A server starting method, system and device, a server and a storage medium

Abstract

The application discloses a server starting method, system and device, a server and a storage medium, and relates to the field of servers. After a server completes initialization operations on each memory, the server first loads a starting program from each memory by using a memory cross access technology, and detects whether the server successfully starts. When it is determined that the server fails to start by using the memory cross access technology, the server is immediately controlled to load the starting program from the memory by using a non-memory cross access technology, so that the server can be ensured to normally start. When the server still fails to successfully start by using the non-memory cross access technology, an abnormal memory in the server is determined, and the server is controlled to load the starting program from the other memories except the abnormal memory by using the memory cross access technology again, so that the server starting is completed, and the storage performance is improved on the basis of ensuring that the server can normally start.

Description

Technical Field

[0001] This invention relates to the field of servers, and in particular to a server startup method, system, apparatus, server, and storage medium. Background Technology

[0002] Servers, as carriers of information services, play a crucial role in data storage. Servers primarily rely on memory for data storage. To increase data storage capacity, multiple memory modules are typically configured within the server. Furthermore, to optimize memory utilization, memory interleaving is commonly used. While memory interleaving is a parallel storage technique that improves storage speed, it can also impact server boot times. Simply disabling memory interleaving degrades storage performance, while using it may prevent the server from booting properly. Therefore, balancing storage performance with normal boot times is a critical challenge. Summary of the Invention

[0003] The purpose of this invention is to provide a server startup control method, system, device, server, and storage medium that improves storage performance by utilizing cross-access technology while ensuring that the server can start normally.

[0004] To solve the above-mentioned technical problems, the present invention provides a server startup control method, comprising:

[0005] After the server starts up and completes the initialization of the various memory locations used by the server, the server is controlled to load the startup program from each memory location using memory interleaving technology so that the server can start up.

[0006] When it is determined that the server fails to boot using the memory interleaving technology, the server is controlled to reload the boot program from each of the memory locations using a non-memory interleaving technology.

[0007] When it is determined that the server fails to boot using the non-memory inter-access technique, the abnormal memory in each memory used by the server is identified, and the server is controlled to load the startup program from other memory outside the abnormal memory using the memory inter-access technique, so as to re-complete the server boot process.

[0008] On the one hand, determining that the server failed to boot using the memory interleaving technology includes:

[0009] If the server fails to complete the boot process after the server begins loading the startup program from each memory location using the memory interleaving technology and after a preset boot time, it is determined that the server has failed to boot using the memory interleaving technology.

[0010] On the other hand, after the server starts up and completes the initialization of the various memory locations used by the server, the process also includes:

[0011] Obtain the actual installation location of each memory module and the actual amount of memory used by the server;

[0012] When the actual installation location differs from the installation location in the conventional memory settings, the cache of memory that is different from the installation location in the conventional memory settings will be cleared, and / or, when the actual amount of memory differs from the amount of memory in the conventional memory settings, the cache of excess memory in the server will be cleared.

[0013] On the other hand, after identifying the abnormal memory in each memory location used by the server, the process also includes:

[0014] The abnormal memory and other memory in the server are respectively used as two segmented storage units, so that the server can use the two segmented storage units respectively using segmented storage technology.

[0015] On the other hand, identifying abnormal memory in each memory location used by the server includes:

[0016] The memory in the server is divided into multiple segmented storage units according to a preset partitioning rule;

[0017] The server is controlled to load the startup program from each of the segmented storage units using the non-memory interleaved access technology, and to determine whether the server can start successfully in each case.

[0018] If not, the segmented storage unit that fails to start the server will be considered a suspicious storage unit.

[0019] The suspicious storage units are disabled sequentially according to a preset disabling order, and the server is controlled to use the non-memory cross-access technology to load the startup program from the other memory in the suspicious storage units, excluding the disabled memory.

[0020] If the server starts successfully, the disabled memory in the suspicious storage unit will be considered as the abnormal memory.

