Fault reporting method and device, storage medium and electronic equipment

Abstract

The embodiment of the invention provides a fault reporting method and device, a storage medium and electronic equipment, and relates to the field of computers.The fault reporting method comprises the steps that the fault type of a to-be-reported fault is obtained; when the fault type is a correctable fault type, acquiring a first control parameter associated with the correctable fault type; acquiring a second control parameter associated with the correctable fault type under the condition that the first control parameter indicates that the fault of the correctable fault type is allowed to be reported; and under the condition that the second control parameter indicates that the fault of the correctable fault type of the preset bus standard equipment is allowed to be reported, obtaining a first reporting parameter associated with the to-be-reported fault, reading the to-be-reported fault management address from the first reporting parameter, and reporting the to-be-reported fault to the fault management address. By adopting the scheme, the problem of low fault reporting efficiency in related technologies is solved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of computers, and more specifically, to a fault reporting method and device, a storage medium, and an electronic device. Background Art

[0002] In the prior art, such as servers on the Ampere Altra platform, fault reporting strategies are often fixed and inflexible, which may result in correctable errors (CE) being reported to the OS or BMC, thereby increasing the system overhead of handling faults and reducing the overall efficiency of the system.

[0003] Therefore, there is a technical problem in the prior art that the efficiency of fault reporting is low. Summary of the invention

[0004] The embodiments of the present application provide a fault reporting method and device, a storage medium, and an electronic device to at least solve the technical problem of low fault reporting efficiency in the related art.

[0005] According to an embodiment of the present application, a fault reporting method is provided, comprising: obtaining a fault type of a fault to be reported, wherein the fault to be reported is generated in a preset bus standard device; when the fault type is a correctable fault type, obtaining a first control parameter associated with the correctable fault type, wherein the first control parameter is used to perform global reporting control on the fault of the correctable fault type; when the first control parameter indicates that the fault of the correctable fault type is allowed to be reported, obtaining a second control parameter associated with the correctable fault type, wherein the second control parameter is used to perform local reporting control on the fault of the correctable fault type of the preset bus standard device; when the second control parameter indicates that the fault of the correctable fault type of the preset bus standard device is allowed to be reported, obtaining the first reporting parameter associated with the fault to be reported, reading the fault management address to be reported from the first reporting parameter, and reporting the fault to be reported to the fault management address.

[0006] According to another embodiment of the present application, a fault reporting device is provided, including: a first acquisition unit, used to acquire a fault type of a fault to be reported, wherein the fault to be reported is generated in a preset bus standard device; a second acquisition unit, used to acquire a first control parameter associated with a correctable fault type when the fault type is a correctable fault type, wherein the first control parameter is used to perform global reporting control on faults of the correctable fault type; a third acquisition unit, used to acquire a second control parameter associated with the correctable fault type when the first control parameter indicates that a fault of the correctable fault type is allowed to be reported, wherein the second control parameter is used to perform local reporting control on faults of the correctable fault type of the preset bus standard device; a reporting unit, used to acquire the first reporting parameter associated with the fault to be reported when the second control parameter indicates that a fault of the correctable fault type of the preset bus standard device is allowed to be reported, read the fault management address to be reported from the first reporting parameter, and report the fault to be reported to the fault management address.

[0007] According to another embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0008] According to another embodiment of the present application, an electronic device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0009] According to another embodiment of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps of the method in each embodiment of the present application are implemented.

[0010] Through the embodiments provided by the present application, first, the fault type of the fault to be reported is obtained to ensure that the nature of the error can be identified and distinguished; secondly, when the fault type is confirmed to be a correctable type fault, a first control parameter is obtained, which is used to globally control the reporting of the correctable type fault; further, when the first control parameter allows reporting, a second control parameter is obtained, which is a more local and more specific control, used to control the reporting of the correctable type fault for a specific preset bus standard device; finally, under the premise that the second control parameter also allows reporting, the first reporting parameter associated with the fault to be reported is read, and the fault management address (such as OS or BMC) is identified from the parameter, so as to report the fault information to the specified management address. In this way, accurate distribution of error information can be achieved to ensure that errors are correctly processed and recorded. System administrators can dynamically adjust the reporting strategy of correctable type faults according to actual needs, such as globally shielding the reporting of correctable type faults of various devices under high load conditions, or locally shielding the reporting of correctable type faults of specific devices to avoid performance degradation caused by error processing overhead. At the same time, more detailed control can be performed on correctable type faults of specific devices. Through this multi-level, customizable error reporting control strategy, the server's operating efficiency and the flexibility of fault management are significantly improved, achieving the technical effect of improving the efficiency of fault reporting. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 is a hardware structure block diagram of a fault reporting method according to an embodiment of the present application;

[0012] Figure 2 is a flow chart of a fault reporting method according to an embodiment of the present application;

[0013] Figure 3 is a flow chart of another fault reporting method according to an embodiment of the present application;

[0014] Figure 4 It is a structural block diagram of a fault reporting device according to an embodiment of the present application. DETAILED DESCRIPTION

[0015] The embodiments of the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0016] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0017] In order to help you better understand the method embodiments provided in the present invention, the relevant abbreviations and key terms are explained below.

[0018] DXE: Driver Execution Environment, UEFI performs most of the system initialization work at this stage.

[0019] BlOS: Basic Input Output System, basic input output system, generally refers to UEFl.

