Log storage method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of data processing, in particular to a log storage method and device, electronic equipment and a storage medium. Fault log data can be quickly stored to a first storage module through a quick link bus between a central processing unit and the first storage module when a server breaks down; according to the technical scheme, the problem of incomplete log recording or loss caused by faults is avoided, so that the technical problem of incomplete log information storage when the server fails can be solved, the technical effects of ensuring complete storage of fault logs, helping engineers to quickly analyze fault reasons and accelerating repair are achieved, and the reliability and service continuity of the server are improved.

Description

Technical Field

[0001] The present application relates to the technical field of data processing, and in particular, to a method and apparatus for storing logs, an electronic device, and a storage medium. Background Art

[0002] Information technology has made various activities more convenient, while also posing higher requirements for the reliability of servers. To ensure 24-hour uninterrupted service of the server, it is necessary to reduce the failure rate of the server and quickly repair it when a failure occurs to ensure normal business use. Log information reflects the real-time state of the machine, especially the final state recorded when the machine fails. Therefore, for the analysis and repair of server failures, the failure log is a key factor that can help engineers quickly obtain the machine state, determine the cause of the problem, and provide effective solutions as soon as possible.

[0003] When the server fails, the operating state of the machine is unstable. In this case, the time for the server to save logs is limited, which may lead to incomplete or even complete loss of failure log information, affecting subsequent problem analysis and machine repair. Summary of the Invention

[0004] The present application provides a method, apparatus, electronic device, and storage medium for storing logs to at least solve the problem in the related art that the time for the server to save logs is limited, resulting in incomplete or even complete loss of failure log information, affecting subsequent problem analysis and machine repair.

[0005] The present application provides a method for storing logs, including: the baseboard controller is connected to the central processing unit through a high-speed serial bus; the central processing unit is connected to the compute express link memory through a compute express link bus;

[0006] In the case of determining that the server has failed, the baseboard controller reads the failure log data in the local memory and transmits the failure log data to the central processing unit through the high-speed serial bus;

[0007] The central processing unit stores the failure log data in the compute express link memory through the compute express link bus.

[0008] The present application also provides a device for storing logs, including: the baseboard controller is connected to the central processing unit through a high-speed serial bus; the central processing unit is connected to the compute express link memory through a compute express link bus;

[0009] A transmission unit, configured to, in the case of determining that the server has failed, the baseboard controller reads the failure log data in the local memory and transmits the failure log data to the central processing unit through the high-speed serial bus;

[0010] A storage unit for the central processing unit to store fault log data into the compute express link memory through the compute express link bus.

[0011] This application also provides an electronic device, including: a memory for storing a computer program; a processor for implementing the steps of any of the above-mentioned log storage methods when executing the computer program.

[0012] This application also provides a computer-readable storage medium storing a computer program, wherein the computer program implements the steps of any of the above-mentioned log storage methods when executed by a processor.

[0013] This application also provides a computer program product including a computer program, which implements the steps of any of the above-mentioned log storage methods when executed by a processor.

[0014] Through this application, when a server fails, the fault log data can be quickly stored into the first storage module through the fast link bus between the central processing unit and the first storage module, avoiding the problem of incomplete or lost log records caused by the fault. Therefore, the technical problem of incomplete preservation of log information during server failure can be solved, achieving the technical effect of ensuring the complete storage of fault logs, helping engineers quickly analyze the cause of the fault and accelerating the repair, thereby improving the reliability and business continuity of the server. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] To more clearly illustrate the embodiments of this application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of this application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0016] Figure 1 A flowchart of a method for storing logs provided by an embodiment of this application;

[0017] Figure 2 A topology diagram provided by an embodiment of this application;

[0018] Figure 3 Another topology diagram provided by an embodiment of this application;

[0019] Figure 4 A structural diagram of a log storage device provided by an embodiment of this application;

[0020] Figure 5 Another structural diagram of a log storage device provided by an embodiment of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0022] It should be noted that in the description of the present application, the terms "include", "comprise" or any other variation thereof are intended to cover a non-exclusive inclusion, such that a process, method, article or device including a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. The terms "first", "second", etc. in the present application are used to distinguish similar objects and are not used to describe a specific order or sequence.

[0023] To enable those skilled in the art of the present technology to better understand the solution of the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0024] The embodiments of the present application provide a method for storing logs. The method will be described in detail in combination with the execution flow of the method for storing logs.

