Server-based hard disk common-mode fault analysis method and device, equipment and medium

Abstract

The invention relates to the technical field of disks, and discloses a server-based hard disk common-mode fault analysis method, device, equipment and medium, and the method comprises the steps: determining fault related parts according to the pre-collected type and fault mode data of a hard disk of a server; determining a primary fault factor based on the fault-related component; and analyzing the main fault factor, establishing a fault model corresponding to the main fault factor, and determining a common-mode fault factor of the server based on the fault model. According to the scheme, the types and the fault modes of the hard disks of the server are classified, the potential fault factors are effectively identified by deeply analyzing the working environment and the use mode of the hard disks from the perspective of the common-mode faults of the hard disks, and the fault detection accuracy is improved based on the analysis of the main fault factors. And corresponding fault models are respectively established for the main fault factors, so that the analysis of the common-mode failure risk is realized, the capability of identifying potential problems is improved, and a data basis is provided for subsequently taking targeted prevention measures.

Description

Technical Field

[0001] The present invention relates to the field of disk technology, and in particular to a server-based hard disk common mode failure analysis method, device, equipment and medium. Background Art

[0002] With the rapid development of emerging industries such as cloud computing, artificial intelligence, and big data, the server industry has also entered a stage of rapid development. More and more companies and industries have begun to build their own computer rooms, and rack servers have been widely used. In these servers, hard disks are key components, and their reliability is crucial. According to statistics from a cloud service provider, the average annual failure rate of HDDs (hard disk drives) is about 1.4%, and the average annual failure rate of SSDs (solid state drives) is about 1%. As the main carrier of data storage, the failure of hard disks may cause business delays or interruptions, system freezes or crashes, and even cause irrecoverable loss of critical data.

[0003] In related technologies, the prediction of hard disk failures often focuses on the failure or life of a single hard disk, mainly by monitoring the hard disk's own SMART (Self-Monitoring Analysis and Report Technology) parameters, using algorithms and models determined by offline training to predict the time or probability of future hard disk failures. However, related technologies do not provide sufficient analysis of the specific causes of failures, especially when facing batch failures of hard disks for the same customer or in a computer room. There is a lack of analysis of common mode failure risks and the ability to identify potential problems, which cannot provide strong support for failure prevention measures, R&D design, and test improvement. Summary of the invention

[0004] In view of this, the present invention provides a server-based hard disk common mode failure analysis method, device, equipment, and medium to solve the technical problem of lack of common mode risk analysis and potential problem identification.

[0005] In a first aspect, the present invention provides a server-based hard disk common mode failure analysis method, the method comprising: determining failure-related components based on pre-collected server hard disk type and failure mode data; determining main failure factors based on the failure-related components; analyzing the main failure factors, establishing a failure model corresponding to the main failure factors, and determining the common mode failure factors of the server to be tested based on the failure model.

[0006] In combination with the first aspect, in a possible implementation of the first aspect, fault-related components are determined according to the type and failure mode of the hard disk of the server, including: determining a first module, a second module, and a third module based on the type of the hard disk of the server and functional categories of components of the hard disk; and determining fault-related components corresponding to the first module, the second module, and the third module, respectively, based on the failure modes of the first module, the second module, and the third module.

[0007] In combination with the first aspect, in a possible implementation of the first aspect, the main fault factor is determined based on the fault-related components, including: based on the fault-related components corresponding to the first module, the second module, and the third module, respectively, determining the influencing factors of the fault-related components corresponding to each module and the correlation between the influencing factors; based on the correlation and influencing factors corresponding to each module, respectively, determining the main fault factor of the corresponding module.

[0008] In combination with the first aspect, in a possible implementation of the first aspect, the main failure factors of the corresponding modules are determined based on the association relationships and influencing factors corresponding to each module, including: based on the association relationships between the influencing factors of the first module, screening the influencing factors corresponding to the first module, and determining the main influencing factors therein; analyzing the main influencing factors, and determining the first influencing factors that produce the main influencing factors; and determining the main failure factors corresponding to the first module based on the main influencing factors and the first influencing factors.

[0009] In combination with the first aspect, in a possible implementation of the first aspect, the main failure factor of the corresponding module is determined based on the association relationship and influencing factors corresponding to each module, including: based on the association relationship between the influencing factors of the second module, analyzing the influencing factors corresponding to the second module, and determining the main failure factor corresponding to the second module.

[0010] In combination with the first aspect, in a possible implementation method of the first aspect, the main failure factors of the corresponding modules are determined based on the association relationships and influencing factors corresponding to each module, including: determining environmental factors consistent with the working environment of the server based on the association relationship between the influencing factors of the third module; and determining the main failure factors corresponding to the third module based on the environmental factors.

