Method and apparatus for powering off server with dpu, related device and storage medium

Abstract

The application discloses a server power-off method and device with a data processing unit (DPU), related equipment and a storage medium. The physical infrastructure manager (PIM) applied to a cloud management system comprises the following steps: in the case that the board management controller (BMC) of a server managed by the cloud management system completes the power-off of the central processing unit (CPU) of the server with the DPU, receiving first information sent by the BMC; receiving an instruction of a management personnel to power off the independently powered DPU in the server; judging whether the CPU in the server where the DPU is located is powered off based on the first information; in the case that the CPU is powered off, sending a first instruction to the BMC; and the first instruction is used to inform the DPU to be powered off.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of core network, and particularly relates to a power-off method and device of a server with a data processing unit (DPU), related equipment and a storage medium. BACKGROUND

[0002] In a host / DPU (Distributed Processing Unit) power-off process, the power-off linkage of a HOST CPU (Host Central Processing Unit) and a DPU is handled by a Host-BMC (Host-Base board Management Controller), which increases the complexity of the HOST-BMC. SUMMARY

[0003] To solve the existing technical problems, the present application provides a power-off method and device of a server with a DPU (Distributed Processing Unit), related equipment and a storage medium.

[0004] The technical scheme of the present application is implemented as follows:

[0005] The present application provides a power-off method of a server with a DPU (Distributed Processing Unit), applied to a PIM (Personal Information Management System) of a cloud management system, comprising the following steps:

[0006] In the case that a BMC (Baseboard Management Controller) of a server managed by the cloud management system completes the power-off of a CPU (Central Processing Unit) of the server with a DPU, a first information sent by the BMC is received;

[0007] An instruction of the management personnel to power off a DPU (Distributed Processing Unit) independently powered in the server is received;

[0008] Based on the first information, it is judged whether the CPU in the server where the DPU is located is powered off;

[0009] In the case that the CPU is powered off, a first instruction is sent to the BMC; the first instruction is used to inform the DPU to be powered off

[0010] In the above scheme, the method further comprises the following steps:

[0011] In the case that the CPU is not powered off, feedback information of the CPU power-off error is acquired; the feedback information is used for manual processing.

[0012] In the above scheme, the method further comprises:

[0013] Receiving second information sent by the BMC;

[0014] Based on the second information, it is determined that the DPU power-off is completed.

[0015] In the above scheme, the method further comprises:

[0016] Sending a second instruction to the BMC; the second instruction is used for the BMC to inform the CPU to power off.

[0017] In the above scheme, the second information is received through an out-of-band management network of the cloud management system and the server; or the second instruction is sent through the out-of-band management network of the cloud management system and the server.

[0018] Embodiments of the present application also provide a server power-off method with a data processing unit DPU, applied to a BMC of a server managed by a cloud management system, comprising:

[0019] In the case that the BMC completes the CPU power-off of the server of the DPU, first information is sent to a personal information management system (PIM) of the cloud management system; the first information is used to trigger the PIM to determine whether a management personnel issues an instruction to power off and independently supply power to the DPU; in the case that the instruction to power off and independently supply power to the DPU is issued, it is determined whether the CPU is powered off;

[0020] In the case that the CPU is powered off, first instructions sent by the PIM are received;

[0021] Based on the first instructions, the DPU is informed to power off.

[0022] In the above scheme, the method further comprises:

[0023] Second information is sent to the PIM; the second information is used for the PIM to determine that the DPU power-off is completed.

[0024] In the above scheme, the method further comprises:

[0025] Second instructions sent by the PIM are received;

[0026] Based on the second instructions, the CPU is informed to power off.

[0027] In the solution, the method further comprises:

[0028] In a case where the powering-off of the DPU is completed, receiving notification information of the powering-off of the DPU being completed;

[0029] Based on the notification information, sending the second information to the PIM.

[0030] Embodiments of the present application further provide a server powering-off device with a data processing unit DPU, arranged in a PIM of a cloud management system, comprising:

[0031] A first receiving unit, configured to receive first information sent by a board-level management controller BMC of a server managed by the cloud management system and receive an instruction of powering off an independently powered DPU in the server from a management personnel in a case where the powering-off of a central processing unit CPU of the server with the DPU is completed by the BMC;

[0032] A judging unit, configured to judge whether the CPU of the server where the DPU is located is powered off based on the first information.

[0033] A first sending unit, configured to send a first instruction to the BMC in a case where the CPU is powered off; the first instruction is used to notify the DPU to be powered off.

