Equipment power-on method and device, storage medium and electronic equipment

Abstract

The embodiment of the invention provides an equipment power-on method and device, a storage medium and electronic equipment, and the equipment power-on method comprises the steps: obtaining an initial power-on strategy corresponding to a to-be-powered equipment cluster; determining a to-be-powered target device from the to-be-powered device cluster based on the initial power-on strategy, and determining a current cluster load of the to-be-powered device cluster; wherein the current cluster load is used for representing the real-time power capacity of the equipment cluster to be powered on; on the basis of the current cluster load, under the condition that it is determined that the target equipment is electrified according to the initial electrifying strategy, the initial electrifying strategy is adjusted, and a target electrifying strategy is obtained; and electrifying the target equipment based on the target electrifying strategy. According to the invention, the problem that the stability and reliability of a data center are influenced by the situations of power supply fluctuation, uneven load and the like when the equipment is started due to the fact that the equipment always stays at a basic level when the equipment is powered on in the prior art can be solved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computer technology, and in particular, to a method and apparatus for powering on a device, a storage medium, and an electronic device. Background Art

[0002] With the development of computer technology, the scale of data centers and server clusters continues to expand, and the demand for power management and equipment power-on strategies is increasing. Among them, computer equipment is an indispensable part of data centers, and the optimization management of its startup process is increasingly valued.

[0003] Traditional BIOS (Basic Input / Output System) power-on strategies mostly remain at the basic level, providing only simple boot, shutdown, and restart functions. Although these functions can meet basic startup requirements, when faced with large-scale data centers, they can easily lead to power supply fluctuations and uneven loads when the data center equipment is started, thereby affecting the stability and reliability of the data center.

[0004] Therefore, developing a power-on method that can improve the stability and reliability of data centers has become an important research direction. Summary of the invention

[0005] The embodiments of the present application provide a method and apparatus for powering on a device, a storage medium, and an electronic device, so as to at least solve the problem that when powering on a device in the related technology is often done at a basic level, which may lead to power supply fluctuations, uneven loads, etc. when the device is started, affecting the stability and reliability of the data center.

[0006] According to an embodiment of the present application, a method for powering on a device is provided, comprising: obtaining an initial power-on strategy corresponding to a device cluster to be powered on; determining a target device to be powered on from the device cluster to be powered on based on the initial power-on strategy, and determining a current cluster load of the device cluster to be powered on; wherein the current cluster load is used to characterize the real-time power capacity of the device cluster to be powered on; when it is determined, based on the current cluster load, that there is a power-on abnormality when the target device is powered on according to the initial power-on strategy, adjusting the initial power-on strategy to obtain a target power-on strategy; and powering on the target device based on the target power-on strategy.

[0007] In an exemplary embodiment, determining the initial power-on strategy includes: determining device attribute parameters of each device in the device cluster to be powered on; determining the power-on priority of each device based on the device attribute parameters of each device; and determining the initial power-on strategy according to the power-on priority of each device.

[0008] In an exemplary embodiment, determining the initial power-on strategy according to the power-on priority of each device includes: determining the cluster load of the device cluster to be powered on in a historical time period; wherein the cluster load of the historical time period is used to indicate the historical power capacity of the device cluster to be powered on before a first time point, the first time point being the time point when a power-on instruction for the device cluster to be powered on is obtained, and the power-on instruction is an instruction for instructing to power on each device in the device cluster to be powered on; based on the cluster load of the historical time period, determining the delay duration of each device in the device cluster to be powered on; wherein the delay duration represents the duration between obtaining the first time point and a second time point when each device starts to power on; determining the initial power-on strategy according to the power-on priority of each device and the delay duration.

[0009] In an exemplary embodiment, when it is determined based on the current cluster load that there is a power-on abnormality when the target device is powered on according to the initial power-on strategy, the initial power-on strategy is adjusted to obtain a target power-on strategy, including: comparing the current cluster load with the rated load of the target device to obtain a load comparison result; when the load comparison result is that the current cluster load is less than the rated load, obtaining the cluster load of the device cluster to be powered on at multiple preset moments; selecting a first preset moment and a second preset moment from the device cluster to be powered on from the multiple preset moments, and determining the cluster load at the first preset moment as the first cluster load, and determining the cluster load at the second preset moment as the second cluster load; wherein the first preset moment is the cluster load at the multiple preset moments. the moment when the load value is the largest; the second preset moment is the moment when the interval with the first preset moment is the shortest; based on the difference between the first cluster load and the second cluster load, determine the load change of the device cluster to be powered on; multiply the load change by a preset basic delay duration to obtain the product of the load change and the basic delay duration, and determine the quotient between the product and the rated load of the device cluster to be powered on as the delay adjustment amount; wherein the delay adjustment amount is a parameter for adjusting the delay duration in the initial power-on strategy; the basic delay duration is determined based on the device performance of the device cluster to be powered on; based on the delay adjustment amount, increase or decrease the delay duration in the initial power-on strategy to obtain a target delay duration; obtain a target power-on strategy based on the target delay duration.

[0010] In an exemplary embodiment, powering on the target device based on the target power-on strategy includes: determining a target delay duration for powering on the target device based on the target power-on strategy; and controlling initialization processing of the target device to complete powering on the target device when the duration of the power-on instruction obtained reaches the target delay duration.

[0011] In an exemplary embodiment, determining the target device to be powered on from the device cluster to be powered on based on the initial power-on strategy includes: based on the power-on priority specified in the initial power-on strategy, determining the device with the highest power-on priority in the device cluster to be powered on as the target device to be powered on.