[0020] Altra: Ampere's first generation ARM CPU, designed for cloud native, provides consistent and predictable performance for big data scenarios. Its high core count, excellent single-threaded performance, and consistent frequency enable big data workloads to scale out very effectively.

[0021] Grace: A CPU designed for large-scale AI and HPC released by NVIDIA, it uses energy-efficient Arm cores and achieves a 10x performance improvement for systems training giant AI models. Together with GPUs and DPUs, Grace provides NVIDIA with a third foundational technology for computing and the ability to reconstruct data centers to advance AI development.

[0022] ATF: ATF (ARM Trusted Firmware) is an open source security firmware provided by ARM, which is designed to provide root of trust and secure boot functions for systems based on ARM architecture. ATF (ARM Trusted Firmware) achieves hardware-level isolation through TrustZone technology, provides isolation between secure and non-secure areas at the hardware level, ensures the protection of sensitive data and code, and ensures that secure and non-secure components in the system can run independently of each other, thereby improving the security of the system.

[0023] UEFI: Unified Extensible Firmware Interface (UEFI) is a personal computer system specification that defines the software interface between the operating system and the system firmware as an alternative to BIOS. The Extensible Firmware Interface is responsible for the power-on self-test (POST), contacting the operating system, and providing an interface between the operating system and the hardware.

[0024] RAS: (Reliabilty, Availability, Serviceability) is the requirement for a server to be used reliably, namely reliability, availability, and maintainability. Its realization requires the close combination of software and hardware.

[0025] PCI-Express (Peripheral Component Interconnect Express) is a high-speed serial computer expansion bus standard. Its original name was "3GIO". It was proposed by Intel in 2001 to replace the old PCI, PCI-X and AGP bus standards. This article mainly refers to PCIe devices, such as hard disks and network cards.

[0026] BMC: Baseboard Management Controller (BMC) is a dedicated controller used to monitor and manage servers. In layman's terms, BMC is an independent system under the host server system.

[0027] CE: Correct Error, refers to correctable errors.

[0028] UE: Uncorrect Error, refers to an uncorrectable error.

[0029] The method embodiments provided in the embodiments of the present application can be executed in a computer terminal or a similar computing device. Taking running on a computer terminal as an example, Figure 1 1 is a hardware structure block diagram of a computer terminal of a fault reporting method according to an embodiment of the present application. Figure 1 As shown, the computer terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the above-mentioned computer terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1The structure shown is only for illustration and does not limit the structure of the above-mentioned computer terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0030] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method for determining the mapping relationship in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0031] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of a computer terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0032] As an optional solution, the fault reporting method includes the following specific steps:

[0033] S202, obtaining a fault type of a fault to be reported, wherein the fault to be reported is generated in a preset bus standard device;

[0034] S204, when the fault type is a correctable fault type, obtaining a first control parameter associated with the correctable fault type, wherein the first control parameter is used to perform global reporting control on faults of the correctable fault type;

[0035] S206, when the first control parameter indicates that a fault of a correctable fault type is allowed to be reported, obtaining a second control parameter associated with the correctable fault type, wherein the second control parameter is used to perform local reporting control on the fault of the correctable fault type of the preset bus standard device;

[0036] S208, when the second control parameter indicates that the fault of the correctable fault type of the preset bus standard device is allowed to be reported, obtain the first reporting parameter associated with the fault to be reported, read the fault management address to be reported from the first reporting parameter, and report the fault to be reported to the fault management address.

[0037] Optionally, in this embodiment, the preset bus standard device refers to a hardware device connected to the server using a standard bus protocol (such as PCIe), including but not limited to a hard disk, a network card, a GPU, etc. The correctable fault type may be, but is not limited to, a fault type that may be encountered during the operation of the device and can be corrected by hardware self-repair or software intervention, such as a single-bit error in an ECC memory.

[0038] Optionally, in this embodiment, the first control parameter is a parameter used to globally control the reporting of faults of correctable fault types, which determines whether to allow all types of faults of correctable fault types (hereinafter referred to as CE) to be reported to the system fault management area, such as OS and / or BMC. The second control parameter is a parameter used to locally control CE reporting, which determines whether to perform reporting control on the CE of a specific preset bus standard device, allowing more detailed adjustment of the CE reporting strategy of a single device. The first reporting parameter is a parameter containing management address information to which the reported fault should be sent, such as the address of the OS kernel, BMC or remote monitoring server. The fault management address is the address of the system management component that receives and processes server fault information, which can be OS, BMC, remote monitoring center, etc.

[0039] Optionally, in this embodiment, it is first necessary to identify and classify the faults generated by the preset bus standard device and confirm the fault type, wherein the fault type may include but is not limited to correctable fault type and uncorrectable fault type. For example, when the server detects CE on the PCIe device, the nature of the error will be further analyzed, which is the basis for the subsequent implementation of the control strategy.

[0040] Optionally, in this embodiment, once the fault is confirmed to be a CE, a first control parameter associated with the CE type is searched. The first control parameter is used to determine whether to globally allow reporting of this type of CE. For example, a global parameter is set to shield CE reporting of all devices to reduce the impact of fault management on performance in high-load scenarios.