[0025] Figure 1 It is a schematic flow chart of a method for storing logs provided by the embodiments of the present application. As Figure 1 shown, the method includes the following steps:

[0026] The baseboard controller is connected to the central processing unit through a high-speed serial bus; the central processing unit is connected to the compute express link memory through a compute express link bus.

[0027] Please refer to Figure 2 , Figure 2 It is a schematic topology diagram provided by the embodiments of the present application. As shown in Figure 2, the Baseboard Management Controller (BMC) is connected to the Central Processing Unit (CPU) through a high-speed serial bus, and the high-bandwidth characteristic of the high-speed serial bus is utilized to ensure that the data transmission between the BMC and the CPU can be carried out quickly and efficiently.

[0028] The CPU is connected to the CXL memory via the CXL bus. The Compute Express Link (CXL) bus, as a high-performance interconnection technology, has a working frequency of up to 32 - 64 GT / s, which can significantly improve the efficiency of data transmission. Through the CXL bus, the CPU can quickly write the received log data into the CXL memory to ensure the integrity and real-time nature of the data during transmission and storage.

[0029] Step 101, in the case of determining that the server has failed, the baseboard controller reads the fault log data in the local memory and transmits the fault log data to the central processing unit via the high-speed serial bus.

[0030] During the operation of the server, the baseboard management controller continuously collects and analyzes the log data to determine whether there is a fault in the server based on the log data. When it detects that the server has failed, the BMC first reads the fault log data from the local memory, which was stored in the local memory of the BMC during the normal operation of the server. Due to the risk of data loss caused by server failure, the BMC will preferentially transmit these critical log data to the central processing unit via the high-speed serial bus.

[0031] In some embodiments, the high-speed serial bus is a bus with high-bandwidth characteristics, which further ensures that the fault log data can be quickly and efficiently transmitted from the BMC to the CPU, thus minimizing the possibility of data loss.

[0032] The BMC is an embedded hardware component located on the motherboard of the server. It provides remote management and monitoring functions for the server, enabling administrators to remotely control the server via the network when the operating system is not started or has failed, including power on / off and reset operations. At the same time, it can also monitor hardware status such as temperature, voltage, and fan speed, record system event logs, and access the server console via remote desktop. In addition, the BMC supports firmware updates and configuration management, enhancing the manageability and security of the server and providing great convenience for the maintenance of data centers and servers.

[0033] Step 102, the central processing unit stores the fault log data into the Compute Express Link memory via the Compute Express Link bus.

[0034] After the fault log data is transferred from the BMC to the BMC via the high-speed serial bus, the central processing unit further stores the fault log data in the Compute Express Link (CXL) memory via the Compute Express Link bus. As a high-performance interconnection technology, the CXL bus can operate at a frequency of 32 - 64 GT / s, which is much higher than the transmission rate of traditional buses, significantly improving the efficiency of data transmission. Through the CXL bus, the CPU can quickly write the received fault log data into the CXL memory, ensuring the integrity and real-time nature of the data during transmission.

[0035] With this application, when a server fails, the fault log data can be quickly stored in the first storage module via the express link bus between the central processing unit and the first storage module, avoiding problems such as incomplete or lost log records caused by the failure. Therefore, the technical problem of incomplete preservation of log information during server failures can be solved, achieving the technical effect of ensuring the complete storage of fault logs, helping engineers quickly analyze the cause of the failure, and accelerating the repair, thereby enhancing the reliability and business continuity of the server.

[0036] In some embodiments, after the central processing unit stores the fault log data in the Compute Express Link memory via the Compute Express Link bus, the following steps are further included:

[0037] In the case where the server failure is a power-off of the server, based on the hardware mechanism, the fault log data in the Compute Express Link memory is stored in the Compute Express Link device; wherein, the Compute Express Link memory is a volatile storage module, and the Compute Express Link device is a non-volatile storage module; the Compute Express Link device is connected to the Compute Express Link memory via the Compute Express Link bus.