[0011] In combination with the first aspect, in a possible implementation of the first aspect, the main fault factors are analyzed and a fault model corresponding to the main fault factors is established, including: analyzing the main fault factors to determine the type of parameter information corresponding to the main fault factors; in response to the parameter information corresponding to the main fault factors having corresponding thresholds, establishing fault judgment models corresponding to the main fault factors based on the corresponding thresholds; in response to the parameter information corresponding to the main fault factors not having corresponding thresholds, establishing fault physical models corresponding to the main fault factors based on the parameter information corresponding to the main fault factors.

[0012] In combination with the first aspect, in a possible implementation of the first aspect, the parameter information corresponding to the main fault factor includes: head flying height, and the steps of establishing the fault determination models corresponding to the main fault factors based on the corresponding thresholds respectively include: The fault judgment model corresponding to the head flying height is established by the following formula:

[0013] in, H FAFH-T Indicates the head flying height threshold, Indicates i Disk No. j The flying height of the magnetic head, Indicates i The average flying height of all heads on a disk, a Indicates parameter deviation.

[0014] In combination with the first aspect, in a possible implementation of the first aspect, the parameter information corresponding to the main fault factor includes: the number of bad sectors, and the steps of establishing the fault determination models corresponding to the main fault factors based on the corresponding thresholds respectively include: The fault judgment model corresponding to the number of bad sectors is established through the following formula:

[0015] in, H Glist-T Indicates the bad sector number threshold. Indicates i The number of bad sectors on each disk, Indicates i Disks T 2 The number of bad sectors at the moment, Indicates i Disks T 1 The number of bad sectors at the moment, b Represents parameter deviation.

[0016] In combination with the first aspect, in a possible implementation manner of the first aspect, the parameter information corresponding to the main fault factor includes: high-frequency vibration, and the steps of establishing the fault determination models corresponding to the main fault factors based on the corresponding thresholds respectively include: The fault judgment model corresponding to high-frequency vibration is established through the following formula:

[0017] in, H fre-T represents the high frequency vibration threshold, Indicates the vibration frequency of the disk.

[0018] In combination with the first aspect, in a possible implementation manner of the first aspect, the parameter information corresponding to the main fault factor includes: impact, and the steps of establishing the fault determination models corresponding to the main fault factors based on the corresponding thresholds respectively include: The fault judgment model corresponding to the impact is established through the following formula:

[0019] in, H G-T represents the shock threshold, Indicates the impact of the disk G value.

[0020] In combination with the first aspect, in a possible implementation manner of the first aspect, the parameter information corresponding to the main fault factor includes: voltage, and the steps of establishing the fault physical model corresponding to the main fault factor based on the parameter information corresponding to the main fault factor respectively include: The fault physical model corresponding to the floating gate oxide layer degradation is established by the following formula:

[0021] in, OF TDDB represents the fault physics model corresponding to floating gate oxide degradation, r represents the electric field acceleration, v h Indicates the actual voltage of the floating gate oxide layer, v n Indicates the standard voltage of the floating gate oxide layer, t ox Indicates the thickness of the floating gate oxide layer.

[0022] In combination with the first aspect, in a possible implementation manner of the first aspect, the parameter information corresponding to the main fault factor includes: current, and the steps of establishing the fault physical model corresponding to the main fault factor based on the parameter information corresponding to the main fault factor respectively include: The fault physics model corresponding to hot carrier injection is established by the following formula:

[0023] in, OF HCI represents the fault physics model corresponding to hot carrier injection, I subh represents the actual substrate current, I subn Indicates the substrate standard current.

[0024] In combination with the first aspect, in a possible implementation manner of the first aspect, the parameter information corresponding to the main fault factor includes: temperature, and the steps of establishing the fault physical model corresponding to the main fault factor based on the parameter information corresponding to the main fault factor respectively include: The physical model of failure corresponding to solder joint fatigue is established by the following formula:

[0025] in, OF T represents the failure physics model corresponding to solder joint fatigue, T n Indicates the operating temperature of the disk when the environment dimension is c. T h Indicates the actual operating temperature of the disk.

[0026] In combination with the first aspect, in a possible implementation of the first aspect, the step of determining the common mode failure factor of the server to be tested based on the fault model includes: obtaining parameter information corresponding to the server to be tested and the main failure factor; and determining the common mode failure factor of the server to be tested based on the parameter information and the corresponding fault model.

[0027] In combination with the first aspect, in a possible implementation of the first aspect, obtaining parameter information corresponding to the server to be tested and the main failure factors includes: obtaining parameter information corresponding to the server to be tested and the main failure factors based on an offline and / or online method.

[0028] In a second aspect, the present invention provides a server-based hard disk common mode failure analysis device, the device comprising: a component determination module, used to determine the failure-related components according to the pre-collected type and failure mode data of the server's hard disk; a factor determination module, used to determine the main failure factors based on the failure-related components; a model establishment module, used to analyze the main failure factors, establish a failure model corresponding to the main failure factors, and determine the common mode failure factors of the server to be tested based on the failure model.

