Control method for electronic device to operate, electronic device, server, and storage medium

Abstract

The application discloses a control method for running an electronic device, an electronic device, a server and a storage medium, and relates to the technical field of computers, wherein the method comprises: configuring a specified energy efficiency scene for the electronic device in multiple energy efficiency scenes, wherein the specified energy efficiency scene is associated with a specified energy efficiency mode, and at least part of multiple RAS functions is enabled in the specified energy efficiency mode; and in response to the specified energy efficiency scene taking effect, the electronic device is controlled to run with the at least part of the RAS functions enabled. Since the running state of the RAS function is associated with the configured energy efficiency scene, the change of performance and energy consumption in the energy efficiency scene can be matched with the running state of the RAS function, thereby solving the problem that the control method for running the device in the prior art has a low service life of the device due to poor reliability of the device running, and achieving the technical effect of improving the service life of the device.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a control method for the operation of an electronic device, an electronic device, a server, and a storage medium. Background Technology

[0002] For electronic devices, energy efficiency scenarios can be configured to improve their performance and energy consumption. However, changes in performance and energy consumption can affect the reliability of device operation, and consequently, the lifespan of the device.

[0003] It is evident that the control methods for equipment operation in related technologies suffer from poor equipment reliability, leading to a short equipment lifespan. Summary of the Invention

[0004] This application provides a control method for operating an electronic device, an electronic device, a server, and a storage medium, to at least solve the problem of low device lifespan caused by poor device operation reliability in related technologies.

[0005] According to one aspect of the embodiments of this application, a control method for operating an electronic device is provided, comprising: configuring a specified energy efficiency scenario for the electronic device in multiple energy efficiency scenarios, wherein the specified energy efficiency scenario is associated with a specified energy efficiency mode, and in the specified energy efficiency mode, at least some of the multiple RAS functions are enabled; and controlling the electronic device to operate when the specified energy efficiency scenario is enabled in response to the specified energy efficiency scenario taking effect.

[0006] According to another aspect of the embodiments of this application, an electronic device is also provided, including: a processor and a management controller, the processor being configured to execute a basic input / output system; wherein at least one of the management controller and the basic input / output system is configured to configure a specified energy efficiency scenario for the electronic device in a plurality of energy efficiency scenarios, wherein the specified energy efficiency scenario is associated with a specified energy efficiency mode, and in the specified energy efficiency mode, at least some of the plurality of RAS functions are enabled; in response to the specified energy efficiency scenario taking effect, the electronic device is controlled to operate when the at least some RAS functions are enabled.

[0007] According to another aspect of the embodiments of this application, a server is also provided, including: a processor and a management controller, the processor being configured to execute a basic input / output system; wherein at least one of the management controller and the basic input / output system is configured to configure a specified energy efficiency scenario for the server among multiple energy efficiency scenarios, wherein the specified energy efficiency scenario is associated with a specified energy efficiency mode, and in the specified energy efficiency mode, at least some of the multiple RAS functions are enabled; in response to the specified energy efficiency scenario taking effect, the server is controlled to operate when the at least some RAS functions are enabled.

[0008] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, wherein a computer program is stored therein, wherein the computer program is configured to perform the steps in any of the above method embodiments when executed by a processor.

[0009] According to another aspect of the embodiments of this application, a computer program product or computer program is provided, the computer program product or computer program including 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 the processor executes the computer instructions, causing the computer device to perform the steps in any of the method embodiments described above.

[0010] This application associates the energy efficiency mode of a device with the operating status of its Reliability, Availability, and Serviceability (RAS) functions. It also associates a specific energy efficiency scenario with a specific energy efficiency mode within multiple energy efficiency scenarios. Under the specified energy efficiency mode, at least some of the RAS functions are enabled. Through this association method, the changes in performance energy consumption under energy efficiency scenarios can be matched with the operating status of the RAS functions. This improves the reliability of device operation while ensuring performance energy consumption, thereby extending the device's lifespan. This addresses the technical problem in related technologies where poor device reliability leads to a short device lifespan. Attached Figure Description

[0011] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1This is a structural block diagram of an optional electronic device according to an embodiment of this application.

[0013] Figure 2 This is a flowchart illustrating an optional control method for operating an electronic device according to an embodiment of this application.

[0014] Figure 3 This is a schematic diagram of an optional bathtub curve according to an embodiment of this application.

[0015] Figure 4 This is a schematic diagram of an optional High RAS mode framework according to an embodiment of this application.

[0016] Figure 5 This is a schematic diagram of an optional error monitoring and handling method according to an embodiment of this application.

[0017] Figure 6 This is a flowchart illustrating another optional control method for operating an electronic device according to an embodiment of this application.

[0018] Figure 7 This is a structural block diagram of another optional electronic device according to an embodiment of this application. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of this application.

[0020] It should be noted that, in the description of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. The terms "first," "second," etc., in this application are used to distinguish similar objects and are not used to describe a specific order or sequence.

[0021] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0022] According to one aspect of the embodiments of this application, a control method for operating an electronic device is provided. Optionally, in this embodiment, the control method for operating the electronic device may be applied, but is not limited to, to... Figure 1 In the electronic device shown. For example... Figure 1 As shown, the electronic device may include: one or more ( Figure 1 (Only one is shown) a processor 102, a memory 104, a RAM 106, and a management controller 108. These components can be integrated onto the motherboard of the electronic device. Furthermore, the electronic device may also include transmission devices for communication functions and input / output devices. 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 electronic device described above. For example, the electronic device 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.

[0023] Optionally, processor 102 may include, but is not limited to, a processing device such as a central processing unit (CPU), a microprocessor (MCU), or a programmable logic device (FPGA). Memory 104 can be used to store data, such as computer programs, application software programs, and modules. Processor 102 can execute various functional applications and data processing by running the computer programs stored in memory 104. Memory 104 may include high-speed random access memory (RAM) and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memories. In some instances, memory 104 may further include memory remotely located relative to processor 102, and these remote memories can be connected to electronic devices via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks (LANs), mobile communication networks, and combinations thereof.

[0024] Memory 106 can be used to perform at least one of the following operations: data storage and fast access, operating system operation, application execution, error detection and correction, and data exchange and communication. Memory 106 can also act as a cache. Optionally, processor 102 can be used to execute the Basic Input Output System (BIOS), and the BIOS program can be stored in memory 104, for example, in non-volatile memory. When the electronic device is powered on, processor 102 can load the BIOS program from memory 104. The BIOS runs in the memory of the electronic device and is executed by the processor. The BIOS can be responsible for initializing the processor and other hardware components of the electronic device, such as memory, Peripheral Component Interconnect Express (PCIe) devices, performing hardware self-tests, configuring hardware parameters, and loading the operating system.

[0025] A transmission device is used to receive or send data via a network. This network can be a wireless network provided by the communication provider of the electronic device. In one example, the transmission device may include 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 may be a Radio Frequency (RF) module, which can be used to communicate with the Internet wirelessly.

[0026] The management controller 108 can be a standalone microcontroller responsible for out-of-band management functions of the electronic device, such as remote monitoring, management, and control of device status. The management controller 108 can communicate with the BIOS on the processor, but it runs its own firmware and is independent of the BIOS. During normal operation of the electronic device, the management controller 108 can monitor the system status and interact with the BIOS when necessary. For example, the electronic device can be a server or other devices, and the management controller 108 can be a Baseboard Management Controller (BMC) or other microcontrollers.

[0027] The control method for operating the electronic device according to the embodiments of this application can be executed by the processor 102, the management controller 108, or jointly by the processor 102 and the management controller 108. The processor 102 can also execute the control method for operating the electronic device according to the embodiments of this application through a basic input / output system running on it.

[0028] Taking the control method for the operation of the electronic device in this embodiment, which is jointly executed by the basic input / output system and the management controller 108, as an example, Figure 2 This is a flowchart illustrating an optional control method for operating an electronic device according to an embodiment of this application, as shown below. Figure 2 As shown, the process of this method may include the following steps S202 and S204.

[0029] Step S202: Configure a specified energy efficiency scenario for the electronic device in multiple energy efficiency scenarios, wherein the specified energy efficiency scenario is associated with a specified energy efficiency mode, and in the specified energy efficiency mode, at least some of the RAS functions among the multiple RAS functions are enabled.

[0030] Step S204: In response to the specified energy efficiency scenario taking effect, control the electronic device to operate with at least some RAS functions enabled.

[0031] The electronic device operation control method in this embodiment can be applied to the field of computer technology, specifically to scenarios involving the operation control of electronic devices. In related technologies, various energy efficiency scenarios can be configured for electronic devices to improve their performance and energy consumption. However, changes in performance and energy consumption can affect the reliability of device operation, and consequently, the lifespan of the device. Taking a server as an example, as data centers increasingly demand higher reliability and performance from servers, server manufacturers have introduced various energy efficiency scenarios corresponding to different performance and energy efficiency modes, such as high-performance modes, aiming to improve the server's performance and energy consumption in different scenarios. However, changes in performance and energy consumption can also affect the reliability of server operation, and consequently, the lifespan of the server.

[0032] To at least partially address the aforementioned technical problems, in this embodiment, the electronic device may be configured with a Reliability and Availability System (RAS) function to improve its reliability, availability, and maintainability. The device's energy efficiency mode is associated with the operating state of the RAS function. A specific energy efficiency scenario among multiple energy efficiency scenarios is associated with a specific energy efficiency mode (e.g., High RAS mode). Under the specified energy efficiency mode, at least some of the multiple RAS functions are enabled. Energy efficiency scenarios are related to the device's performance and energy consumption, which in turn affects the device's operational reliability. Therefore, through the aforementioned association method, the changes in performance and energy consumption under energy efficiency scenarios can be controlled to match the operating state of the RAS function, thereby ensuring the reliability and performance of the electronic device in different scenarios and ultimately improving the device's lifespan.

[0033] Multiple energy efficiency scenarios can include custom scenarios and high-performance scenarios, and each energy efficiency scenario can be associated with one energy efficiency mode. A specified energy efficiency scenario can be one or more of multiple scenarios. When there are multiple specified energy efficiency scenarios, the operating status of the RAS functions within the multiple RAS functions can be the same or different under different specified energy efficiency scenarios. Under a specified energy efficiency mode, the operating status of all or some of the multiple RAS functions can be configured. The operating status of a RAS function can be at least one of the following: enabled, disabled, adaptive, or other. At least some of the multiple RAS functions are enabled to ensure the reliability of device operation.

[0034] For example, as data centers increasingly demand higher reliability and performance from servers, they can be configured with various performance and energy efficiency modes, such as High RAS mode and high-performance mode, to improve the reliability and performance of servers in different scenarios.

[0035] Optionally, in this embodiment, the specified energy efficiency mode may have a set of linked functions, which may include multiple RAS functions and multiple performance energy efficiency functions. Under the specified energy efficiency mode, the operating status of the performance energy efficiency functions can use the default configuration or can be adjusted through configuration commands.

[0036] Optionally, in this embodiment, each of the multiple RAS functions can correspond to one of the multiple function options (referred to as a RAS function option), and one option value of a function option can correspond to a certain operating state. Multiple function options and their corresponding option values ​​can be recorded through option configuration information. The option configuration information can be used to record the operating state of the RAS functions among the multiple function options, and can also record the option values ​​of the function options corresponding to the performance and energy efficiency functions among the multiple performance and energy efficiency functions. The option value of a function option corresponding to a performance and energy efficiency function is used to indicate the operating state of that performance and energy efficiency function.

