Granted Patent B2

US 12,222,796 · App. 18/008,398 · Granted Feb 11, 2025

Inventors: Yihai Duan (Shandong, CN); Fan Shao (Shandong, CN)

Assignee: SHANDONG YINGXIN COMPUTER TECHNOLOGIES CO., LTD.

G06F1/3296

Abstract

Claims (50)

1. A control method for a power consumption upper limit of a server, comprising:

determining, according to a server policy, a power consumption upper limit of a management engine (ME) to be a first expected upper limit;

in response to an intelligent platform management interface (IPMI) command, controlling the ME to perform a power consumption limitation on the server according to a first desired upper limit as a current power consumption upper limit of the ME;

acquiring a current actual power consumption of the server;

comparing the current actual power consumption with the first expected upper limit and a second expected upper limit; and

in response to the current actual power consumption being greater than the first expected upper limit and not exceeding the second expected upper limit, lowering the current power consumption upper limit of the ME until the current actual power consumption is lowered by the ME such that the current actual power consumption of the server does not exceed the first expected upper limit;

wherein, the lowering the current power consumption upper limit of the ME until the current actual power consumption is lowered by the ME such that the current actual power consumption of the server does not exceed the first expected upper limit comprises:

updating the current power consumption upper limit of the ME according to a lowering formula, the lowering formula comprising:

a n+1 =a n −e n+1 ,e n+1 =s ( x n −a n )+(1 −s ) e n ,n= 1,2, . . . ;

wherein x n refers to the current actual power consumption of the server at an nth lowering; a n refers to the current power consumption upper limit of the ME at the nth lowering; a 1 is set at a value equal to the first expected upper limit; e n refers to a current allowable error interval value at the nth lowering; e 1 is set at a difference value between the second expected upper limit and the first expected upper limit; and s refers to a correction coefficient.

2. The control method according to claim 1 , wherein the correction coefficient is greater than 0.5.

3. The control method according to claim 1 , further comprising:

in response to the current actual power consumption exceeding the second expected upper limit, determining that the power consumption limitation of the ME fails.

4. The control method according to claim 3 , wherein the determining, according to a server policy, a power consumption upper limit of an ME to be a first expected upper limit comprises:

determining, according to the server policy, the power consumption upper limit of the ME to be the first expected upper limit through the IPMI command.

5. The control method according to claim 4 , wherein the in response to the current actual power consumption being greater than the first expected upper limit and not exceeding the second expected upper limit, lowering the current power consumption upper limit of the ME until the current actual power consumption is lowered by the ME such that the current actual power consumption of the server does not exceed the first expected upper limit comprises:

in response to the current actual power consumption being greater than the first expected upper limit and not exceeding the second expected upper limit, lowering the current power consumption upper limit through the IPMI command until the current actual power consumption is lowered such that the current actual power consumption does not exceed the first expected upper limit.

6. The control method according to claim 1 , wherein the second expected upper limit is a power value less than 105% of the first expected upper limit.

7. A control device for a power consumption upper limit of a server comprising:

a memory, configured to store a computer program; and

a processor, configured to execute the computer program, wherein the computer program is configured to cause the processor to perform operations comprising:

determining, according to a server policy, a power consumption upper limit of a management engine (ME) to be a first expected upper limit;

in response to an intelligent platform management interface (IPMI) command, controlling the ME to perform a power consumption limitation on the server according to a first desired upper limit as a current power consumption upper limit of the ME;

acquiring a current actual power consumption of the server;

comparing the current actual power consumption with the first expected upper limit and a second expected upper limit; and

in response to the current actual power consumption being greater than the first expected upper limit and not exceeding the second expected upper limit, lowering the current power consumption upper limit of the ME until the current actual power consumption is lowered by the ME such that the current actual power consumption of the server does not exceed the first expected upper limit;

wherein, the lowering the current power consumption upper limit of the ME until the current actual power consumption is lowered by the ME such that the current actual power consumption of the server does not exceed the first expected upper limit comprises:

updating the current power consumption upper limit of the ME according to a lowering formula, the lowering formula comprising:

a n+1 =a n −e n+1 ,e n+1 =s ( x n −a n )+(1 −s ) e n ,n= 1,2, . . . ;

wherein x n refers to the current actual power consumption of the server at an nth lowering; a n refers to the current power consumption upper limit of the ME at the nth lowering; a 1 is set at a value equal to the first expected upper limit; e n refers to a current allowable error interval value at the nth lowering; e 1 is set at a difference value between the second expected upper limit and the first expected upper limit; and s refers to a correction coefficient.

8. The control device according to claim 7 , wherein the correction coefficient is greater than 0.5.

9. The control device according to claim 7 , further comprising:

in response to the current actual power consumption exceeding the second expected upper limit, determining that the power consumption limitation of the ME fails.

10. The control device according to claim 9 , wherein the determining, according to a server policy, a power consumption upper limit of an ME to be a first expected upper limit comprises:

determining, according to the server policy, the power consumption upper limit of the ME to be the first expected upper limit through the IPMI command.

11. A non-transitory computer-readable storage medium, storing a computer program that is executed executable by a processor, and upon execution by the processor, the computer program is configured to cause the processor to perform operations comprising:

determining, according to a server policy, a power consumption upper limit of a management engine (ME) to be a first expected upper limit;

in response to an intelligent platform management interface (IPMI) command, controlling the ME to perform a power consumption limitation on a server according to a first desired upper limit as a current power consumption upper limit of the ME;

acquiring a current actual power consumption of the server;

comparing the current actual power consumption with the first expected upper limit and a second expected upper limit; and

in response to the current actual power consumption being greater than the first expected upper limit and not exceeding the second expected upper limit, lowering the current power consumption upper limit of the ME until the current actual power consumption is lowered by the ME such that the current actual power consumption of the server does not exceed the first expected upper limit;

wherein, the lowering the current power consumption upper limit of the ME until the current actual power consumption is lowered by the ME such that the current actual power consumption of the server does not exceed the first expected upper limit comprises:

updating the current power consumption upper limit of the ME according to a lowering formula, the lowering formula comprising:

a n+1 =a n −e n+1 ,e n+1 =s ( x n −a n )+(1 −s ) e n ,n= 1,2, . . . ;

wherein x n refers to the current actual power consumption of the server at an nth lowering; a n refers to the current power consumption upper limit of the ME at the nth lowering; a 1 is set at a value equal to the first expected upper limit; e n refers to a current allowable error interval value at the nth lowering; ej is set at a difference value between the second expected upper limit and the first expected upper limit; and s refers to a correction coefficient.

12. The non-transitory computer-readable storage medium according to claim 11 , wherein the correction coefficient is greater than 0.5.

13. The non-transitory computer-readable storage medium according to claim 11 , further comprising:

in response to the current actual power consumption exceeding the second expected upper limit, determining that the power consumption limitation of the ME fails.

14. The non-transitory computer-readable storage medium according to claim 13 , wherein the determining, according to a server policy, a power consumption upper limit of an ME to be a first expected upper limit comprises:

determining, according to the server policy, the power consumption upper limit of the ME to be the first expected upper limit through the IPMI command.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (17)