[0029] In combination with the second aspect, in a possible implementation of the first aspect, the device also includes: an information acquisition module, used to obtain parameter information corresponding to the server to be tested and the main fault factor; a common mode factor determination module, used to determine the common mode failure factor of the server to be tested based on the parameter information and the corresponding fault model.

[0030] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the server-based hard disk common mode failure analysis method of the above-mentioned first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0031] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the server-based hard disk common mode failure analysis method of the above-mentioned first aspect or any corresponding embodiment thereof.

[0032] The technical solution of the present invention has the following advantages: The present invention provides a method, device, equipment, and medium for analyzing common mode failures of hard disks based on servers. The method uses the pre-collected data on the types and failure modes of the hard disks of the servers to determine the failure-related components and the main failure factors. By analyzing the main failure factors, a failure model corresponding to the main failure factors is established, and the common mode failure factors of the server to be tested are determined based on the failure model. In this process, by classifying the types and failure modes of the hard disks of the servers, starting from the perspective of common mode failures of the hard disks, through in-depth analysis of the working environment and usage patterns of the hard disks, potential failure factors are effectively identified, and based on the analysis of the main failure factors, corresponding failure models are established for the main failure factors, thereby realizing the analysis of the common mode failure risk, improving the ability to identify potential problems, and providing a data basis for subsequent targeted preventive measures. In addition, based on the established failure model corresponding to the main failure factors, strong support can be provided for the improvement of failure prevention measures, research and development design, and testing processes, thereby further improving the reliability and stability of the server, and ensuring the continuity of business and the security of data. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0034] Figure 1It is a flow chart of a method for analyzing common mode failures of hard disks based on a server according to an embodiment of the present invention; Figure 2 is a schematic diagram of a change in head height according to an embodiment of the present invention; Figure 3 is a schematic diagram of the change in the number of bad sectors of a disk provided according to an embodiment of the present invention; Figure 4 It is a structural block diagram of a hard disk common mode failure analysis device based on a server according to an embodiment of the present invention; Figure 5 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0036] According to an embodiment of the present invention, a server-based hard disk common mode failure analysis method embodiment is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0037] This embodiment provides a method for analyzing common mode failures of hard disks based on a server. Figure 1 As shown, the method comprises the following steps: S101 . Determine fault-related components according to pre-collected data on the type and failure mode of a hard disk of a server.

[0038] Specifically, determining fault-related components based on the type and failure mode of the server's hard disk means starting from the perspective of common mode failure of the hard disk, and determining fault-related components by classifying the type and failure mode of the server's hard disk, that is, determining the common mode components that exist in the batch failure problem of hard disks in the same customer or computer room.

[0039] S102: Determine the main fault factor based on the fault-related components.

[0040] Specifically, based on fault-related components, determining the main fault factors means that after determining the fault-related components, for hard disks of different categories, the main fault factors are determined by analyzing the influencing factors of the faulty components under each category and the correlation between the influencing factors. That is, starting from the perspective of common mode failure of hard disks, the main factors causing failures in server operating environments under different categories are determined.

[0041] S103: Analyze the main fault factors, establish a fault model corresponding to the main fault factors, and determine the common mode fault factors of the server to be tested based on the fault model.

[0042] Specifically, analyzing the main failure factors and establishing failure models corresponding to the main failure factors means establishing corresponding failure models for each main failure factor, so that when the server's hard disk faces common mode problems, it can use various failure models to identify related problems, thereby providing strong support for failure prevention measures, R&D design and testing process improvement, thereby further improving the reliability and stability of the server and ensuring business continuity and data security.

[0043] The present invention provides a method, device, equipment, and medium for analyzing common mode failures of hard disks based on servers. The method uses the type and failure mode of the hard disk of the server to determine the failure-related components and the main failure factors. By analyzing the main failure factors, a failure model corresponding to the main failure factors is established. In this process, by classifying the type and failure mode of the hard disk of the server, starting from the perspective of common mode failures of the hard disk, through in-depth analysis of the working environment and usage mode of the hard disk, potential failure factors are effectively identified, and based on the analysis of the main failure factors, corresponding failure models are established for the main failure factors, thereby realizing the analysis of common mode failure risks, improving the ability to identify potential problems, and providing a data basis for subsequent targeted preventive measures. In addition, based on the established failure model corresponding to the main failure factors, it can provide strong support for the improvement of failure prevention measures, research and development design, and testing processes, thereby further improving the reliability and stability of the server and ensuring business continuity and data security.

[0044] In an optional implementation, determining the fault-related components according to the type and failure mode of the hard disk of the server includes: Based on the type of the server's hard disk and the functional categories of the hard disk components, the first module, the second module and the third module are determined; based on the failure modes of the first module, the second module and the third module, the failure-related components corresponding to the first module, the second module and the third module are respectively determined.

[0045] Specifically, the types of the server hard disk include: HDD and SSD, and the functions of the server hard disk include: control module and storage module. The following Table 1 exemplarily shows the process of classifying the hard disk components based on the types of the server hard disk.

