Power supply control method and device for multi-node server

Abstract

The embodiment of the application provides a power supply control method and device of a multi-node server, the multi-node server comprises: a plurality of groups of one-to-one corresponding server nodes and power suppliers, and a power supply controller, each server node is deployed with a power distributor, and the method comprises the following steps: detecting a power-on signal of the multi-node server; in the case of detecting the power-on signal, detecting a fault power supplier existing in each power supplier according to power supply information corresponding to each power supplier; in the case of detecting the fault power supplier, controlling a target power distributor deployed on a target server node corresponding to the fault power supplier to supply power to the target server node. Through the application, the problem of low power supply efficiency of the multi-node server is solved, and the effect of improving the power supply efficiency of the multi-node server is achieved.

Description

Technical Field

[0001] This application relates to the field of computers, and more specifically, to a power supply control method and apparatus for a multi-node server. Background Technology

[0002] In a multi-node server, multiple server nodes are powered by their respective connected power supplies. However, if a power supply fails to provide power, the server node corresponding to that power supply will completely crash and become unusable, further impacting the normal operation of the multi-node server. This current power supply method is inefficient for multi-node servers. Summary of the Invention

[0003] This application provides a power supply control method and apparatus for a multi-node server, which at least solves the problem of low power supply efficiency for multi-node servers in related technologies.

[0004] According to one embodiment of this application, a power supply control method for a multi-node server is provided. The multi-node server includes: multiple sets of server nodes and power supplies connected in a one-to-one correspondence, and a power supply controller. Each server node is equipped with a power distributor, and each power supply is used to supply power to its corresponding server node. The power supply controller is connected to each power supply and also to each power distributor. The method is applied to the power supply controller. The method includes: detecting a power-on signal of the multi-node server, wherein the power-on signal is used to control the multi-node server to power on; upon detecting the power-on signal, detecting a faulty power supply among the power supplies based on power supply information corresponding to each power supply, wherein the power supply information is used to indicate the connection status between the corresponding power supply and the corresponding server node and the power output status of the corresponding power supply; and upon detecting the faulty power supply, controlling a target power distributor deployed on a target server node corresponding to the faulty power supply to supply power to the target server node.

[0005] As an optional implementation, the step of detecting faulty power supplies among the power supplies based on the power supply information corresponding to each power supply includes: detecting a first signal state of each received first power supply signal, wherein the first signal state is used to indicate the connection state between the corresponding power supply and the corresponding server node, the power receiving state of the corresponding power supply, and the conversion output state of the corresponding power supply for the received power, the power supply information including the first power supply signal; if a target first signal state is detected indicating that the connection state, the power receiving state, and / or the conversion output state are abnormal, determining that the power supply corresponding to the detected target first signal state is the faulty power supply; or, detecting a second signal state of each received second power supply signal, wherein the second signal state is used to indicate the operating state of the corresponding power supply, the power supply information including the second power supply signal; if a target second signal state is detected indicating that the operating state is abnormal, determining that the power supply corresponding to the detected target second signal state is the faulty power supply.

[0006] As an optional implementation, the power supply controller establishes a first connection with each power supply via a first pin, a second connection via a second pin, and a third connection via a third pin. The detection of the first signal state of each received first power supply signal includes detecting the level state of a first signal from the first connection, the level state of a second signal from the second connection, and the level state of a third signal from the third connection, wherein the first power supply signal includes the first signal, the second signal, and the third signal. If the level state of the first signal is detected to be high, a target first signal state is determined to indicate that the connection state is abnormal. If the level state of the second signal is detected to be low, a target first signal state is determined to indicate that the power receiving state is abnormal. If the level state of the third signal is detected to be low, a target first signal state is determined to indicate that the conversion output state is abnormal.

[0007] As an optional implementation, the power supply controller establishes a fourth connection with each power supply via a fourth pin and a fifth connection with each power supply via a fifth pin. The detection of the second signal state of each received second power supply signal includes: detecting the level state of the fourth signal from the fourth connection of each power supply, wherein the second power supply signal includes the fourth signal; if the level state of the fourth signal is detected to be low, determining that a target second signal state is detected to indicate that the operating state is abnormal; after detecting that the level state of the fourth signal is low, the method further includes: sending a fault information acquisition request to the faulty power supply via the fifth connection, wherein the fault information acquisition request is used to request fault information of the faulty power supply.

[0008] As an optional implementation, the power supply controller includes a power supply processor and a power aggregator. The power supply processor is connected to the power aggregator, and both the power aggregator and the power supply processor are connected to each of the power distributors. The power aggregator is also connected to each of the power suppliers. Controlling the target power distributor deployed on the target server node corresponding to the faulty power supplier to supply power to the target server node includes: the power aggregator allocating target power to the target power distributor; and the power supply processor sending an enable signal to the target power distributor, wherein the target power distributor responds to the enable signal by using the target power to supply power to the target server node.