[0034] Embodiments of the present application further provide a server powering-off device with a data processing unit DPU, arranged in a BMC of a DPU server, comprising:

[0035] A second sending unit, configured to send first information to a physical infrastructure manager PIM of the cloud management system in a case where the powering-off of a central processing unit CPU of the server of the DPU is completed by the BMC; the first information is used to trigger the PIM to judge whether an instruction of powering off the independently powered DPU is issued by the management personnel; and in a case where the instruction of powering off the independently powered DPU is issued, judge whether the CPU is powered off.

[0036] A second receiving unit, configured to receive a first instruction sent by the PIM in a case where the CPU is powered off.

[0037] A control unit, configured to notify the DPU to be powered off based on the first instruction.

[0038] Embodiments of the present application further provide a PIM of a cloud management system, comprising a first processor and a first memory for storing a computer program capable of running on the processor,

[0039] When the first processor is used to run the computer program, the steps of any method of the PIM side described above are executed.

[0040] The embodiment of the application further provides a BMC of a server managed by a cloud management system, comprising a second processor and a second memory for storing a computer program capable of running on the processor,

[0041] The second processor is configured to execute the computer program, and perform the steps of any of the methods on the BMC side.

[0042] The embodiment of the application further provides a computer program product comprising a computer program, which, when executed by a processor, implements the steps of any of the methods on the VIM side, or implements the steps of any of the methods on the PIM side, or implements the steps of any of the methods on the DPU OS side.

[0043] The embodiment of the application further provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods on the PIM side, or implements the steps of any of the methods on the BMC side.

[0044] The power-off method, device, related equipment and storage medium of the server with the DPU provided by the embodiment of the application, the PIM receives the first information sent by the BMC in the case that the BMC of the server managed by the cloud management system completes the power-off of the central processing unit CPU of the server with the DPU; receives the instruction of the management personnel to power off the DPU independently powered in the server; judges whether the CPU in the server where the DPU is located is powered off based on the first information; in the case that the CPU is powered off, sends the first instruction to the BMC; the first instruction is used to inform the DPU to power off. By using the embodiment of the application, the PIM receives the first information sent by the BMC in the case that the BMC of the server managed by the cloud management system completes the power-off of the CPU of the server with the DPU, and receives the instruction of the management personnel to power off the DPU independently powered in the server; judges whether the CPU in the server where the DPU is located is powered off based on the first information; in the case that the CPU is powered off, sends the first instruction to the BMC, which is used to inform the DPU to power off; that is, the PIM of the cloud management system completes the power-off management of the bare metal server, the management capability is moved up, and the complexity of the BMC is avoided from being excessively increased. BRIEF DESCRIPTION OF DRAWINGS

[0045] Figure 1 It is a schematic diagram of the in-band and out-of-band management block diagram of the DPU-based bare metal server;

[0046] Figure 2 It is a schematic diagram of the DPU independent power supply mode;

[0047] Figure 3 It is a schematic diagram of the power-off process of the DPU S5 independently powered in the bare metal server;

[0048] Figure 4 This is a schematic flowchart illustrating a method for powering down a server with a DPU according to an embodiment of this application.

[0049] Figure 5 This is a schematic flowchart illustrating another method for powering down a server with a DPU according to an embodiment of this application;

[0050] Figure 6 This is a schematic diagram illustrating the graceful power-down process of the bare metal server DPU S5 with independent power supply in an embodiment of this application.

[0051] Figure 7 This is a schematic diagram of the structure of a server power-off device with a DPU according to an embodiment of this application;

[0052] Figure 8 This is a schematic diagram of the structure of another server power-off device with DPU according to an embodiment of this application;

[0053] Figure 9 This is a schematic diagram of the structure of VIM in an embodiment of this application;

[0054] Figure 10 This is a schematic diagram of the BMC structure in the embodiments of this application;

[0055] Figure 11 This is a schematic diagram of the power-down system structure of a server with a data processing unit (DPU) according to an embodiment of this application. Detailed Implementation

[0056] The present application will now be described in further detail with reference to the accompanying drawings and embodiments.

[0057] Bare-metal servers based on DPUs manage and distribute bare metal via DPU cards. In-band, they interface with the cloud management system VIM through cloud platform software (OpenStack Agent) installed on the DPU. Out-of-band, the out-of-band management module on the DPU receives out-of-band management messages sent by the cloud management system PIM via the Host-BMC. Figure 1 As shown, Figure 1 This is a schematic diagram of the in-band and out-of-band management of a bare metal server based on a DPU.