[0046] Table 1

[0047] Specifically, the first module may be a HDD storage module, the second module may be an SSD storage module, and the third module may be a control module. This embodiment does not specifically limit this, and it can be set according to actual working conditions. It should be understood that the main control function of the HDD and SSD control modules is PCBA, so the HDD and SSD control modules are combined into the same module, i.e., the third module. For ease of explanation, the following description will be based on the first module being the HDD storage module, the second module being the SSD storage module, and the third module being the control module.

[0048] Specifically, the failure modes of the first module include: head damage and disk bad sectors, the failure modes of the second module include: charge changes in the double-layer floating gate NMOS tube of the flash memory particles and degradation of the floating gate oxide layer, and the failure modes of the third module include: solder joint fatigue of the PCBA.

[0049] Specifically, based on the failure mode of the first module, determining the failure-related components corresponding to the first module means determining the corresponding components in which the corresponding failure mode may occur, that is, the failure-related components corresponding to head damage are: the head, and the failure-related components corresponding to disk bad sectors are: the disk.

[0050] Specifically, based on the failure mode of the second module, determining the failure-related components corresponding to the second module refers to determining the corresponding components in which the corresponding failure mode can occur, that is, the failure-related components corresponding to the charge change of the double-layer floating gate NMOS tube of the flash memory particle and the degradation of the floating gate oxide layer are: NMOS-like double-layer floating gate MOS tube.

[0051] Specifically, based on the failure mode of the third module, determining the failure-related components corresponding to the third module refers to determining corresponding components that can cause the corresponding failure mode, that is, the failure-related components corresponding to solder joint fatigue of the PCBA are solder joints in the PCBA.

[0052] In an optional implementation, determining the main fault factor based on the fault-related components includes: Based on the fault-related components corresponding to the first module, the second module, and the third module, respectively, the influencing factors of the fault-related components corresponding to each module and the correlation between the influencing factors are determined; based on the correlation and influencing factors corresponding to each module, the main fault factors of the corresponding modules are determined.

[0053] Specifically, based on the fault-related components corresponding to the first module, the second module, and the third module, respectively, determining the influencing factors of the fault-related components corresponding to each module and the correlation between the influencing factors means determining the influencing factors of the fault-related components corresponding to each module respectively, and determining the correlation between the various influencing factors.

[0054] Specifically, the influencing factors of the fault-related components corresponding to the first module include: head flying height, number of bad sectors and bit error rate. Among them, the head flying height (FAFH Passive Clearance) is a key indicator to measure the distance between the head and the disk. Abnormal flying height may cause the head to contact the disk, affecting the stability of data reading; the number of bad sectors (G-list) is the disk area that cannot read or write data due to physical damage or magnetic degradation. The increase in bad sectors may directly affect the reliability and data integrity of the hard disk; the bit error rate (Bit Error Rate) reflects the frequency of erroneous bits during data transmission or storage. A high bit error rate usually means that the reliability of the storage medium is reduced. The correlation between the head flying height, the number of bad sectors and the bit error rate is a promoting relationship, that is, abnormal head flying height promotes the increase in the number of bad sectors, and then promotes the increase in the bit error rate, such as Figure 2 , Figure 3 As shown, the promoting relationship between the abnormal flying height of the magnetic head and the abnormal number of bad sectors is exemplarily demonstrated.

[0055] Specifically, the influencing factors of the fault-related components corresponding to the second module include: TDDB (Time Dependent Breakdown, time-dependent dielectric breakdown) and hot carrier injection. TDDB is the lossy breakdown that occurs after a certain period of time when the applied electric field is lower than the breakdown voltage of the gate oxide layer; hot carrier injection is the high-energy carrier injected into the gate through the oxide thin layer under the action of the electric field, resulting in the degradation of the electrical characteristics of the transistor. The correlation between TDDB and hot carrier injection is a competitive relationship.

[0056] Specifically, the influencing factors of the fault-related components corresponding to the third module include: solder joint thermal fatigue and mechanical fatigue. Among them, solder joint thermal fatigue is due to the different thermal expansion coefficients of solder joints, PCBs and components. The temperature changes around the solder joints may cause stress accumulation in the solder joints, thereby causing fatigue damage to the solder joints; mechanical fatigue is due to the repeated mechanical stress on the solder joints caused by continuous vibration, which causes the microcracks of the solder joints to grow, and eventually cause poor contact or complete breakage. The correlation between solder joint thermal fatigue and mechanical fatigue is damage accumulation.

[0057] In an optional implementation, based on the association relationship and influencing factors corresponding to each module, determining the main failure factor of the corresponding module includes: Based on the correlation between the influencing factors of the first module, the influencing factors corresponding to the first module are screened to determine the main influencing factors; the main influencing factors are analyzed to determine the first influencing factors that produce the main influencing factors; based on the main influencing factors and the first influencing factors, the main fault factors corresponding to the first module are determined.