[0021] On the other hand, after the server starts up and completes the initialization of the various memory locations used by the server, the process also includes:

[0022] Obtain the initialization time required for each memory to complete initialization and the actual installation location of each memory;

[0023] Before classifying the disabled memory in the suspicious storage unit as the anomalous memory, the method further includes:

[0024] Determine whether the actual installation location of the disabled memory in the suspected storage unit is consistent with the actual installation location of the memory with the longest initialization time;

[0025] If so, proceed to the step of treating the disabled memory in the suspicious storage unit as the abnormal memory.

[0026] To address the aforementioned technical problems, this application also provides a server startup control system, comprising:

[0027] The first startup unit is used to control the server to load the startup program from each memory using memory cross-access technology after the server starts up and completes the initialization of each memory used by the server, so that the server can start up.

[0028] The second startup unit is used to control the server to reload the startup program from each of the memory locations using non-memory inter-access technology when it is determined that the server fails to boot using the memory inter-access technology.

[0029] The third startup unit is used to determine the abnormal memory in each memory used by the server when it is determined that the server fails to boot using the non-memory inter-access technology, and to control the server to load the startup program from other memory outside the abnormal memory using the memory inter-access technology so as to re-complete the server boot process.

[0030] On the one hand, the second startup unit is specifically used to determine that the server has failed to start up using the memory inter-access technology after the server starts loading the startup program from each of the memory locations using the memory inter-access technology and after a preset startup time has elapsed, and to control the server to reload the startup program from each of the memory locations using non-memory inter-access technology.

[0031] On the other hand, it also includes:

[0032] The first memory parameter acquisition unit is used to acquire the actual installation location of each memory and the actual amount of memory used by the server after the server starts up and completes the initialization of each memory used by the server.

[0033] The cache clearing unit is used to clear the cache of memory that is different from the installation location in the conventional memory setting when the actual installation location is different from the installation location in the conventional memory setting, and / or to clear the cache of excess memory in the server when the actual memory quantity is different from the memory quantity in the conventional memory setting.

[0034] On the other hand, it also includes:

[0035] The segmented storage control unit is used to, after determining the abnormal memory in each memory used by the server, divide the abnormal memory and other memory in the server other than the abnormal memory into two segmented storage units, so that the server can use the two segmented storage units respectively using segmented storage technology.

[0036] On the other hand, the third startup unit includes:

[0037] The segmented storage unit is used to divide the memory in the server into multiple segmented storage units according to a preset partitioning rule when it is determined that the server fails to boot using the non-memory interleaved access technology.

[0038] The segmented startup unit is used to control the server to load the startup program from each of the segmented storage units using the non-memory interleaved access technology, and to determine whether the server can start successfully; if not, the suspicious determination unit is triggered.

[0039] The suspicious determination unit is used to identify segmented storage units that fail to enable the server to start successfully as suspicious storage units.

[0040] An abnormal memory investigation unit is used to disable each memory in the suspicious storage unit in a preset disabling order, and control the server to load the startup program from the memory other than the disabled memory in the suspicious storage unit using the non-memory cross-access technology.

[0041] An abnormal memory determination unit is used to identify disabled memory in the suspicious storage unit as abnormal memory when the server starts successfully.

[0042] The abnormal memory disables the startup unit, which controls the server to load the startup program from other memory outside the abnormal memory using the memory cross-access technology.

[0043] On the other hand, it also includes:

[0044] The second memory parameter acquisition unit is used to acquire the initialization time required for each memory to complete initialization and the actual installation location of each memory after the server starts up and completes the initialization of each memory used by the server.

[0045] An abnormal memory comparison unit is used to determine whether the actual installation location of the disabled memory in the suspicious storage unit is consistent with the actual installation location of the memory with the longest initialization time before the disabled memory in the suspicious storage unit is identified as the abnormal memory; if so, the abnormal memory determination unit is triggered.