[0038] After the CPU stores the fault log data in the CXL memory via the CXL bus, if the server failure is a power-off of the server, the system will, based on the hardware mechanism, store the fault log data in the CXL memory in the CXL device. As a volatile storage module, the CXL memory cannot retain data in the event of a power-off. The CXL device supports the Global Persistent Flush (GPF) function, which can automatically save data to a preset non-volatile storage space when the machine experiences an abnormal power-off, ensuring that the data remains retained after the power-off. The CXL device is connected to the CXL memory via the CXL bus, enabling the data to be directly transferred from the CXL memory to the CXL device without going through additional intermediate links, thereby improving the efficiency and reliability of data transmission.

[0039] The specific location of the non-volatile storage space can be customized by the server user in the DVSEC (Designated Vendor-Specific Extended Capability) register. For example, for a solid-state drive, specifically, the embodiments of the present application do not limit the specific location of the non-volatile storage space.

[0040] In the case of a server power outage, the hardware mechanism will automatically trigger the data migration process, refreshing the fault log data in the CXL memory to the preset non-volatile storage space, which can store data for a long time after a power outage, thus avoiding the risk of data loss due to power outage. In addition, the high-performance characteristics of the CXL bus also support efficient data transmission and management, making the entire data migration process faster and more reliable.

[0041] In some embodiments, the hardware mechanism can be the Global Persistent Flush (GPF) function. The GPF function is a feature used in data storage systems that ensures that even in the event of a system failure or power interruption, the written data can be safely saved to a persistent storage medium. The GPF function is typically implemented in a solid-state drive (SSD) or enterprise-level storage system, and it guarantees data persistence through specific algorithms and hardware designs. When the GPF function is enabled, the system monitors all outstanding data write operations and, when detecting a potential system failure risk, automatically performs a flush operation to force the data in the cache to be written to the non-volatile storage medium, thus avoiding data loss. For example, in a typical server system, the working frequency of the CXL bus can reach 32 - 64 GT / s, and it can transfer hundreds of MB of fault log data from the CXL memory to the preset non-volatile storage space within a few milliseconds, which can store data for a long time after a power outage, thus avoiding the risk of data loss due to power outage.

[0042] By storing the fault log data in the CXL memory to the CXL device, the data migration can be automatically triggered when the server is powered off, ensuring that the critical log data is safely saved, providing a solid data foundation for subsequent fault analysis and system recovery.

[0043] In some embodiments, when the fault that occurs in the server is a server power outage, before storing the fault log data in the Compute Express Link memory to the Compute Express Link device based on the hardware mechanism, the following steps are further included:

[0044] Pre-divide a target storage area in the Compute Express Link device for storing the fault log data when the fault that occurs in the server is a server power outage;

[0045] The target storage area is a dedicated storage space within the CXL device for storing the fault log data migrated from the CXL memory. By pre - partitioning the target storage area, the system can quickly locate and store the fault log data when a power failure occurs, avoiding chaos and delays during the data storage process.

[0046] In the case where the fault that occurs in the server is a server power failure, storing the fault log data in the Compute Express Link memory to the Compute Express Link device based on a hardware mechanism includes:

[0047] Storing the fault log data in the Compute Express Link memory to the target storage area within the Compute Express Link device based on a hardware mechanism.

[0048] The triggering of the hardware mechanism is automated and can immediately start the data migration operation when a power - off signal is detected, thus minimizing the risk of data loss. By storing the fault log data in the CXL memory to the target storage area of the CXL device, the system can respond quickly when the server power fails, ensuring that critical log data is safely saved. The use of the target storage area makes the data storage process more orderly and efficient, providing a solid data foundation for subsequent fault analysis and system recovery.

[0049] In some embodiments, in the case of determining that a fault has occurred in the server, before the baseboard controller reads the fault log data in the local memory and transmits the fault log data to the central processing unit through a high - speed serial bus, the following steps are further included:

[0050] Storing the normal log data collected by the baseboard controller in the local memory;

[0051] The baseboard controller reads the normal log data in the local memory and stores the normal log data in the flash device.

[0052] Please refer to Figure 3 , Figure 3 which is another topology schematic diagram provided by the embodiments of the present application. As Figure 3 shown, after the normal log data is stored in the local memory (Dynamic Random Access Memory, DRAM) of the BMC, the BMC will regularly read this data and store it in the flash device (Flash device). As a non - volatile storage medium, the flash device can store data for a long time and will not be lost even in the case of a server power failure. By migrating the normal log data from the local memory to the flash device, the system can release the storage space of the local memory while ensuring the persistence and accessibility of the log data.