[0058] Specifically, since the correlation between the head flying height, the number of bad sectors and the bit error rate is a promoting relationship, that is, the abnormal head flying height promotes the increase in the number of bad sectors, and then promotes the increase in the bit error rate, therefore, in the process of screening the influencing factors corresponding to the first module, the abnormal head flying height should be taken as the main influencing factor.

[0059] Specifically, the cause of abnormal head flying height failure is usually due to internal particle contamination of the HDD or external mechanical stress. Among them, regarding the internal particle contamination of the HDD, since the distance between the head and the disk is about 5-10nm, fine particle contamination, under the influence of high-speed rotating disk, can easily hit the head and cause abnormal head flying height. At present, HDD is mainly a sealed helium disk. Particle contamination is affected by the manufacturer's process. There is a lack of particle contamination monitoring methods and the probability of occurrence is low; the influence of external mechanical stress refers to high-frequency noise or vibration causing head resonance and external impact, and the probability of occurrence is relatively high. Therefore, the first influencing factor of the main influencing factors is high-frequency vibration or impact.

[0060] Specifically, based on the main influencing factors and the first influencing factors, determining the main fault factors corresponding to the first module means taking the main influencing factors and the first influencing factors together as the main fault factors corresponding to the first module, that is, the main fault factors corresponding to the first module include: abnormal head flying height, abnormal number of bad sectors, abnormal high-frequency vibration and abnormal impact.

[0061] In an optional implementation, based on the association relationship and influencing factors corresponding to each module, determining the main failure factor of the corresponding module includes: Based on the correlation relationship between the influencing factors of the second module, the influencing factors corresponding to the second module are analyzed to determine the main fault factors corresponding to the second module.

[0062] Specifically, the correlation between TDDB and reactive hot carriers is a competitive relationship. The NMOS-like double-layer floating gate MOS tube used in SSD flash memory particles is used as a basic storage unit. Its write and erase operations rely on the injection and extraction of electrons from the floating gate layer. The write operation applies a positive voltage to the control electrode to allow electrons to enter the floating gate layer through the insulating layer, while the erase operation applies a positive voltage to the substrate to absorb electrons from the floating gate layer. The read operation determines the stored data by detecting the floating gate layer voltage (i.e., the number of electrons). For example, in TLC (Triple-Level Cell) flash memory, each storage cell can store three bits of information, which means it has eight different threshold voltage states, which are used to represent 8 different data states. Since TLC flash memory has very high requirements for voltage control accuracy, any problem that causes leakage or injection of electrons in the insulating layer may cause data errors. Degradation of the floating gate oxide layer can cause electron leakage in the insulating layer, which is usually caused by physical and chemical changes in the oxide layer material under the action of a long-term electric field. Hot carrier injection is caused by the injection of high-energy electrons into the insulating layer under the action of a high electric field, which may lead to the generation of interface traps and degradation of the oxide layer during the long-term operation of the device. These two phenomena have a certain competitive relationship in TLC flash memory because they both affect the stability of electrons in the floating gate layer, thereby affecting the storage and reading of data. Therefore, the main failure factors corresponding to the second module include: floating gate oxide layer degradation and hot carrier injection.

[0063] In an optional implementation, based on the association relationship and influencing factors corresponding to each module, determining the main failure factor of the corresponding module includes: Based on the correlation relationship between the influencing factors of the third module, the environmental factors consistent with the working environment of the server are determined; based on the environmental factors, the main fault factors corresponding to the third module are determined.

[0064] Specifically, the correlation between solder joint thermal fatigue and mechanical fatigue is damage accumulation, that is, thermal fatigue caused by temperature changes and vibration fatigue caused by vibration. Thermal fatigue of solder joints refers to the change in ambient temperature and its own workload when electronic components are working. Due to the different thermal expansion coefficients of PCB and electronic devices, the solder joints are fatigued due to periodic thermal stress, resulting in cracks in the solder joints. The cracks extend along the interface between the solder and the pad, and the interface between the device and the solder, eventually leading to solder joint breakage.

[0065] Specifically, vibration fatigue refers to fatigue damage caused by repeated strain of solder joint materials under periodic mechanical vibration. This fatigue damage is usually caused by periodic bending deformation of PCB and electronic devices under vibration environment, which causes stress on solder joints. The stress level is related to load intensity and frequency.

[0066] Specifically, based on the correlation between the influencing factors of the third module, determining the environmental factors that are consistent with the working environment of the server means accumulating damage based on the correlation between solder joint thermal fatigue and mechanical fatigue, and determining the temperature factors and vibration factors that are consistent with the working environment of the server.

[0067] Specifically, the failure mechanisms of solder joint thermal fatigue and vibration fatigue both lead to fatigue damage of solder joints, which eventually lead to cracks and splitting. The failure relationship between them is damage accumulation. In a stable working environment such as a server, since it is usually in a well-controlled computer room environment, the probability of vibration is small, so thermal fatigue is often the main cause of failure. Therefore, the main failure factor corresponding to the third module is solder joint thermal fatigue.