[0046] To address the aforementioned technical problems, this application also provides a server startup control device, comprising:

[0047] Memory, used to store computer programs;

[0048] A processor, used to implement the steps of any of the above-described server startup control methods when executing the computer program.

[0049] To address the aforementioned technical problems, this application also provides a server, including the aforementioned server startup control device.

[0050] To address the aforementioned technical problems, this application also provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of any of the above-described server startup control methods.

[0051] In summary, this invention discloses a server startup control method, system, device, server, and storage medium. After the server completes the initialization operations for each memory location, it first loads the startup program from each memory location using memory interleaving technology and checks whether the server has successfully booted. If it is determined that the server fails to boot using memory interleaving technology, it immediately controls the server to load the startup program from memory using non-memory interleaving technology, prioritizing ensuring the server can boot normally. If the server still fails to boot using non-memory interleaving technology, it identifies the abnormal memory location in the server and controls the server to load the startup program from other memory locations (excluding the abnormal memory) again using memory interleaving technology to complete the server startup. This improves storage performance while ensuring the server can boot normally. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the prior art and embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 A flowchart of a server startup control method provided by the present invention;

[0054] Figure 2 A schematic diagram of the structure of a server startup control system provided by the present invention;

[0055] Figure 3 A schematic diagram of the structure of a server startup control device provided by the present invention;

[0056] Figure 4 This is a schematic diagram of the structure of a storage medium provided by the present invention. Detailed Implementation

[0057] The core of this invention is to provide a server startup control method, system, device, server, and storage medium that improves storage performance by utilizing cross-access technology while ensuring the server can start normally.

[0058] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0059] Please refer to Figure 1 , Figure 1 A flowchart of a server startup control method provided by the present invention is provided, the server startup control method comprising:

[0060] S1: After the server starts up and completes the initialization of the various memory locations used by the server, the server control system uses memory interleaving technology to load the startup program from each memory location so that the server can start up.

[0061] S2: When it is determined that the server fails to boot using memory interleaving technology, control the server to reload the startup program from each memory using non-memory interleaving technology;

[0062] S3: When it is determined that the server fails to boot using non-memory inter-access technology, identify the abnormal memory in each memory used by the server, and control the server to load the startup program from other memory outside the abnormal memory using memory inter-access technology in order to complete the server boot process again.

[0063] Memory, as a fundamental component of a server for information storage, is crucial for efficient allocation and usage, especially for developers. To optimize memory utilization, developers typically allocate multiple memory locations within a server and utilize memory interleaving technology to retrieve necessary data for server functionality. Memory interleaving is a technique to accelerate memory access by separating odd and even memory addresses, allowing subsequent bytes to be accessed without affecting the flushing of the current set of bytes. While memory interleaving improves server storage performance, its application in various slots can lead to anomalies. For example, it can result in unavailable memory locations, preventing the server from booting and causing irreparable damage to customers. Disabling memory interleaving during server startup allows the server to start, but significantly reduces memory performance. Therefore, the current challenge is to balance storage performance with successful server boot-up.

[0064] It should be noted that the server startup control method provided in this application is executed by the processor running BIOS (Basic Input Output System) firmware in the server. The BIOS provides the lowest-level and most direct hardware control for the server. Utilizing the server firmware BIOS ensures that the server can operate efficiently and stably under different memory usage modes, providing users with a better user experience.

[0065] Specifically, in this application, after the server starts up and completes the initialization of various memory locations, the server first uses memory interleaving technology to read and load the startup program from these initialized memories. The startup program refers to the program that the server needs to call to start up. If the server can start up normally using memory interleaving technology, both the server's storage performance and its normal startup and operation are guaranteed.