[0009] As an optional implementation, after detecting the power-on signal, the method further includes: searching for a reference server node configured with leakage detection function among the server nodes according to the leakage detection configuration of each server node, wherein the leakage detection configuration is used to indicate the configuration of the leakage detection circuit in the corresponding server node; if the reference server node is found, controlling the reference power distributor deployed on the reference server node to replace the power supply corresponding to the reference server node to supply power to the reference server node, and monitoring the leakage information of the leakage detection circuit of the reference server node, wherein the leakage information is used to indicate the leakage status on the reference server node; if the leakage information is monitored to indicate that there is leakage on the reference server node, controlling the reference power distributor to stop supplying power to the reference server node.

[0010] According to another embodiment of this application, a multi-node server is provided, the multi-node server comprising: multiple sets of server nodes and power supplies connected in a one-to-one correspondence, and a power supply controller, wherein each server node is equipped with a power distributor, the power supply controller is connected to each power supply, and the power supply controller is also connected to each power distributor; each power supply is used to supply power to the corresponding server node; the power supply controller is used to implement the steps in any of the above method embodiments.

[0011] According to another embodiment of this application, a power supply device for a multi-node server is provided. The multi-node server includes: multiple sets of server nodes and power supplies connected in a one-to-one correspondence, and a power supply controller. Each server node is equipped with a power distributor. Each power supply is used to supply power to its corresponding server node. The power supply controller is connected to each power supply and also to each power distributor. The device is applied to the power supply controller and includes:

[0012] The first detection module is used to detect the power-on signal of the multi-node server, wherein the power-on signal is used to control the power-on of the multi-node server;

[0013] The second detection module is used to detect, when the power-on signal is detected, the faulty power supply among the power supply units according to the power supply information corresponding to each power supply unit, wherein the power supply information is used to indicate the connection status between the corresponding power supply unit and the corresponding server node and the power output status of the corresponding power supply unit.

[0014] The first control module is used to control the target power distributor deployed on the target server node corresponding to the faulty power supply to supply power to the target server node when the faulty power supply is detected.

[0015] According to yet another embodiment of this application, a computer-readable storage medium is also provided, wherein a computer program is stored therein, and the computer program is configured to perform the steps in any of the above method embodiments when it is run.

[0016] According to yet another embodiment of this application, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0017] This application addresses the issue of low power supply efficiency in multi-node servers. Each server node is connected to a corresponding power supply and also has a power distributor deployed within it. Each power supply is connected to a power controller. The power controller detects the power-on signal of the multi-node server. Upon detection, it identifies faulty power supplies based on their power supply information. If a faulty power supply is detected, the power controller activates the corresponding power distributor deployed on the target server node to supply power. This ensures the target server node receives power even when its connected power supply fails, preventing complete server node downtime due to power supply failure and mitigating any adverse impact on the normal operation of the multi-node server. Therefore, this solution addresses the problem of low power supply efficiency in multi-node servers, effectively improving their overall power supply efficiency. Attached Figure Description

[0018] Figure 1 This is a hardware structure block diagram of a server device for a power supply control method for a multi-node server according to an embodiment of this application.

[0019] Figure 2 This is a flowchart of a power supply control method for a multi-node server according to an embodiment of this application;

[0020] Figure 3 This is a schematic diagram of a power supply control method for a dual-node server according to an embodiment of this application;

[0021] Figure 4 This is a connection diagram of a power supply and a power controller according to an embodiment of this application;

[0022] Figure 5 This is a schematic diagram of a multi-node server power supply method according to an embodiment of this application;

[0023] Figure 6 This is a schematic diagram of a power supply method for a reference server node according to an embodiment of this application;

[0024] Figure 7 This is a schematic diagram of a method for a multi-node server BMC to obtain information according to an embodiment of this application;

[0025] Figure 8 This is a schematic diagram of a multi-node server according to an embodiment of this application;

[0026] Figure 9 This is a structural block diagram of a power supply control device for a multi-node server according to an embodiment of this application. Detailed Implementation

[0027] The embodiments of this application will be described in detail below with reference to the accompanying drawings and examples.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0029] The methods and embodiments provided in this application can be executed on a server device or a similar computing device. Taking running on a server device as an example, Figure 1 This is a hardware structure block diagram of a server device for a power supply control method for a multi-node server according to an embodiment of this application. For example... Figure 1 As shown, the server device may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The server device may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the server equipment described above. For example, the server equipment may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0030] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the power supply control method for a multi-node server in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thus implementing the aforementioned method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the server device via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0031] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider for the server device. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0032] This embodiment provides a power supply control method for a multi-node server. The multi-node server includes multiple sets of server nodes and power supplies connected in a one-to-one correspondence, as well as a power supply controller. Each server node is equipped with a power distributor. Each power supply is used to supply power to its corresponding server node. The power supply controller is connected to each power supply and also to each power distributor. This method is applied to the power supply controller. Figure 2 This is a flowchart of a power supply control method for a multi-node server according to an embodiment of this application, such as... Figure 2 As shown, the process includes the following steps:

[0033] Step S202: Detect the power-on signal of the multi-node server, wherein the power-on signal is used to control the power-on of the multi-node server;

[0034] Step S204: When a power-on signal is detected, the faulty power supply with power supply failure is detected in each power supply according to the power supply information corresponding to each power supply. The power supply information is used to indicate the connection status between the corresponding power supply and the corresponding server node and the power output status of the corresponding power supply.