[0037] The control method for the operation of the electronic device in this embodiment can be executed by at least one of the BIOS and the management controller. Users can configure energy efficiency scenarios for the electronic device through an interface or configuration information. By detecting operations performed on the configuration interface, obtaining instructions triggered by operations performed on the configuration interface, or parsing configuration information, a specific energy efficiency scenario can be configured for the electronic device among multiple energy efficiency scenarios.

[0038] The specified energy efficiency scenario configured for an electronic device can take effect immediately or upon meeting certain conditions (e.g., system restart). In response to the specified energy efficiency scenario taking effect, the electronic device can be controlled to operate with at least some RAS functions enabled. Here, during the operation of the electronic device, at least some RAS functions are enabled, and the enabled RAS functions can perform their corresponding functions to ensure the reliability of device operation. Other RAS functions can be disabled or in other operating states; in response to the specified energy efficiency scenario taking effect, these other RAS functions can be controlled according to their configured operating states to match the specified energy efficiency scenario.

[0039] The embodiments provided in this application configure specified energy efficiency scenarios for electronic devices in multiple energy efficiency scenarios. The specified energy efficiency scenario is associated with a specified energy efficiency mode. Under the specified energy efficiency mode, at least some of the RAS functions among multiple RAS functions are enabled. In response to the specified energy efficiency scenario taking effect, the electronic device is controlled to operate with at least some RAS functions enabled. This solves the technical problem of low device lifespan caused by poor device operation reliability in the control methods of device operation in related technologies, improves the reliability of device operation, and thus improves the lifespan of the device.

[0040] In one exemplary embodiment, configuring a specified energy efficiency scenario for an electronic device in multiple energy efficiency scenarios includes: displaying a scenario configuration interface in response to a detected first trigger operation; displaying a specified mode tab on the scenario configuration interface in response to a selection operation performed on a specified scenario tab in the scenario configuration interface; and generating a first configuration save instruction in response to a configuration save operation performed on the scenario configuration interface, so as to configure the specified energy efficiency scenario for the electronic device.

[0041] Configuring energy efficiency scenarios for electronic devices can be achieved through a scenario configuration interface. This interface can be a BIOS setup interface, a management controller interface (e.g., a BMC interface), or any other configuration interface that allows configuration of energy efficiency scenarios for electronic devices. In response to a detected first trigger operation, the scenario configuration interface is displayed. This first trigger operation is the action that initiates the display of the scenario configuration interface. It can be a single operation or a combination of multiple operations, such as a click, double-click, swipe, or long-press. In this embodiment, the type of the first trigger operation is not limited.

[0042] The scene configuration interface can include a scene selection area. It can display a specified scene tab by default, or, in response to a detected switching operation (e.g., a selection operation performed on the scene tab list within the scene selection area), configure the selected scene tab within the scene selection area as a specified scene tab. The specified scene tab is the scene tab corresponding to a specified energy efficiency scene. For the selected scene tab, the associated mode tab can be directly displayed on the scene configuration interface, or, in response to a detected selection operation, the mode tab configured for the selected scene tab can be displayed on the scene configuration interface. Alternatively, scene tabs and mode tabs can be directly associated based on configuration information without displaying the associated mode tab on the scene configuration interface. Here, the mode tab can be associated with the selected scene tab and correspond to a specific energy efficiency mode. The specified mode tab is the mode tab associated with the specified scene tab and corresponds to the specified energy efficiency mode.

[0043] It's worth noting that tabs can be interface elements used to organize and categorize different configuration settings, similar to tabs in a web browser. They help users switch between different functional areas to browse and edit settings. For the aforementioned cases where it's unnecessary to display associated mode tabs in the scene configuration interface, the backend can directly associate scene options and mode options.

[0044] If the scene configuration interface displays a specified scene tab by default, the scene configuration interface displayed in response to the first detected trigger operation will include the specified scene tab. In this case, no selection is required, and the specified mode tab will be displayed on the scene configuration interface. If the scene configuration interface displays other scene tabs by default or does not display any scene tabs, the specified mode tab can be displayed on the scene configuration interface in response to a selection operation performed on the specified scene tab.

[0045] The specified mode tab can have a set of linked options. These linked options can be performance and energy efficiency options or functional options of RAS (Reliability, Automation, and Sustainability) functions. A set of linked options can include multiple functional options, and one RAS function can correspond to one of the multiple functional options. The scene configuration interface can display all or some of the linked options in a set, as well as their values. The displayed values ​​can be adjustable or are the specified values ​​corresponding to the specified mode tab (not adjustable). The displayed linked options can include all or some of the multiple functional options. Optionally, the scene configuration interface can also choose not to display any of the linked options in a set, and the value of each linked option in the set can use the default configuration (the value configured for the specified energy efficiency mode).

[0046] If a user wants to save the current scene configuration, they can perform a save operation on the scene configuration interface. This save operation can be a click on a designated button (virtual button) on the scene configuration interface, or a swipe, double-click, long-press, or a combination of these operations—anything that indicates saving the current scene configuration is acceptable. For electronic devices, in response to the save operation on the scene configuration interface, a first save instruction can be generated to configure the electronic device with the specified energy efficiency scene.

[0047] Here, the first configuration save command is used to save the current scene configuration. It can carry the scene identifier of the specified energy efficiency scene, as well as other configuration information. The scene identifier of the specified energy efficiency scene can be a scene name, scene number, or a fixed command number that corresponds to the specified energy efficiency scene and can serve as a scene identifier for the specified energy efficiency scene. Alternatively, the first configuration save command can also be in other forms, as long as it can indicate that the currently configured energy efficiency scene is the specified energy efficiency scene.

[0048] Through this embodiment, by performing configuration operations on the scene configuration interface, a specified energy efficiency scene can be configured for electronic devices in multiple energy efficiency scenarios, thereby achieving visualized scene configuration and improving the convenience and accuracy of scene configuration.

[0049] In one exemplary embodiment, after generating the first configuration save instruction, the method further includes: in response to the first configuration save instruction, determining the option values ​​configured for a set of linkage options for a specified energy efficiency mode, and obtaining first option configuration information to be updated; updating the operating status of multiple RAS functions according to the first option configuration information, so that at least some RAS functions are enabled.

[0050] In this embodiment, the specified energy efficiency mode may have a set of linked options. This set of linked options may include function options corresponding to the RAS functions among multiple RAS functions, and may also include function options corresponding to other linked functions (e.g., energy efficiency functions) (e.g., energy efficiency options). In response to the first configuration save command, the electronic device can determine the option values ​​configured for the set of linked options and obtain the first option configuration information to be updated. Here, the option values ​​configured for the set of linked options may be the default configuration, or they may be set through the scene configuration interface. Alternatively, some linked option values ​​may be the default configuration, while others may be set through the scene configuration interface. Other determination methods are also possible, and this embodiment does not limit this approach.

[0051] According to the configuration information in the first option, the running status of multiple RAS functions can be updated, thereby enabling at least some RAS functions. For example, the running status of all multiple RAS functions can be updated (for a certain RAS function, the running status before and after the update can be the same or different), or only the running status of the RAS functions whose running status has changed can be updated. In addition to updating the running status of multiple RAS functions, the running status of other linked functions can also be updated. The running status of multiple RAS functions and other linked functions can be configured simultaneously or separately as needed.

[0052] In this embodiment, the configuration and saving instructions are used to configure the operating status of linkage functions for a specified energy efficiency scenario. This eliminates the need to configure the operating status of individual linkage functions separately (for example, to configure the operating status of different linkage functions through different configuration instructions), thereby improving the convenience and reliability of configuring the operating status of linkage functions.

[0053] In one exemplary embodiment, under a specified energy efficiency mode, the operating status of multiple RAS functions can be statically configured. Static configuration means that the operating status of the multiple RAS functions is independent of the operating status of the electronic device; for example, at least some of the RAS functions are enabled in different hardware health states of the electronic device. The operating status of the multiple RAS functions can be indicated by function configuration information. If static configuration is used, the function configuration information will not change with the operating status of the electronic device. This function configuration information can be the aforementioned option configuration information.

[0054] Optionally, in this embodiment, controlling the electronic device to operate with at least some RAS functions enabled in response to the specified energy efficiency scenario taking effect includes: controlling the electronic device to operate with at least some RAS functions enabled during the duration of the specified energy efficiency scenario taking effect.

[0055] In the case of static configuration of the operating status of multiple RAS functions, the operating status of the multiple RAS functions will not change after the specified energy efficiency scenario takes effect. That is, during the duration of the specified energy efficiency scenario, the electronic device will operate with at least some RAS functions enabled.

[0056] If the operating status of multiple RAS functions needs to be adjusted, this can be achieved by modifying the aforementioned function configuration information through configuration commands or other methods. If the operating status of one or more RAS functions is adjusted, to ensure the reliability of the electronic device, the electronic device can be restarted to re-enable the specified energy efficiency scenario. During the duration of a single effective period of the specified energy efficiency scenario, the operating status of the multiple RAS functions remains unchanged. Correspondingly, in response to the effective period of the specified energy efficiency scenario, the electronic device is controlled to operate with at least some RAS functions enabled during the effective period of the specified energy efficiency scenario.

[0057] This embodiment uses a static configuration method to configure the operating status of the RAS function, which improves the convenience and reduces the difficulty of configuring the operating status of the RAS function; maintaining the operating status of the RAS function for the duration of the specified energy efficiency scenario can improve the reliability of equipment operation.

[0058] In one exemplary embodiment, multiple RAS functions can be configured according to device operating requirements. Under a specified energy efficiency mode, the operating status of the multiple RAS functions can be configured as needed and adjusted as required. The multiple RAS functions may include, but are not limited to, at least one of the following: System Errors, Failure Detection and Management (FDM), Page Policy, Adaptive DoubleDevice Data Correction (ADDDC), Custom Refresh, Attempt Fast Cold Boot, Patrol Scrubbing, Partial Cache Line Sparing (PCLS), and Post Packet Repair (PPR) Type.

[0059] Optionally, in this embodiment, under a specified energy efficiency mode, the operating state of multiple RAS functions may include at least one of the following: the system error detection function is enabled; the memory error isolation and protection function is enabled; the page management and error handling function is adaptive; the adaptive dual-device data correction spare part function is enabled; the custom refresh function is enabled; the attempt to quickly start the function is disabled; the patrol erase function is enabled; the partial cache line protection function is enabled; and the double data rate grouping repair type function is soft-packaged repair.