[0041] Optionally, in this embodiment, if the first control parameter allows CE reporting, then a second control parameter is further obtained. The second control parameter allows local control of CE reporting of a specific preset bus standard device (such as a specific PCIe hard disk). For example, the server may choose to only block CE reporting of some high-latency PCIe devices, while allowing CE reporting of other devices to ensure stable operation of key devices.

[0042] Optionally, in this embodiment, after the CE of a specific preset bus standard device is allowed to report, the first reporting parameter is read to determine the specific fault management address. Subsequently, the fault is reported to the specified management address, such as the error management module of the BMC or OS. This mechanism ensures that the fault information can be correctly received and processed, avoiding redundant reporting and processing delays.

[0043] It should be noted that this embodiment introduces a multi-level control mechanism to achieve dynamic and precise management of CE reports. Not only does it take into account the global management of CE, but it also provides local control for specific devices, while ensuring that fault information can be correctly processed, reducing redundant reports and processing delays, significantly improving the operating efficiency of the server and the flexibility of fault management, and helping to better balance system performance and reliability to meet the needs of different scenarios. In high-load or sensitive business scenarios, you can avoid performance degradation due to error processing overhead by shielding all or some CE reports. In scenarios that require high reliability, you can turn on reporting for all CEs to ensure that potential problems are discovered and handled as soon as possible to avoid critical system failures.

[0044] In addition, this embodiment also provides intelligent management and secure transmission of error information, ensuring the security of data during the reporting process and avoiding the leakage of sensitive information. By combining intelligent analysis, the system can predict future error patterns based on error types and historical data, adjust reporting strategies in advance, and achieve more forward-looking error management.

[0045] Through the embodiments provided by the present application, first, the fault type of the fault to be reported is obtained to ensure that the nature of the error can be identified and distinguished; secondly, when the fault type is confirmed to be a correctable type fault, a first control parameter is obtained, which is used to globally control the reporting of the correctable type fault; further, when the first control parameter allows reporting, a second control parameter is obtained, which is a more local and more specific control, used to control the reporting of the correctable type fault for a specific preset bus standard device; finally, under the premise that the second control parameter also allows reporting, the first reporting parameter associated with the fault to be reported is read, and the fault management address (such as OS or BMC) is identified from the parameter, so as to report the fault information to the specified management address. In this way, accurate distribution of error information can be achieved to ensure that errors are correctly processed and recorded. System administrators can dynamically adjust the reporting strategy of correctable type faults according to actual needs, such as globally shielding the reporting of correctable type faults of various devices under high load conditions, or locally shielding the reporting of correctable type faults of specific devices to avoid performance degradation caused by error processing overhead. At the same time, more detailed control can be performed on correctable type faults of specific devices. Through this multi-level, customizable error reporting control strategy, the server's operating efficiency and the flexibility of fault management are significantly improved, achieving the technical effect of improving the efficiency of fault reporting.

[0046] As an optional solution, after obtaining the second control parameter associated with the correctable fault type, the method further includes:

[0047] When the second control parameter indicates that reporting of a fault of a correctable fault type of a preset bus standard device is prohibited, obtaining a first identification parameter of the fault to be reported;

[0048] The first identification parameter is set and written back, wherein the fault to be reported after the setting and writing back is prohibited from being reported.

[0049] Optionally, in this embodiment, the second control parameter is a control parameter specific to the preset bus standard device, which is used to locally control the CE reporting strategy of the preset bus standard device and can be set to allow or prohibit CE reporting of the preset bus standard device.

[0050] Optionally, in this embodiment, the first identification parameter is an identification bit related to the fault to be reported, which is used to mark whether the fault to be reported is allowed to be reported to the system management component. For example, if the identification bit is set, it indicates that the fault is prohibited from being reported.

[0051] Optionally, in this embodiment, when it is detected that the second control parameter indicates that the CE reporting of a specific device needs to be prohibited, the first identification parameter associated with the CE is read. This parameter can be set to a state of prohibiting reporting through a set operation in the configuration space of the device. Subsequently, the modified parameter is written back to the device to ensure that the device will no longer report this type of CE in the future. This process ensures the real-time and effectiveness of the error management strategy. Even during the operation of the server, the CE reporting strategy can be dynamically adjusted as needed to avoid unnecessary consumption of system resources.

[0052] It can be understood that the first identification parameter after setting the write-back, as a local switch for CE reporting control, limits the CE reporting of specific devices, which helps to maintain the operation of key services and applications of the system in performance-sensitive or resource-constrained scenarios.

[0053] Through the embodiment provided by the present application, by introducing the write-back operation of the first identification parameter, a local disabling function is provided for the CE report of a specific preset bus standard device. The multi-level fault reporting control method is further improved, the flexibility and reliability of the system are enhanced, and the operation efficiency of the server is optimized while meeting the requirements of different business scenarios.

[0054] As an optional solution, after obtaining the first control parameter associated with the correctable fault type, the method further includes:

[0055] When the first control parameter indicates that reporting of a fault of a correctable fault type is prohibited, obtaining a second identification parameter of all interfaces for reporting faults of the correctable fault type;

[0056] The second identification parameter is modified, wherein all interfaces after the modification are prohibited from reporting faults of the correctable fault type.

[0057] Optionally, in this embodiment, the first control parameter is a global control parameter, which is used to comprehensively decide whether to allow all types of CE reports, such as shielding CE reports of all CPUs, memories, and PCIe devices.