[0012] In an exemplary embodiment, the method further includes: determining a status parameter associated with the target device; wherein the status parameter is used to characterize the current status of the target device; in a case where it is determined based on the device status parameter that the target device has a fault, ending powering on the target device, and determining a new target device from the device cluster to be powered on based on the initial power-on strategy; based on the new target device, returning to the step of determining the current cluster load of the device cluster to be powered on, until a preset stop condition is met.

[0013] According to another embodiment of the present application, a power-on device for a device is provided, comprising: an acquisition module, used to acquire an initial power-on strategy corresponding to a device cluster to be powered on; a determination module, used to determine a target device to be powered on from the device cluster to be powered on based on the initial power-on strategy, and determine a current cluster load of the device cluster to be powered on; wherein the current cluster load is used to characterize the real-time power capacity of the device cluster to be powered on; an adjustment module, used to adjust the initial power-on strategy to obtain a target power-on strategy when it is determined, based on the current cluster load, that there is a power-on abnormality when the target device is powered on according to the initial power-on strategy; and a power-on module, used to power on the target device based on the target power-on strategy.

[0014] According to another embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when run.

[0015] According to another embodiment of the present application, an electronic device is 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 execute the steps in any one of the above method embodiments.

[0016] According to another embodiment of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0017] Through the present application, an initial power-on strategy corresponding to a device cluster to be powered on is obtained; based on the initial power-on strategy, a target device to be powered on is determined from the device cluster to be powered on, so as to avoid all devices being powered on at the same time, resulting in current shock and insufficient power supply, thereby reducing the risk of startup failure. And further determine the current cluster load of the device cluster to be powered on; wherein the current cluster load is used to characterize the real-time power capacity of the device cluster to be powered on; when it is determined based on the current cluster load that there is a power-on anomaly when the target device is powered on according to the initial power-on strategy, the initial power-on strategy is adjusted to obtain a target power-on strategy; the target device is powered on based on the target power-on strategy. That is, when it is determined that there is a power-on anomaly when the target device is powered on according to the initial power-on strategy, the power-on strategy can be adjusted in time, the target power-on strategy can be obtained, and the power-on can be performed according to the target power-on strategy, so as to avoid the negative impact of abnormal power-on on the operation of the entire device cluster, thereby ensuring the stable startup of the entire device cluster. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a hardware structure block diagram of a baseboard management controller of a power-on method of a device in an embodiment of the present application;

[0019] Figure 2 is a flow chart of a method for powering on a device according to an embodiment of the present application;

[0020] Figure 3 is another flow chart of a method for powering on a device according to an embodiment of the present application;

[0021] Figure 4 is a schematic diagram of an interface of a method for powering on a device according to an embodiment of the present application;

[0022] Figure 5 It is a structural block diagram of a power-on device of a device according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] The embodiments of the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0025] The method embodiments provided in the embodiments of the present application can be executed in a BMC (Baseboard Management Controller) or a similar computing device, wherein the BMC can be deployed in a computer device or can be independent of the computer device. Taking running on a BMC as an example, Figure 1 FIG. 1 is a hardware structure block diagram of a BMC of a device power-on method according to an embodiment of the present application. Figure 1 As shown, the BMC may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the above-mentioned BMC may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the above BMC. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0026] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method for allocating load resources in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a 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 a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the server via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0027] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by the communication provider of the BMC. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0028] Figure 21 is a flow chart of a method for powering on a device according to an embodiment of the present application, and the method is applied to a BMC as an example for explanation. Figure 2 As shown, the process includes the following steps:

[0029] Step S202, obtaining an initial power-on strategy corresponding to the device cluster to be powered on;

[0030] It should be noted that the initial power-on strategy refers to the preset power-on sequence and parameters of the devices before any intelligent optimization or adjustment. It can include the power-on priority of the device, group information, the power-on priority of each group of devices, the delay time of the device startup or the key parameters of the device power-on, which are used to guide the startup sequence of the device for the first time or after power restoration.

[0031] A device cluster refers to a data center consisting of multiple servers or multiple computer terminals.

[0032] In some embodiments, the initial power-on strategy can be obtained by accessing a non-volatile memory (such as NVRAM or EEPROM), which can ensure that data is retained after the server or computer terminal is restarted or powered off. Of course, the initial power-on strategy can also be saved in a system database as part of power management, and then queried and obtained through a software interface.

[0033] In some embodiments, in addition to setting a power-on priority for each device to be powered on, the devices to be powered on can also be divided into different groups based on factors such as business type, hardware configuration, or geographic location, so as to facilitate power-on control in a specific order. A power-on priority is set for each device group, and a high-priority device group will have priority in obtaining startup resources during the power-on process to ensure that critical business devices can start quickly. A power-on delay time is set for each device group or individual device. This time refers to the time interval from the time the main power switch is powered on to the time when the device group or device starts trying to start. The setting of a delayed power-on time helps to prevent the data center from being subjected to excessive startup current in a short period of time and reduce the pressure on the power load.

[0034] Step S204, determining a target device to be powered on from the device cluster to be powered on based on the initial power-on strategy, and determining a current cluster load of the device cluster to be powered on; wherein the current cluster load is used to characterize the real-time power capacity of the device cluster to be powered on;

[0035] It should be noted that the target device to be powered on can be determined based on the read initial power-on strategy. The determination process can be based on the power-on priority of the device, device grouping, etc. in the initial power-on strategy, that is, the target device is selected from the current device cluster in descending order of priority to be powered on.