[0060] For example, High RAS mode can be implemented using static configuration, and the linkage option settings can include at least one of the following: "Hardware Prefetcher" is enabled; "Adjacent Cache Prefetch" is enabled; "DCU IP Prefetcher (DataCache Unit Instruction Pointer Prefetcher)" is enabled; "LLC Prefetch (Last Level Cache Prefetch)" is disabled; "Enable LP [Global] (Enable Low Power [Global])" is set to ALL LPs; "DCU Streamer Prefetcher" is disabled; "CPU Flex Ratio Override (Central ProcessingUnitFlex Ratio Override)" is disabled; "NUMA (Non-Uniform Memory)" is disabled. The following functions are enabled: "Access (non-uniform memory access)"; "Link L0p Enable"; "Link L1p Enable"; "KTI Prefetch"; "Link Frequency Select"; "XPTPrefetch"; "Enable MWAIT"; and "Uncore Freq Scaling".The "DEMT (Direct Evict Memory Tiering)" function option is set to "Disabled"; the "EIST PSD Function" function option is set to "HW_ALL" (full hardware control); the "Boot performance mode" function option is set to "MaxPerformance"; the "Power Performance Tuning" policy option is set to "OS Controls EPB (Operating System Controls Enhanced Power Profile for Business)"; the "ENERGY_PERF_BIAS_CFG mode" is set to "Balanced Performance"; the "SpeedStep (Pstates)" function option is set to "Enabled"; the "Turbo Mode" function option is set to "Enabled"; the "EPP (Enhanced Power Profiles)" function option is set to "Enabled"; the "EPP profile" is set to "Balanced Performance"; and the "Static" function option is set to "Employment Controls for Business". The following settings are configured: "Turbo Boost" is off; "CPU Frequency Select" is set to 40; "Enhanced Halt State (C1E)" is off; "CPU C6 report" is off; "Hardware P-State" is off; "Package C-State" is set to Auto; "System Errors" is on; "FDM" is on; "System Memory Poisoning" is on; and "CKE Power Down" is off.The "Refresh Options" option is set to Dynamic Mode; the "Page Policy" option is set to Adaptive; the "ADDDCSparing" option is enabled; the "Custom Refresh" option is enabled; the "Custom Refresh Rate" is set to 20; the "Attempt Fast Cold Boot" option is disabled; the "Patrol Scrubbing" option is enabled; the "Partial Cache Line Sparing" option is enabled; and the "DDR PPR Type" option is set to Soft PPR.

[0061] This embodiment demonstrates how configuring the operating status of different RAS functions among multiple RAS functions under a specified energy efficiency mode can improve both the reliability of device operation and the energy consumption performance of the device.

[0062] In one exemplary embodiment, under a specified energy efficiency mode, the operating state of the RAS functions among multiple RAS functions can remain unchanged; that is, the operating state of the RAS functions remains unchanged regardless of the operating stage of the electronic device. Considering that some RAS functions, while contributing to improving the reliability, availability, and maintainability of electronic devices, can also significantly impact the performance of electronic devices, and that the failure rate of electronic devices changes throughout their lifecycle, the failure rate changes of electronic devices throughout their lifecycle can be divided into different failure rate stages. Different failure rate stages correspond to different RAS function configuration information, and the RAS function configuration information corresponding to a failure rate stage is used to indicate the operating state of the RAS functions among multiple RAS functions within that failure rate stage.

[0063] Taking servers as an example, the failure rate of a server is not constant throughout its lifecycle; the change in the failure rate of a server during its lifecycle typically follows the following pattern: Figure 3The "bathtub curve" illustrates how server failure rates are divided into three main phases: early failure, random failure, and wear-out failure. In the early failure phase, the failure rate is relatively high when the server is first put into use, but it decreases rapidly over time. These early failures are usually caused by manufacturing defects, design problems, or material flaws. During this phase, rigorous early testing and burn-in can screen out components that may fail prematurely, thus reducing the failure rate after actual deployment. After the early failure phase, the server enters a relatively stable period, the random failure phase, during which the failure rate is low and roughly constant, representing the server's optimal operating state. In this phase, failures usually occur randomly, possibly caused by environmental factors, operational errors, or unforeseen hardware problems. After a long period of operation, the server enters its late lifespan, the wear-out failure phase, where hardware components begin to gradually fail due to aging, causing the failure rate to rise again. During this phase, implementing appropriate RAS (Reliability, Serviceability, and Availability) functions, maintaining and replacing aging components can extend the server's lifespan and improve its reliability. Figure 3 As shown, the service life of a server starts at point A, where the failure rate falls below the specified failure rate during the early failure period, and ends at point B, where the failure rate rises above the specified failure rate during the wear and tear failure period. During the wear and tear failure period, the failure rate will decrease after the server is repaired.

[0064] If a server's mode options are statically configured, it can lead to a deficiency in balancing system reliability and performance / energy consumption. For example, in High RAS mode, if the ADDDC function is always enabled, it can cause approximately 7% performance loss during periods of low server failure rate, such as a 6% to 9% decrease in memory read / write performance, and in severe cases, a performance loss of 25% to 29%. Therefore, based on the server's failure rate variation throughout its lifespan, some functions like ADDDC do not need to be constantly enabled. They can be activated only when the failure rate of related components rises to a certain level, ensuring server reliability while reducing performance degradation over the server's lifespan. To adapt to changes in server failure rate, the server's RAS function options can be adjusted. One possible configuration method for RAS is: when the server failure rate is low, use basic RAS functions to reduce the impact on server performance; when the server failure rate increases, use enhanced RAS functions to improve server reliability.

[0065] As an optional implementation, to dynamically adjust the operating status of multiple RAS functions based on changes in the failure rate of electronic devices, the failure rate of the electronic device can be characterized by its hardware health status, which is negatively correlated with the failure rate. In a specified energy efficiency mode, at least some RAS functions change with the hardware health status of the electronic device; that is, the activated RAS functions are dynamically adjusted according to the hardware health status. In this case, the specified energy efficiency mode can be called a performance-priority mode.

[0066] As an alternative implementation, to ensure reliability throughout the entire lifecycle of the electronic device, in a specified energy efficiency mode, at least some RAS functions can be independent of the hardware health status of the electronic device. That is, among multiple RAS functions, the enabled RAS functions are independent of the hardware health status of the electronic device. In this case, the specified energy efficiency mode can be called a reliability priority mode, i.e., RAS Priority mode.

[0067] Optionally, to adapt to different usage scenarios, the specified energy efficiency mode may include the following two sub-modes: performance-priority mode and reliability-priority mode. Performance-priority mode prioritizes ensuring the performance and energy consumption of the electronic device, while reliability-priority mode prioritizes ensuring reliability. In performance-priority mode, at least some RAS functions change with the hardware health status of the electronic device; in reliability-priority mode, at least some RAS functions are independent of the hardware health status of the electronic device.

[0068] For example, depending on the use case, the High RAS mode can be further refined into High RAS–RAS Priority mode and High RAS–Performance Priority mode, representing reliability-first mode and performance-power-first mode, respectively. To achieve this, a High RAS mode option can be added under the "Performance-Power-Consciousness Scenarios" tab in the BIOS Setup and BMC interfaces. In the BIOS Setup or BMC interface, an initialization mode (High RAS–RAS Priority mode or High RAS–Performance Priority mode) that suits the current application scenario can be selected. Different initialization modes correspond to different sets of RAS tabs. After selecting an initialization mode, the corresponding RAS tabs will be configured according to preset policies. Once the RAS tab configuration takes effect, the BMC's dynamic policy engine dynamically configures the RAS function.

[0069] For example, such as Figure 4 As shown, in the BIOS Setup interface, the two modes can be enabled or disabled through the options "High RAS – RAS Priority" and "High RAS – Performance Priority" in the "Performance and Power Consumption Scenarios" tab. When an option is selected, a series of tabs will be set according to the preset policy to make the server conform to the relevant scenario. The settings will be synchronized with the BMC in real time through the Intelligent Platform Management Interface (IPMI). The settings will take effect after the system saves the settings and restarts.

[0070] Additionally, the above functions can also be controlled through the "Performance & Energy Consumption Scenarios" tab in the BMC interface, specifically the options "HighRAS – RAS Priority" and "High RAS – Performance Priority". When an option is selected, the BMC will activate the High RAS dynamic policy engine to dynamically configure the RAS function and synchronize it to the BIOS via the Redfish channel. All settings will take effect upon system restart.

[0071] To configure sub-modes within a specified energy efficiency mode, a specified mode tab and associated sub-mode options can be displayed on the scene configuration interface. The sub-mode options include a first option value corresponding to the performance-energy-priority mode and a second option value corresponding to the reliability-priority mode. Correspondingly, in response to a selection operation on the specified scene tab in the scene configuration interface, the specified mode tab is displayed on the scene configuration interface, including: in response to a selection operation on the specified scene tab, the specified mode tab and associated sub-mode options are displayed on the scene configuration interface.

[0072] Here, the sub-mode option values ​​can include a first option value corresponding to the performance / energy consumption priority mode and a second option value corresponding to the reliability priority mode. The sub-mode option values ​​displayed on the scenario configuration interface can be one of the first and second option values, or they can be empty. The selected sub-mode can be changed by performing a change operation on the sub-mode option values ​​(for example, by adjusting the selected option value).

[0073] For example, when the High RAS – RAS Priority mode is selected, the server initially enables higher-level RAS functions by default, including but not limited to DDR Mirroring (i.e., memory mirroring) and ADDDC functions, Uncorrectable Error Correcting Code (UECC) retry for Dynamic Random Access Memory (DRAM), and Cyclic Redundancy Check (CRC) with replay for DRAM write data. This mode improves system data reliability by strengthening server redundancy checks and fault tolerance capabilities, making it suitable for business scenarios with extremely high data consistency requirements, such as financial and medical systems. When the High RAS – Performance Priority mode is selected, the server initially only enables basic RAS functions that meet the specified failure rate, moderately reducing redundancy check strength and fault tolerance overhead to achieve higher computing efficiency and lower energy consumption. This mode is suitable for application environments with large load fluctuations, high resource utilization, and energy efficiency sensitivity, such as cloud computing and virtualization.

[0074] During server operation, the dynamic policy engine in the BMC continuously monitors the system's hardware health and dynamically adjusts RAS and energy efficiency options accordingly. Furthermore, users can specify the server's initial state by configuring the associated features in the High RAS-RASPriority mode or High RAS-Perform Priority mode on the BMC.

[0075] For example, in a computing platform, the High RAS–RAS Priority mode linkage options can be set as follows: "Hardware Prefetcher" is enabled; "Adjacent Cache Prefetch" is enabled; "DCU Streamer Prefetcher" is enabled; "DCU IPPrefetcher" is enabled; "Hyper-Threading" is set to Auto; "Turbo Mode" is enabled; "KTI Prefetch" is enabled; "NUMA" is enabled; "Energy Efficient Turbo" is disabled; "Page Policy" is set to Adaptive; "Hardware P-States" is disabled; "Static Turbo Mode" is disabled; "Patrol Scrubbing" is enabled; "Enhanced Halt" is enabled. The "State (C1E)" function option is set to off; the "VMX (Virtual Machine Extensions)" function option is set to off; the "SpeedStep" function option is set to on; the "Enable MWAIT" function option is set to on; the "ADDDC Sparing" function option is set to on; the "Partial Cache Line Sparing" function option is set to on; and the "DDRPPR Type" option is set to Soft PPR.The High RAS – Performance Priority mode linkage options can be set as follows: "Hardware Prefetcher" function set to Auto; "Adjacent Cache Prefetch" function set to Auto; "DCU Streamer Prefetcher" function set to Auto; "DCU IP Prefetcher" function set to Auto; "Hyper-Threading" function set to Auto; "Turbo Mode" function set to Auto; "KTI Prefetch" function set to Auto; "NUMA" function set to Auto; "Energy Efficient Turbo" function set to Auto; "Page Policy" function set to Adaptive; "Hardware P-States" function set to Auto; "Static Turbo Mode" function set to Auto; "PatrolScrubbing" function set to Enable; "Enhanced Halt State (C1E)" function set to Auto; "VMX" function set to Auto; "SpeedStep" function set to Auto; "Enable" function set to Enable. The "MWAIT" function option is set to Auto; the "ADDDC Sparing" function option is set to Auto; the "Partial Cache Line Sparing" function option is set to Auto; and the "DDR PPR Type" option is set to Soft PPR.