[0068] In an optional implementation manner, analyzing the main fault factors and establishing a fault model corresponding to the main fault factors includes: Analyze the main fault factors and determine the types of parameter information corresponding to the main fault factors; in response to the parameter information corresponding to the main fault factors having corresponding thresholds, establish fault judgment models corresponding to the main fault factors based on the corresponding thresholds; in response to the parameter information corresponding to the main fault factors not having corresponding thresholds, establish fault physical models corresponding to the main fault factors based on the parameter information corresponding to the main fault factors.

[0069] Specifically, analyzing the main fault factors and determining the types of parameter information corresponding to the main fault factors means that after the main fault factors of the corresponding modules are determined respectively, the parameter information corresponding to the main fault factors are collected respectively, and different types of fault models are established according to the types of parameter information, wherein the types of fault models include: fault judgment model and fault physical model.

[0070] Specifically, the parameter information corresponding to the main fault factors are: abnormal head flying height corresponds to the head flying height, abnormal number of bad sectors corresponds to the number of bad sectors, abnormal high-frequency vibration corresponds to high-frequency vibration, abnormal impact corresponds to impact, floating gate oxide layer degradation corresponds to voltage, hot carrier injection corresponds to current, and solder joint thermal fatigue corresponds to temperature.

[0071] In an optional implementation manner, the parameter information corresponding to the main fault factor includes: head flying height, and the steps of establishing the fault determination models corresponding to the main fault factors based on the corresponding thresholds include: The fault judgment model corresponding to the head flying height is established by the following formula:

[0072] in, H FAFH-T Indicates the head flying height threshold, Indicates iDisk No. j The flying height of the magnetic head, Indicates i The average flying height of all heads on a disk, a Indicates parameter deviation.

[0073] Specifically, H FAFH-T Usually determined by the characteristics of the HDD, it can be selected according to the actual working conditions, such as 95 angstroms or other values. Parameter deviation is used to indicate the parameter differences between different heads and different HDDs. a It can be 10%, 15% or other values, which can be selected according to actual working conditions, and this embodiment does not make any specific limitation on this.

[0074] In an optional implementation manner, the parameter information corresponding to the main fault factor includes: the number of bad sectors, and the step of establishing the fault determination model corresponding to the main fault factor based on the corresponding thresholds includes: The fault judgment model corresponding to the number of bad sectors is established through the following formula:

[0075] in, H Glist-T Indicates the bad sector number threshold. Indicates i The number of bad sectors on each disk, Indicates i Disks T 2 The number of bad sectors at the moment, Indicates i Disks T 1 The number of bad sectors at the moment, b Indicates parameter deviation.

[0076] Specifically, H Glist-T It is also determined by the characteristics of the HDD and can be selected according to the actual working conditions, such as 9000 or other values. b Indicates the time dimension, usually in hours. For example, when the sampling period is 24 hours, b The value of is usually set to 1, which is not specifically limited in this embodiment and can be set according to actual working conditions.

[0077] In an optional implementation manner, the parameter information corresponding to the main fault factor includes: high frequency vibration, and the steps of establishing the fault judgment models corresponding to the main fault factors based on the corresponding thresholds respectively include: The fault judgment model corresponding to high-frequency vibration is established through the following formula:

[0078] in, H fre-T represents the high frequency vibration threshold, Indicates the vibration frequency of the disk.

[0079] Specifically, Usually detected by sensors installed on the back panel. H fre-T Usually, when the RV test corresponds to an HDD performance impact of 5% or more, it is determined by monitoring the high-frequency vibration response, which is a vibration interval and there may be multiple ones, which is not specifically limited in this embodiment, for example, 6% or 4% and above.

[0080] In an optional implementation manner, the parameter information corresponding to the main fault factor includes: impact, and the steps of establishing the fault determination models corresponding to the main fault factors based on the corresponding thresholds respectively include: The fault judgment model corresponding to the impact is established through the following formula:

[0081] in, H G-T represents the shock threshold, Indicates the impact of the disk G value.

[0082] Specifically, Usually detected by sensors installed on the back panel. H G-T Generally, during the startup shock test, the corresponding HDD has an impact G value of 5% or more, which is not specifically limited in this embodiment, for example, 6% or 4% or more.

[0083] In an optional implementation manner, the parameter information corresponding to the main fault factor includes: voltage, and the step of establishing the fault physical model corresponding to the main fault factor based on the parameter information corresponding to the main fault factor includes: The fault physical model corresponding to the floating gate oxide layer degradation is established by the following formula:

[0084] in, OF TDDB represents the fault physics model corresponding to floating gate oxide degradation, r represents the electric field acceleration, v h Indicates the actual voltage of the floating gate oxide layer, v n Indicates the standard voltage of the floating gate oxide layer,t ox Represents the thickness of the floating gate oxide layer.