[0058] Optionally, in this embodiment, the second identification parameter is an identification parameter of all interfaces for reporting faults of all types of CEs. When the first control parameter indicates that CE reporting is prohibited, the second identification parameter will be read and corrected to ensure that CE reporting is prohibited on all interfaces.

[0059] Optionally, in this embodiment, when it is detected that the first control parameter indicates that all types of CE reporting is prohibited, the second identification parameter associated with the CE will be read. This step ensures that all possible requests to report CE can be identified and intercepted. Subsequently, the second identification parameter will be corrected, that is, its identification bit will be adjusted so that all reporting interfaces prohibit reporting on CE. This correction operation ensures the consistency and globality of the error reporting strategy, and can effectively control the reporting of CE even in a complex and changeable operating environment, avoiding unnecessary error handling and maintaining the system's resources and performance.

[0060] Through the embodiments provided in the present application, global disabling of all types of CEs can be achieved, which is crucial for maintaining the operation of key services and applications of the system under high load or resource-constrained scenarios.

[0061] As an optional solution, after obtaining the fault type of the fault to be reported, the method further includes:

[0062] In the case where the fault type is an uncorrectable fault type, the fault management address to be reported is read from the first reporting parameter, and the fault to be reported is reported to the fault management address.

[0063] Optionally, in this embodiment, the uncorrectable fault type (UE) is a fault type encountered by the device during operation that cannot be resolved by hardware self-repair or software intervention, and such faults may pose a serious threat to system stability and data integrity.

[0064] Optionally, in this embodiment, the first reporting parameter is a parameter including management address information of the fault to be reported, and is used to instruct to report the fault information to a correct management component, such as an OS kernel, a BMC or a remote monitoring server.

[0065] It is understandable that when the fault type is confirmed to be an uncorrectable fault type, the fault management address information will be immediately read from the first reporting parameter. This information has been stored in the first reporting parameter according to the preset fault management strategy when the system is started, ensuring that when an uncorrectable fault type occurs, the system can quickly locate and report it to the specified management address. Subsequently, the system reports the uncorrectable fault type to this address, triggering the uncorrectable fault type response process of the management component, including but not limited to error log recording, fault diagnosis, and alarm notification. This reporting process ensures that the uncorrectable fault type is handled in a timely manner, avoids the deterioration of the fault, and protects the stability of the system and data integrity.

[0066] Through the embodiments provided by this application, it is possible to achieve rapid response and reporting of uncorrectable fault types, which is crucial to ensure high reliability and high availability of the server. It not only improves the multi-level fault reporting control framework, but also ensures that the system can take effective emergency measures when facing uncorrectable fault types, avoiding the impact of faults on business operations and improving the overall operation and maintenance management level of the system.

[0067] As an optional solution, report the unreported fault to the fault management address, including one of the following:

[0068] When the first reporting parameter indicates that the fault management address is an operating system address, reporting the fault to be reported to the operating system;

[0069] When the first reporting parameter indicates that the fault management address is a baseboard management controller address, reporting the fault to be reported to the baseboard management controller;

[0070] When the first reporting parameter indicates that the fault management address is the operating system address and the baseboard management controller address, the fault to be reported is reported to the operating system and the baseboard management controller.

[0071] Optionally, in this embodiment, the fault management address is the address of a specific component in the system that receives and manages fault information, which may be the address of an OS kernel, a BMC, or a remote monitoring server, and is used to guide the reporting direction of the fault to be reported.

[0072] Optionally, in this embodiment, the operating system address refers to the address of an error management module in the OS kernel, which is used to process error information generated by bus standard devices, such as CE and UE.

[0073] Optionally, in this embodiment, the baseboard management controller address refers to the address of the BMC, which is a hardware component specifically used to manage servers. It is used to monitor and manage server hardware status, such as temperature, voltage, and fan speed, and is also responsible for receiving and processing error information from server hardware.

[0074] Optionally, in this embodiment, three reporting path selection mechanisms are described, namely reporting to OS, reporting to BMC, or reporting to both at the same time, depending on the fault management address indication in the first reporting parameter. The implementation of this mechanism not only enhances the flexibility of fault reporting, but also ensures that fault information can be correctly processed, avoids processing delays or redundant reporting, and maintains efficient operation of the system.

[0075] In the path of reporting to the OS, the system directly reports the fault information to the error management module of the OS by reading the operating system address in the first reporting parameter, triggering the OS error handling process, such as error analysis, logging, and system reset, etc., which is suitable for fault scenarios that require OS intervention.

[0076] The path for reporting to BMC ensures that fault information can be received by a hardware management unit independent of the OS. BMC can independently diagnose and record faults and trigger alarm notifications. This is suitable for situations where the OS is unavailable or needs to maintain stable operation. For example, when the OS crashes or restarts, BMC can continue to manage the server hardware status to ensure uninterrupted system monitoring and management.

[0077] Finally, the path of reporting to both the OS and BMC reflects the synergy of system management. It is suitable for scenarios where the OS and BMC need to work together to quickly respond to and handle faults, such as critical hardware failures or system-level errors. This ensures that the system can respond to faults in an all-round and multi-level manner, and improves the comprehensiveness and efficiency of fault management.

[0078] Through the embodiments provided in the present application, by introducing three different reporting paths, a wider range of choices is provided for the fault reporting strategy of the platform server, ensuring that the fault information can be processed correctly and promptly according to its characteristics and system requirements.