[0058] Because a virtualization layer is installed in the DPU, if the host CPU and DPU power on and off simultaneously, the virtualization layer software in the DPU card needs to be reinstalled when the host poweres on again, which is a relatively complex process. Therefore, the requirement for independent power-on and power-off for the host CPU and DPU was proposed. To support this function, the bare-metal server designed an S5 independent power supply mode for the DPU on the motherboard. Figure 2 As shown, Figure 2 This diagram illustrates the independent power supply mode for the DPU. The power-off process for the bare metal server is as follows: Figure 3 As shown,Figure 3 A schematic diagram of a power-off process of a bare metal server DPU S5.

[0059] In the host / DPU power-off process, the power-off linkage of the HOST CPU and the DPU is handled by the HOST-BMC, which increases the complexity of the HOST-BMC.

[0060] Based on this, in various embodiments of the embodiments of the present application, in accordance with the principle of simplifying hardware as much as possible and software processing complex logic, the present application proposes to move the power-off management logic of the HOST CPU and the DPU to the cloud management system PIM for processing, to complete the graceful power-off of the DPU bare metal server.

[0061] The embodiments of the present application provide a server with DPU power-off method, applied to the PIM of the cloud management system, as shown in Figure 4 , the embodiments of the present application provide a server with DPU power-off method, applied to the PIM of the cloud management system, as shown in Figure 4 A schematic diagram of a method for power-off of a server with DPU according to an embodiment of the present application, comprising:

[0062] Step 401: In the case that the BMC of the server managed by the cloud management system completes the power-off of the CPU of the server with DPU, receiving the first information sent by the BMC;

[0063] Step 402: Receiving the instruction of the management personnel to power off the DPU with independent power supply in the server;

[0064] Step 403: Based on the first information, judging whether the CPU in the server where the DPU is located is powered off;

[0065] Step 404: In the case that the CPU is powered off, sending a first instruction to the BMC; the first instruction is used to notify the DPU to power off.

[0066] It should be noted that the PIM and the BMC can be determined according to actual conditions, which are not limited here. As an example, the PIM can be a cloud management system PIM module A; the BMC can be a Host-BMC module B. In actual application, the cloud management system PIM module A can also be referred to as a cloud management platform PIM module A.

[0067] In step 401, the first information can be determined according to specific conditions, which are not limited here. As an example, the first information can be information notifying the completion of CPU power-off.

[0068] In actual application, the Host-BMC power-off management module notifies the cloud management system PIM power-off management module that the Host-CPU power-off has been completed through out-of-band.

[0069] In step 402, an instruction of powering off the DPU in the server is received, which is given by a manager; the manager can be determined according to actual conditions, and is not limited herein; the instruction can be determined according to actual conditions, and is not limited herein; as an example, the instruction can be an operation instruction.

[0070] In actual application, the manager gives an operation instruction of powering off the DPU in the server.

[0071] In step 403, it is determined whether the CPU in the server where the DPU is located is powered off based on the first information; the determination can be understood as determining whether the CPU in the server where the DPU is located is powered off based on the information of informing that the powering off of the CPU is completed.

[0072] In actual application, the PIM of the cloud management system determines whether to power off the DPU; if no, the powering off process is terminated; if yes, it is determined whether the Host-CPU is powered off; if no, an error information is returned for manual processing; if yes, a DPU powering off instruction is issued to the Host-BMC power off management module through out-of-band.

[0073] In step 404, the first instruction is used to inform the DPU to be powered off; the first instruction can be determined according to actual conditions, and is not limited herein; as an example, the first instruction can be a powering off instruction.

[0074] In actual application, in the case that the CPU is powered off, a DPU powering off instruction is issued to the Host-BMC power off management module.

[0075] In the embodiment, the PIM receives the first information sent by the BMC and the instruction of powering off the DPU in the server given by the manager in the case that the BMC of the server managed by the cloud management system completes the powering off of the CPU of the server with DPU; it is determined whether the CPU in the server where the DPU is located is powered off based on the first information; in the case that the CPU is powered off, a first instruction for informing the DPU to be powered off is sent to the BMC; that is, the cloud management system PIM completes the bare metal server power off management, the management capability is moved up, and the complexity of the BMC is avoided from being increased too much.

[0076] In an embodiment, the method further comprises:

[0077] In the case that the CPU is not powered off, feedback information of the powering off error of the CPU is acquired; the feedback information is used for manual processing.

[0078] In the embodiment of the present application, the feedback information can be determined according to specific circumstances, which is not limited herein, and as an example, the feedback information can be prompt information of CPU power-off error. The feedback information used for manual processing can be understood as prompting manual processing of CPU power-off error.

[0079] In actual application, whether the Host-CPU is powered off is determined, and if not, an error information is returned for manual processing.

[0080] In an embodiment, the method further comprises:

[0081] receiving second information sent by the BMC;

[0082] determining that the DPU power-off is completed based on the second information.