[0036] The current cluster load may refer to the remaining power capacity after deducting the total power consumed by the currently running devices and the unpowered devices. The BMC may obtain the current and voltage data of the PDU (Power Distribution Unit) to calculate the real-time power consumption of the device cluster and obtain the current cluster load. When calculating the cluster load, the instantaneous high current demand of the device at the moment of powering on may also be considered, which is not limited in the embodiments of the present application.

[0037] It is understandable that the current cluster load can be used to evaluate the current remaining power capacity of the device cluster and whether the next wave of target devices can be started safely and efficiently. If the current cluster load is low, the initial power-on strategy can be adjusted to extend the power-on delay of the target device to avoid power peaks and ensure the stable operation of the entire device cluster. Conversely, if the current cluster load is close to the maximum capacity of the data center, the delay can be appropriately shortened to speed up the device startup and improve the responsiveness and efficiency of the data center. After determining the target device and the current cluster load, the power-on strategy is dynamically adjusted based on real-time data and preset optimization algorithms. Possible adjustments include changing the delay time of the target device, rearranging the startup order of the device, and even adjusting the output power of the data center to adapt to the current power demand.

[0038] In an exemplary embodiment, determining the target device to be powered on from the device cluster to be powered on based on the initial power-on strategy includes: based on the power-on priority specified in the initial power-on strategy, determining the device with the highest power-on priority in the device cluster to be powered on as the target device to be powered on.

[0039] It is understandable that the initial power-on strategy assigns a power-on priority to each device or device group. This priority can be determined based on factors such as the urgency of the business, the hardware configuration of the device, the geographical location, or the power demand. For example, critical business servers, storage devices, or network core switches may be set to a high priority to ensure that they can be quickly started when power is restored to meet the needs of business continuity and data security.

[0040] When it is determined that a device cluster is to be powered on, the BMC can first parse the power-on priority information in the initial power-on strategy and sort the devices in the device cluster according to the priority. The device with the highest priority will be placed at the front of the sequence, which means that it will get power resources first during the power-on process. Based on the result of the power-on priority sorting, the device with the highest priority can be selected as the target device to be powered on.

[0041] In some embodiments, when determining the target device, the available resources and current load of the device cluster may also be evaluated. If the remaining capacity of the power system is sufficient, the target device will be powered on according to the settings in the initial power-on strategy. On the contrary, if the current power system is close to full load, the initial power-on strategy can be dynamically adjusted to extend the power-on delay of the target device to avoid the occurrence of power peaks and ensure the stable operation of the data center.

[0042] In other implementations, when the power resources of the device cluster are tight, in addition to determining the target device according to the power-on priority, the power-on sequence can also be adjusted according to the power demand of the device. For example, the device with lower power demand can be started first to ensure a smooth transition of the power system. When the power demand is low, the high-priority device can be started faster to improve the business response speed.

[0043] In a specific application, the target device to be powered on can also be determined according to the device group. If the device group with the highest priority in the initial power-on strategy is the "critical business server group", devices can be first selected from the critical business server group to be determined as the target device to be powered on.

[0044] Step S206, when it is determined based on the current cluster load that there is a power-on abnormality when the target device is powered on according to the initial power-on strategy, the initial power-on strategy is adjusted to obtain a target power-on strategy;

[0045] It should be noted that the BMC determines through the current cluster load that it has approached or exceeded the preset safety threshold, that is, the data center may not be able to withstand the instantaneous high current demand when the target device is started, and will determine that there is an abnormal power load, that is, there is a power-on abnormality. The BMC will intelligently adjust the initial power-on strategy based on the real-time cluster load and device status.

[0046] When adjusting the initial power-on strategy, it can include adjusting the power-on delay time of the target device; if the current cluster load is close to full load, the power-on delay time of the target device can be extended to avoid the occurrence of power peaks and ensure the stable operation of the power system.

[0047] Step S208: Power on the target device based on the target power-on strategy.

[0048] In an exemplary embodiment, the powering on the target device based on the target power-on strategy includes: determining a target delay duration for powering on the target device based on the target power-on strategy; and when the duration of the power-on instruction obtained reaches the target delay duration, controlling initialization processing of the target device to complete powering on the target device.

[0049] It should be noted that when the BMC receives the power-on command, it will start timing and monitor the duration from the issuance of the power-on command to the current moment. This monitoring process ensures that the power system can accurately control the power-on time of the device when executing the power-on strategy to avoid early or delayed power-on. Once the duration reaches the target delay duration, the BMC will send an initialization command to the target device to start the power-on process of the device. The initialization process usually includes steps such as detecting the device hardware, loading the system software, and checking the device status to ensure that the device can start safely and orderly. The initialization process can also run a pre-startup check program to ensure that the hardware and software status of the device meet the startup requirements to avoid startup failures or abnormalities after startup.

[0050] In the above embodiment, the BMC can accurately control the power-on time of the target device based on the target power-on strategy, and complete the safe and orderly startup of the target device under the premise of ensuring the stable operation of the device cluster. This process avoids the negative impact of abnormal power-on on the operation of the entire cluster and ensures the stable startup of the entire device cluster.