[0066] However, in actual use, the server may fail to boot using memory interleaving technology, resulting in a stalled state. Therefore, the BIOS needs to actively control the server to restart in another way. In this application, when the BIOS detects a boot failure using memory interleaving technology, it controls the server to reload the boot program from each initialized memory location using non-memory interleaving technology, prioritizing ensuring the server can boot normally within a certain timeframe. Memory interleaving technology generally stores and accesses odd and even addresses of the memory bank separately, while non-memory interleaving technology treats the memory bank as a single entity for data storage and access. Furthermore, server boot failure includes the entire boot process, or the server failing to boot within a preset time period. The specific judgment method can be adjusted according to the actual situation.

[0067] If the BIOS detects that the server still fails to boot using non-memory interleaving technology, it indicates a possible memory anomaly. Therefore, it's necessary to identify and disable the faulty memory, load the bootloader from the remaining memory, and attempt to restart the server again. Since the faulty memory has been disabled and the bootloader is loaded from the remaining memory, the reliability of the memory is currently high. Therefore, memory interleaving technology can be used again to load the bootloader from this memory, ensuring both server boot speed and storage performance, as well as a safe and stable boot process.

[0068] In summary, this invention provides a server startup method. After the server completes the initialization operations for each memory location, it first loads the startup program from each memory location using memory interleaving technology and checks whether the server has successfully booted. If it is determined that the server fails to boot using memory interleaving technology, it immediately controls the server to load the startup program from memory using non-memory interleaving technology, prioritizing ensuring the server can boot normally. If the server still fails to boot using non-memory interleaving technology, it identifies the abnormal memory location in the server and controls the server to load the startup program from other memory locations (excluding the abnormal memory location) again using memory interleaving technology to complete the server startup. This improves storage performance while ensuring the server can boot normally.

[0069] Based on the above embodiments:

[0070] In some embodiments, determining that the server failed to boot using memory interleaving technology includes:

[0071] If the server fails to complete the boot process after using memory interleaving technology to load the startup program from various memory locations and after a preset boot time, it is determined that the server has failed to boot using memory interleaving technology.

[0072] Server boot failure typically refers to the server failing to start within a specified time period. A prolonged server startup time can also be considered as the server failing to start within the specified time period. Therefore, in this embodiment, server boot failure using memory interleaving technology specifically means that the server has not completed the boot process within a preset startup time period. The preset startup time period is calculated from the start of the server loading the startup program from various memory locations using memory interleaving technology. This embodiment does not impose a specific limit on the value of the preset startup time period and can be adjusted according to the actual situation of the server.

[0073] Similarly, the above method can also be used to determine if the server is booting using non-memory interleaving access technology. Specifically, if the server still has not completed booting after the server starts using non-memory interleaving access technology to load the startup program from various memory locations and after a preset boot time, it is determined that the server has failed to boot using non-memory interleaving access technology.

[0074] In some embodiments, after the server starts up and completes the initialization of the various memory locations used by the server, the method further includes:

[0075] Obtain the actual installation location of each memory module and the actual amount of memory used by the server;

[0076] The cache of memory that is installed at a different location than the one specified in the standard memory settings will be cleared, and / or the cache of excess memory in the server will be cleared if the actual amount of memory is different from the amount of memory specified in the standard memory settings.

[0077] To further ensure the server can successfully boot using memory interleaving technology, in this embodiment, after the server completes memory initialization, the BIOS also obtains the actual installation locations of these memory modules and the actual amount of memory used by the server. Typically, users record some standard memory settings for the server, including the amount of memory used and the installation location of each memory module (e.g., which slot it's installed in). When the server's memory is configured according to these standard memory settings, the server usually does not fail to boot.

[0078] Therefore, in this embodiment, by comparing whether the actual installation location of the memory is the same as the installation location recorded in the conventional memory settings, and by comparing whether the actual amount of memory used by the server is the same as the amount of memory in the conventional memory settings, a preliminary judgment is made as to whether the memory may be abnormal. When one or both of the above comparison results are different, the cache in the corresponding memory is cleared to avoid anomalies when the server loads the startup program from these memories using memory interleaving technology or non-memory interleaving technology, further ensuring that the server can boot up and start normally.