[0083] In the embodiment, the second information can be determined according to specific circumstances, which is not limited herein, and as an example, the second information can be received through an out-of-band management network of the cloud management system and the server; and the second information can be out-of-band notification.

[0084] The specific determination process of determining that the DPU power-off is completed based on the second information can be determined according to specific circumstances, which is not limited herein, and as an example, determining that the DPU power-off is completed based on the second information can be understood as that if the second information indicates that the Host-CPU power-off managed by the PIM power-off management module has been completed through out-of-band notification, it is determined that the DPU power-off is completed.

[0085] In actual application, the Host-BMC power-off management module is notified by the PIM power-off management module that the Host-CPU power-off has been completed through out-of-band.

[0086] In an embodiment, the method further comprises:

[0087] sending a second instruction to the BMC; the second instruction is used for the BMC to notify the CPU to power off.

[0088] In the embodiment, the second instruction can be determined according to specific circumstances, which is not limited herein, and as an example, the second instruction can be received through an out-of-band management network of the cloud management system and the server; and the second information can be a power-off instruction.

[0089] In actual application, the PIM power-off management module of the cloud management system issues a host power-off instruction to the Host-BMC through out-of-band, the Host-BMC notifies the Host-CPU to power off, and the Host-OS receives a shutdown instruction to close application programs and drivers.

[0090] In an embodiment, the second information is received by the cloud management system through an out-of-band management network of the server; or, the second instruction is sent by the cloud management system through the out-of-band management network of the server.

[0091] In the embodiment, the second information can be received by the cloud management system through an out-of-band management network of the server; the second information can be an out-of-band notification. In actual application, the Host-BMC power-off management module notifies the cloud management system PIM power-off management module that the Host-CPU power-off has been completed through the out-of-band notification.

[0092] The second instruction is sent by the cloud management system through an out-of-band management network of the server; the second instruction can be a power-off instruction. In actual application, the cloud management system PIM power-off management module sends a host power-off instruction to the Host-BMC through the out-of-band, the Host-BMC notifies the Host-CPU to power off, and the Host-OS receives the shutdown instruction to close the application program and the driver.

[0093] Correspondingly, the embodiment of the application further provides a server power-off method with a DPU, as shown in Figure 5 Figure 5 Fig. 2 is another server power-off method flow diagram with a DPU according to the embodiment of the application, which is applied to the BMC of the server managed by the cloud management system, and includes the following steps:

[0094] Step 501: in the case that the BMC completes the CPU power-off of the server with the DPU, send first information to the PIM of the cloud management system; the first information is used to trigger the PIM to determine whether the management personnel issues an instruction to power off the DPU; in the case that the instruction to power off the DPU is issued, determine whether the CPU is powered off;

[0095] Step 502: in the case that the CPU is powered off, receive the first instruction sent by the PIM;

[0096] Step 503: notify the DPU to power off based on the first instruction.

[0097] It should be noted that the PIM and the BMC can be determined according to actual conditions, which are not limited herein, and as an example, the PIM can be a cloud management system PIM module A; the BMC can be a Host-BMC module B. In actual application, the cloud management system PIM module A can also be referred to as a cloud management platform PIM module A.

[0098] In step 501, the first information can be determined according to specific conditions, which are not limited herein, and as an example, the first information can be information notifying that the CPU power-off is completed. ​

[0099] In actual application, the Host-BMC power-off management module notifies the cloud management system PIM that the Host-CPU power-off management module has completed power-off.

[0100] The first information is used to trigger the PIM to determine whether a management personnel issues an instruction to power off the DPU independently powered; the management personnel can be determined according to specific conditions, which is not limited herein, and the management personnel can be any management personnel; the instruction can be determined according to specific conditions, which is not limited herein, and as an example, the instruction can be an operation instruction.

[0101] In actual application, the management personnel issues an operation instruction to power off the DPU independently powered in the server.

[0102] In the case of issuing an instruction to power off the DPU independently powered, determining whether the CPU is powered off can be understood as determining whether the CPU in the server where the DPU is located is powered off based on the information notifying that the CPU power-off is completed.

[0103] In actual application, the cloud management system PIM power-off management module determines whether to power off the DPU, if “no”, the power-off process is terminated; if “yes”, it is determined whether the Host-CPU is powered off, if “no”, an error information is returned for manual processing, if “yes”, a DPU power-off instruction is issued to the Host-BMC power-off management module through out-of-band.

[0104] In step 502, the first instruction is used to notify the DPU to be powered off; the first instruction can be determined according to specific conditions, which is not limited herein, and as an example, the first instruction can be a power-off instruction.