[0051] Through the above steps, the initial power-on strategy corresponding to the device cluster to be powered on is obtained; based on the initial power-on strategy, the target device to be powered on is determined from the device cluster to be powered on, so as to avoid all devices being powered on at the same time, resulting in current shock and insufficient power supply, thereby reducing the risk of startup failure. And further determine the current cluster load of the device cluster to be powered on; wherein the current cluster load is used to characterize the real-time power capacity of the device cluster to be powered on; when it is determined based on the current cluster load that there is a power-on anomaly when the target device is powered on according to the initial power-on strategy, the initial power-on strategy is adjusted to obtain the target power-on strategy; the target device is powered on based on the target power-on strategy. That is, when it is determined that there is a power-on anomaly when the target device is powered on according to the initial power-on strategy, the power-on strategy can be adjusted in time, the target power-on strategy can be obtained, and the power-on is performed according to the target power-on strategy, so as to avoid the negative impact of abnormal power-on on the operation of the entire device cluster, thereby ensuring the stable startup of the entire device cluster.

[0052] In an exemplary embodiment, determining the initial power-on strategy includes: determining device attribute parameters of each device in the device cluster to be powered on; determining the power-on priority of each device based on the device attribute parameters of each device; and determining the initial power-on strategy according to the power-on priority of each device.

[0053] It is understandable that for each device, the BMC can collect its device attribute parameters, which may include device type, hardware configuration, power requirements, business importance, geographic location, health status, etc. For example, a critical business server may have high computing and storage capabilities, and also require greater power support; while a network switch may be located at the core of the cluster and is crucial to the connectivity of the entire network.

[0054] The BMC can determine the power-on priority of each device through a preset priority algorithm based on device attribute parameters. The priority algorithm may take into account factors such as the device's hardware configuration, business importance, power demand, geographic location, and health status to determine the most reasonable power-on order. Based on the calculated priority, the devices are sorted, with the higher priority devices at the front, which means that when power is restored, they will get power resources first.

[0055] According to the determined power-on priority, an initial power-on strategy is constructed, which includes the startup sequence of the device, the delayed power-on time, and the possible power resource allocation plan. The constructed initial power-on strategy is stored in the BIOS or BMC configuration so that it can be automatically read and applied at the next startup. The BMC can also synchronize the power-on strategy to other management components in the data center, such as PDU, through out-of-band programs such as redfish (an open standard), to achieve global power resource management and power-on control.

[0056] In the above embodiment, the BMC can intelligently determine the power-on priority based on the device attribute parameters and build the initial power-on strategy accordingly. This strategy not only ensures the priority startup of key business equipment, but also fully considers the reasonable allocation of power resources and the orderly progress of the power-on process, which is an important embodiment of the intelligent power management of the data center.

[0057] In an exemplary embodiment, determining the initial power-on strategy according to the power-on priority of each device includes: determining the cluster load of the device cluster to be powered on in a historical time period; wherein the cluster load of the historical time period is used to indicate the historical power capacity of the device cluster to be powered on before a first time point, the first time point being the time point when a power-on instruction for the device cluster to be powered on is obtained, and the power-on instruction is an instruction for instructing to power on each device in the device cluster to be powered on; based on the cluster load of the historical time period, determining the delay duration of each device in the device cluster to be powered on; wherein the delay duration represents the duration between obtaining the first time point and a second time point when each device starts to power on; determining the initial power-on strategy according to the power-on priority of each device and the delay duration.

[0058] It should be noted that BMC can determine the power consumption data of the device cluster in a certain historical period before the power-on command is issued. These data reflect the power demand and consumption pattern of the device cluster under normal operation. By analyzing the historical power consumption data, key indicators such as the average load, peak load, and load change trend of the device cluster are calculated. These indicators provide an important reference for predicting the power demand of the device under the current power-on command.

[0059] Based on historical load data and combined with device attribute parameters (such as power demand), the delay time for each device to start powering on is calculated. This delay is usually to avoid power peaks and ensure a smooth transition of the power system.

[0060] According to the power-on priority of the device and the calculated delay time, the initial power-on strategy is constructed. This strategy specifies the order of device startup, delay time, and power resource allocation plan in detail. The initial power-on strategy will be stored in the BIOS or BMC configuration. When the power-on command is received, this strategy will be loaded and executed to control the power-on process of the device.

[0061] In the above embodiment, combined with the cluster load of the device cluster to be powered on in the historical time period, the initial power-on strategy can be intelligently determined to ensure that power resources can be reasonably allocated when the power demand peaks, while avoiding the impact of power peaks on the power system. This strategy not only takes into account the business importance and power demand of the equipment, but also combines the real-time status and historical load trends of the power system, providing an efficient and stable solution for power management in the data center.

[0062] In an exemplary embodiment, when it is determined based on the current cluster load that there is a power-on abnormality when the target device is powered on according to the initial power-on strategy, the initial power-on strategy is adjusted to obtain a target power-on strategy, including: comparing the current cluster load with the rated load of the target device to obtain a load comparison result; when the load comparison result is that the current cluster load is less than the rated load, obtaining the cluster load of the device cluster to be powered on at multiple preset moments; selecting a first preset moment and a second preset moment from the device cluster to be powered on from the multiple preset moments, and determining the cluster load at the first preset moment as the first cluster load, and determining the cluster load at the second preset moment as the second cluster load; wherein the first preset moment is the cluster load at the multiple preset moments. the moment when the load value is the largest; the second preset moment is the moment when the interval with the first preset moment is the shortest; based on the difference between the first cluster load and the second cluster load, determine the load change of the device cluster to be powered on; multiply the load change by a preset basic delay duration to obtain the product of the load change and the basic delay duration, and determine the quotient between the product and the rated load of the device cluster to be powered on as the delay adjustment amount; wherein the delay adjustment amount is a parameter for adjusting the delay duration in the initial power-on strategy; the basic delay duration is determined based on the device performance of the device cluster to be powered on; based on the delay adjustment amount, increase or decrease the delay duration in the initial power-on strategy to obtain a target delay duration; obtain a target power-on strategy based on the target delay duration.