[0076] In another computing platform, the linkage options for the two sub-modes can be different from those for the two sub-modes in the aforementioned computing platform. The High RAS–RAS Priority mode linkage options can be set as follows: "SMT (Simultaneous Multi-threading)" is enabled; "L1StreamHwPrefetcher" is enabled; "L2StreamHwPrefetcher" is enabled; "CorePerformance Boost" is enabled; "Global C-stateControl" is disabled; "Determinism Control" is set to Manual; "Determinism Enable" is set to Power; "TDP Control (Thermal Design Power Control)" is set to Auto; "L3 Cache As NUMA Domain" is disabled; "Data Poisoning" is enabled; and "DRAM Error check and..." The following functions are enabled: "Scrub (DRAM Error Check and Erase)"; "DRAM Patrol Scrubber"; "SMI (System Management Interrupt) Storm Suppression"; "DRAM Boot Time Post Package Repair"; "DRAM Runtime Post Package Repair"; "On-chip ECC / Parity"; and "DRAM UECC Retry".The "DRAM Write Data CRC with Replay" function option is set to enabled; the "Automatic Boot-time Core Disable" function option is set to enabled; and the "DRAM Memory Tester" function option is set to enabled. The High RAS – Performance Priority mode linkage options can be set as follows: "SMT" function set to Auto; "L1StreamHwPrefetcher" function set to Auto; "L2StreamHwPrefetcher" function set to Auto; "Core Performance Boost" function set to Auto; "Global C-state Control" function set to Auto; "Determinism Control" function set to Default Determinism; "Determinism Enable" function set to power; "TDP Control" function set to Auto; "L3 Cache As NUMA Domain" function set to Auto; "Data Poisoning" function set to Auto; "DRAM Error check and Scrub" function set to Auto; "DRAM Patrol Scrubber" function set to Auto; "SMI Storm Suppression" function set to Auto; "DRAM Boot Time Post Package Repair" function set to Auto; "DRAM Runtime Post Package Repair" function set to Auto; "On-chip" function set to Auto; "On-chip" function set to Auto. The following functions are set to Auto: "ECC / Parity", "DRAM UECC Retry", "DRAM Write Data CRC with Replay", "Automatic Boot-time Core Disable", and "DRAM Memory Tester".

[0077] This embodiment subdivides the specified energy efficiency mode into a performance-priority mode and a reliability-priority mode, which can adapt to different scenario requirements and improve the flexibility and reliability of RAS function operation status control. Displaying the specified mode tab and associated sub-mode options on the scenario configuration interface can improve the convenience of sub-mode configuration.

[0078] In one exemplary embodiment, the method further includes: displaying a mode configuration interface in response to a detected second triggering operation, wherein the mode configuration interface is used to configure the operating state of a RAS function among a plurality of RAS functions for a specified sub-mode of a specified energy efficiency mode, the mode configuration interface including a plurality of function options, the function options among the plurality of function options corresponding to the RAS functions among the plurality of RAS functions; adjusting the option value corresponding to at least one function option displayed on the mode configuration interface in response to an option value setting operation performed on at least one function option among the plurality of function options; and generating a second configuration save instruction in response to a configuration save operation performed on the mode configuration interface, so as to configure the operating state of the RAS function among the plurality of RAS functions for the specified sub-mode.

[0079] In this embodiment, the operating status of linked functions in a specified sub-mode of a specified energy efficiency mode can be configured through the mode configuration interface. The linked functions that can be configured through the mode configuration interface can include RAS functions from multiple RAS functions, as well as other functions, such as performance energy consumption functions (energy efficiency functions). The mode configuration interface can be the aforementioned BIOS settings interface or BMC interface, or any other interface capable of configuring the operating status of linked functions for a specified sub-mode. This embodiment does not limit the type of linked function or the type of mode configuration interface.

[0080] The mode configuration interface can be displayed via a second trigger operation. This second trigger operation can be one operation or a combination of multiple operations, including but not limited to mouse operations, keyboard operations, and touch operations. In response to the detected second trigger operation, the mode configuration interface can be displayed on the electronic device. This interface is used to configure the operating status of linked functions for a specified sub-mode, such as the operating status of the RAS function among multiple RAS functions. The mode configuration interface includes multiple function options, each corresponding to a RAS function within the multiple RAS functions. Furthermore, the mode configuration interface may also include function options corresponding to other linked functions besides the multiple RAS functions.

[0081] Users can perform option value setting operations on at least one of multiple function options to adjust the operating status of the corresponding RAS function. For electronic devices, in response to the detected option value setting operation, the option value corresponding to at least one function option displayed on the mode configuration interface is adjusted. The option value setting operation can be a single operation or a combination of multiple operations, which may include, but is not limited to, mouse operations, keyboard operations, touch operations, etc.

[0082] Here, the specified sub-mode can be either a performance / energy consumption priority mode or a reliability priority mode. Under this sub-mode, the adjustable linkage options can be all or some. The function options displayed on the mode configuration interface can include all linkage options or only those with adjustable values. Furthermore, recommended values ​​or value ranges can be set for some linkage options to facilitate user configuration.

[0083] Users can trigger the saving of a specified sub-mode configuration by performing a configuration save operation on the mode configuration interface. For electronic devices, in response to the configuration save operation performed on the mode configuration interface, a second configuration save instruction is generated to configure the operating state of the RAS function among multiple RAS functions for the specified sub-mode. The configuration save operation can be a single operation or a combination of multiple operations, which may include, but is not limited to, mouse operations, keyboard operations, touch operations, etc. The second configuration save instruction can be a similar configuration save instruction to the first configuration save instruction, or it can be a different configuration save instruction.

[0084] It should be noted that the different operations in this embodiment can be similar operations or different operations. Each operation can be adjusted as needed, as long as it can accurately trigger the required operation. This embodiment does not limit the implementation method of various operations.

[0085] In this embodiment, the option values ​​of the linkage options are configured for the sub-mode of a specified energy efficiency mode through the mode configuration interface, thereby adjusting the running status of the corresponding linkage function. This can improve the convenience of sub-mode configuration and the flexibility of sub-mode operation.

[0086] In one exemplary embodiment, the specified energy efficiency mode includes the following sub-mode: a performance-energy-priority mode, in which at least some RAS functions change with changes in the hardware health status of the electronic device. The performance-energy-priority mode and hardware health status are similar to those described in the foregoing embodiments and will not be repeated here.

[0087] In this embodiment, in response to the activation of a specified energy efficiency scenario, controlling the electronic device to operate with at least some RAS functions enabled includes: when the sub-mode of the specified energy efficiency mode is the performance-energy consumption priority mode, in response to the activation of the performance-energy consumption priority mode, initializing the operating state of multiple RAS functions so that the electronic device operates with at least some RAS functions enabled.

[0088] If the specified energy efficiency mode sub-mode is performance-priority mode, in response to the performance-priority mode taking effect, the running status of multiple RAS functions can be initialized. Initialization of the running status of multiple RAS functions can be achieved by restarting the system. After initialization, at least some RAS functions will be enabled.

[0089] Optionally, if the specified energy efficiency mode includes other sub-modes (e.g., reliability priority mode, i.e., RAS priority mode), and if the sub-mode of the specified energy efficiency mode is another sub-mode, in response to the other sub-mode taking effect, the operating state of multiple RAS functions can be initialized in the same or similar manner, and at least some of the RAS functions will be enabled after initialization.

[0090] Through this embodiment, the activated RAS function is dynamically adjusted according to changes in the hardware health status of the electronic device, which can improve the device's performance and energy consumption while ensuring the device's operational reliability.

[0091] In an exemplary embodiment, after controlling the electronic device to operate with at least some RAS functions enabled in response to a specified energy efficiency scenario taking effect, the method further includes: continuously monitoring the hardware health status of the electronic device, and dynamically adjusting the operating status of multiple RAS functions based on the monitored hardware health status.

[0092] In this embodiment, after the specified energy efficiency scenario takes effect, the hardware health status of the electronic device can be continuously monitored to ensure the reliability of the RAS function's operational status control. The operational status of the electronic device can characterize its failure rate, and the monitored hardware health status can include the health status of the device's hardware. The device hardware can include, but is not limited to, at least one of the following: CPU, memory (memory module), and PCIe device.

[0093] Here, the performance-energy-priority mode effectively balances the reliability and performance-energy consumption of electronic devices by dynamically adjusting RAS function options and performance-energy-consumption strategies based on the failure rate changes of hardware such as CPU, memory, and PCIe devices. This adjustment process can be executed by the management controller. During the operation of electronic devices (e.g., servers), the dynamic policy engine in the management controller (e.g., BMC) continuously monitors the hardware health status of the system, including, for example, the number and types of memory errors, memory error frequency, storage device self-monitoring, analysis and reporting technology (SMART) status information, comprehensively assesses hardware health, and dynamically adjusts RAS and energy efficiency options accordingly.

[0094] Based on the monitored hardware health status, the operational status of multiple RAS functions can be dynamically adjusted. This adjustment can be achieved by updating the option values ​​of RAS options and restarting the operating system. Here, the updated RAS option values ​​can be the values ​​of all RAS options, or only the values ​​of the RAS options whose values ​​have changed. To avoid affecting the continuity of service execution on electronic devices due to excessively frequent adjustments to the operational status of RAS functions, the operational status of multiple RAS functions can be adjusted only when the hardware health status meets the set adjustment conditions (the set adjustment conditions are associated with the hardware health status).

[0095] This embodiment improves the matching degree between the operating status of multiple RAS functions and the hardware health status of the electronic device by continuously monitoring the hardware health status and dynamically adjusting the operating status of multiple RAS functions based on the monitored hardware health status, thereby improving the timeliness of RAS function operation status adjustment.

[0096] In one exemplary embodiment, the hardware health status of an electronic device can be monitored through a combination of out-of-band and in-band monitoring. Correspondingly, the hardware health status of the electronic device is obtained by parsing the collected out-of-band and in-band monitoring information. Optionally, the electronic device may include a management controller (e.g., a BMC) for out-of-band monitoring, which can collect at least one of the following: external status information during the operation of the electronic device, and fault information in the event of an electronic device failure. The electronic device may run a basic input / output system, i.e., a BIOS, which is used for in-band monitoring and can collect at least one of the following: error detection information during the startup phase of the electronic device, and error detection information during the operation of the electronic device. The aforementioned error detection information may include error detection reports.

[0097] Optionally, in this embodiment, continuously monitoring the hardware health status of the electronic device includes: continuously collecting external status information during the operation of the electronic device and fault information in the event of a system crash through the management controller to obtain out-of-band monitoring information, and continuously collecting error detection information during the startup phase and operation of the electronic device through the basic input / output system to obtain in-band monitoring information; and parsing the out-of-band monitoring information and the in-band monitoring information to obtain the hardware health status of the electronic device.