[0079] In some embodiments, after determining the abnormal memory in each memory segment used by the server, the method further includes:

[0080] The abnormal memory and the other memory in the server are treated as two separate segmented storage units, so that the server can use the two segmented storage units separately using segmented storage technology.

[0081] The abnormal memory defined in this application refers to memory that cannot enable the server to load the startup program and complete the boot process normally. It does not mean that the basic read and write functions of the memory are abnormal. Therefore, in order to improve the utilization rate of each memory in the server, in this embodiment, the abnormal memory and other memory in the server are respectively regarded as two segmented storage units. These two segmented storage units do not affect each other. The server can use memory interleaving technology or non-memory interleaving technology to read data from these two segmented storage units respectively.

[0082] If the server is subsequently unable to complete read and write operations using the abnormal memory, the abnormal memory can be disabled, and its installation location and other relevant parameters can be recorded so that users can handle and maintain it in a timely manner.

[0083] In some embodiments, determining abnormal memory in various memory locations used by the server includes:

[0084] The memory in the server is divided into multiple segmented storage units according to a preset partitioning rule;

[0085] The control server uses non-memory interleaving technology to load the startup program from each segmented storage unit and determines whether the server can start successfully in each segment.

[0086] If not, the segmented storage unit that fails to start the server will be considered a suspicious storage unit.

[0087] The system disables each memory in the suspicious storage unit in a preset order, and controls the server to load the startup program from the memory in the suspicious storage unit other than the disabled memory using non-memory cross-access technology.

[0088] If the server starts successfully, the disabled memory in the suspicious storage unit will be treated as abnormal memory.

[0089] In this embodiment, abnormal memory in the various memory segments used by the server is determined through segmented judgment. First, all the server's memory is divided into multiple segmented storage units according to a preset partitioning rule to narrow down the scope of abnormal memory. Then, a non-memory interleaving technique is used to load the boot program from each segmented storage unit to determine whether the server can boot normally using that segmented storage unit. It should be noted that this embodiment does not impose any special limitations on the preset partitioning rule, such as dividing all the memory in the server into segments according to a certain number. In addition, the use of segmented memory interleaving technique to load the boot program from the segmented storage units is considered because non-memory interleaving techniques are more reliable and can ensure the accuracy of the abnormal memory determination results.

[0090] If the server can boot normally from a segmented storage unit, it proves that there is no abnormal memory in that segmented storage unit. If the server cannot boot from a segmented storage unit, it proves that there is abnormal memory in that segmented storage unit. This segmented storage unit is designated as a suspicious storage unit, and each memory in the suspicious storage unit needs to be disabled sequentially according to a preset disabling order. If the server can boot normally using the suspicious storage unit after disabling one of its memory modules, it proves that the disabled memory is abnormal memory.

[0091] In summary, this embodiment divides the server's memory into different segmented storage units, and then locates abnormal memory from these segmented storage units respectively, which can reduce the difficulty of finding abnormal memory and improve the search efficiency.

[0092] In some embodiments, after the server starts up and completes the initialization of the various memory locations used by the server, the method further includes:

[0093] Obtain the initialization time required for each memory module to complete initialization, as well as the actual installation location of each memory module;

[0094] Before classifying disabled memory in a suspicious storage unit as anomalous memory, the process also includes:

[0095] Determine whether the actual installation location of the disabled memory in the suspicious storage unit is consistent with the actual installation location of the memory with the longest initialization time;

[0096] If so, proceed to the step of treating the disabled memory in the suspicious storage unit as abnormal memory.