[0063] It is understandable that the BMC compares the current cluster load with the rated load of the target device to determine whether there is a potential risk of insufficient power resources. If the current cluster load is less than the rated load, it indicates that the remaining load of the device cluster is less than the rated load, the power resources are insufficient, and delay measures need to be implemented. If the current cluster load is greater than the rated load, it indicates that the remaining load of the device cluster is greater than the rated load, the power resources are sufficient, and delay measures do not need to be implemented.

[0064] The BMC can search and obtain the cluster loads at multiple preset moments, which can be within a few hours or days before the power-on command is issued. From these preset moments, the moment with the largest cluster load is selected as the first preset moment, and another moment with the shortest time interval with the first preset moment is selected as the second preset moment for analyzing the load change trend. The difference between the first cluster load (the load at the first preset moment) and the second cluster load (the load at the second preset moment) is calculated, that is, the load change amount.

[0065] The delay adjustment is calculated by multiplying the load change by the preset basic delay duration, and then dividing the product by the rated load of the cluster of devices to be powered on. The delay adjustment reflects the degree of influence of the load change on the delay duration adjustment; based on the calculated delay adjustment, the delay duration of the target device is adjusted. If the load change causes the load to increase, the delay is increased, and vice versa. According to the adjusted delay value, the target delay duration is determined, that is, the adjusted device power-on delay time. The updated delay information is integrated into the initial power-on strategy to form a target power-on strategy, which will guide the subsequent device power-on process. When the power-on is executed, the target power-on strategy will be followed to control the startup sequence and delay duration of the device to ensure the reasonable allocation of power resources and the stable startup of the device.

[0066] In the above embodiment, the changes in power demand are monitored and responded to in real time, the initial power-on strategy is intelligently adjusted, the optimal allocation of power resources is achieved, and the occurrence of power peaks is avoided, thereby improving the operating efficiency of the data center and the reliability of power management.

[0067] In an exemplary embodiment, the method further includes: determining a status parameter associated with the target device; wherein the status parameter is used to characterize the current status of the target device; in a case where it is determined based on the device status parameter that the target device has a fault, ending powering on the target device, and determining a new target device from the device cluster to be powered on based on the initial power-on strategy; based on the new target device, returning to the step of determining the current cluster load of the device cluster to be powered on, until a preset stop condition is met.

[0068] It should be noted that the BMC (Baseboard Management Controller) can continuously collect the status parameters of the target device, which may include the device's hardware status (such as CPU (Central Processing Unit) temperature, memory status, power module failure, etc.), software status (such as operating system status, service operation status, etc.) and environmental parameters (such as room temperature, humidity, etc.). The collected status parameters are analyzed in real time to determine whether the device is in normal working condition and whether there is a potential risk of failure.

[0069] If the status parameter analysis results show that the target device has a fault, it can be determined whether the device can be powered on safely. If the fault causes the device to fail to power on or affects the stability of the power system, the power-on operation of the target device will be terminated. The faulty device can be excluded from the power-on queue to ensure that it does not affect the power-on process of subsequent devices. Based on the priority ranking of devices in the initial power-on strategy, the system will determine the new target device from the device cluster to be powered on, that is, the next device to be started according to the power-on strategy.

[0070] Based on the new target device, re-evaluate the current cluster load of the cluster of devices to be powered on to determine whether the power resources are sufficient and whether the delayed power-on strategy needs to be adjusted. If the current cluster load still meets the power distribution requirements, the power-on strategy will continue to be executed; if the load situation changes, the delay parameters in the power-on strategy will be adjusted to adapt to the change in power demand. The power-on process is continuously monitored until the preset stop condition is met. The preset stop condition may include but is not limited to: all devices to be powered on have completed power-on, power resources have reached the preset critical value, and a manual power-on stop instruction has been received.

[0071] In the above embodiments, it is possible to intelligently monitor and respond to changes in the state of the device, ensuring the safety of the power-on process and the rational allocation of power resources. When a device fails, the power-on strategy can be quickly adjusted to eliminate the failed device and select a new target device to continue the power-on process, thereby reducing the impact of device failures on the operation of the data center and improving the flexibility and reliability of power management.

[0072] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0073] In order to better understand the process of the power-on method of the above-mentioned device, the implementation process of the power-on method of the above-mentioned device is described below in combination with an optional embodiment, but it is not used to limit the technical solution of the embodiment of the present application.

[0074] Most of the existing power-on strategies remain at the basic level, providing only simple functions such as power on, power off, and restart. They lack intelligent management and decision-making capabilities and cannot dynamically adjust the power-on strategy according to the actual operating status of the server or the power load. This low level of intelligence limits the efficient operation and stability of the data center, especially in large-scale server clusters, which may lead to low startup efficiency and energy waste. There are usually no flexible configuration options and cannot be customized according to specific needs. For example, it is impossible to set the startup priority, delay time of the server, or group management according to the server type. This lack of flexibility makes it difficult to respond flexibly when facing a complex and changing operating environment, increasing the complexity and difficulty of operation and maintenance. In addition, the existing power-on strategies often do not have real-time monitoring and dynamic adjustment functions. They cannot automatically adjust the power-on strategy according to real-time data such as power load and server status. This static power-on strategy may cause the server to encounter problems such as power fluctuations and uneven loads when starting, affecting the stability and reliability of the system. Furthermore, in the prior art, many traditional setting interfaces are complex and difficult to operate. For non-professionals, configuring power strategies may be a difficult task. This not only increases the configuration error rate, but may also cause system startup failure or performance degradation.