[0098] Hardware health can be monitored using both out-of-band monitoring by the management controller and in-band monitoring by the BIOS. The monitored hardware can include, but is not limited to, all or some of the CPU, memory, and PCIe devices. Out-of-band monitoring can collect external status information during electronic device operation, such as all or some of key parameters like temperature, voltage, and fan speed, as well as detailed fault information when the electronic device crashes, thus obtaining out-of-band monitoring information. In-band monitoring by the BIOS is responsible for error detection and reporting during the startup and operation phases of the electronic device, including but not limited to at least one of the following: correctable errors and uncorrectable errors.

[0099] Here, BIOS in-band monitoring refers to a monitoring method in which the BIOS directly monitors and manages hardware resources during the computer system startup or operation. The BIOS is one of the first programs loaded when the system starts up, responsible for initializing hardware devices, performing a power-on self-test (POST), and preparing for the operating system to load.

[0100] For example, the dynamic policy engine monitors hardware health using both BMC out-of-band monitoring and BIOS in-band monitoring. BMC out-of-band monitoring collects external status information during server operation and detailed fault information when the server crashes. BIOS in-band monitoring is responsible for error detection and reporting during server startup and operation, including both correctable and uncorrectable errors.

[0101] In computer systems, correctable errors in hardware devices (such as CPU, memory, PCIe devices, etc.) have corresponding correctable error thresholds. When the number of correctable errors reaches the set threshold, an interrupt is generated, notifying the BIOS to process it. Figure 5As shown. However, this processing mechanism suffers from an accumulation problem in the number of correctable errors. That is, when the number of correctable errors reaches a set threshold and triggers an interrupt, it is impossible to determine whether the interrupt is triggered by a sudden surge in the number of correctable errors in a short period of time or by the accumulation of correctable errors over a long period of time, which can interfere with the assessment of hardware health status. Therefore, when evaluating hardware health status based on correctable errors, the frequency of correctable error occurrence can be considered.

[0102] This embodiment uses both out-of-band monitoring by the management controller and in-band monitoring by the BIOS to monitor hardware health status, which improves the comprehensiveness of hardware health status monitoring and thus enhances the accuracy of device control.

[0103] In one exemplary embodiment, the hardware health status may include the health status of at least one piece of device hardware of an electronic device, which may include at least one of the following: a processor (e.g., a CPU), memory, and a PCIe device. For each piece of device hardware, its health status can be represented by a health score of the corresponding device hardware health degree; the higher the health score of the hardware health degree, the better the corresponding health status.

[0104] Optionally, in this embodiment, continuously monitoring the hardware health status of the electronic device includes: continuously monitoring the hardware of at least one device to obtain hardware operation data of the hardware of at least one device; and continuously updating the health score of the hardware health of the hardware of at least one device based on the hardware operation data of the hardware of at least one device.

[0105] For a given type of device hardware, its hardware operation data can be continuously acquired. Using the aforementioned combination of out-of-band and in-band monitoring, the hardware operation data of the same device hardware acquired from both methods can be combined to obtain the hardware operation data for that specific device hardware. Based on the hardware operation data of at least one type of device hardware, the health score of that device hardware is continuously updated.

[0106] Here, for a specific type of device hardware, its hardware operation data can characterize its hardware health. For example, the higher the number of anomalies parsed from the hardware operation data, the worse the hardware health, and the lower the corresponding health score. Therefore, the health score of the corresponding device hardware can be updated based on the acquired hardware operation data.

[0107] For multiple RAS functions, their operational status can be dynamically adjusted based on the health scores of the hardware in at least one device. For example, the health score of each device can affect the operational status of multiple RAS functions as a whole. Alternatively, the health score of one device can affect the operational status of some of the multiple RAS functions. The RAS functions affected by the health scores of different devices can be partially the same or different. Or, the operational status of multiple RAS functions can be dynamically adjusted based on a merged health score obtained by fusing the health scores of the hardware in at least one device.

[0108] For example, a dynamic policy engine can comprehensively assess the health of the CPU, memory, and PCIe devices based on collected information, and then dynamically allocate the corresponding RAS function options according to the health status of the CPU, memory, and PCIe devices. Here, multiple RAS functions can be divided into CPU RAS functions, memory RAS functions, and PCIe device RAS functions, with the corresponding RAS function options dynamically allocated according to the health status of the CPU, memory, and PCIe devices respectively.

[0109] The adjusted option configuration parameters can be persistently saved in the file system specified on the BMC. When the server restarts, the BMC resets the relevant tabs in the BIOS based on the saved option configuration information, restoring the system to its optimal operating state.

[0110] In this embodiment, the health score based on the hardware health of the device hardware represents the health status of the device hardware, which can improve the convenience of representing the health status of the device hardware; based on the obtained hardware operation data of the device hardware, the corresponding hardware health score is continuously updated, which can improve the timeliness and accuracy of the hardware health score update.

[0111] In one exemplary embodiment, hardware health status can include the health status of the electronic device's memory modules, i.e., memory health status. Memory health status can be represented by a memory health score (memory health score). For example, a memory health score can be used as an indicator to quantify memory health status, with a score range of 0 to 100. 100 is the highest score, indicating that the current memory module is in a completely healthy state with no errors detected, while 0 is the lowest score, indicating that the current memory has seriously failed. A higher score indicates a healthier memory module, while a lower score indicates a higher probability of memory module failure, requiring the corresponding RAS (Reliability, Availability, and Security) function option to be enabled.

[0112] To reasonably assess memory health, a multi-dimensional deduction rule can be defined, grading points based on different error types, frequencies, and impact levels. Correspondingly, the hardware health status of electronic devices is continuously monitored, including: when a specified memory error is detected, determining the corresponding deduction value for the specified memory error according to the correspondence between error type and error score; updating the memory health score according to the deduction value to obtain the updated memory health score.

[0113] In this embodiment, a correspondence between error types and error scores of memory modules can be defined, and this correspondence can be recorded through a data table or other means. For example, the correspondence between error types, error scores (deduction values), and trigger condition descriptions can be shown in Table 1.

[0114] Table 1

[0115]

[0116] Among them, UCNA error is a non-high-level uncorrectable error, SRAO error is a high-level uncorrectable error related to row address strobe signals, and SRAR error is a high-level uncorrectable error observed on a single memory rank.

[0117] The type of memory error can be determined by the UC, PCC, S, and AR bits of the MCI_STATUS register. When UC=0, it is a correctable error; when UC=1, it is an uncorrectable error. When UC=1, PCC=0, S=0, and AR=0, it is a UCNA error; when UC=1, PCC=0, S=1, and AR=0, it is a SRAO error; when UC=1, PCC=0, S=1, and AR=1, it is a SRAR error.

[0118] If a specified memory error is detected in an electronic device, the correspondence between the error type and the error score can be looked up according to the specified error type to determine the corresponding deductible error score. The memory health score is then updated according to the deductible error score. For example, the deductible error score is subtracted from the current memory health score, and the resulting health score is determined as the updated memory health score.

[0119] It should be noted that hardware health status can also include the health status of other hardware devices (such as processors, PCIe devices, etc.). The evaluation method for the health status of other hardware devices can be similar to that for the health status of memory modules, which has already been explained and will not be repeated here.

[0120] This embodiment improves the rationality of hardware health status monitoring by monitoring memory health status as part of the hardware health status of electronic devices; and enhances the convenience of memory health status monitoring by defining the correspondence between error types and error scores and updating the memory health score based on detected memory errors.

[0121] In one exemplary embodiment, a time decay factor α (1 > α > 0) can be introduced into the deduction rule to weight the impact of historical errors, where recent errors have a greater impact on the current health score than earlier errors. Optionally, to balance the time decay factor with computational complexity, an Exponentially Weighted Moving Average (EWMA) method can be used to optimize the fault deduction rule. This method not only effectively addresses the time decay issue but also significantly reduces computational complexity.

[0122] Correspondingly, in this embodiment, the memory health score is updated according to the error score to be deducted, and the updated memory health score is obtained. This includes updating the memory health score to the product of the first coefficient and the error score to be deducted plus the product of the second coefficient and the memory health score. Here, the first coefficient is a set time decay factor, and the second coefficient is the difference between 1 and the time decay factor, where 0 < time decay factor < 1.

[0123] The process of optimizing the memory fault scoring rules using the EWMA method can include: First, setting a time decay factor α, satisfying 1 > α > 0, which determines the degree of influence of the current error on the health score. The closer α is to 1, the greater the influence of the current error; the closer α is to 0, the more persistent the influence of historical errors. Second, for each error event, updating the health score according to formula (1):

[0124] (1)

[0125] in, This is the updated health score. This is the current health score. This indicates the historical deduction of points. This is the deduction value corresponding to the current error, and it is a positive value. The deductions are made item by item, not cumulatively. For example, suppose a high-frequency correctable error occurs, deducting one point, resulting in the current health score. (i.e., 1 point) and α are updated to obtain the updated health score.

[0126] In this embodiment, by introducing a time decay factor to weight the impact of historical errors and using an exponential moving average method to optimize the fault deduction rules, the time decay problem can be effectively addressed, and the computational complexity can be significantly reduced.

[0127] In one exemplary embodiment, hardware health status is represented by a health score of the electronic device's hardware health. The calculation method for the hardware health score is similar to that in the previous embodiments and has been explained, so it will not be repeated here. RAS functions can be divided into multiple levels (multiple RAS functions are divided into multiple functional levels), each level corresponding to different performance impacts and reliability improvements. The dynamic policy engine can adjust RAS-related functional options based on the memory health score results to restore server reliability. To adapt to multiple functional levels, the range of hardware health scores can be divided into multiple score intervals; one functional level corresponds to one score interval among the multiple score intervals.

[0128] Correspondingly, in this embodiment, based on the monitored hardware health status, the operating status of multiple RAS functions is dynamically adjusted, including: when the score range of the hardware health score decreases from the first score range to the second score range, the operating status of the RAS function whose function level corresponds to the second score range is adjusted to be enabled.

[0129] If the hardware health score drops from the first score range to the second score range (the functional level corresponding to the first score range is lower than the functional level corresponding to the second score range), it indicates that the electronic device's hardware health is low, and more RAS (Reliability and Serviceability) functions can be enabled to ensure device reliability. Therefore, the RAS functions whose functional level corresponds to the second score range can be enabled. RAS functions that are already enabled can remain enabled.

[0130] For example, for memory health, the RAS function can be divided into 3 levels, and the dynamic adjustment strategy of the RAS function options is shown in Table 2.

[0131] Table 2

[0132]

[0133] Among them, MHS in the trigger condition is the health score of the aforementioned memory module, and the linked performance compensation is a strategy used to compensate for device performance while adjusting the memory RAS function.

[0134] In this embodiment, the RAS function is divided into multiple levels according to its functions. Each level corresponds to a score range of the hardware health score. The operating status of the RAS function is dynamically adjusted based on the changes in the score range to which the health score belongs, which can improve the rationality and convenience of adjusting the operating status of the RAS function.

[0135] In one exemplary embodiment, the method further includes: dynamically adjusting the operating status of the energy efficiency function in the performance-energy consumption priority mode based on the health score of the hardware health.

[0136] In this embodiment, in addition to adjusting the operating status of the RAS function, the operating status of the energy efficiency function in the performance-energy-priority mode can also be dynamically adjusted based on the hardware health score. The hardware health score is positively correlated with the total energy consumption of the energy efficiency functions enabled in the performance-energy-priority mode; the higher the hardware health score, the greater the total energy consumption of the enabled energy efficiency functions, and vice versa.