[0097] Considering that memory with excessively long initialization times may be abnormal, this embodiment, after the server completes the initialization of each memory, also obtains the time required for each memory to complete its initialization. The initialization times of each memory within the server are compared horizontally, and the memory with the longest initialization time is considered likely to be abnormal. To further ensure the accuracy of abnormal memory identification, the actual installation location of the memory with the longest initialization time is compared with the actual installation location of the memory previously identified as abnormal. If the two locations match, the memory is confirmed to be abnormal.

[0098] Of course, if the actual installation location of the disabled memory in a suspicious storage unit is different from the installation location of the memory with the longest initialization time, users can still treat the disabled memory in the suspicious storage unit as abnormal memory in order to ensure the server boots up normally to the greatest extent. Specific settings can be adjusted according to actual needs.

[0099] Please refer to Figure 2 , Figure 2 This invention provides a schematic diagram of a server startup control system, which includes:

[0100] The first startup unit 11 is used to control the server to load the startup program from each memory using memory interleaving technology after the server starts up and completes the initialization of each memory used by the server, so that the server can start up.

[0101] The second startup unit 12 is used to control the server to reload the startup program from each memory using non-memory inter-access technology when it is determined that the server has failed to boot using memory inter-access technology.

[0102] The third startup unit 13 is used to determine the abnormal memory in each memory used by the server when it is determined that the server has failed to boot using non-memory inter-access technology, and to control the server to load the startup program from other memory outside the abnormal memory using memory inter-access technology so as to complete the server boot process again.

[0103] This invention provides a server startup system, comprising a first startup unit 11, a second startup unit 12, and a third startup unit 13. Firstly, after the server completes initialization operations on each memory location, the first startup unit 11 loads the startup program from each memory location using memory interleaving technology and checks whether the server has successfully booted. When the second startup unit 12 determines that the server has failed to boot using memory interleaving technology, it immediately controls the server to load the startup program from memory using non-memory interleaving technology, prioritizing ensuring the server can boot normally. When the third startup unit 13 detects that the server still cannot boot successfully using non-memory interleaving technology, it identifies the abnormal memory in the server and controls the server to load the startup program from other memory locations (excluding the abnormal memory) again using memory interleaving technology to complete the server boot process, thereby improving storage performance while ensuring the server can boot normally.

[0104] Based on the above embodiments:

[0105] In some embodiments, the second startup unit 12 is specifically used to determine that the server has failed to start up using memory inter-access technology after the server starts loading the startup program from each memory using memory inter-access technology and after a preset startup time has elapsed, and to control the server to reload the startup program from each memory using non-memory inter-access technology.

[0106] In some embodiments, it also includes:

[0107] The first memory parameter acquisition unit is used to acquire the actual installation location of each memory and the actual amount of memory used by the server after the server starts up and completes the initialization of each memory used by the server.

[0108] The cache clearing unit is used to clear the cache of memory that is installed at a different location than the one specified in the standard memory settings when the actual installation location is different from the one specified in the standard memory settings, and / or to clear the cache of excess memory in the server when the actual amount of memory is different from the amount of memory specified in the standard memory settings.

[0109] In some embodiments, it also includes:

[0110] The segmented storage control unit is used to, after identifying the abnormal memory in each memory used by the server, divide the abnormal memory and the other memory in the server as two segmented storage units respectively, so that the server can use the two segmented storage units respectively using segmented storage technology.

[0111] In some embodiments, the third activation unit 13 includes:

[0112] The segmented storage unit is used to divide the memory in the server into multiple segmented storage units according to a preset partitioning rule when it is determined that the server has failed to boot using non-memory interleaving technology.

[0113] The segmented startup unit is used to control the server to load the startup program from each segmented storage unit using non-memory interleaved access technology, and to determine whether the server can start successfully in each segment; if not, the suspicious determination unit is triggered.

[0114] The suspicious storage unit is used to identify segmented storage units that fail to enable the server to start successfully as suspicious storage units.

[0115] The abnormal memory investigation unit is used to disable each memory in the suspicious storage unit in a preset disabling order, and control the server to load the startup program from the memory in the suspicious storage unit other than the disabled memory using non-memory cross-access technology.