[0035] Step S206: If a faulty power supply is detected, control the target power distributor deployed on the target server node corresponding to the faulty power supply to supply power to the target server node.

[0036] Through the above steps, since each server node in the multi-node server is connected to its corresponding power supply and also deploys a power distributor, and each power supply is connected to the power controller, the power controller in the multi-node server will detect the power-on signal of the multi-node server. When a power-on signal is detected, the power controller will detect the faulty power supply among the power supplies according to the power supply information corresponding to each power supply. When a faulty power supply is detected, the power controller will control the target power distributor deployed on the target server node corresponding to the faulty power supply to supply power to the target server node. The target server node can still receive power support even if the corresponding connected power supply fails, avoiding the complete downtime of the corresponding server node due to power supply failure, and further avoiding adverse effects on the normal operation of the multi-node server. Therefore, the problem of low power supply efficiency for multi-node servers can be solved, and the effect of improving the power supply efficiency of multi-node servers can be achieved.

[0037] Optionally, in this embodiment, a multi-node server refers to a server cluster composed of multiple server nodes that can jointly process client requests and provide services. Compared to ordinary servers, multi-node servers have higher reliability and better load balancing capabilities. Multi-node servers can improve system reliability by replicating data and services across multiple nodes. Even if one node fails, other nodes can continue to provide services. Furthermore, load balancing strategies can evenly distribute client requests across different nodes, preventing individual nodes from becoming overloaded. When one or more server nodes in a multi-node server fail to operate normally due to a power supply failure, it affects the overall reliability of the multi-node server. Other server nodes in the multi-node server need to handle client requests from the malfunctioning server nodes, increasing their node load. In the method provided in this application, the power supply is connected to the corresponding server node and also to the power controller. The power controller is also connected to the power distributor deployed on the server node. When a faulty power supply that cannot supply power to the server node is detected, other power supplies can supply power to the power controller through their connection. Furthermore, the power controller supplies the power supplied by the other power supplies to the power distributor deployed on the server node. Therefore, the power distributor deployed on the server node can be controlled to supply power to the server node, avoiding the situation where the server node cannot operate normally due to power supply problems, and ensuring the normal operation of the multi-node server.

[0038] Optionally, the power supply may be, but is not limited to, a device that supplies power to the server nodes; for example, the power supply may be a PSU (Power Supply Unit).

[0039] Optionally, in the embodiments of this application, the power supply controller may be, but is not limited to, a device for storing control logic and transferring electrical energy, such as a combination of CPLD (Complex Programmable Logic Devices) and BUSBAR (bus).

[0040] Optionally, in the embodiments of this application, the power distributor may be used, but is not limited to, to convert the received power to power the connected electrical equipment, for example, it may be a VR (Voltage Regulator).

[0041] In the embodiment provided in step S202, the power-on signal is a signal that controls the power-on of the multi-node server. The power-on signal can, but is not limited to, controlling the power-on of all server nodes in the multi-node server, or controlling the power-on of some server nodes in the multi-node server. This application does not limit this.

[0042] Optionally, in this embodiment, detecting the power-on signal of the multi-node server includes, but is not limited to, detecting the on / off state of the power switch of the multi-node server. If the switch is detected to be in a closed state, it is determined that a power-on signal has been detected, or a power-on signal from other server nodes is detected.

[0043] In the embodiment provided in step S204, the power supply information may include, but is not limited to, information indicating the connection status between the corresponding power supply and the corresponding server node, and information indicating the power output status of the corresponding power supply. The power supply information is used to indicate whether the corresponding power supply can output power normally and whether it has successfully established a connection with the corresponding server node. If the power supply cannot output power normally or fails to establish a connection with the corresponding server node, the power supply cannot supply power to the corresponding server node normally, and the power supply will be determined as a faulty power supply.

[0044] In the embodiment provided in step S206, controlling the target power distributor deployed on the target server node corresponding to the faulty power supply to supply power to the target server node includes, but is not limited to, detecting fault information of the faulty power supply, wherein the power supply information includes fault information used to indicate that the faulty power supply has a fault; when the fault information indicates that the connection status in the faulty power supply has a fault, controlling the target power distributor to provide target power to the target server node, wherein the target power is the power required for the operation of the target server node; when the fault information indicates that the power output status in the faulty power supply has a fault, detecting the faulty output power of the current faulty power supply, wherein the faulty output power is the power that the faulty power supply can currently provide to the target server node; controlling the target power distributor to provide supplementary power to the target server node, wherein the supplementary power is the difference between the target power and the faulty output power. Through the above steps, all available power resources are utilized as much as possible, avoiding waste of power resources, and improving the power supply efficiency for multi-node servers from another perspective.