[0137] For example, referring to Table 2, at level L0, the memory RAS function has a low impact on performance, and more energy efficiency options can be enabled to improve the device's energy efficiency. At level L0, the memory RAS function has a moderate impact on performance, and an energy efficiency mode strategy is adopted, which reduces the total energy consumption of the enabled energy efficiency functions, and so on.

[0138] This embodiment uses the health score of hardware health to dynamically adjust the operating status of energy efficiency functions in the performance-energy consumption priority mode, which can adapt to changes in the operating status of RAS functions and improve the reliability of equipment operation.

[0139] In one exemplary embodiment, the hardware health status includes the health status of at least two types of device hardware of the electronic device. One of the at least two types of device hardware corresponds to at least some of the multiple RAS functions. The types of device hardware and their corresponding RAS functions are similar to those in the foregoing embodiments and will not be repeated here.

[0140] Correspondingly, in this embodiment, the operating status of multiple RAS functions is dynamically adjusted based on the monitored hardware health status, including: dynamically adjusting the operating status of the RAS function corresponding to the device hardware in at least two types of device hardware based on the monitored health status of the device hardware in at least two types of device hardware.

[0141] Based on the monitored health status of a device hardware, it can be determined whether the operating status of the corresponding RAS function needs to be adjusted. For example, according to the score range of the hardware health score, it can be determined whether the operating status of the corresponding RAS function needs to be adjusted. If so, the operating status of the corresponding RAS function is adjusted. The RAS functions adjusted based on the health status of different device hardware can be different, or at least partially the same; this embodiment does not limit this.

[0142] This embodiment allows for the adjustment of the corresponding RAS function's operating status based on the health status of different types of device hardware. This improves the rationality of RAS function operating status adjustments and thus enhances the reliability of device operation.

[0143] In one exemplary embodiment, one of the multiple RAS functions corresponds to one of the multiple function options. The correspondence between RAS functions and function options is similar to that in the previous embodiments and will not be repeated here.

[0144] Correspondingly, based on the monitored hardware health status, the operating status of multiple RAS functions is dynamically adjusted, including: based on the monitored hardware health status, determining the RAS function to be adjusted and the operating status to be adjusted for the RAS function to be adjusted, and obtaining the second option configuration information to be updated; adjusting the operating status of the RAS function to be adjusted according to the second option configuration information.

[0145] In this embodiment, based on the monitored hardware health status, the RAS functions to be adjusted and the operating states to be adjusted for each RAS function can be determined. Based on the option identifier of the function option corresponding to the RAS function to be adjusted and the option value corresponding to the operating state to be adjusted for, second option configuration information can be generated. The generated second option configuration information may include the option identifier of the function option corresponding to the RAS function to be adjusted and the option value corresponding to the operating state to be adjusted for.

[0146] According to the configuration information of the second option, the running status of the RAS function to be adjusted can be adjusted. The method of adjusting the running status of the RAS function to be adjusted is similar to the method of configuring the running status of multiple RAS functions according to the configuration information of the second option, which has been explained before and will not be repeated here.

[0147] In this embodiment, option configuration information is generated based on the option identifier of the function option corresponding to the RAS function to be adjusted and the option value corresponding to the running state to which the RAS function to be adjusted is to be adjusted. The running state of the corresponding RAS function is adjusted based on the generated option configuration information, which can improve the convenience of adjusting the running state of the RAS function.

[0148] In one exemplary embodiment, the electronic device may include a management controller, and a basic input / output system may be running on the electronic device. Through the interaction between the management controller and the basic input / output system, the operating state of the RAS function can be adjusted. In this embodiment, a configuration structure can be used to record the option identifiers of the function options corresponding to the RAS functions among multiple RAS functions, as well as the option values ​​corresponding to the operating states of the multiple RAS functions, and the management controller can modify them based on changes in the operating states of the RAS functions.

[0149] In this embodiment, adjusting the operating state of the RAS function to be adjusted according to the second option configuration information includes: updating the configuration structure according to the second option configuration information through the management controller to obtain the updated configuration structure, and setting the synchronization flag to a specified value; during the startup phase of the electronic device, in response to detecting that the synchronization flag is set to the specified value, obtaining the updated configuration structure from the management controller through the basic input / output system, extracting the option configuration information to be updated from the updated configuration structure, writing the option configuration information to be updated to the configuration area of ​​the non-volatile random access memory, and controlling the electronic device to restart, so as to adjust the operating state of the RAS function to be adjusted by loading the option configuration information to be updated.

[0150] The second option configuration information can record either the RAS function whose operating status has changed and its new operating status, or the operating status of all RAS functions out of multiple RAS functions. The management controller can update the configuration structure according to the second option configuration information to obtain an updated configuration structure. The updated configuration structure can be placed in a designated storage area, which is used for data synchronization between the management controller and the basic input / output system. The management controller can generate a synchronization flag and set the synchronization flag to a specified value. In addition, to improve the reliability of data synchronization, a checksum can be generated, which can be generated using methods such as cyclic redundancy check (CRC) and parity check.

[0151] For example, all changes to RAS feature options modified by the dynamic policy engine are recorded and saved in the file system specified by the BMC. Based on the changed RAS feature options, the BMC modifies the original JSON (JavaScript Object Notation, a lightweight data exchange format) structure (an example of a configuration structure) generated according to the option names and corresponding option values ​​of the current BIOS configuration options, generates the target JSON structure and stores it in a dedicated storage area (i.e., the specified storage area), and generates a checksum and synchronization flag.

[0152] During the startup phase of an electronic device, in response to the detection that the synchronization flag has been set to a specified value, the Basic Input / Output System (PIS) can obtain an updated configuration structure from the management controller, for example, by reading the updated configuration structure from a specified storage area via a read command or other commands. If verification is required, the management controller can first verify the data integrity using a checksum. If the verification passes, the updated configuration structure can be sent to the PIS. If the verification fails, an error message can be displayed, or backup configuration information can be enabled and verified.

[0153] After obtaining the updated configuration structure, the Basic Input / Output System (PIS) can extract the configuration information of the options to be updated from the updated configuration structure, write the configuration information of the options to be updated to the configuration area of ​​Nonvolatile Random Access Memory (NVRAM), and control the electronic device to restart. The synchronization flag can be cleared after the configuration information of the options to be updated is written to the configuration area of ​​NVRAM. After the electronic device restarts, the configuration information of the options to be updated can be loaded, thereby adjusting the operating state of the RAS function to be adjusted. The PIS can synchronize the latest configuration option information back to the management controller. If the restart process fails, the management controller can trigger a configuration rollback mechanism to ensure that the system can be restored to its previous state.

[0154] For example, during server startup, after detecting the synchronization flag, the BIOS retrieves the target JSON structure from the BMC via a command. At this point, the BMC first verifies the data integrity using a checksum. If the verification fails, it activates backup configuration information and verifies it. If the verification passes, the BIOS can read the target JSON structure, write the configuration options information to the Setup area of ​​NVRAM, and clear the synchronization flag. After completing the write operation to NVRAM, the system can automatically reboot to load the new configuration, and the BIOS will synchronize the latest configuration options information back to the BMC. If the reboot process fails, the BMC will trigger a configuration rollback mechanism to ensure the system can be restored to its previous state.

[0155] This embodiment demonstrates how the interaction between the management controller and the basic input / output system enables the adjustment of the operating status of the RAS function, ensuring the orderly and reliable operation of the equipment while guaranteeing the success rate of the RAS function's operating status adjustment.

[0156] The control method for the operation of the electronic device in this embodiment will be explained below with reference to an optional example. In this optional example, the electronic device is a server, the specified energy efficiency mode is High RAS mode, the specified energy efficiency mode includes two sub-modes, namely High RAS-RAS Priority mode and High RAS-Performance Priority mode, the management controller is BMC, and the configuration structure is a JSON structure.

[0157] Combination Figure 4 and Figure 6 The flow of the control method for operating the electronic device in this optional example may include the following steps S602 to S610.

[0158] In step S602, the user specifies the initial state of the server by configuring the function options associated with the High RAS-RAS Priority mode or High RAS-Performance Priority mode on the BMC.

[0159] Step S604: Select High RAS-RAS Priority mode or High RAS-Performance Priority mode, and the server initializes the RAS function.

[0160] Step S606: BMC's dynamic policy engine monitors the server hardware health status and comprehensively evaluates the hardware health.

[0161] Step S608: Dynamically adjust the RAS and energy efficiency option configurations and persistently save them to the file system specified on the BMC.

[0162] In step S610, when the server restarts, the BMC resets the relevant BIOS tabs according to the saved option configuration, restoring the system to its optimal operating state.

[0163] This optional example allows for the assessment of the hardware health status of the CPU, memory, and PCIe devices, and the dynamic adjustment of the corresponding RAS function options for each device type. This enables a closed loop of real-time monitoring, policy calculation, and hardware execution, effectively balancing server reliability and performance energy consumption. It improves the server's performance, energy consumption, and reliability throughout its entire lifecycle, providing a more flexible and intelligent solution for server configuration in different application scenarios.

[0164] 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.

[0165] According to another aspect of the embodiments of this application, an electronic device is also provided, which can be used to implement the control method for operating the electronic device provided in the above embodiments, and will not be repeated hereafter. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated. Optionally, the above electronic device can be a server.

[0166] Figure 7 This is a structural block diagram of an optional electronic device according to an embodiment of this application, such as... Figure 7 As shown, the electronic device includes: a processor 702 and a management controller 704. The processor 702 is used to execute a basic input / output system. The management controller 704 and at least one of the basic input / output systems are used to configure a specified energy efficiency scenario for the electronic device among multiple energy efficiency scenarios. The specified energy efficiency scenario is associated with a specified energy efficiency mode, in which at least some of the multiple energy efficiency functions (RAS) are enabled. In response to the specified energy efficiency scenario taking effect, the electronic device is controlled to operate with at least some RAS functions enabled.

[0167] It should be noted that at least one of the management controller 704 and the basic input / output system in this embodiment can be used to perform the above steps S202 and S204.

[0168] The embodiments provided in this application configure specified energy efficiency scenarios for electronic devices in multiple energy efficiency scenarios. The specified energy efficiency scenario is associated with a specified energy efficiency mode. Under the specified energy efficiency mode, at least some of the RAS functions among multiple RAS functions are enabled. In response to the specified energy efficiency scenario taking effect, the electronic device is controlled to operate with at least some RAS functions enabled. This solves the technical problem of low device lifespan caused by poor device operation reliability in the control methods of device operation in related technologies, improves the reliability of device operation, and thus improves the lifespan of the device.

[0169] In one exemplary embodiment, the electronic device further includes a display component, such as a display screen and components associated with the screen display. The display component is configured to display a scene configuration interface in response to a detected first trigger operation, wherein the scene configuration interface is used to configure an energy efficiency scene for the electronic device; and to display a specified mode tab on the scene configuration interface in response to a selection operation performed on a specified scene tab in the scene configuration interface, wherein the specified scene tab is a scene tab corresponding to a specified energy efficiency scene, and the specified mode tab is a mode tab associated with the specified scene tab and corresponding to a specified energy efficiency mode; at least one of the management controller 704 and the basic input / output system is further configured to generate a first configuration save instruction in response to a configuration save operation performed on the scene configuration interface, to configure the specified energy efficiency scene for the electronic device.