[0105] In actual application, in the case that the CPU is powered off, a DPU power-off instruction is issued to the Host-BMC power-off management module.

[0106] In step 503, based on the first instruction notifying the DPU to be powered off can be understood as notifying the DPU to be powered off based on the power-off instruction.

[0107] In actual application, the Host-BMC notifies the DPU-BMC to be powered off, the DPU-OS completes application program and driver closing, and the DPU-BMC controls the DPU to be powered off.

[0108] In an embodiment, the method further comprises:

[0109] sending second information to the PIM; the second information is used for the PIM to determine that the DPU power-off is completed.

[0110] In the embodiment, the second information can be determined according to specific conditions, which is not limited herein, and as an example, the second information can be received by the out-of-band management network of the cloud management system and the server; and the second information can be out-of-band notification.

[0111] The specific determination process of determining that the DPU power-off is completed based on the second information can be determined according to specific conditions, which is not limited herein, and as an example, determining that the DPU power-off is completed based on the second information can be understood as that if the second information indicates that the out-of-band notification cloud management system PIM power-off management module Host-CPU power-off has been completed, it is determined that the DPU power-off is completed.

[0112] In actual application, the Host-BMC power-off management module indicates that the out-of-band notification cloud management system PIM power-off management module Host-CPU power-off has been completed.

[0113] In an embodiment, the method further comprises:

[0114] receiving a second instruction sent by the PIM;

[0115] notifying the CPU to power off based on the second instruction.

[0116] In the embodiment, the second instruction can be determined according to specific conditions, which is not limited herein, and as an example, the second instruction can be received by the out-of-band management network of the cloud management system and the server; and the second information can be a power-off instruction.

[0117] In actual application, the cloud management system PIM power-off management module sends a host power-off instruction to the Host-BMC through the out-of-band, the Host-BMC notifies the Host-CPU to power off, and the Host-OS receives a shutdown instruction to close the application program and the driver.

[0118] In an embodiment, the method further comprises:

[0119] In the case that the DPU power-off is completed, receiving notification information that the DPU power-off is completed;

[0120] sending the second information to the PIM based on the notification information.

[0121] In the embodiment, the notification information can be determined according to specific conditions, which is not limited herein, and as an example, the notification information can be received by the out-of-band management network of the cloud management system and the server; and the notification information can be notification information that the out-of-band notification cloud management system PIM host power-off is completed.

[0122] In actual application, the power-off management module of the cloud management system PIM issues a host power-off instruction to the Host-BMC out of band, the Host-BMC notifies the Host-CPU to power off, the Host-OS receives the shutdown instruction and closes the application program and driver.

[0123] The second information can be determined according to specific conditions, which is not limited here. As an example, the second information can be received by the cloud management system through an out-of-band management network of the server. The second information can be an out-of-band notification.

[0124] In actual application, the Host-BMC notifies the cloud management system PIM of host power-off completion out of band

[0125] In the embodiments of the present application, the cloud management system PIM and the Host-BMC increase the power-off management module, and the following server power-off scheme is provided. The cloud management system PIM completes the bare metal server power-off management, and the management capability is moved up to avoid excessive increase of the complexity of the BMC.

[0126] For the convenience of understanding, the server power-off method with DPU in the embodiments of the present application is specifically a DPU server power-off method based on the cloud management system. The cloud management system PIM and the Host-BMC increase the power-off management module, and the following server power-off scheme is provided. The flow is as shown in Figure 6 Figure 6 The flowchart of the graceful power-off of the bare metal server DPU S5 independent power supply in the embodiments of the present application is shown.

[0127] (1) The power-off management module of the cloud management system PIM issues a host power-off instruction to the Host-BMC out of band;

[0128] (2) The Host-BMC notifies the Host-CPU to power off, and the Host-OS receives the shutdown instruction and closes the application program and driver;

[0129] (3) The Host-BMC completes the Host-CPU power supply power-off (at this time, the DPU is still in the S5 power-on state);

[0130] (4) The power-off management module of the Host-BMC notifies the cloud management system PIM out of band that the Host-CPU power-off has been completed;

[0131] (5) The power-off management module of the cloud management system PIM judges whether to power off the DPU. If no, the power-off flow is terminated. If yes, it is judged whether the Host-CPU is powered off. If no, an error message is returned for manual processing. If yes, a DPU power-off instruction is issued to the power-off management module of the Host-BMC out of band;

[0132] ​(6) The Host-BMC informs the DPU-BMC to power off, the DPU-OS completes application and driver closing, and the DPU-BMC controls the DPU to power off;

[0133] (7) The Host-BMC informs the cloud management system PIM host to power off through out-of-band.