[0045] As an optional implementation method, Figure 3 This is a schematic diagram of a power supply control method for a dual-node server according to an embodiment of this application. The multi-node server includes a dual-node server, such as... Figure 3 As shown, the dual-node server includes server node 0 and server node 1. Server node 0 is connected to power supply 0, and a power distributor 0 is also deployed on server node 0. Server node 1 is connected to power supply 1, and a power distributor 1 is also deployed on server node 1. The power supply controller is connected to power distributor 0, power distributor 1, power supply 0, and power supply 1. The power supply controller detects the power-on signal of the dual-node server. Upon detecting a power-on signal, the power supply controller detects faulty power supplies in power supply 0 and power supply 1 based on the power supply information corresponding to power supply 0 and power supply 1. If no faulty power supply is detected, server node 0 is powered by power supply 0 through the connection between power supply 0 and server node 0, and server node 1 is powered by power supply 1 through the connection between power supply 1 and server node 1. If a faulty power supply is detected, for example, if power supply 0 is detected as faulty, the power controller will control power distributor 0 to power server node 0, and server node 1 will be powered by power supply 1 through the connection between power supply 1 and server node 1. The situation is similar if power supply 1 is detected as faulty.

[0046] As an optional implementation, detecting faulty power supplies among the power supplies based on the power supply information corresponding to each power supply includes: detecting the first signal state of each received first power supply signal, wherein the first signal state is used to indicate the connection state between the corresponding power supply and the corresponding server node, the power receiving state of the corresponding power supply, and the conversion output state of the corresponding power supply for the received power, and the power supply information includes the first power supply signal; if a target first signal state is detected indicating an abnormal state in the connection state, power receiving state, and / or conversion output state, the power supply corresponding to the detected target first signal state is determined to be a faulty power supply; or, detecting the second signal state of each received second power supply signal, wherein the second signal state is used to indicate the operating state of the corresponding power supply, and the power supply information includes the second power supply signal; if a target second signal state is detected indicating an abnormal state in the operating state, the power supply corresponding to the detected target second signal state is determined to be a faulty power supply.

[0047] Optionally, in the embodiments of this application, the power supply information may include, but is not limited to, information for indicating the operating status of the power supply, and / or information for indicating the status of specific operating indicators of the power supply. Specific operating indicators may include, but are not limited to, the connection status between the power supply and the corresponding server node, the power supply's power receiving status, and the power supply's conversion and output status of the received power, etc.

[0048] Optionally, in this embodiment, detecting faulty power supplies with power supply faults based on the power supply information corresponding to each power supply includes, but is not limited to, detecting the operating status information of the power supply and determining the faulty power supply based on the operating status information. In this case, if it is necessary to obtain specific fault information, the power supply controller needs to interact with the faulty power supply to obtain the corresponding fault information.

[0049] Optionally, in this embodiment of the application, the faulty power supply that has a power supply fault is detected in each power supply according to the power supply information corresponding to each power supply, including but not limited to the information on the indicator status of the specific operating indicators of the power supply, and the information on the indicator status determines which indicators are abnormal, thereby identifying the faulty power supply.

[0050] Optionally, in this embodiment of the application, one end of the power supply receives power and the other end is connected to the appliance to supply power to the appliance. The power supply's power receiving state is the state in which the power supply receives the power output from the power source. The power supply's conversion and output state of the received power is the state in which the power supply converts and outputs the received power to the appliance when it receives the power output from the power source.

[0051] As an optional implementation, the power supply controller establishes a first connection with each power supply via a first pin, a second connection via a second pin, and a third connection via a third pin. It detects the first signal state of each received first power supply signal, including detecting the level state of the first signal from the first connection, the level state of the second signal from the second connection, and the level state of the third signal from the third connection, wherein the first power supply signal includes a first signal, a second signal, and a third signal. If the level state of the first signal is detected to be high, a target first signal state is determined to indicate an abnormal connection state. If the level state of the second signal is detected to be low, a target first signal state is determined to indicate an abnormal power reception state. If the level state of the third signal is detected to be low, a target first signal state is determined to indicate an abnormal conversion output state.

[0052] Optionally, in this embodiment, the first signal may be, but is not limited to, the PSU_PRSNT signal obtained by the power supply controller from the first pin of the power supply. When the power supply is successfully connected to the corresponding server node, the PSU_PRSNT signal received by the power supply controller is in a low-level state; otherwise, it is in a high-level state.

[0053] Optionally, in the embodiments of this application, the second signal may be, but is not limited to, the PSU_AC_OK signal obtained by the power supply controller from the second pin of the power supply. When the power supply normally receives the power output from the power source, the PSU_AC_OK signal received by the power supply controller is in a high-level state; otherwise, it is in a low-level state.

[0054] Optionally, in the embodiments of this application, the third signal may be, but is not limited to, the PSU_PWRGD signal obtained by the power supply controller from the third pin of the power supply. When the power supply normally converts and outputs the electrical energy received from the power source, the PSU_PWRGD signal received by the power supply controller is in a high-level state; otherwise, it is in a low-level state.

[0055] Through the above steps, the status of various operating indicators of the power supply is determined by the level states of the first, second, and third signals. By directly identifying abnormal operating indicators, the corresponding faulty power supply can be more directly and clearly identified, further enabling timely replenishment of power to the power distributor and preventing the server node from lacking power support.