[0075] The present application aims to solve a series of core problems existing in the current technical field, which are mainly due to the limitations of existing technical solutions and cannot meet the requirements of growing market demand and technological progress. Specifically, the present application is committed to solving the following comprehensive technical problems: First, the present application focuses on improving the level of intelligence. Existing technical solutions often lack intelligent decision-making and management capabilities, and cannot be dynamically adjusted according to real-time data and system status. This leads to problems such as low system efficiency, waste of resources, and inability to respond to environmental changes in a timely manner. The present application can automatically optimize the system state according to real-time data to improve overall performance and efficiency. Secondly, in terms of control strategy, although some existing advanced BIOS functions have begun to try to introduce intelligent elements, they are often limited to the optimization of a single hardware component, such as CPU frequency adjustment, and lack systematic power-on strategy management. The present application adopts a more refined control strategy, which realizes all-round and multi-level management of the power-on process through server grouping, priority setting, and delay time adjustment. This refined control not only ensures the priority power-on of key business servers, but also effectively reduces the power load pressure by staggered power-on, avoiding the potential threat of current shock to system stability.

[0076] refer to Figure 3As shown, it is a flowchart of the power-on method of the device of the present application; for a data center composed of multiple servers, first, in the setting stage 302, the BIOS interface can be accessed through the BIOS setting interface or the remote management interface (such as IPMI, KVM, etc.). This is usually during the server startup process of the server cluster, through a specific key combination (such as Del key, F2 key, etc.) to enter the BIOS setting menu and navigate to the configuration part related to the power-on strategy.

[0077] refer to Figure 4 As shown in the figure, it is a schematic diagram of the interface of the BIOS setting interface. In the setting interface, there are multiple modules including AC (Alternating Current, AC control strategy, power-on delay strategy, device grouping, cabinet number, and delayed power-on time. The user can enter the module to be set to start viewing, setting and other processing procedures. Each module can define related parameters. For example, the user can view the delayed power-on module, determine that the delay time is 5 minutes, view that the cabinet number of the server is 001, view that the device group to which the service area belongs is Grub1, and view that the power-on delay strategy is Auto (Automatic).

[0078] In the BIOS, you can see one or more server grouping options. Servers can be divided into different groups based on actual server usage, such as business type, geographical location, hardware configuration, and other factors. For each group, users can set its startup priority, usually by dragging, selecting, or entering numbers. Groups with high priority will have priority in obtaining startup resources during the power-on process. After setting the grouping and priority, users need to set the power-on self-start delay time for each group or individual server. This delay time refers to the time interval from the main switch powering on to the group or server starting to try to start. Users can set different delay times for different groups or servers based on actual needs and power load conditions to achieve staggered power-on.

[0079] After all settings are completed, the initial power-on strategy is obtained, and then enter 304, that is, write the initial power-on strategy to the storage unit. The initial power-on strategy can usually be stored in a non-volatile memory (such as NVRAM) so that these settings can be automatically loaded and applied at the next startup.

[0080] Further, the process of machine power-on 306 is entered. In machine power-on 306, specifically, the main switch is powered on, that is, when the main switch of the data center is powered on, the BMC starts to execute the preset initial power-on strategy. At this time, the BMC enters the initial power-on strategy reading 308, first checking and loading the initial power-on strategy stored in NVRAM. According to the loaded configuration information, according to the preset priority and delay time order, the server with the highest priority is selected as the target device to be powered on.

[0081] After determining the target device to be powered on, the dynamic adjustment phase 310 is entered, and the BMC performs power data monitoring and function support, and determines whether there are any abnormal conditions in the power-on process based on the real-time monitored information. These abnormal conditions may include excessive power load, server failure and inability to start, network delay causing startup timeout, etc. The BMC automatically analyzes and adjusts the power-on strategy based on the abnormal conditions. For example, if the power load is too high, the management module will modify the BIOS settings out-of-band to increase the delay time of subsequent server groups to reduce the number of servers powered on at the same time; if a server fails and cannot start, the BMC may skip the server and continue to start other servers. The adjusted power-on strategy will take effect immediately, and the BMC will modify the BIOS options out-of-band through redfish and continue to control the server's power-on process according to the new strategy.

[0082] The delay setting option is displayed and set through BIOS, but the actual control depends on BMC for delay. When the power-on policy is manual, the relevant power-on policy is passed to BMC through redfish (an open standard). When the administrator performs a power on (starting or turning on an electronic device) operation through BMC, BMC will perform a delay before the operation to delay the power-on time. The power on command will not be executed until the delay is completed. At the same time, based on considerations for server security, the power on policy of physical buttons is still the first priority. Powering on with an external power button ignores the control of the BIOS power-on delay policy. When the power-on delay policy is in Auto state, BMC will perform a delay according to the allocation of the intelligent control system before executing power on.