[0085] Specifically, r When expressing electric field acceleration, the values ​​are usually 1.8 for silicon dioxide, 1.3 for silicon nitride, and 1.1 for high-k dielectrics. v h When representing the actual voltage of the floating gate oxide layer, generally only 1.2 times or more is extracted v n The corresponding value is not specifically limited in this embodiment, for example, 1.3 times or 1.5 times or more.

[0086] In an optional implementation manner, the parameter information corresponding to the main fault factor includes: current, and the step of establishing the fault physical model corresponding to the main fault factor based on the parameter information corresponding to the main fault factor includes: The fault physics model corresponding to hot carrier injection is established by the following formula:

[0087] in, OF HCI represents the fault physics model corresponding to hot carrier injection, I subh represents the actual substrate current, I subn Indicates the substrate standard current.

[0088] Specifically, I subh When representing the actual substrate current, generally only 1.02 times or more is extracted I subn The corresponding value is not specifically limited in this embodiment, for example, 1.01 times or 1.04 times or more.

[0089] In an optional implementation manner, the parameter information corresponding to the main fault factor includes: temperature, and the step of establishing the fault physical model corresponding to the main fault factor based on the parameter information corresponding to the main fault factor includes: The physical model of failure corresponding to solder joint fatigue is established by the following formula:

[0090] in, OF T represents the failure physics model corresponding to solder joint fatigue, T n Indicates the operating temperature of the disk when the environment dimension is c. T h Indicates the actual operating temperature of the disk.

[0091] Specifically, the ambient temperature c is generally selected to be 25 degrees Celsius. T h Only the temperature reaching 60 degrees Celsius is extracted. This embodiment does not make any specific limitation on this. For example, c selects a temperature of 26, 30 degrees Celsius or other values, and extracts a temperature reaching 50 or 65 degrees Celsius or other values.

[0092] In an optional implementation manner, the step of determining the common mode failure factor of the server to be tested based on the failure model includes: Obtain parameter information corresponding to the server to be tested and the main fault factors; and determine the common mode fault factor of the server to be tested based on the parameter information and the corresponding fault model.

[0093] Specifically, the parameter information corresponding to the main fault factors is detailed in the relevant description of the above embodiment and will not be elaborated here.

[0094] Specifically, determining the common mode failure factor of the server to be tested based on parameter information and corresponding fault models means inputting the acquired parameter information into the corresponding fault models respectively, thereby determining the common mode failure factor of the server to be tested through the respective corresponding fault models, thereby providing strong support for fault prevention measures, R&D design and improvement of the testing process, thereby further improving the reliability and stability of the server and ensuring business continuity and data security.

[0095] In an optional implementation manner, obtaining parameter information corresponding to the server to be tested and the main failure factor includes: Obtain parameter information corresponding to the test server and the main fault factors in an offline and / or online manner.

[0096] In this embodiment, a server-based hard disk common mode failure analysis 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.

[0097] This embodiment provides a server-based hard disk common mode fault analysis device, such as Figure 4 As shown, including: The component determination module 201 is used to determine the fault-related components according to the pre-collected hard disk type and fault mode data of the server. The specific process can be found in the description of step S101 in the above embodiment, which will not be repeated here. The factor determination module 202 is used to determine the main fault factor based on the fault-related components. The specific process can be found in the description of step S102 in the above embodiment, which will not be repeated here.

[0098] The model building module 203 is used to analyze the main fault factors, build fault models corresponding to the main fault factors, and determine the common mode fault factors of the server to be tested based on the fault models. The specific process can be found in the description of step S103 in the above embodiment, which will not be repeated here.

[0099] In an optional embodiment, the device further includes: The information acquisition module is used to obtain parameter information corresponding to the server to be tested and the main fault factor; the common mode factor determination module is used to determine the common mode fault factor of the server to be tested based on the parameter information and the corresponding fault model. The specific process can be referred to the relevant description in the above embodiment, which will not be repeated here.

[0100] The server-based hard disk common mode failure analysis device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0101] The embodiment of the present invention also provides a computer device having the above Figure 4 The server-based hard disk common mode failure analysis device is shown.

[0102] See also Figure 5 , Figure 5 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 5 As shown, the computer device includes: one or more processors 301, memory 302, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components utilize different buses to communicate with each other, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in the memory or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 3 A processor 301 is taken as an example.

[0103] The processor 301 may be a central processing unit, a network processor or a combination thereof. The processor 301 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable logic gate array, a general purpose array logic or any combination thereof.

[0104] The memory 302 stores instructions executable by at least one processor 301, so that the at least one processor 301 executes the method shown in the above embodiment.

[0105] The memory 302 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 302 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 302 may optionally include a memory remotely arranged relative to the processor 301, and these remote memories may be connected to the computer device 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.