[0056] As an optional implementation, the power supply controller establishes a fourth connection with each power supply via a fourth pin and a fifth connection with each power supply via a fifth pin; detecting the second signal state of each received second power supply signal includes: detecting the level state of the fourth signal from the fourth connection of each power supply, wherein the second power supply signal includes the fourth signal; if the level state of the detected fourth signal is low, determining that a target second signal state is detected to indicate an abnormal operating state; after detecting that the level state of the detected fourth signal is low, the method further includes: sending a fault information acquisition request to the faulty power supply via the fifth connection, wherein the fault information acquisition request is used to request the acquisition of fault information of the faulty power supply.

[0057] Optionally, in this embodiment, the fourth signal may be, but is not limited to, the PSU_ALERT signal obtained by the power supply controller from the fourth pin of the power supply. In the event of an error by the power supply, the power supply controller will receive a low PSU_ALERT signal.

[0058] Optionally, in this embodiment, the fifth connection may be, but is not limited to, an I2C connection established between the power supply controller and the power supply unit.

[0059] By following the steps above, the faulty power supply can be identified based on the operating status information of the power supply indicated by the fourth signal. Without needing to determine the specific fault, the faulty power supply can be detected more quickly, and the power distributor can be used to supply power to the corresponding server nodes as soon as possible, thereby improving the power supply efficiency for multi-node servers.

[0060] Optionally, in the embodiments of this application, Figure 4 This is a connection diagram of a power supply and a power controller according to an embodiment of this application, as shown below. Figure 4As shown, the PSU (Power Supply Unit) of each compute node (i.e., server node) is connected to the CPLD (Power Controller) on the backplane via the PSU management bus. The PSU management bus includes the PSU_AC_OK signal (second signal), PSUvPWRGD signal (third signal), PSU_PRSNT signal (first signal), PSU_ALERT signal (fourth signal), and PSU_12C signal sent by the PSU to the backplane. The PSU_AC_OK signal indicates whether the PSU is plugged into an AC power source. If an AC power source is plugged in, this signal is high; otherwise, it is low. The PSU_PWRGD signal indicates whether the PSU output power is normal. If normal, this signal is high; otherwise, it is low. The PSU_PRSNT signal indicates whether the PSU is connected to a compute node. If connected, this signal is low; otherwise, it is high. The PSU_ALERT signal is an interrupt signal. When the PSU reports an error, it pulls this signal low. After the backplane CPLD receives this low signal, it can communicate with the PSU via I2C (i.e., the fifth connection) to obtain the error information.

[0061] As an optional implementation, the power supply controller includes a power supply processor and a power aggregator. The power supply processor is connected to the power aggregator, and both the power aggregator and the power supply processor are connected to each power distributor. The power aggregator is also connected to each power supply unit. Controlling the target power distributor deployed on the target server node corresponding to the faulty power supply unit to supply power to the target server node includes: the power aggregator allocating target power to the target power distributor; and the power supply processor sending an enable signal to the target power distributor, which responds to the enable signal by using the target power to supply power to the target server node.

[0062] Optionally, in the embodiments of this application, the power supply processor may be, but is not limited to, a device with logic processing capabilities similar to a CPLD, and the power aggregator may be, but is not limited to, a device similar to a BUSBAR that can receive multiple power inputs and distribute the received power output.

[0063] By following the steps above, when directly powering the server node with the corresponding power supply is not feasible, a combination of power aggregators and other power supplies can be used to utilize the power output from other power supplies to power the server node corresponding to the faulty power supply. This avoids the situation where the corresponding server node cannot operate normally due to the failure of a single power supply, and improves the power supply efficiency for multi-node servers.

[0064] Optionally, in the embodiments of this application, Figure 5 This is a schematic diagram of a multi-node server power supply method according to an embodiment of this application, as shown below. Figure 5As shown, taking two compute nodes (i.e., server nodes) as an example, a BUSBAR (i.e., power aggregator) is designed to connect the P12V_PSU output of each compute node's PSU (i.e., power supply unit) to a power network. Each compute node is designed with a VR (i.e., power distributor), whose power input is P12V_PSU. The VR is enabled by a backplane CPLD (i.e., power processor). The VR output of each compute node, P12V_STBY, supplies power to the corresponding compute node. When a PSU error occurs, the backplane CPLD obtains the PSU error information through the PSU_AC_OK, PSU_PWRGD, and PSU_PRSNT signals, or after the PSU_ALERT signal is pulled low, the backplane CPLD communicates with the PSU via I2C to obtain the PSU error information.

[0065] As an optional implementation, after detecting a power-on signal, the method further includes: searching for a reference server node configured with leakage detection function from each server node according to the leakage detection configuration of each server node, wherein the leakage detection configuration is used to indicate the configuration of the leakage detection circuit in the corresponding server node; if a reference server node is found, controlling the reference power distributor deployed on the reference server node to replace the power supply corresponding to the reference server node to supply power to the reference server node, and monitoring the leakage information of the leakage detection circuit of the reference server node, wherein the leakage information is used to indicate the leakage status on the reference server node; if the leakage information is monitored to indicate that there is leakage on the reference server node, controlling the reference power distributor to stop supplying power to the reference server node.