[0079] As an optional solution, obtaining a first control parameter associated with a correctable fault type includes: reading the first control parameter from an option setting;

[0080] Acquiring a second control parameter associated with the correctable fault type includes: reading the second control parameter from an option setting;

[0081] The option setting includes a plurality of control switches, and each control switch corresponds to the content indicated by a control parameter.

[0082] Optionally, in this embodiment, the option setting is a series of configuration options preset in the system, including control switches for reporting strategies for correctable type faults (CE) and uncorrectable type faults (UE), which are set by the user or system administrator as needed before the server is started.

[0083] Optionally, in this embodiment, the control switch is a function in the option setting, used to enable or disable specific control parameters, such as whether to shield all CEs (through the first control parameter), or whether to shield the CE of a specific device (such as a PCIe device) (through the second control parameter).

[0084] Optionally, in this embodiment, by reading the control switch in the option setting, the first and second control parameters associated with the CE type can be obtained, which provides a basis for dynamically adjusting the CE reporting strategy. The option setting is a series of configuration options preset in the system, including multiple control switches, each of which corresponds to the content indicated by a control parameter, such as the Mask_CE_ALL switch for global control of CE reporting and the Mask_PCI_E_CE_ONLY switch for local control of PCIe device CE reporting.

[0085] It is understandable that when the first or second control parameter needs to be obtained, the state of the corresponding control switch will be read directly from the option setting. This reading process ensures that the setting of the control parameter is consistent with the preset policy of the user or system administrator, so that the reporting behavior of CE can be dynamically adjusted according to the current system status and business needs. For example, if the Mask_CE_ALL switch is set to on, the system will globally block all CE reports; if

[0086] When the Mask_PCI_E_CE_ONLY switch is set to on, the system will mask the CE reporting of specific PCIe devices, providing more flexible and sophisticated control methods for server fault management.

[0087] Through the embodiments provided in this application, dynamic adjustment of the CE reporting strategy can be achieved, which not only enhances the flexibility of system fault management, but also improves the operating efficiency and reliability of the system, and builds a comprehensive, multi-level fault reporting control system that can adapt to business needs in different scenarios.

[0088] As an optional solution, after obtaining the fault type of the fault to be reported, the method further includes at least one of the following:

[0089] Obtaining a load state of a preset bus standard device when a fault to be reported occurs; when the load state indicates that the operating load level of the preset bus standard device is higher than a preset load threshold, prioritizing the faults of the uncorrectable fault type, wherein the fault type includes an uncorrectable fault type, a first uncorrectable fault with a priority level higher than a preset priority threshold is always allowed to be reported, and a second uncorrectable fault with a priority level lower than the preset priority threshold is prohibited from being reported within a first time period, and the first time period is a time period in which the operating load level of the preset bus standard device is higher than the preset load threshold;

[0090] Acquire the temperature status of the preset bus standard device when the fault to be reported occurs, wherein, when the temperature status indicates that the operating temperature of the preset bus standard device is higher than the preset temperature threshold, the first uncorrectable fault is always allowed to be reported, and the second uncorrectable fault is prohibited from being reported within a second time period, and the second time period is a time period when the operating temperature of the preset bus standard device is higher than the preset temperature threshold.

[0091] Optionally, in this embodiment, the load state refers to the resource occupancy of a preset bus standard device (such as a PCIe device) during operation, including processor usage, memory usage, network traffic, etc., which is used to evaluate whether the device is in a high-load operation state. The preset load threshold is a threshold preset in the system, which is used to determine whether the load state of the device has reached the high-load standard. When the load level of the device is higher than the threshold, a specific UE reporting strategy will be adopted.

[0092] Optionally, in this embodiment, the temperature state is the temperature condition when the device is in operation, which is used to evaluate whether the device is in an abnormally high temperature state, which may affect the stability and life of the device. The preset temperature threshold is a temperature threshold of the system, which is used to determine whether the temperature state of the device has reached the abnormally high temperature standard. When the operating temperature of the device is higher than the threshold, the system will adopt a specific UE reporting strategy.

[0093] Optionally, in this embodiment, not only the type of fault is taken into consideration, but also the load state and temperature state of the device when the fault occurs are further considered to dynamically adjust the reporting strategy of the UE. In the case of high load or abnormal temperature, the system will prioritize the UE to ensure that critical UEs are always allowed to report, while non-critical UEs are temporarily prohibited from reporting until the load or temperature returns to normal.

[0094] It is understandable that the complex environment and business requirements that the server may face in actual operation are fully considered. For example, in a high-load environment, if all UEs report to the system management component, it may further occupy valuable system resources, resulting in performance degradation or even system crash. Through priority classification, the system can ensure the reporting of key UEs while avoiding the impact of non-key UE reports on the system, thus maintaining the stable operation of the system.

[0095] In the case of abnormal temperature, the system also needs to prioritize UEs, because abnormal temperature may affect the stability and data integrity of the equipment, and improper handling may even cause permanent damage to the hardware. By giving priority to reporting critical UEs, the system can respond quickly and take measures to avoid significant impact of abnormal temperature on business operations.