[0134] The application completes bare metal server power-off management by the cloud management system PIM, moves up the management capability, and avoids excessive increase of the complexity of the BMC.

[0135] In order to realize the method of the embodiments of the application, the embodiments of the application further provide a DPU-equipped server power-off device arranged on the PIM of the cloud management system, as shown in Figure 7 , which is a structural schematic diagram of a DPU-equipped server power-off device according to an embodiment of the application. The device 700 comprises: Figure 7

[0136] The first receiving unit 701 is configured to receive first information sent by a board-level management controller BMC of a server managed by the cloud management system and receive an instruction of powering off a DPU independently powered in the server, in the case that the BMC completes powering off a central processing unit CPU of the DPU-equipped server.

[0137] The judging unit 702 is configured to judge whether the CPU in the server where the DPU is located is powered off or not, based on the first information.

[0138] The first sending unit 703 is configured to send a first instruction to the BMC, in the case that the CPU is powered off; the first instruction is used to inform the DPU to power off.

[0139] In an embodiment, the device 700 further comprises an obtaining unit configured to obtain feedback information of the CPU power-off error, in the case that the CPU is not powered off; the feedback information is used for manual processing.

[0140] In an embodiment, the device 700 further comprises a determining unit; wherein,

[0141] The first receiving unit 701 is further configured to receive second information sent by the BMC.

[0142] The determining unit is configured to determine that the DPU power-off is completed, based on the second information.

[0143] In an embodiment, the first sending unit is further configured to send a second instruction to the BMC; the second instruction is used for the BMC to inform the CPU to power off.

[0144] ​In an embodiment, the second information is received by the cloud management system through an out-of-band management network of the server; or the second instruction is sent by the cloud management system through the out-of-band management network of the server.

[0145] To implement the method of the BMC side of the embodiment of the present application, the embodiment of the present application further provides a server power-off device with a DPU, which is arranged on a BMC of a server managed by a cloud management system, as shown in Figure 8 Figure 8 Fig. 8 is a structural schematic diagram of another server power-off device with a DPU according to an embodiment of the present application. The device 800 includes:

[0146] A second sending unit 801 is configured to send first information to a physical infrastructure manager (PIM) of the cloud management system in a case where the BMC completes power-off of a central processing unit (CPU) of the server with the DPU; the first information is used to trigger the PIM to determine whether an order of powering off the DPU is given by a management personnel; and in a case where the order of powering off the DPU is given, it is determined whether the CPU is powered off.

[0147] A second receiving unit 802 is configured to receive a first instruction sent by the PIM in a case where the CPU is powered off.

[0148] A control unit 803 is configured to notify the DPU to be powered off based on the first instruction.

[0149] In an embodiment, the second sending unit 801 is further configured to send second information to the PIM; the second information is used for the PIM to determine that the DPU is powered off.

[0150] In an embodiment, the second receiving unit 802 is further configured to receive a second instruction sent by the PIM.

[0151] The control unit 803 is further configured to notify the CPU to be powered off based on the second instruction.

[0152] In an embodiment, the second receiving unit 802 is further configured to receive notification information that the DPU is powered off in a case where the DPU is powered off.

[0153] The second sending unit 801 is further configured to send the second information to the PIM based on the notification information.

[0154] ​It should be noted that the server with DPU power-off device provided in the above embodiment is only exemplified by the division of the above program modules when the server with DPU is powered off. In actual application, the above processing can be completed by different program modules according to needs, that is, the internal structure of the device is divided into different program modules to complete all or part of the above-described processing. In addition, the server with DPU power-off device and the server with DPU power-off method provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0155] Based on the hardware implementation of the above program module, the embodiment of the application further provides a VIM of a cloud management system, comprising: a first processor and a first memory for storing a computer program capable of running on the processor, wherein the first processor is used to run the computer program, and the steps of the server with DPU power-off method provided in the above embodiment are implemented.

[0156] Based on the hardware implementation of the above program module, the embodiment of the application further provides a BMC of a server managed by a cloud management system, comprising: a second processor and a second memory for storing a computer program capable of running on the processor, wherein the second processor is used to run the computer program, and the steps of the server with DPU power-off method provided in the above embodiment are implemented.

[0157] Correspondingly, the embodiment of the application provides a computer program product, comprising a computer program, and a computer program is stored on the computer program. The computer program is executed by the processor to implement the steps of the server with DPU power-off method provided in the above embodiment.

[0158] Correspondingly, the embodiment of the application provides a computer readable storage medium, which stores a computer program. The computer program is executed by the processor to implement the steps of the server with DPU power-off method provided in the above embodiment.