[0066] Optionally, in the embodiments of this application, Figure 6 This is a schematic diagram of a power supply method for a reference server node according to an embodiment of this application. Figure 6 As shown, a leak detection and alarm circuit is deployed in compute node 0 (i.e., the reference server node). Compute node 0 is a reference server node configured with leak detection functionality. The output of the leak detection and alarm circuit is connected to the CPLD of compute node 0. When a leak occurs, the CPLD of compute node 0 notifies the backplane CPLD (i.e., the power supply controller). The backplane CPLD cuts off the power supply to compute node 0 by controlling the enable of VR (i.e., the reference power distributor). When the leak is resolved, the backplane CPLD restores the power supply to compute node 0 by controlling the enable of VR.

[0067] By following the above steps, in the event of a leak, the occurrence of a leak can be detected in a timely manner, and the power supply to the server node where the leak occurs can be cut off promptly. This avoids the adverse effects of improper power supply on the server node and improves the power supply efficiency for multi-node servers.

[0068] As an optional implementation, the power supply controller is also connected to a baseboard management controller deployed on each server node; in the event of a faulty power supply, the method further includes: receiving a power supply information acquisition request from the baseboard management controller, wherein the power supply information acquisition request is used to acquire the power supply information of the faulty power supply; and sending the power supply information of the faulty power supply to the baseboard management controller in response to the power supply information acquisition request.

[0069] Optionally, in the embodiments of this application, Figure 7 This is a schematic diagram illustrating a method for obtaining information using a multi-node server BMC according to an embodiment of this application, as shown below. Figure 7 As shown, the BMC (Baseboard Management Controller) of each compute node (i.e., server node) is interconnected with the backplane CPLD via I2C. The backplane CPLD enables the BMC to manage the PSU (Power Supply Unit). Each compute node's BMC obtains PSU error information via I2C with the backplane CPLD. Furthermore, when the BMC needs to upgrade the PSU firmware, it first sets the backplane CPLD I2C to bypass mode (i.e., high-speed transmission mode) using predefined instructions. Through the backplane CPLD, the BMC establishes I2C interconnection with the PSU, thus enabling the BMC to upgrade the PSU firmware. This scheme allows each compute node's BMC to upgrade the firmware of each PSU and manage PSU error messages.

[0070] The solution provided in this application enables the reuse of PSUs by different computing nodes in a multi-node server, as well as the upgrade management of each PSU by the BMC on each computing node. It also enables the liquid cooling leakage detection and leakage management functions of multi-node servers. Users can also obtain the current leakage status and leakage management status of each computing node through the BMC of any computing node.

[0071] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0072] As an optional implementation, this application also provides a multi-node server, which includes: multiple sets of server nodes and power supplies that are connected one-to-one, and a power supply controller. Each server node is equipped with a power distributor, and the power supply controller is connected to each power supply and also to each power distributor. Each power supply is used to supply power to the corresponding server node. The power supply controller is used to implement the steps in any of the above method embodiments.

[0073] Optionally, in the embodiments of this application, Figure 8 This is a schematic diagram of a multi-node server according to an embodiment of this application. Figure 8 As shown, the multi-node server includes N+1 groups of server nodes and power supplies that are connected one-to-one, as well as a power controller. Each of server nodes 0 to N has a power distributor deployed. The power controller is connected to each of the power supplies 0 to N and also to the power distributors 0 to N. The power supplies 0 to N are used to supply power to the corresponding server nodes 0 to N. The power controller supplies power to the multi-node server by implementing the steps in any of the above method embodiments.

[0074] This embodiment also provides a power supply control device for a multi-node server. The multi-node server includes: multiple sets of server nodes and power supplies connected in a one-to-one correspondence, and a power supply controller. Each server node is equipped with a power distributor. Each power supply is used to supply power to its corresponding server node. The power supply controller is connected to each power supply and also to each power distributor. This device is applied to the power supply controller and is used to implement the above embodiments and preferred embodiments. Details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0075] Figure 9 This is a structural block diagram of a power supply control device for a multi-node server according to an embodiment of this application, such as... Figure 9 As shown, the device includes:

[0076] The first detection module 902 is used to detect the power-on signal of the multi-node server, wherein the power-on signal is used to control the power-on of the multi-node server;

[0077] The second detection module 904 is used to detect, when a power-on signal is detected, the faulty power supply among the power supply units according to the power supply information corresponding to each power supply unit. The power supply information is used to indicate the connection status between the corresponding power supply unit and the corresponding server node, as well as the power output status of the corresponding power supply unit.

[0078] The first control module 906 is used to control the target power distributor deployed on the target server node corresponding to the faulty power supply to supply power to the target server node when a faulty power supply is detected.

[0079] Through the above steps, since each server node in the multi-node server is connected to its corresponding power supply and also deploys a power distributor, and each power supply is connected to the power controller, the power controller in the multi-node server will detect the power-on signal of the multi-node server. When a power-on signal is detected, the power controller will detect the faulty power supply among the power supplies based on the power supply information corresponding to each power supply. When a faulty power supply is detected, the power controller will control the target power distributor deployed on the target server node corresponding to the faulty power supply to supply power to the target server node. The target server node can still receive power support even if the corresponding connected power supply fails, avoiding the complete downtime of the corresponding server node due to power supply failure, and further avoiding adverse effects on the normal operation of the multi-node server. Therefore, the problem of low power supply efficiency for multi-node servers can be solved, and the effect of improving the power supply efficiency of multi-node servers can be achieved.