[0096] Optionally, in this embodiment, the load status and temperature status of the device can be monitored in real time through, but not limited to, integrated sensors and monitoring modules. These data are used to evaluate whether the device is in a high load or abnormal temperature state, and are the basis for system decision-making. For example, the load status of the PCIe device can be evaluated by monitoring indicators such as processor usage, memory occupancy, and network traffic; the operating temperature of the device can be monitored through a built-in temperature sensor to determine whether it exceeds a preset temperature threshold.

[0097] Optionally, in this embodiment, when it is detected that the device is in a high load or abnormal temperature state, the UE is dynamically prioritized. This classification process ensures priority reporting and processing of critical UEs based on the nature of the UE (such as hardware failure, software failure or network failure), the potential impact range and the urgency of processing. For example, a UE with hardware failure may pose a threat to data security, and its priority will be higher than a UE with software failure; a UE with a wide impact range will have a higher priority than a UE with a local impact; a UE that needs to be processed urgently will have a higher priority than a UE that can be processed later.

[0098] Optionally, in this embodiment, the reporting strategy of the UE is adjusted based on the priority classification result. Critical UEs will always be allowed to report to system management components, such as the error management module or BMC of the OS, to ensure that these faults can be responded to and processed in a timely manner. Reporting by non-critical UEs may be temporarily prohibited until the load or temperature of the device returns to normal. This policy adjustment avoids the consumption of system resources by non-critical UE reports, improves the efficiency of critical UE processing, and ensures the stability and reliability of the system in a complex operating environment.

[0099] Through the embodiments provided in this application, the processing efficiency of key UEs is effectively improved in dealing with complex operating environments such as high load and temperature abnormalities, ensuring the stability and reliability of the system, which is of great significance to improving the operation and maintenance management level of data centers and high-performance computing fields.

[0100] As an optional solution, the above fault reporting method is applied to a scenario based on the management of the fault reporting policy of the Nvidia platform server. In this scenario, this embodiment provides a flexible fault reporting policy control method based on the Nvidia platform server based on the above fault reporting method. This method can dynamically adjust the fault reporting policy according to the preset control parameters and fault type, and realize the refined control of correctable errors (CE) and uncorrectable errors (UE). Specifically, it includes the following key steps:

[0101] (I) Create RAS policy control options

[0102] There are two options, one for CE and the other for UE. The control strategies of CE and UE are slightly different, as follows:

[0103] (1) CE category control options

[0104] MASK_PCIE_CE_ONLY: Since many users require separate shielding of PCIE CE, shielding PCIE CE is made an optional option that can be set to on or off.

[0105] MASK_CE_ALL: Mask the CE of CPU, memory and Pice, which can be set to on or off.

[0106] (2) CE reporting control options (not available when MASK_CE_ALL is enabled)

[0107] The Ce_ReportPolicy option has the following options.

[0108] ToBmc: Report only to the BMC.

[0109] ToOS: Report only to OS.

[0110] ToOSandBMC: Report to OS and BMC.

[0111] (3)UE reporting control options

[0112] The Ue_ReportPolicy option has the following options.

[0113] ToBmc: Report only to the BMC.

[0114] ToOS: Report only to OS.

[0115] ToOSandBMC: Report to OS and BMC.

[0116] (II) CE reporting strategy

[0117] (1) The option to read user settings during BIOS startup.

[0118] (2) If it is detected that MASK_PCIE_CE_ONLY is set to on, all PCIE devices are traversed, the CE Mask register in the PCIE device configuration space is read, the corresponding Mask flag bit is set to 1 and then written back, so that all PCIE devices will not report CE.

[0119] (3) If it is detected that MASK_CE_ALL is set to on, after receiving the error log, determine whether the error type is CE. If it is CE, set its flag to not report to OS / BMC when calling the NV RAS reporting interface.

[0120] (4) If both MASK_PCIE_CE_ONLY and MASK_CE_ALL are set to off, all CEs can be generated normally. First read the error information type. If it is CE, continue to read the Ce_ReportPolicy option value. If it is ToBmc, set the parameter sent to the BMC to 1 in the NV RAS reporting interface, and set the parameter sent to the OS to 0. If it is ToOS, set the parameter sent to the BMC to 0 in the NV RAS reporting interface, and set the parameter sent to the OS to 1. If it is ToOSandBMC, set the parameter sent to the BMC to 1 in the NV RAS reporting interface, and set the parameter sent to the OS to 1. If the parameter of the BMC or OS in the NV RAS reporting interface is set to 1, it indicates that the CE error is reported to the BMC or OS normally. If it is 0, it is not reported.

[0121] (III) Processing UE reporting strategy

[0122] (1) The option to read user settings during BIOS startup.

[0123] (2) First read the error information type. If it is UE, read the Ue_ReportPolicy option value. If it is ToBmc, set the parameter sent to BMC to 1 in the NV RAS reporting interface, and set the parameter sent to OS to 0. If it is ToOS, set the parameter sent to BMC to 0 in the NV RAS reporting interface, and set the parameter sent to OS to 1. If it is ToOSandBMC, set the parameter sent to OS to 1 in the NV RAS reporting interface, and set the parameter sent to BMC to 1. If the parameter of BMC or OS in the NV RAS reporting interface is set to 1, it indicates that the UE error is reported to BMC or OS normally. If it is 0, it is not reported.

[0124] To further illustrate, a functional implementation flow chart based on the above fault reporting method is as follows: Figure 3 As shown, including:

[0125] S302, detecting an error at an error source.

[0126] S304, read the error type.

