the multiple servers and the communicating with the backup power sources; and

controlling power delivery via an electrically conductive path distinct from the communication bus to the multiple servers from the selected one or more backup power sources for support of the number of hardware loads;

wherein the communication is received from a software-based virtual controller operating on a chassis manager external to the backup power sources, the centralized controller, and the multiple nodes, the virtual controller communicating with each of the nodes and transmitting the communication to the centralized controller via the communication bus, and the communication including the number of hardware loads supported by the multiple nodes.

7. The method of claim 6 wherein if the amount of power available is below a power consumption by the number of hardware loads associated with the multiple servers, the method further comprises:

charging the backup power sources until the power available at the backup sources reaches the power consumption by the number of hardware loads associated with the multiple servers.

8. The method of claim 6 wherein receiving the communication associated with the multiple servers further comprises:

writing the number of hardware loads into a register internal to the centralized controller.

9. The method of claim 6 wherein receiving the communication associated with the multiple severs further comprises:

receiving an address of each of the multiple servers.

10. The method of claim 6, wherein each of the backup power sources is configured to deliver power to each of the servers.

11. The method of claim 6, further comprising:

receiving communication, via the communication bus, indicating a potential power outage at one or more of the multiple servers;

selecting the one or more backup power sources based on the potential power outage; and

controlling the selected one or more backup power sources to deliver power to the multiple servers based on the potential power outage.

12. A non-transitory machine-readable storage medium comprising instructions that when executed by a processor of a centralized controller cause the processor to:

receive, via a communication bus, a communication indicating a number of hardware loads supported by multiple nodes;

communicate with multiple backup power sources, external to the centralized controller and the multiple nodes, upon receiving the communication;

determine an amount of power available at each backup power source;

select one or more of the backup power sources to deliver power to the multiple nodes, the selecting based on the received communication indicating the number of hardware loads supported by the multiple nodes and the communicating with the backup power sources; and

control power delivery via an electrically conductive path distinct from the communication bus to the multiple nodes from the selected one or more backup power sources;

wherein;

the communication is received from a software-based virtual controller operating on a chassis manager external to the backup power sources, the centralized controller, and the multiple nodes, the virtual controller communicating with each of the nodes and transmitting the communication to the centralized controller via the communication bus, and the communication including the number of hardware loads supported by the multiple nodes; and

to receive the communication indicating the number of hardware loads supported by the multiple nodes, the instructions when executed by the processor cause the processor to;

write a value corresponding to the number of hardware loads into a register at the centralized controller prior to the determination of the amount of power available at each backup power source.

13. The non-transitory machine-readable storage medium including the instructions of claim 12 wherein to receive the communication indicating the number of hardware loads supported by the multiple nodes, the instructions when executed by the processor cause the processor to:

receive an address associated with each of the multiple nodes; and

identify each of the hardware loads supported by each of the multiple nodes.

14. The non-transitory machine-readable storage medium including the instructions of claim 12 wherein if the amount of power available at the backup power source is below a power consumption by the number of hardware loads, the instructions when executed by the processor cause the processor to:

charge the backup power source until the power available at the backup power source reaches the power consumption by the number of hardware loads.

15. The non-transitory machine-readable storage medium including the instructions of claim 12, wherein each of the backup power sources is configured to deliver power to each of the nodes.

16. The non-transitory machine-readable storage medium including the instructions of claim 12, wherein the instructions when executed by the processor cause the processor to:

receive communication, via the communication bus, indicating a potential power outage at one or more of the multiple nodes; and

select the one or more backup power sources based on the potential power outage.