[0159] It should be noted that the description of the above storage medium and device embodiments is similar to the description of the above method embodiments, and has similar beneficial effects to the method embodiments. For technical details not disclosed in the storage medium and device embodiments of the application, please refer to the description of the method embodiments of the application.

[0160] It should be noted that, Figure 9 The structure diagram of the VIM of the embodiment of the application is shown in Figure 9 The PIM 900 includes a first processor 901 and a first memory 903. Optionally, the PIM 900 can further include a first communication interface 902.

[0161] It can be understood that the first memory 903 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a ferromagnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM). The magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example but not limitation, many forms of RAM can be used, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus random access memory (DRRAM).The first memory 903 described in the embodiments of the present application is intended to include, but not limited to, these and any other suitable type of memory.

[0162] The method disclosed in the embodiments of the present application can be applied in or implemented by the first processor 901. The first processor 901 can be an integrated circuit chip with processing capability of signals. In the implementation process, each step of the above method can be completed by integrated logic circuits or instructions in software form of the first processor 901. The first processor 901 described above can be a general processor, a digital signal processor (DSP), or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc. The first processor 901 can implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general processor can be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the embodiments of the present application, the hardware decoding processor can be directly embodied to execute the above steps, or the hardware and software modules in the decoding processor can be combined to execute the above steps. The software module can be located in a storage medium, which is located in the first memory 903, and the first processor 901 reads the information in the first memory 903 to complete the above steps in combination with the hardware.

[0163] It should be noted that, Figure 10 The structure of the BMC in the embodiments of the present application is shown in FIG. 10, which includes a second processor 1001 and a second memory 1003. Optionally, the BMC 1000 can further include a second communication interface 1002. Figure 10

[0164] ​It can be understood that the second memory 1003 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a ferromagnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM). The magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example but not limitation, many forms of RAM can be used, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus random access memory (DRRAM).The second memory 1003 described in the embodiments of the present application is intended to include, but not limited to, these and any other suitable types of memory.

[0165] The method disclosed in the embodiments of the present application can be applied to or implemented by the second processor 1001. The second processor 1001 can be an integrated circuit chip with processing capability of signals. In the implementation process, each step of the above method can be completed by integrated logic circuits of hardware or instructions in the form of software in the second processor 1001. The second processor 1001 described above can be a general processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The second processor 1001 can implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general processor can be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the embodiments of the present application, the hardware decoding processor can be directly embodied to execute the above steps, or the combination of hardware and software modules in the decoding processor can be executed. The software module can be located in a storage medium, and the storage medium is located in the second memory 1003. The second processor 1001 reads the information in the second memory 1003 and combines the hardware to complete the steps of the above method.

[0166] To implement the method provided by the embodiments of the present application, the embodiments of the present application further provide a server power-off system with a DPU, as shown in Figure 11 Figure 11 The server power-off system structure diagram with a data processing unit DPU in the embodiments of the present application, the system includes: PIM 1101, BMC 1102.

[0167] Here, it should be noted that the specific processing process of PIM 1101 and BMC 1102 has been described in detail above, and will not be repeated here.

[0168] ​In exemplary embodiments, an apparatus can be implemented by one or more application specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field programmable gate arrays (FPGAs), general purpose processors, controllers, micro controllers (MCUs), microprocessors (Microprocessors), or other electronic elements for performing the aforementioned methods.

[0169] It should be understood that all technological and scientific terms used herein have the same meanings as those that are generally used by those skilled in the art. It should be further understood that the terms "one embodiment" or "an embodiment" as used herein mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. The appearances of the phrases "in one embodiment" or "in an embodiment" in various places in the specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that the sequence of the processes described above does not mean the execution order of the processes, and the execution order of the processes should be determined according to their functions and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the application. The sequence of the embodiments of the application described above is only for description, and does not represent the advantages or disadvantages of the embodiments.

[0170] It should be noted that, in this application, the terms "comprising", "including", or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or apparatus that includes a list of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent in such a process, method, article, or apparatus. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0171] The methods disclosed in the several method embodiments provided by the present application can be combined arbitrarily without conflict, to obtain new method embodiments.

[0172] The features disclosed in the several product embodiments provided by the present application can be combined arbitrarily without conflict, to obtain new product embodiments.

[0173] The features disclosed in the several method or device embodiments provided by the present application can be arbitrarily combined, without conflict, to obtain new method or device embodiments.

[0174] The above is only the preferred embodiment of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0175] It should be noted that "first", "second", etc. are used to distinguish similar objects, and do not necessarily describe a specific order or sequence.