[0053] Storing normal log data in local memory and migrating it to a flash device can efficiently manage log data during the normal operation of the server, avoiding excessive occupation of the storage space of local memory.

[0054] In some embodiments, after the baseboard controller reads the normal log data in the local memory and stores the normal log data in the flash device, the following steps are further included:

[0055] When it is determined that the server has not failed, the baseboard controller reads the normal log data stored in the flash device based on a preset interval;

[0056] Transmit the normal log data to the central processing unit through a high-speed serial bus;

[0057] The central processing unit stores the normal log data in the Compute Express Link memory through the Compute Express Link bus.

[0058] In some embodiments, the preset interval can be configured according to actual needs, or it can be set to perform transmission when the occupancy rate of the high-speed serial bus is lower than a certain threshold, so as to ensure that the reading and transmission of log data will not have a significant impact on the server performance. The occupancy rate threshold of the high-speed serial bus can be set according to actual needs, and the embodiments of the present application do not limit this.

[0059] After reading the normal log data in the flash device, the BMC will transmit this data to the CPU through the high-speed serial bus.

[0060] In some embodiments, the high-speed serial bus is a Peripheral Component Interconnect express (PCIE) bus. The high bandwidth characteristic of the PCIE bus (the operating frequency can reach 5 - 16 GT / s) ensures that the normal log data can be quickly transmitted to the CPU, thus providing support for subsequent data processing and analysis.

[0061] The design of transmitting normal log data through the high-speed serial bus not only optimizes the data transmission efficiency, but also makes full use of the server hardware resources, avoiding the bottleneck of the traditional low-speed bus in data transmission efficiency.

[0062] After the normal log data is transferred to the CPU, the CPU further stores this data in the CXL memory via the CXL bus. The high operating frequency of the CXL bus (32 - 64 GT / s) enables it to transfer data at an extremely high rate, ensuring that the normal log information can be quickly written into the CXL memory. As a high-performance storage medium, the CXL memory supports concurrent access by the CPU and CXL devices, which provides higher flexibility and efficiency for the storage of normal log data. By storing the normal log data in the CXL memory, the system can achieve efficient management and quick access to the log data, providing a solid data foundation for the monitoring of the server's operating status and fault analysis.

[0063] In some embodiments, after storing the fault log data in the compute express link memory to the target storage area within the compute express link device based on a hardware mechanism, the following steps are further included:

[0064] After the server is powered on, based on a hardware mechanism, the fault log data in the target storage area of the compute express link device is stored in the compute express link memory.

[0065] After the server is powered on, the hardware mechanism automatically triggers a data recovery process to transfer the fault log data in the target storage area of the CXL device to the CXL memory via the CXL bus. Utilizing the high-bandwidth characteristic of the CXL bus, it ensures that the data can be migrated from the CXL device to the CXL memory at the fastest speed. The high-performance characteristic of the CXL memory enables the fault log data to be quickly loaded and accessed by the CPU, thus providing real-time data support for fault analysis and system recovery.

[0066] Through the solution of re-storing the fault log data in the target storage area of the CXL device to the CXL memory, the system can quickly recover the critical log data after the server is powered on, ensuring the continuity and efficiency of fault analysis. It solves the problem of data loss in the case of power failure and further improves the availability and accessibility of the fault log data. At the same time, the combination of the CXL bus and the CXL memory also provides a strong guarantee for the overall stability and data security of the server system. This data recovery mechanism provides a reliable data foundation for the diagnosis and repair of server faults, thus minimizing the risk of service interruption and data loss caused by faults.

[0067] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware, but in many cases, the former is a better implementation method.

[0068] The embodiments of the present application also provide a log storage device. Figure 4A schematic structural diagram of a log storage device provided by an embodiment of the present application is as follows Figure 4 As shown, it includes: The baseboard controller is connected to the central processing unit through a high-speed serial bus; the central processing unit is connected to the Compute Accelerated Link Memory through the Compute Accelerated Link bus;

[0069] A transmission unit 21, configured to, when it is determined that the server fails, the baseboard controller reads the fault log data in the local memory and transmits the fault log data to the central processing unit through the high-speed serial bus;

[0070] A first storage unit 22, configured to store the fault log data to the Compute Accelerated Link Memory by the central processing unit through the Compute Accelerated Link bus.