[0127] S306: When the error type is UE type, read the Ue_ReportPolicy option value.

[0128] S308: Set RAS reporting interface parameters according to the Ue_ReportPolicy option value to complete error reporting.

[0129] S310: When the error type is CE, read the MASK_CE_ALL option value.

[0130] S312: When the MASK_CE_ALL option value indicates that it is turned on, set the RAS reporting interface parameters to prohibit error reporting.

[0131] S314, when the MASK_CE_ALL option value indicates off, read the MASK_PCIE_CE_ONLY option value.

[0132] S316, when the MASK_PCIE_CE_ONLY option value indicates that it is turned on, the PCIE CEMASK register is read and set and written to disable error reporting of the PCIE device.

[0133] S318: When the MASK_PCIE_CE_ONLY option value indicates closed, read the PCIE Ce_ReportPolicy option value.

[0134] S320: Set RAS reporting interface parameters according to the PCIE Ce_ReportPolicy option value to complete error reporting.

[0135] Through the embodiment provided by the present application, this embodiment implements a flexible way of managing server fault reporting based on the Nvidia Grace platform server, creates a RAS policy control option, which is used to control the reporting strategy of CE / UE; shields the CE of PCIE separately; parses the error information, and controls whether to report to OS or BMC according to the option setting. It enriches the fault reporting strategy on the NV Gracep platform and is easy to operate. It meets the needs of users and enhances the competitiveness of ARM server products.

[0136] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0137] In this embodiment, a fault reporting device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0138] Figure 4 is a structural block diagram of a fault reporting device according to an embodiment of the present application, such as Figure 4 As shown, the device comprises:

[0139] A first acquisition unit 402 is used to acquire a fault type of a fault to be reported, wherein the fault to be reported is generated in a preset bus standard device;

[0140] A second acquisition unit 404 is used to acquire a first control parameter associated with the correctable fault type when the fault type is a correctable fault type, wherein the first control parameter is used to perform global reporting control on the fault of the correctable fault type;

[0141] A third acquisition unit 406 is used to acquire a second control parameter associated with the correctable fault type when the first control parameter indicates that the fault of the correctable fault type is allowed to be reported, wherein the second control parameter is used to perform local reporting control on the fault of the correctable fault type of the preset bus standard device;

[0142] The reporting unit 408 is used to obtain the first reporting parameter associated with the fault to be reported, read the fault management address to be reported from the first reporting parameter, and report the fault to be reported to the fault management address when the second control parameter indicates that the correctable fault type of the preset bus standard device is allowed to be reported.

[0143] As an optional solution, the device also includes:

[0144] A first acquisition module is used to acquire a first identification parameter of a to-be-reported fault after acquiring a second control parameter associated with a correctable fault type, when the second control parameter indicates that reporting of a fault of a correctable fault type of a preset bus standard device is prohibited;

[0145] The setting module is used to set and write back the first identification parameter after acquiring the second control parameter associated with the correctable fault type, wherein the fault to be reported after the setting and writing back is prohibited from being reported.

[0146] As an optional solution, the device also includes:

[0147] A second acquisition module is used to, after acquiring the first control parameter associated with the correctable fault type, acquire second identification parameters of all interfaces used to report faults of the correctable fault type when the first control parameter indicates that reporting of the fault of the correctable fault type is prohibited;

[0148] The correction module is used to correct the second identification parameter after obtaining the first control parameter associated with the correctable fault type, wherein all interfaces after the correction are prohibited from reporting faults of the correctable fault type.

[0149] As an optional solution, the device also includes:

[0150] The first reading module is used to, after obtaining the fault type of the fault to be reported, read the fault management address to be reported from the first reporting parameter when the fault type is an uncorrectable fault type, and report the fault to be reported to the fault management address.

[0151] As an optional solution, the reporting unit 408 includes one of the following:

[0152] A first reporting module, configured to report the fault to be reported to the operating system when the first reporting parameter indicates that the fault management address is the operating system address;

[0153] A second reporting module, configured to report the fault to be reported to the baseboard management controller when the first reporting parameter indicates that the fault management address is the baseboard management controller address;

[0154] The third reporting module is used to report the fault to be reported to the operating system and the baseboard management controller when the first reporting parameter indicates that the fault management address is the operating system address and the baseboard management controller address.

[0155] As an optional solution, the second acquisition unit 404 includes: a second reading module, configured to read the first control parameter from the option setting;

[0156] The third acquisition unit 406 includes: a third reading module, configured to read the second control parameter from the option setting;

[0157] The option setting includes a plurality of control switches, and each control switch corresponds to the content indicated by a control parameter.

[0158] As an optional solution, the device further includes at least one of the following:

[0159] A third acquisition module is used to obtain the load state of the preset bus standard device when the fault to be reported occurs after obtaining the fault type of the fault to be reported; a classification module is used to classify the faults of the uncorrectable fault type according to the priority level after obtaining the fault type of the fault to be reported, when the load state indicates that the operating load level of the preset bus standard device is higher than the preset load threshold, wherein the fault type includes the uncorrectable fault type, the first uncorrectable fault with a priority level higher than the preset priority threshold is always allowed to be reported, and the second uncorrectable fault with a priority level lower than the preset priority threshold is prohibited from being reported within a first time period, and the first time period is a time period in which the operating load level of the preset bus standard device is higher than the preset load threshold;

[0160] The fourth acquisition module is used to obtain the temperature status of the preset bus standard device when the fault to be reported occurs after obtaining the fault type of the fault to be reported, wherein, when the temperature status indicates that the operating temperature of the preset bus standard device is higher than the preset temperature threshold, the first uncorrectable fault is always allowed to be reported, and the second uncorrectable fault is prohibited from being reported within a second time period, and the second time period is a time period when the operating temperature of the preset bus standard device is higher than the preset temperature threshold.