[0176] In addition, the technical solutions described in the embodiments of the present application can be arbitrarily combined without conflict.

[0177] The above is only the preferred embodiment of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for powering down a server with a data processing unit (DPU) based on a cloud management system, characterized in that, A board management controller (BMC) applied to a cloud management system, comprising: In a case where the BMC completes powering off a central processing unit (CPU) of a server with a DPU, first information is sent to a physical infrastructure manager (PIM) of the cloud management system; the first information is used to trigger the PIM to determine whether an administrator issues an instruction to power off the DPU; in a case where the instruction to power off the DPU is issued, it is determined whether the CPU is powered off; In a case where the CPU is powered off, a first instruction sent by the PIM is received; Based on the first instruction, the DPU is informed to be powered off; The method further comprises: Second information is sent to the PIM; the second information is used for the PIM to determine that the DPU is powered off; In a case where the DPU is powered off, notification information that the DPU is powered off is received; Based on the notification information, the second information is sent to the PIM.

2. The method of claim 1, wherein, The method further comprises: A second instruction sent by the PIM is received; Based on the second instruction, the CPU is informed to be powered off.

3. A method for powering down a server with a data processing unit (DPU), the method comprising: A physical infrastructure manager (PIM) applied to a cloud management system, comprising: In a case where a board management controller (BMC) of a server managed by the cloud management system completes powering off a central processing unit (CPU) of a server with a DPU, first information sent by the BMC is received; An instruction to power off a DPU powered independently in the server and issued by an administrator is received; Based on the first information, it is determined whether the CPU in the server where the DPU is located is powered off; In a case where the CPU is powered off, a first instruction is sent to the BMC; the first instruction is used to inform the DPU to be powered off; the BMC is used to execute the method of claim 1.

4. The method of claim 3, wherein, The method further comprises: In a case where the CPU is not powered off, feedback information of a CPU powering off error is acquired; the feedback information is used for manual processing.

5. The method of claim 3, wherein, The method further comprises: Second information sent by the BMC is received; Based on the second information, it is determined that the DPU is powered off.

6. The method of claim 5, wherein, The method further comprises: A second instruction is sent to the BMC; the second instruction is used for the BMC to inform the CPU to be powered off.

7. The method of claim 6, wherein, The second information is received through an out-of-band management network of the cloud management system and the server; or, the second instruction is sent through the out-of-band management network of the cloud management system and the server.

8. A server power-off device with a data processing unit (DPU) based on a cloud management system, characterized in that, A physical infrastructure manager (PIM) applied to a cloud management system, comprising: A first receiving unit is configured to, in a case where a board management controller (BMC) of a server managed by the cloud management system completes powering off a central processing unit (CPU) of a server with a DPU, receive first information sent by the BMC and receive an instruction to power off a DPU powered independently in the server and issued by an administrator; A determining unit is configured to, based on the first information, determine whether the CPU in the server where the DPU is located is powered off; A first sending unit is configured to send a first instruction to the BMC when the CPU is powered off, wherein the first instruction is used to inform the DPU to be powered off, and the BMC is configured to execute the method in claim 1.

9. A server power-off device with a data processing unit (DPU) based on a cloud management system, characterized in that, The BMC applied to the DPU server comprises: A second sending unit is configured to send first information to a PIM of the cloud management system when the BMC completes powering off a CPU of the DPU server, wherein the first information is used to trigger the PIM to determine whether an administrator issues an instruction to power off and independently supply power to the DPU, and the second sending unit is further configured to determine whether the CPU is powered off when the instruction to power off and independently supply power to the DPU is issued. A second receiving unit is configured to receive a first instruction sent by the PIM when the CPU is powered off. A control unit is configured to inform the DPU to be powered off based on the first instruction. The second sending unit is configured to send second information to the PIM, wherein the second information is used for the PIM to determine that the DPU is powered off. The second receiving unit is configured to receive notification information that the DPU is powered off when the DPU is powered off. The second sending unit is configured to send the second information to the PIM based on the notification information.

10. A physical infrastructure manager (PIM) of a cloud management system, characterized in that, Comprise: A first processor and a first memory for storing a computer program capable of running on the processor, When the first processor is used to run the computer program, the steps of the method in any one of claims 3 to 7 are executed. 11.A board level management controller (BMC) of a server, characterized in that, Comprise: A second processor and a second memory for storing a computer program capable of running on the processor, When the second processor is used to run the computer program, the steps of the method in any one of claims 1 to 2 are executed.

12. A storage medium having stored thereon a computer program, characterized in that The computer program is executed by the processor to realize the steps of the method in any one of claims 1 to 2, or realize the steps of the method in any one of claims 3 to 7.

Images