[0071] Furthermore, in a possible implementation manner of an embodiment of the present application, as Figure 5 shown, the device includes:

[0072] A second storage unit 23, configured to, after the first storage unit 22 stores the fault log data to the Compute Accelerated Link Memory by the central processing unit through the Compute Accelerated Link bus, when the fault that occurs in the server is a power failure of the server, store the fault log data in the Compute Accelerated Link Memory to the Compute Accelerated Link device based on a hardware mechanism; wherein, the Compute Accelerated Link Memory is a volatile storage module, and the Compute Accelerated Link device is a non-volatile storage module; the Compute Accelerated Link device is connected to the Compute Accelerated Link Memory through the Compute Accelerated Link bus.

[0073] Through the present application, since the fault log data can be quickly stored to the first storage module through the fast link bus between the central processing unit and the first storage module when the server fails, the problem of incomplete or lost log records caused by the fault is avoided. Therefore, the technical problem of incomplete preservation of log information during server failure can be solved, and the technical effect of ensuring the complete storage of the fault log, helping engineers quickly analyze the cause of the fault and accelerating the repair can be achieved, thereby improving the reliability and business continuity of the server.

[0074] Furthermore, in a possible implementation manner of an embodiment of the present application, as Figure 5 shown, the device further includes:

[0075] A partitioning unit 24, configured to, before the second storage unit 23 stores the fault log data in the Compute Accelerated Link Memory to the Compute Accelerated Link device based on a hardware mechanism when the fault that occurs in the server is a power failure of the server, pre-partition a target storage area in the Compute Accelerated Link device for storing the fault log data when the fault that occurs in the server is a power failure of the server;

[0076] The second storage unit 23 is further configured to:

[0077] Based on a hardware mechanism, store the fault log data in the computing acceleration link memory to the target storage area within the computing acceleration link device.

[0078] Further, in a possible implementation manner of the embodiment of the present application, as Figure 5 shown, the device further includes:

[0079] A third storage unit 25, configured to store the normal log data collected by the baseboard controller in the local memory before the baseboard controller reads the fault log data in the local memory and transmits the fault log data to the central processing unit through a high-speed serial bus when the second storage unit 23 determines that the server has a fault;

[0080] A fourth storage unit 26, configured to store the normal log data read by the baseboard controller from the local memory in the flash device.

[0081] Further, in a possible implementation manner of the embodiment of the present application, as Figure 5 shown, the device further includes:

[0082] A reading unit 27, configured to read the normal log data stored in the flash device by the baseboard controller at a preset interval when it is determined that the server has no fault after the fourth storage unit 26 stores the normal log data read by the baseboard controller from the local memory in the flash device;

[0083] A transmission unit 21, further configured to transmit the normal log data to the central processing unit through a high-speed serial bus;

[0084] A fifth storage unit 28, configured to store the normal log data in the computing acceleration link memory by the central processing unit through the computing acceleration link bus.

[0085] Further, in a possible implementation manner of the embodiment of the present application, as Figure 5 shown, the device further includes:

[0086] The second storage unit 23 is further configured to, after storing the fault log data in the computing acceleration link memory to the target storage area within the computing acceleration link device based on a hardware mechanism, store the fault log data in the target storage area of the computing acceleration link device in the computing acceleration link memory based on a hardware mechanism after the server is powered on.

[0087] Further, in a possible implementation manner of the embodiment of the present application, as Figure 5 shown, the high-speed serial bus is a Peripheral Component Interconnect Express bus.

[0088] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases, the former is a better implementation method.

[0089] For the description of the features corresponding to the embodiments of the log storage device, reference can be made to the relevant descriptions of the corresponding embodiments of the log storage method, which will not be elaborated here one by one.

[0090] An embodiment of the present application also provides an electronic device, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any of the above embodiments of the log storage method.

[0091] An embodiment of the present application also provides a computer-readable storage medium, in which a computer program is stored. The computer program is configured to execute the steps in any of the above embodiments of the log storage method when running.

[0092] In an exemplary embodiment, the above computer-readable storage medium may include, but is not limited to: USB flash drive, read-only memory (ROM for short), random access memory (RAM for short), mobile hard disk, magnetic disk or optical disk, etc., various media that can store computer programs.

[0093] An embodiment of the present application also provides a computer program product. The above computer program product includes a computer program, and when the computer program is executed by a processor, it implements the steps in any of the above embodiments of the log storage method.