[0161] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0162] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0163] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0164] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0165] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0166] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0167] An embodiment of the present application further provides a computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores the computer program product, and when the computer program is executed by a processor, the steps of the method in each embodiment of the present application are implemented.

[0168] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0169] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0170] The above are only preferred embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A fault reporting method, characterized in that: include: Obtaining a fault type of a fault to be reported, wherein the fault to be reported is generated in a preset bus standard device; In the case where the fault type is a correctable fault type, obtaining a first control parameter associated with the correctable fault type, wherein the first control parameter is used to perform global reporting control on the fault of the correctable fault type; In the case where the first control parameter indicates that the fault of the correctable fault type is allowed to be reported, obtaining a second control parameter associated with the correctable fault type, wherein the second control parameter is used to perform local reporting control on the fault of the correctable fault type of the preset bus standard device; When the second control parameter indicates that the correctable fault type of the preset bus standard device is allowed to be reported, obtain the first reporting parameter associated with the fault to be reported, read the fault management address to be reported from the first reporting parameter, and report the fault to be reported to the fault management address.

2. The method according to claim 1, characterized in that After obtaining the second control parameter associated with the correctable fault type, the method further includes: When the second control parameter indicates that the fault of the correctable fault type of the preset bus standard device is prohibited from being reported, obtaining a first identification parameter of the fault to be reported; The first identification parameter is set and written back, wherein the fault to be reported after the setting and writing back is prohibited from being reported.

3. The method according to claim 1, characterized in that After obtaining the first control parameter associated with the correctable fault type, the method further includes: When the first control parameter indicates that reporting of the fault of the correctable fault type is prohibited, obtaining a second identification parameter of all interfaces for reporting the fault of the correctable fault type; The second identification parameter is modified, wherein after the modification, all the interfaces are prohibited from reporting faults of the correctable fault type.

4. The method according to claim 1, characterized in that: After obtaining the fault type of the fault to be reported, the method further includes: In a case where the fault type is an uncorrectable fault type, the fault management address to be reported is read from the first reporting parameter, and the fault to be reported is reported to the fault management address.

5. The method according to claim 4, characterized in that Reporting the to-be-reported fault to the fault management address includes one of the following: When the first reporting parameter indicates that the fault management address is an operating system address, reporting the fault to be reported to the operating system; When the first reporting parameter indicates that the fault management address is a baseboard management controller address, reporting the fault to be reported to the baseboard management controller; When the first reporting parameter indicates that the fault management address is the operating system address and the baseboard management controller address, the fault to be reported is reported to the operating system and the baseboard management controller.

6. The method according to any one of claims 1 to 5, characterized in that: The obtaining of the first control parameter associated with the correctable fault type comprises: reading the first control parameter from option settings; The obtaining of the second control parameter associated with the correctable fault type comprises: reading the second control parameter from the option setting; The option setting includes a plurality of control switches, and each control switch corresponds to a content indicated by a control parameter.

7. The method according to any one of claims 1 to 5, after obtaining the fault type of the fault to be reported, the method further comprises at least one of the following: Obtaining the load state of the preset bus standard device when the fault to be reported occurs; and prioritizing the uncorrectable fault type when the load state indicates that the operating load level of the preset bus standard device is higher than a preset load threshold, wherein: The fault type includes the uncorrectable fault type, a first uncorrectable fault with a priority classification higher than a preset priority threshold is always allowed to be reported, and a second uncorrectable fault with a priority classification lower than the preset priority threshold is prohibited from being reported within a first time period, and the first time period is a time period in which the operating load degree of the preset bus standard device is higher than the preset load threshold; Obtaining a temperature state of the preset bus standard device when the fault to be reported occurs, wherein, when the temperature state indicates that the operating temperature of the preset bus standard device is higher than a preset temperature threshold, the first uncorrectable fault is always allowed to be reported, and the second uncorrectable fault is prohibited from being reported within a second time period, and the second time period is a time period when the operating temperature of the preset bus standard device is higher than the preset temperature threshold.

8. A fault reporting device, characterized in that: include: A first acquisition unit is used to acquire a fault type of a fault to be reported, wherein the fault to be reported is generated in a preset bus standard device; A second acquisition unit, configured to acquire, when the fault type is a correctable fault type, a first control parameter associated with the correctable fault type, wherein the first control parameter is used to perform global reporting control on faults of the correctable fault type; A third acquisition unit is used to acquire a second control parameter associated with the correctable fault type when the first control parameter indicates that the fault of the correctable fault type is allowed to be reported, wherein the second control parameter is used to perform local reporting control on the fault of the correctable fault type of the preset bus standard device; A reporting unit is used to obtain a first reporting parameter associated with the fault to be reported, read the fault management address to be reported from the first reporting parameter, and report the fault to be reported to the fault management address when the second control parameter indicates that a correctable fault type of a preset bus standard device is allowed to be reported.

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

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

Images