[0083] After receiving the group information of the server, the BMC will read the PDU information of the group where the server is located and obtain the current load occupancy of the PDU. When the current remaining load power is less than the rated power of the server, the BMC will perform delayed startup measures; the BMC reads the power information three times within one minute and predicts the subsequent PDU power load according to the current power change trend. The greater the power decline trend, the shorter the delay time. Conversely, if the power is on the rise, the startup delay time will be appropriately extended according to the power increase range. The extension time is (power increase range * 60 / PDU rated power ratio) seconds.

[0084] The device power-on method of the present application, through intelligent management and dynamic adjustment mechanism, brings significant beneficial effects to the data center, including improving system stability and reliability, reducing operation and maintenance costs and maintenance difficulties, enhancing system flexibility and adaptability, improving resource utilization efficiency, and improving user experience and satisfaction, etc. These effects work together on the overall performance and management level of the data center, bringing users a more efficient, stable and reliable server operation environment.

[0085] In this embodiment, a power-on device for a device is also provided, which is used to implement the above embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0086] Figure 5 is a structural block diagram of a power-on device of a device according to an embodiment of the present application, such as Figure 5 As shown, the device comprises:

[0087] An acquisition module 52, used to acquire an initial power-on strategy corresponding to the device cluster to be powered on;

[0088] A determination module 54 is used to determine the target device to be powered on from the device cluster to be powered on based on the initial power-on strategy, and determine the current cluster load of the device cluster to be powered on; wherein the current cluster load is used to characterize the real-time power capacity of the device cluster to be powered on;

[0089] An adjustment module 56 is configured to adjust the initial power-on strategy to obtain a target power-on strategy when it is determined based on the current cluster load that there is a power-on abnormality when the target device is powered on according to the initial power-on strategy;

[0090] The power-on module 58 is configured to power on the target device based on the target power-on strategy.

[0091] Through the above device, an initial power-on strategy corresponding to the device cluster to be powered on is obtained; based on the initial power-on strategy, the target device to be powered on is determined from the device cluster to be powered on, so as to avoid all devices being powered on at the same time, resulting in current shock and insufficient power supply, thereby reducing the risk of startup failure. And further determine the current cluster load of the device cluster to be powered on; wherein the current cluster load is used to characterize the real-time power capacity of the device cluster to be powered on; when it is determined based on the current cluster load that there is a power-on anomaly when the target device is powered on according to the initial power-on strategy, the initial power-on strategy is adjusted to obtain the target power-on strategy; the target device is powered on based on the target power-on strategy. That is, when it is determined that there is a power-on anomaly when the target device is powered on according to the initial power-on strategy, the power-on strategy can be adjusted in time, the target power-on strategy can be obtained, and the power-on is performed according to the target power-on strategy, so as to avoid the negative impact of abnormal power-on on the operation of the entire device cluster, thereby ensuring the stable startup of the entire device cluster.

[0092] In an exemplary embodiment, the acquisition module 52 is also used to determine the device attribute parameters of each device in the device cluster to be powered on; determine the power-on priority of each device based on the device attribute parameters of each device; and determine the initial power-on strategy according to the power-on priority of each device.

[0093] In an exemplary embodiment, the acquisition module 52 is also used to determine the cluster load of the device cluster to be powered on in a historical time period; wherein the cluster load of the historical time period is used to indicate the historical power capacity of the device cluster to be powered on before a first time point, and the first time point is the time point when the power-on instruction for the device cluster to be powered on is obtained, and the power-on instruction is an instruction for instructing to power on each device in the device cluster to be powered on; based on the cluster load of the historical time period, the delay duration of each device in the device cluster to be powered on is determined; wherein the delay duration represents the duration between obtaining the first time point and a second time point when each device starts to power on; and the initial power-on strategy is determined according to the power-on priority of each device and the delay duration.

[0094] In an exemplary embodiment, the adjustment module 56 is further used to compare the current cluster load with the rated load of the target device to obtain a load comparison result; if the load comparison result is that the current cluster load is less than the rated load, obtain the cluster load of the device cluster to be powered on at multiple preset moments; select a first preset moment and a second preset moment from the device cluster to be powered on from the multiple preset moments, and determine the cluster load at the first preset moment as the first cluster load, and determine the cluster load at the second preset moment as the second cluster load; wherein the first preset moment is the moment when the cluster load value is the largest among the multiple preset moments; the second preset moment is the interval time from the first preset moment. the shortest moment; based on the difference between the load of the first cluster and the load of the second cluster, determining the load change of the device cluster to be powered on; multiplying the load change by a preset basic delay duration to obtain the product of the load change and the basic delay duration, and determining the quotient between the product and the rated load of the device cluster to be powered on as the delay adjustment amount; wherein the delay adjustment amount is a parameter for adjusting the delay duration in the initial power-on strategy; the basic delay duration is determined based on the device performance of the device cluster to be powered on; based on the delay adjustment amount, the delay duration in the initial power-on strategy is increased or decreased to obtain a target delay duration; based on the target delay duration, a target power-on strategy is obtained.

[0095] In an exemplary embodiment, the power-on module 58 is also used to determine the target delay duration for powering on the target device based on the target power-on strategy; when the duration of the power-on instruction obtained reaches the target delay duration, control the initialization processing of the target device to complete the power-on of the target device.

[0096] In an exemplary embodiment, the determination module 54 is further configured to determine, based on the power-on priority specified in the initial power-on strategy, a device with the highest power-on priority in the device cluster to be powered on as a target device to be powered on.