[0116] An abnormal memory determination unit is used to identify disabled memory in suspicious storage units as abnormal memory when the server starts successfully.

[0117] The abnormal memory disables the startup unit, which is used to control the server to load the startup program from other memory outside the abnormal memory using memory interleaving technology.

[0118] In some embodiments, it also includes:

[0119] The second memory parameter acquisition unit is used to acquire the initialization time required for each memory to complete initialization and the actual installation location of each memory after the server starts up and completes the initialization of each memory used by the server.

[0120] The abnormal memory comparison unit is used to determine whether the actual installation location of the disabled memory in the suspicious storage unit is consistent with the actual installation location of the memory with the longest initialization time before the disabled memory in the suspicious storage unit is identified as abnormal memory; if so, the abnormal memory determination unit is triggered.

[0121] Please refer to Figure 3 , Figure 3 This is a schematic diagram of a server startup control device provided by the present invention. The server startup control device includes:

[0122] Memory 21 is used to store computer programs;

[0123] Processor 22 is used to implement the steps of any of the above server startup control methods when executing a computer program.

[0124] The processor 22 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 22 may be implemented using at least one of the following hardware forms: DSP (Digital Signal Processor), FPGA (Field-Programmable Gate Array), or PLA (Programmable Logic Array). The processor 22 may also include a main processor and a coprocessor. The main processor, also known as the central processing unit, is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state.

[0125] The memory 21 may include one or more computer-readable storage media, which may be non-transitory. The memory 21 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In this embodiment, the memory 21 is used to store at least the following computer program, which, after being loaded and executed by the processor 22, is capable of implementing the relevant steps of the server startup control method disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 21 may also include an operating system and data, and the storage method may be temporary or permanent storage. The operating system may include Windows, Unix, Linux, etc. The data may include, but is not limited to, data related to the server startup control method.

[0126] To address the aforementioned technical problems, this application also provides a server, including the aforementioned server startup control device.

[0127] For a detailed description of the server provided in this application, please refer to the above-described embodiment of the server startup control method; this application will not elaborate further here.

[0128] This application does not specify the type of server; for example, it can be an AMD (Advanced Micro Devices) server.

[0129] Please refer to Figure 4 , Figure 4 This is a schematic diagram of a storage medium provided by the present invention. The storage medium 31 stores a computer program, which, when executed by a processor, implements the steps of any of the above-described server startup control methods.

[0130] It is understood that if the server startup control method in the above embodiments is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and executes all or part of the steps of the methods described in the various embodiments of this application. Specifically, the readable storage medium 31 can include, but is not limited to, any type of disk, including floppy disks, optical disks, and portable hard drives, or any type of media or device suitable for storing instructions and data, etc., and this application does not make any special limitations here.

[0131] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0132] It should also be noted that the terms "comprising," "including," or any other variations thereof used in this specification are intended to cover a 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. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A server startup control method, characterized in that, include: After the server starts up and completes the initialization of the various memory locations used by the server, the server is controlled to load the startup program from each memory location using memory interleaving technology so that the server can start up. Obtain the initialization time required for each memory to complete initialization and the actual installation location of each memory; When it is determined that the server fails to boot using the memory interleaving technology, the server is controlled to reload the boot program from each of the memory locations using a non-memory interleaving technology. When it is determined that the server fails to boot using the non-memory cross-access technology, the memory in the server is divided into multiple segmented storage units according to a preset partitioning rule; The server is controlled to load the startup program from each of the segmented storage units using the non-memory interleaved access technology, and to determine whether the server can start successfully in each case. If not, the segmented storage unit that fails to start the server will be considered a suspicious storage unit. The suspicious memory units are disabled sequentially according to a preset disabling order, and the server is controlled to use the non-memory cross-access technology to load the startup program from the other memory units in the suspicious memory units, excluding the disabled memory. If the server starts successfully, it is determined whether the actual installation location of the disabled memory in the suspicious storage unit is consistent with the actual installation location of the memory with the longest initialization time. If so, the disabled memory in the suspicious storage unit is designated as abnormal memory, and the server is controlled to use the memory cross-access technology to load the startup program from other memory outside the abnormal memory in order to re-complete the server's boot process.