[0080] As an optional implementation, the second detection module includes: a first detection unit, configured to detect the first signal state of each received first power supply signal, wherein the first signal state indicates the connection state between the corresponding power supply and the corresponding server node, the power receiving state of the corresponding power supply, and the conversion output state of the corresponding power supply for the received power, and the power supply information includes the first power supply signal; a first determination unit, configured to determine that the power supply corresponding to the detected target first signal state is a faulty power supply when the detected target first signal state indicates an abnormal state in the connection state, power receiving state, and / or conversion output state; a second detection unit, configured to detect the second signal state of each received second power supply signal, wherein the second signal state indicates the operating state of the corresponding power supply, and the power supply information includes the second power supply signal; and a second determination unit, configured to determine that the power supply corresponding to the detected target second signal state is a faulty power supply when the detected target second signal state indicates an abnormal state in the operating state.

[0081] Optionally, the power supply controller establishes a first connection with each power supply via a first pin, a second connection via a second pin, and a third connection via a third pin. The first detection unit is further configured to: detect the level of a first signal from the first connection, the level of a second signal from the second connection, and the level of a third signal from the third connection, wherein the first power supply signal includes the first signal, the second signal, and the third signal; if the level of the first signal is detected to be high, determine that a target first signal state is detected to indicate an abnormal connection state; if the level of the second signal is detected to be low, determine that a target first signal state is detected to indicate an abnormal power reception state; and if the level of the third signal is detected to be low, determine that a target first signal state is detected to indicate an abnormal conversion output state.

[0082] Optionally, the power supply controller establishes a fourth connection with the power supply through the fourth pin of each power supply and a fifth connection with the power supply through the fifth pin of each power supply; the second detection unit is further configured to: detect the level state of the fourth signal from the fourth connection of each power supply, wherein the second power supply signal includes the fourth signal; and determine that the detected target second signal state is used to indicate that the operating state is abnormal when the detected level state of the fourth signal is low.

[0083] Optionally, the second detection module further includes: a first transmitting unit, configured to send a fault information acquisition request to the faulty power supply via a fifth connection after detecting that the level of the fourth signal is low, wherein the fault information acquisition request is used to request the acquisition of fault information of the faulty power supply.

[0084] As an optional implementation, the power supply controller includes a power supply processor and a power aggregator. The power supply processor is connected to the power aggregator, and both the power aggregator and the power supply processor are connected to each power distributor. The power aggregator is also connected to each power supply unit. The first control module further includes: a distribution unit for distributing target power to the target power distributor by the power aggregator; and a second sending unit for sending an enable signal from the power supply processor to the target power distributor, which responds to the enable signal by using the target power to supply power to the target server node.

[0085] As an optional implementation, the power supply control device for the multi-node server further includes: a lookup module, used to find a reference server node configured with leakage detection function from among the server nodes according to the leakage detection configuration of each server node, wherein the leakage detection configuration is used to indicate the configuration of the leakage detection circuit in the corresponding server node; a second control module, used to control the reference power distributor deployed on the reference server node to replace the power supply corresponding to the reference server node to supply power to the reference server node when the reference server node is found, and to monitor the leakage information of the leakage detection circuit of the reference server node, wherein the leakage information is used to indicate the leakage status on the reference server node; and a third control module, used to control the reference power distributor to stop supplying power to the reference server node when the leakage information indicates that there is leakage on the reference server node.

[0086] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0087] Embodiments of this application also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above method embodiments when run.

[0088] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0089] Embodiments of this application also provide an electronic device, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0090] In one exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0091] Embodiments of this application also provide a computer program product, which includes a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0092] Embodiments of this application also provide another computer program product, including a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in any of the above method embodiments.

[0093] Embodiments of this application also provide a computer program that includes computer instructions stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps in any of the above method embodiments.

[0094] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0095] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0096] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the principles of this application should be included within the protection scope of this application.

Claims

1. A power supply control method for a multi-node server, characterized in that, A multi-node server includes: multiple sets of one-to-one connected server nodes and power supplies, and a power controller. Each server node is equipped with a power distributor. Each power supply provides power to its corresponding server node. The power controller is connected to each power supply and also to each power distributor. The method is applied to the power controller, and the method includes: The power-on signal of the multi-node server is detected, wherein the power-on signal is used to control the power-on of the multi-node server; When the power-on signal is detected, the faulty power supply with power supply failure is detected in each of the power supply units according to the power supply information corresponding to each power supply unit. The power supply information is used to indicate the connection status between the corresponding power supply unit and the corresponding server node and the power output status of the corresponding power supply unit. If the faulty power supply is detected, control the target power distributor deployed on the target server node corresponding to the faulty power supply to supply power to the target server node. The method further includes, after detecting the power-on signal: Based on the leakage detection configuration of each of the server nodes, a reference server node configured with leakage detection function is located among the server nodes. The leakage detection configuration indicates the configuration of the leakage detection circuit in the corresponding server node. If the reference server node is found, a reference power distributor deployed on the reference server node is controlled to replace the power supply corresponding to the reference server node to supply power to the reference server node, and leakage information of the leakage detection circuit of the reference server node is monitored. The leakage information indicates the leakage status on the reference server node. If the leakage information indicates that leakage exists on the reference server node, the reference power distributor is controlled to stop supplying power to the reference server node.