[0097] In an exemplary embodiment, the apparatus further comprises a processing module; the processing module is used to determine a status parameter associated with the target device; wherein the status parameter is used to characterize a current status of the target device; in a case where it is determined based on the device status parameter that the target device has a fault, powering on the target device is terminated, and a new target device is determined from the device cluster to be powered on based on the initial power-on strategy; based on the new target device, the step of returning to determine a current cluster load of the device cluster to be powered on is stopped until a preset stop condition is met.

[0098] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0099] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0100] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0101] In an 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.

[0102] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps in any one of the above method embodiments are implemented.

[0103] An embodiment of the present application further provides another computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0104] An embodiment of the present application also provides a computer program, which includes computer instructions, and the computer instructions are stored in a computer-readable storage medium; a processor of an electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device performs the steps in any one of the above method embodiments.

[0105] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0106] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0107] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for powering on a device, characterized in that: include: Obtaining an initial power-on strategy corresponding to the device cluster to be powered on; Determine the target device to be powered on from the device cluster to be powered on based on the initial power-on strategy, and determine the current cluster load of the device cluster to be powered on; wherein the current cluster load is used to characterize the real-time power capacity of the device cluster to be powered on; When it is determined based on the current cluster load that there is a power-on abnormality when the target device is powered on according to the initial power-on strategy, adjusting the initial power-on strategy to obtain a target power-on strategy; The target device is powered on based on the target power-on strategy.

2. The method according to claim 1, characterized in that Determining the initial power-on strategy includes: Determine device attribute parameters of each device in the device cluster to be powered on; Determining the power-on priority of each device based on the device attribute parameters of each device; The initial power-on strategy is determined according to the power-on priority of each device.

3. The method according to claim 2, characterized in that The determining the initial power-on strategy according to the power-on priority of each device includes: Determine the cluster load of the device cluster to be powered on in a historical time period; wherein the cluster load in the historical time period is used to indicate the historical power capacity of the device cluster to be powered on before a first time point, the first time point is the time point when a power-on instruction for the device cluster to be powered on is obtained, and the power-on instruction is an instruction for instructing to power on each device in the device cluster to be powered on; Determine the delay time of each device in the device cluster to be powered on based on the cluster load in the historical time period; wherein the delay time represents the duration between obtaining the first time point and the second time point at which each device starts to power on; The initial power-on strategy is determined according to the power-on priority of each device and the delay duration.

4. The method according to claim 1, characterized in that The step of, when it is determined based on the current cluster load that a power-on abnormality exists when the target device is powered on according to the initial power-on strategy, adjusting the initial power-on strategy to obtain a target power-on strategy comprises: Compare the current cluster load with the rated load of the target device to obtain a load comparison result; if the load comparison result is that the current cluster load is less than the rated load, obtain the cluster load of the device cluster to be powered on at multiple preset times; A first preset time and a second preset time are selected from the device cluster to be powered on from a plurality of preset times, and the cluster load at the first preset time is determined as the first cluster load, and the cluster load at the second preset time is determined as the second cluster load; wherein the first preset time is the time when the cluster load value is the largest among the plurality of preset times; and the second preset time is the time when the interval with the first preset time is the shortest; Determining a load change amount of the device cluster to be powered on based on a difference between the first cluster load and the second cluster load; The load change amount and a preset basic delay duration are multiplied to obtain the product of the load change amount and the basic delay duration, and the quotient between the product and the rated load of the device cluster to be powered on is determined as the delay adjustment amount; wherein the delay adjustment amount is a parameter for adjusting the delay duration in the initial power-on strategy; and the basic delay duration is determined based on the device performance of the device cluster to be powered on; Based on the delay adjustment amount, increasing or decreasing the delay duration in the initial power-on strategy to obtain a target delay duration; A target power-on strategy is obtained based on the target delay duration.

5. The method according to claim 1, characterized in that The powering on the target device based on the target power-on strategy includes: Based on the target power-on strategy, determining a target delay duration for powering on the target device; When it is obtained that the duration of the power-on instruction reaches the target delay duration, the target device is controlled to be initialized to complete the power-on of the target device.

6. The method according to claim 1, characterized in that The determining the target device to be powered on from the device cluster to be powered on based on the initial power-on strategy includes: Based on the power-on priority specified in the initial power-on strategy, a device with the highest power-on priority in the device cluster to be powered on is determined as a target device to be powered on.

7. The method according to claim 1, characterized in that The method further comprises: Determining a state parameter associated with the target device; wherein the state parameter is used to characterize a current state of the target device; In the case where it is determined based on the device status parameter that the target device has a fault, powering on the target device is terminated, and a new target device is determined from the device cluster to be powered on based on the initial power-on strategy; Based on the new target device, return to the step of determining the current cluster load of the device cluster to be powered on, and stop until a preset stop condition is met.

8. A power-on device for a device, characterized in that: include: An acquisition module, used to acquire an initial power-on strategy corresponding to a device cluster to be powered on; A determination module, configured to determine a target device to be powered on from the device cluster to be powered on based on the initial power-on strategy, and to determine a current cluster load of the device cluster to be powered on; wherein the current cluster load is used to characterize the real-time power capacity of the device cluster to be powered on; The adjustment module is used to adjust the initial power-on strategy to obtain the target power-on strategy when it is determined based on the current cluster load that there is a power-on anomaly when the target device is powered on according to the initial power-on strategy; the power-on module is used to power on the target device based on the target power-on strategy.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program implements the steps of the method described in any one of claims 1 to 7 when executed by a processor.

10. 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, the steps of the method described in any one of claims 1 to 7 are implemented.

Images