2. The server startup control method as described in claim 1, characterized in that, Determining that the server failed to boot using the memory interleaving technology includes: If the server fails to complete the boot process after the server begins loading the startup program from each memory location using the memory interleaving technology and after a preset boot time, it is determined that the server has failed to boot using the memory interleaving technology.

3. The server startup control method as described in claim 1, characterized in that, After the server starts up and completes the initialization of the various memory locations used by the server, the process also includes: Obtain the actual installation location of each memory module and the actual amount of memory used by the server; When the actual installation location differs from the installation location in the conventional memory settings, the cache of memory that is different from the installation location in the conventional memory settings will be cleared, and / or, when the actual amount of memory differs from the amount of memory in the conventional memory settings, the cache of excess memory in the server will be cleared.

4. The server startup control method as described in claim 1, characterized in that, After identifying the abnormal memory, the process also includes: The abnormal memory and other memory in the server are respectively used as two segmented storage units, so that the server can use the two segmented storage units respectively using segmented storage technology.

5. A server startup control system, characterized in that, include: The first startup unit is used to control the server to load the startup program from each memory using memory cross-access technology after the server starts up and completes the initialization of each memory used by the server, so that the server can start up. The second memory parameter acquisition unit is used to acquire the initialization time required for each memory to complete initialization and the actual installation location of each memory after the server starts up and completes the initialization of each memory used by the server. The second startup unit is used to control the server to reload the startup program from each of the memory locations using non-memory inter-access technology when it is determined that the server fails to boot using the memory inter-access technology. The third startup unit is used to determine the abnormal memory in each memory used by the server when it is determined that the server fails to boot using the non-memory inter-access technology, and to control the server to load the startup program from other memory outside the abnormal memory using the memory inter-access technology so as to re-complete the boot process of the server. The third startup unit includes: The segmented storage unit is used to divide the memory in the server into multiple segmented storage units according to a preset partitioning rule when it is determined that the server fails to boot using the non-memory interleaved access technology. The segmented startup unit is used to control the server to load the startup program from each of the segmented storage units using the non-memory interleaved access technology, and to determine whether the server can start successfully; if not, the suspicious determination unit is triggered. The suspicious determination unit is used to identify segmented storage units that fail to enable the server to start successfully as suspicious storage units. An abnormal memory investigation unit is used to disable each memory in the suspicious storage unit in a preset disabling order, and control the server to load the startup program from the memory other than the disabled memory in the suspicious storage unit using the non-memory cross-access technology. An abnormal memory determination unit is used to identify the disabled memory in the suspicious storage unit as the abnormal memory when the server starts successfully and the actual installation location of the disabled memory in the suspicious storage unit is consistent with the actual installation location of the memory with the longest initialization time. The abnormal memory disables the startup unit, which controls the server to load the startup program from other memory outside the abnormal memory using the memory cross-access technology; The server startup control system also includes: An abnormal memory comparison unit is used to determine whether the actual installation location of the disabled memory in the suspicious storage unit is consistent with the actual installation location of the memory with the longest initialization time before the disabled memory in the suspicious storage unit is identified as the abnormal memory; if so, the abnormal memory determination unit is triggered.

6. A server startup control device, characterized in that, include: Memory, used to store computer programs; A processor, configured to implement the steps of the server startup control method as described in any one of claims 1 to 4 when executing the computer program.

7. A server, characterized in that, Includes the server startup control device as described in claim 6.

8. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the steps of the server startup control method as described in any one of claims 1 to 4.

Images