2. The method according to claim 1, characterized in that, The step of detecting faulty power supplies among the power supplies based on the power supply information corresponding to each power supply includes: The system detects the first signal status of each received first power supply signal, wherein the first signal status indicates the connection status between the corresponding power supply and the corresponding server node, the power receiving status of the corresponding power supply, and the conversion output status of the corresponding power supply for the received power. The power supply information includes the first power supply signal. If a target first signal status is detected indicating an abnormal connection status, power receiving status, and / or conversion output status, the power supply corresponding to the detected target first signal status is determined to be the faulty power supply. Alternatively... The second signal status of each received second power supply signal is detected, wherein the second signal status is used to indicate the operating status of the corresponding power supply unit, and the power supply information includes the second power supply signal; if a target second signal status is detected to indicate that the operating status is abnormal, the power supply unit corresponding to the detected target second signal status is determined to be the faulty power supply unit.

3. The method according to claim 2, characterized in that, The power supply controller establishes a first connection with the power supply through the first pin of each power supply, a second connection with the power supply through the second pin of each power supply, and a third connection with the power supply through the third pin of each power supply. The first signal state of each of the first power supply signals received by the detection includes: The level of a first signal from the first connection, the level of a second signal from the second connection, and the level of a third signal from the third connection of each power supply are detected, wherein the first power supply signal includes the first signal, the second signal, and the third signal; If the level of the first signal is detected to be high, it is determined that the detected target first signal state is used to indicate that the connection state is abnormal. If the level of the second signal is detected to be low, it is determined that the detected target first signal state is used to indicate that the power receiving state is abnormal. If the level of the third signal is detected to be low, it is determined that the detected target first signal state is used to indicate that the conversion output state is abnormal.

4. The method according to claim 2, characterized in that, The power supply controller establishes a fourth connection with each of the power supplies through the fourth pin and a fifth connection with each of the power supplies through the fifth pin. The second signal state of each received second power supply signal includes: The level of the fourth signal from the fourth connection of each power supply is detected, wherein the second power supply signal includes the fourth signal; if the level of the fourth signal is detected to be low, a target second signal state is determined to indicate that the operating state is abnormal. After detecting that the level of the fourth signal is low, the method further includes: sending a fault information acquisition request to the faulty power supply via the fifth connection, wherein the fault information acquisition request is used to request the acquisition of fault information of the faulty power supply.

5. The method according to claim 1, characterized in that, The power supply controller includes a power supply processor and a power collection unit. The power supply processor is connected to the power collection unit. Both the power collection unit and the power supply processor are connected to each of the power distributors. The power collection unit is also connected to each of the power suppliers. The control of the target power distributor deployed on the target server node corresponding to the faulty power supply to supply power to the target server node includes: The energy collector distributes the target energy to the target energy distributor. The power supply processor sends an enable signal to the target power distributor, wherein the target power distributor is used to supply power to the target server node using the target power in response to the enable signal.

6. A multi-node server, characterized in that, The multi-node server includes: multiple sets of server nodes and power supplies that are connected one-to-one, and a power supply controller. Each server node is equipped with a power distributor. The power supply controller is connected to each power supply and also to each power distributor. Each of the aforementioned power supplies is used to power the corresponding server node; The power supply controller is used to implement the steps of the method described in any one of claims 1 to 5.

7. A power supply control device for a multi-node server, characterized in that, A multi-node server includes: multiple sets of one-to-one connected server nodes and power supplies, and a power controller. Each server node is equipped with a power distributor. Each power supply provides power to its corresponding server node. The power controller is connected to each power supply and also to each power distributor. A device is applied to the power controller, and the device includes: The first detection module is used to detect the power-on signal of the multi-node server, wherein the power-on signal is used to control the power-on of the multi-node server; The second detection module is used to detect, when the power-on signal is detected, the faulty power supply among the power supply units according to the power supply information corresponding to each power supply unit, wherein the power supply information is used to indicate the connection status between the corresponding power supply unit and the corresponding server node and the power output status of the corresponding power supply unit. The first control module is used to control the target power distributor deployed on the target server node corresponding to the faulty power supply to supply power to the target server node when the faulty power supply is detected. The device further includes: a lookup module, configured to, after detecting the power-on signal, search for a reference server node configured with leakage detection function from among the server nodes according to the leakage detection configuration of each server node, wherein the leakage detection configuration is used to indicate the configuration of the leakage detection circuit in the corresponding server node; a second control module, configured to, when the reference server node is found, control a reference power distributor deployed on the reference server node to replace the power supply corresponding to the reference server node to supply power to the reference server node, and monitor the leakage information of the leakage detection circuit of the reference server node, wherein the leakage information is used to indicate the leakage status on the reference server node; and a third control module, configured to, when the leakage information is monitored to indicate that there is leakage on the reference server node, control the reference power distributor to stop supplying power to the reference server node.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the steps of the method described in any one of claims 1 to 5.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method described in any one of claims 1 to 5.

Images