[0094] An embodiment of the present application also provides another computer program product, including a non-volatile computer-readable storage medium. The non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the steps in any of the above embodiments of the log storage method.

[0095] Those skilled in the art can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0096] The above has introduced in detail a method and apparatus for storing logs, an electronic device, and a storage medium provided by this application. Specific examples are used in this article to elaborate on the principle and implementation manner of this application. The description of the above embodiments is only used to help understand the method and its core idea of this application. It should be noted that for those of ordinary skill in the art, without departing from the principle of this application, several improvements and modifications can be made to this application, and these improvements and modifications also fall within the protection scope of the claims of this application.

Claims

1. A method for storing logs, characterized in that, Including: The baseboard controller is connected to the central processing unit via a high-speed serial bus; The central processing unit is connected to the Compute Acceleration Link memory via the Compute Acceleration Link bus; When it is determined that the server has a fault, the baseboard controller reads the fault log data in the local memory and transmits the fault log data to the central processing unit via the high-speed serial bus; The central processing unit stores the fault log data in the Compute Acceleration Link memory via the Compute Acceleration Link bus.

2. The storage method of the log according to claim 1, characterized in that After the central processing unit stores the fault log data in the Compute Acceleration Link memory via the Compute Acceleration Link bus, the method further includes: When the fault that occurs in the server is a power-off of the server, based on a hardware mechanism, the fault log data in the Compute Acceleration Link memory is stored in a Compute Acceleration Link device; wherein, the Compute Acceleration Link memory is a volatile storage module, and the Compute Acceleration Link device is a non-volatile storage module; the Compute Acceleration Link device is connected to the Compute Acceleration Link memory via the Compute Acceleration Link bus.

3. The storage method of the log according to claim 2, characterized in that, Before, when the fault that occurs in the server is a power-off of the server, based on a hardware mechanism, the fault log data in the Compute Acceleration Link memory is stored in the Compute Acceleration Link device, the method further includes: Pre-dividing a target storage area in the Compute Acceleration Link device for storing the fault log data when the fault that occurs in the server is a power-off of the server; When the fault that occurs in the server is a power-off of the server, based on a hardware mechanism, storing the fault log data in the Compute Acceleration Link memory in the Compute Acceleration Link device includes: Based on a hardware mechanism, storing the fault log data in the Compute Acceleration Link memory in the target storage area within the Compute Acceleration Link device.

4. The storage method of the log according to claim 1, characterized in that, Before the baseboard controller reads the fault log data in the local memory and transmits the fault log data to the central processing unit via the high-speed serial bus when it is determined that the server has a fault, the method further includes: Storing the normal log data collected by the baseboard controller in the local memory; The baseboard controller reads the normal log data in the local memory and stores the normal log data in a flash device.

5. The storage method of the log according to claim 4, characterized in that, After the baseboard controller reads the normal log data in the local memory and stores the normal log data in the flash device, the method further includes: When it is determined that the server has no fault, the baseboard controller reads the normal log data stored in the flash device based on a preset interval; Transmitting the normal log data to the central processing unit via the high-speed serial bus; The central processing unit stores the normal log data in the Compute Acceleration Link memory via the Compute Acceleration Link bus.

6. The storage method of the log according to claim 3, characterized in that, After storing the fault log data in the Compute Acceleration Link memory in the target storage area within the Compute Acceleration Link device based on a hardware mechanism, the method further includes: After the server is powered on, the fault log data of the target storage area of the compute acceleration link device is stored in the compute acceleration link memory based on the hardware mechanism.

7. The storage method of the log according to any one of claims 1-6, characterized in that The high-speed serial bus is a Peripheral Component Interconnect Express (PCIe) bus.

8. A storage device for logs, characterized in that, It includes: The baseboard controller is connected to the central processing unit through the high-speed serial bus; The central processing unit is connected to the compute acceleration link memory through the compute acceleration link bus; A transmission unit, configured to, when it is determined that the server fails, the baseboard controller reads the fault log data in the local memory and transmits the fault log data to the central processing unit through the high-speed serial bus; A first storage unit, configured to store the fault log data in the compute acceleration link memory by the central processing unit through the compute acceleration link bus.

9. An electronic device, characterized in that, It includes: At least one processor; And A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1-7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to execute the method according to any one of claims 1-7.

Images