[0170] In one exemplary embodiment, the specified energy efficiency mode includes two sub-modes: a performance-priority mode and a reliability-priority mode. In the performance-priority mode, at least some RAS functions change with variations in the hardware health status of the electronic device; in the reliability-priority mode, at least some RAS functions are independent of the hardware health status of the electronic device. The display component is further configured to, in response to a selection operation performed on a specified scene tab, display the specified mode tab and its associated sub-mode options on the scene configuration interface. The sub-mode options include a first option value corresponding to the performance-priority mode and a second option value corresponding to the reliability-priority mode.

[0171] In one exemplary embodiment, the display component is further configured to display a mode configuration interface in response to a detected second trigger operation, wherein the mode configuration interface is configured to configure the operating state of a RAS function among a plurality of RAS functions for a specified sub-mode of a specified energy efficiency mode, the mode configuration interface including a plurality of function options, the function options among the plurality of function options corresponding to the RAS functions among the plurality of RAS functions; in response to an option value setting operation performed on at least one of the plurality of function options, the option value corresponding to at least one function option displayed on the mode configuration interface is adjusted; at least one of the management controller 704 and the basic input / output system is further configured to generate a second configuration save instruction in response to a configuration save operation performed on the mode configuration interface, so as to configure the operating state of the RAS function among the plurality of RAS functions for the specified sub-mode.

[0172] In one exemplary embodiment, at least one of the management controller 704 and the basic input / output system is further configured to, after generating a first configuration save instruction, determine, in response to the first configuration save instruction, the option values ​​configured for a set of linkage options for a specified energy efficiency mode, and obtain first option configuration information to be updated, wherein the set of linkage options includes function options corresponding to RAS functions among multiple RAS functions; and update the operating status of multiple RAS functions according to the first option configuration information so that at least some RAS functions are enabled.

[0173] In one exemplary embodiment, under a specified energy efficiency mode, the operating states of multiple RAS functions are statically configured such that at least some of the RAS functions are enabled under different hardware health states of the electronic device. At least one of the management controller 704 and the basic input / output system is further configured to, in response to the activation of a specified energy efficiency scenario, control the electronic device to operate with at least some RAS functions enabled for the duration of the specified energy efficiency scenario.

[0174] In one exemplary embodiment, under a specified energy efficiency mode, the operating state of multiple RAS functions includes at least one of the following: the system error detection function is enabled; the memory error isolation and protection function is enabled; the page management and error handling function is adaptive; the adaptive dual-device data correction spare part function is enabled; the custom refresh function is enabled; the attempt to perform a fast cold start function is disabled; the patrol erase function is enabled; the partial cache line protection function is enabled; and the post-installation repair type function is repaired after soft packaging.

[0175] In one exemplary embodiment, the specified energy efficiency mode includes a sub-mode: a performance-priority mode, in which at least some RAS functions change with changes in the hardware health state of the electronic device. At least one of the management controller 704 and the basic input / output system is further configured to, in response to the performance-priority mode taking effect, initialize the operating states of multiple RAS functions when the sub-mode of the specified energy efficiency mode is the performance-priority mode, so that the electronic device operates with at least some RAS functions enabled, wherein the initialized operating state of at least some RAS functions is enabled.

[0176] In one exemplary embodiment, at least one of the management controller 704 and the basic input / output system is further configured to continuously monitor the hardware health status of the electronic device after controlling the electronic device to operate with at least some RAS functions enabled in response to a specified energy efficiency scenario taking effect, and dynamically adjust the operating status of multiple RAS functions based on the monitored hardware health status.

[0177] In one exemplary embodiment, the management controller 704 is further configured to continuously collect external status information during the operation of the electronic device and fault information in the event of a shutdown of the electronic device, to obtain out-of-band monitoring information; the basic input / output system is further configured to continuously collect error detection information during the startup phase and operation of the electronic device, to obtain in-band monitoring information; at least one of the management controller 704 and the basic input / output system is further configured to parse the out-of-band monitoring information and the in-band monitoring information to obtain the hardware health status of the electronic device.

[0178] In one exemplary embodiment, the hardware health status includes the health status of at least one piece of hardware in the electronic device; the health status of the hardware in the at least one piece of hardware is represented by a health score of the corresponding hardware health. At least one of the management controller 704 and the basic input / output system is further configured to continuously monitor the hardware in the at least one piece of hardware to obtain hardware operation data of the hardware in the at least one piece of hardware; and to continuously update the health score of the hardware health of the hardware in the at least one piece of hardware based on the hardware operation data of the hardware in the at least one piece of hardware. The operating status of multiple RAS functions is dynamically adjusted either separately based on the health scores of the hardware health of the hardware in the at least one piece of hardware, or dynamically adjusted based on a fused health score obtained by fusing the health scores of the hardware health of the hardware in the at least one piece of hardware.

[0179] In one exemplary embodiment, the hardware health status includes the memory health status of the memory modules of the electronic device, which is represented by a health score of the electronic device's memory health. At least one of the management controller 704 and the basic input / output system is further configured to, upon detecting a specified memory error in the electronic device, determine a deductible error score corresponding to the specified memory error according to the correspondence between error type and error score; and update the memory health score according to the deductible error score to obtain an updated memory health score.

[0180] In one exemplary embodiment, at least one of the management controller 704 and the basic input / output system is further configured to update the health score of memory health to the product of a first coefficient and the error score to be deducted plus the product of a second coefficient and the health score of memory health, wherein the first coefficient is a set time decay factor, the second coefficient is the difference between 1 and the time decay factor, and 0 < time decay factor < 1.

[0181] In one exemplary embodiment, the hardware health status is represented by a health score of the electronic device's hardware health, the health score range being divided into multiple score intervals, and multiple RAS functions being divided into multiple function levels; one function level corresponds to one score interval among the multiple score intervals. At least one of the management controller 704 and the basic input / output system is further configured to adjust the operating state of the RAS function whose function level corresponds to the second score interval to "on" when the score interval to which the hardware health score belongs decreases from a first score interval to a second score interval, wherein the function level corresponding to the first score interval is lower than the function level corresponding to the second score interval.

[0182] In one exemplary embodiment, at least one of the management controller 704 and the basic input / output system is further configured to dynamically adjust the operating state of the energy efficiency function in the performance-energy-priority mode based on the health score of the hardware health, wherein the health score of the hardware health is positively correlated with the total energy consumption of the energy efficiency function enabled in the performance-energy-priority mode.

[0183] In one exemplary embodiment, the hardware health status includes the health status of at least two types of device hardware in the electronic device, wherein one of the at least two types of device hardware corresponds to at least a portion of the multiple RAS functions. The management controller 704 and at least one of the basic input / output systems are further configured to dynamically adjust the operating state of the RAS functions corresponding to the at least two types of device hardware based on the monitored health status of the device hardware among the at least two types of device hardware.

[0184] In one exemplary embodiment, one of the multiple RAS functions corresponds to one of the multiple function options. At least one of the management controller 704 and the basic input / output system is further configured to, based on the monitored hardware health status, determine the RAS function to be adjusted among the multiple RAS functions and the operating state to which the RAS function to be adjusted is to be adjusted, and obtain second option configuration information to be updated, wherein the second option configuration information includes an option identifier of the function option corresponding to the RAS function to be adjusted, and an option value corresponding to the operating state to which the RAS function to be adjusted is to be adjusted; and adjust the operating state of the RAS function to be adjusted according to the second option configuration information.

[0185] In an exemplary embodiment, the management controller 704 is further configured to update the configuration structure according to the second option configuration information to obtain the updated configuration structure, and set the synchronization flag bit to a specified value. The configuration structure is used to record the option identifiers of the function options corresponding to the RAS functions among the multiple RAS functions, and the option values ​​corresponding to the operating states of the RAS functions among the multiple RAS functions. The basic input / output system is further configured to, during the startup phase of the electronic device, in response to detecting that the synchronization flag bit is set to a specified value, obtain the updated configuration structure from the management controller, extract the option configuration information to be updated from the updated configuration structure, write the option configuration information to be updated to the configuration area of ​​the non-volatile random access memory, and control the electronic device to restart, so as to adjust the operating state of the RAS function to be adjusted by loading the option configuration information to be updated.

[0186] It should be noted that, without contradiction, the manner in which the management controller, the basic input / output system, or the management controller and the basic input / output system work together to execute the above steps, as well as the interaction method between the management controller and the basic input / output system, can refer to the description in the foregoing embodiments; 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.

[0187] According to another aspect of the embodiments of this application, a server is also provided, which can be used to implement the control method for operating the electronic device provided in the above embodiments, and will not be repeated hereafter. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0188] In this embodiment, the server may include: a processor and a management controller, the processor being configured to execute a basic input / output system. At least one of the management controller and the basic input / output system is configured to configure a specified energy efficiency scenario for an electronic device across multiple energy efficiency scenarios, wherein the specified energy efficiency scenario is associated with a specified energy efficiency mode, and in the specified energy efficiency mode, at least some of the multiple energy efficiency features (RAS) are enabled; in response to the specified energy efficiency scenario taking effect, the electronic device is controlled to operate with at least some RAS functions enabled.

[0189] It should be noted that at least one of the management controller and the basic input / output system in this embodiment can be used to perform the above steps S202 and S204.

[0190] The embodiments provided in this application configure specified energy efficiency scenarios for electronic devices in multiple energy efficiency scenarios. The specified energy efficiency scenario is associated with a specified energy efficiency mode. Under the specified energy efficiency mode, at least some of the RAS functions among multiple RAS functions are enabled. In response to the specified energy efficiency scenario taking effect, the electronic device is controlled to operate with at least some RAS functions enabled. This solves the technical problem of low device lifespan caused by poor device operation reliability in the control methods of device operation in related technologies, improves the reliability of device operation, and thus improves the lifespan of the device.

[0191] Optionally, the structure of the server and the manner in which the control method for operating the electronic device provided in the above embodiments is the same as or similar to the structure of the aforementioned electronic device and the manner in which the control method for operating the electronic device provided in the above embodiments is implemented, and will not be repeated here.

[0192] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, which stores a computer program, wherein the computer program is configured to execute the steps in the control method embodiments of any of the above-described electronic devices when it is run.

[0193] 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 USB flash drives, read-only memory (ROM), RAM, portable hard drives, magnetic disks, or optical disks.

[0194] According to another aspect of the embodiments of this application, the 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 the control method embodiments for operating any of the above-described electronic devices.

[0195] Embodiments of this application also provide another computer program product, including a non-volatile computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in the control method embodiments of any of the above-described electronic devices.

[0196] 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 described herein, 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.

[0197] The above are merely preferred embodiments of this application and are 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 control method for the operation of an electronic device, characterized in that, include: In multiple energy efficiency scenarios, a specified energy efficiency scenario is configured for an electronic device. The energy efficiency scenario in the multiple energy efficiency scenarios is related to the performance and energy consumption of the electronic device. The specified energy efficiency scenario is associated with a specified energy efficiency mode. In the specified energy efficiency mode, at least some of the multiple RAS functions are enabled. The specified energy efficiency mode includes the following two sub-modes: performance and energy consumption priority mode and reliability priority mode. In the performance and energy consumption priority mode, the at least some RAS functions change with the hardware health status of the electronic device. In the reliability priority mode, the at least some RAS functions are independent of the hardware health status of the electronic device. In response to the specified energy efficiency scenario taking effect, the electronic device is controlled to operate when at least some of the RAS functions are enabled.

2. The method according to claim 1, characterized in that, The configuration of specified energy efficiency scenarios for electronic devices in multiple energy efficiency scenarios includes: In response to the detected first trigger operation, a scene configuration interface is displayed, wherein the scene configuration interface is used to configure an energy efficiency scene for the electronic device; In response to a selection operation performed on a specified scene tab in the scene configuration interface, a specified mode tab is displayed on the scene configuration interface, wherein the specified scene tab is a scene tab corresponding to the specified energy efficiency scene, and the specified mode tab is a mode tab associated with the specified scene tab and corresponding to the specified energy efficiency mode. In response to the configuration save operation performed on the scenario configuration interface, a first configuration save instruction is generated to configure the specified energy efficiency scenario for the electronic device.

3. The method according to claim 2, characterized in that, The step of displaying a specified mode tab on the scene configuration interface in response to a selection operation on a specified scene tab in the scene configuration interface includes: In response to a selection operation performed on the specified scenario tab, the specified mode tab and the sub-mode options associated with the specified mode tab are displayed on the scenario configuration interface, wherein the option values ​​of the sub-mode options include a first option value corresponding to the performance and energy consumption priority mode and a second option value corresponding to the reliability priority mode.

4. The method according to claim 3, characterized in that, The method further includes: In response to the detected second trigger operation, a mode configuration interface is displayed, wherein the mode configuration interface is used to configure the operating status of the RAS function among the plurality of RAS functions for a specified sub-mode of the specified energy efficiency mode, and the mode configuration interface includes a plurality of function options, wherein the function options among the plurality of function options correspond to the RAS functions among the plurality of RAS functions. In response to an option value setting operation performed on at least one of the plurality of function options, the option value corresponding to the at least one function option displayed on the mode configuration interface is adjusted; In response to the configuration save operation performed on the mode configuration interface, a second configuration save instruction is generated to configure the running state of the RAS function among the multiple RAS functions for the specified sub-mode.

5. The method according to claim 2, characterized in that, After generating the first configuration save instruction, the method further includes: In response to the first configuration save command, the option values ​​configured for a set of linkage options for the specified energy efficiency mode are determined, and the first option configuration information to be updated is obtained, wherein the set of linkage options includes the function options corresponding to the RAS functions among the multiple RAS functions; Update the running status of the plurality of RAS functions according to the configuration information of the first option, so that at least some of the RAS functions are enabled.

6. The method according to claim 1, characterized in that, In the specified energy efficiency mode, the operating status of the RAS functions among the plurality of RAS functions is statically configured, and at least some of the RAS functions are the same under different hardware health states of the electronic device. The response to the specified energy efficiency scenario, controlling the electronic device to operate when at least some of the RAS functions are enabled, includes: In response to the activation of the specified energy efficiency scenario, during the duration of the activation of the specified energy efficiency scenario, the electronic device is controlled to operate with at least some of the RAS functions enabled.

7. The method according to claim 6, characterized in that, Under the specified energy efficiency mode, the operating states of the plurality of RAS functions include at least one of the following: The system error detection function is enabled. The memory error isolation and protection function is enabled. The page management and error handling functions are running in an adaptive mode. The adaptive dual-device data correction spare parts function is enabled. The custom refresh function is enabled. The fast cold start function is disabled. The patrol and erasure function is enabled. The cache line protection feature is enabled in some cases. The post-installation repair function is currently in the "soft-packaged repair" state.

8. The method according to claim 1, characterized in that, The specified energy efficiency mode includes the following sub-mode: performance energy consumption priority mode, in which at least some of the RAS functions change with the hardware health status of the electronic device; The response to the specified energy efficiency scenario, controlling the electronic device to operate when at least some of the RAS functions are enabled, includes: When the sub-mode of the specified energy efficiency mode is the performance-energy-priority mode, in response to the performance-energy-priority mode taking effect, the operating state of the plurality of RAS functions is initialized so that the electronic device operates when at least some of the RAS functions are enabled, wherein the operating state of the at least some of the RAS functions after initialization is enabled.

9. The method according to claim 8, characterized in that, After the response to the specified energy efficiency scenario takes effect and the electronic device is controlled to operate with at least some of the RAS functions enabled, the method further includes: The hardware health status of the electronic device is continuously monitored, and the operating status of the multiple RAS functions is dynamically adjusted based on the monitored hardware health status.

10. The method according to claim 9, characterized in that, The electronic device includes a management controller and runs a basic input / output system. The continuous monitoring of the hardware health status of the electronic device includes: The management controller continuously collects external status information during the operation of the electronic device and fault information in the event of the electronic device crashing to obtain out-of-band monitoring information, and the basic input / output system continuously collects error detection information during the startup phase and operation of the electronic device to obtain in-band monitoring information. The out-of-band monitoring information and the in-band monitoring information are parsed to obtain the hardware health status of the electronic device.

11. The method according to claim 9, characterized in that, The hardware health status includes the health status of at least one piece of hardware in the electronic device; the health status of the hardware in the at least one piece of hardware is represented by a health score of the corresponding hardware health. The continuous monitoring of the hardware health status of the electronic device includes: Continuously monitor the device hardware in the at least one device hardware to obtain the hardware operation data of the device hardware in the at least one device hardware; Based on the hardware operation data of the at least one device hardware, the health score of the hardware health of the at least one device hardware is continuously updated. The operating status of the multiple RAS functions is dynamically adjusted based on the health score of the hardware health of the at least one device hardware, or dynamically adjusted based on the fused health score obtained by fusing the health scores of the hardware health of the at least one device hardware.

12. The method according to claim 9, characterized in that, The hardware health status includes the memory health status of the memory module of the electronic device, which is represented by a health score of the memory health of the electronic device. The continuous monitoring of the hardware health status of the electronic device includes: If a specified memory error is detected in the electronic device, the corresponding error score to be deducted for the specified memory error is determined according to the correspondence between error type and error score; The memory health score is updated according to the error score to be deducted, resulting in the updated memory health score.

13. The method according to claim 12, characterized in that, The step of updating the memory health score according to the error score to be deducted, to obtain the updated memory health score, includes: The health score of the memory health is updated to the product of the first coefficient and the error score to be deducted, plus the product of the second coefficient and the health score of the memory health, wherein the first coefficient is a set time decay factor, the second coefficient is the difference between 1 and the time decay factor, and 0 < the time decay factor < 1.

14. The method according to claim 9, characterized in that, The hardware health status is represented by a health score of the electronic device's hardware health. The health score range is divided into multiple score intervals, and the multiple RAS functions are divided into multiple function levels. One of the multiple function levels corresponds to one of the multiple score intervals. The dynamic adjustment of the operating status of the multiple RAS functions based on the monitored hardware health status includes: When the score range of the hardware health score decreases from the first score range to the second score range, the operating status of the RAS function whose function level corresponds to the second score range among the multiple RAS functions is adjusted to be enabled, wherein the function level corresponding to the first score range is lower than the function level corresponding to the second score range.

15. The method according to claim 14, characterized in that, The method further includes: Based on the health score of the hardware health, the operating status of the energy efficiency function in the performance-energy consumption priority mode is dynamically adjusted, wherein the health score of the hardware health is positively correlated with the total energy consumption of the energy efficiency function enabled in the performance-energy consumption priority mode.

16. The method according to claim 9, characterized in that, The hardware health status includes the health status of at least two types of device hardware of the electronic device, and one of the at least two types of device hardware corresponds to at least some of the RAS functions among the plurality of RAS functions; The dynamic adjustment of the operating status of the multiple RAS functions based on the monitored hardware health status includes: Based on the monitored health status of the device hardware in the at least two types of device hardware, the operating status of the RAS function corresponding to the device hardware in the at least two types of device hardware is dynamically adjusted.

17. The method according to claim 9, characterized in that, One of the multiple RAS functions corresponds to one of the multiple function options; The dynamic adjustment of the operating status of the multiple RAS functions based on the monitored hardware health status includes: Based on the monitored hardware health status, the RAS function to be adjusted and the operating state to be adjusted of the RAS function to be adjusted are determined among the multiple RAS functions, and the second option configuration information to be updated is obtained. The second option configuration information includes the option identifier of the function option corresponding to the RAS function to be adjusted and the option value corresponding to the operating state to be adjusted of the RAS function to be adjusted. Adjust the running status of the RAS function to be adjusted according to the configuration information of the second option.

18. The method according to claim 17, characterized in that, The electronic device includes a management controller and runs a basic input / output system. The step of adjusting the operating status of the RAS function to be adjusted according to the configuration information of the second option includes: The management controller updates the configuration structure according to the second option configuration information to obtain the updated configuration structure, and sets the synchronization identifier to a specified value. The configuration structure is used to record the option identifier of the function option corresponding to the RAS function in the plurality of RAS functions, and the option value corresponding to the running status of the RAS function in the plurality of RAS functions. During the startup phase of the electronic device, in response to detecting that the synchronization flag bit is set to the specified value, the updated configuration structure is obtained from the management controller through the basic input / output system, the configuration information of the option to be updated is extracted from the updated configuration structure, the configuration information of the option to be updated is written to the configuration area of ​​the non-volatile random access memory, and the electronic device is controlled to restart, so as to adjust the operating state of the RAS function to be adjusted by loading the configuration information of the option to be updated.

19. An electronic device, characterized in that, include: A processor and a management controller, the processor being used to execute a basic input / output system; wherein... At least one of the management controller and the basic input / output system is configured to configure a specified energy efficiency scenario for the electronic device in multiple energy efficiency scenarios, wherein the energy efficiency scenario in the multiple energy efficiency scenarios is related to the performance and energy consumption of the electronic device, the specified energy efficiency scenario is associated with a specified energy efficiency mode, and in the specified energy efficiency mode, at least some of the multiple RAS functions are enabled, the specified energy efficiency mode includes the following two sub-modes: performance and energy consumption priority mode and reliability priority mode. In the performance and energy consumption priority mode, the at least some RAS functions change with the hardware health status of the electronic device, and in the reliability priority mode, the at least some RAS functions are independent of the hardware health status of the electronic device; in response to the specified energy efficiency scenario taking effect, the electronic device is controlled to operate when the at least some RAS functions are enabled.

20. A server, characterized in that, include: A processor and a management controller, the processor being used to execute a basic input / output system; wherein... At least one of the management controller and the basic input / output system is configured to configure a specified energy efficiency scenario for the server among multiple energy efficiency scenarios, wherein the energy efficiency scenario among the multiple energy efficiency scenarios is related to the performance and energy consumption of the electronic device, the specified energy efficiency scenario is associated with a specified energy efficiency mode, and in the specified energy efficiency mode, at least some of the multiple RAS functions are enabled, the specified energy efficiency mode includes the following two sub-modes: performance energy consumption priority mode and reliability priority mode, in the performance energy consumption priority mode, the at least some RAS functions change with the hardware health status of the electronic device, in the reliability priority mode, the at least some RAS functions are independent of the hardware health status of the electronic device; in response to the specified energy efficiency scenario taking effect, the server is controlled to operate with the at least some RAS functions enabled.

21. 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 method of any one of claims 1 to 18.

22. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 18.

Images