[0106] The memory 302 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 302 may also include a combination of the above types of memory. The computer device also includes a communication interface 303, which is used for the computer device to communicate with other devices or communication networks.

[0107] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0108] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A server-based hard disk common mode failure analysis method, characterized in that: The method comprises: Determine the fault-related components based on the pre-collected data on the type and failure mode of the server's hard disk; Based on the fault-related components, determining a major fault factor; The main fault factors are analyzed, a fault model corresponding to the main fault factors is established, and a common mode fault factor of the server to be tested is determined based on the fault model.

2. The method according to claim 1, characterized in that The step of determining the fault-related components according to the type and fault mode of the hard disk of the server includes: Determine a first module, a second module, and a third module based on the type of the hard disk of the server and the functional categories of the components of the hard disk; Based on the failure modes of the first module, the second module, and the third module, failure-related components corresponding to the first module, the second module, and the third module are determined respectively.

3. The method according to claim 2, characterized in that The determining of the main fault factor based on the fault-related components includes: Based on the fault-related components corresponding to the first module, the second module, and the third module, respectively, determining the influencing factors of the fault-related components corresponding to each module and the correlation relationship between the influencing factors; Based on the association relationship and the influencing factors corresponding to each module, the main failure factor of the corresponding module is determined.

4. The method according to claim 3, characterized in that: The determining the main failure factor of the corresponding module based on the association relationship and the influencing factor corresponding to each module respectively includes: Based on the correlation relationship between the influencing factors of the first module, the influencing factors corresponding to the first module are screened to determine the main influencing factors therein; Analyze the main influencing factors and determine the first influencing factor that produces the main influencing factors; Based on the main influencing factors and the first influencing factors, a main fault factor corresponding to the first module is determined.

5. The method according to claim 3, characterized in that: The determining the main failure factor of the corresponding module based on the association relationship and the influencing factor corresponding to each module respectively includes: Based on the correlation relationship between the influencing factors of the second module, the influencing factors corresponding to the second module are analyzed to determine the main fault factors corresponding to the second module.

6. The method according to claim 3, characterized in that The determining the main failure factor of the corresponding module based on the association relationship and the influencing factor corresponding to each module respectively includes: Determining environmental factors that are consistent with the working environment of the server based on the correlation relationship with the influencing factors of the third module; Based on the environmental factors, a main failure factor corresponding to the third module is determined.

7. The method according to claim 1, characterized in that The analyzing the main fault factors and establishing a fault model corresponding to the main fault factors includes: Analyze the main fault factors and determine the type of parameter information corresponding to the main fault factors; In response to the parameter information corresponding to the main fault factor having a corresponding threshold, a fault determination model corresponding to the main fault factor is established based on the corresponding threshold; In response to the parameter information corresponding to the main fault factor not having a corresponding threshold, fault physical models corresponding to the main fault factors are established based on the parameter information corresponding to the main fault factors.

8. The method according to claim 7, characterized in that The parameter information corresponding to the main fault factors includes: head flying height, and the steps of establishing fault judgment models corresponding to the main fault factors based on corresponding thresholds include: The fault judgment model corresponding to the flying height of the magnetic head is established by the following formula: in, H FAFH-T Indicates the head flying height threshold, Indicates i Disk No. j The flying height of the magnetic head, Indicates i The average flying height of all heads on a disk, a Represents parameter deviation.

9. The method according to claim 7, characterized in that: The parameter information corresponding to the main fault factors includes: the number of bad sectors, and the steps of establishing the fault determination models corresponding to the main fault factors based on the corresponding thresholds include: A fault determination model corresponding to the number of bad sectors is established by the following formula: in, H Glist-T Indicates the bad sector number threshold. Indicates i The number of bad sectors on each disk, Indicates i Disks T 2. The number of bad sectors at the moment, Indicates i Disks T The number of bad sectors at one moment, b Indicates parameter deviation.

10. The method according to claim 7, characterized in that The parameter information corresponding to the main fault factors includes: high frequency vibration, and the steps of establishing the fault judgment models corresponding to the main fault factors based on the corresponding thresholds include: The fault judgment model corresponding to the high-frequency vibration is established by the following formula: in, H fre-T represents the high frequency vibration threshold, Indicates the vibration frequency of the disk.

11. The method according to claim 7, characterized in that The parameter information corresponding to the main fault factors includes: impact, and the steps of establishing the fault judgment models corresponding to the main fault factors based on the corresponding thresholds include: The fault judgment model corresponding to the impact is established by the following formula: in, H G-T represents the shock threshold, Indicates the impact of the disk G value.

12. The method according to claim 7, characterized in that The parameter information corresponding to the main fault factor includes voltage. The steps of establishing the fault physical model corresponding to the main fault factor based on the parameter information corresponding to the main fault factor include: The fault physical model corresponding to the floating gate oxide layer degradation is established by the following formula: in, AF TDDB represents the fault physics model corresponding to floating gate oxide degradation, r represents the electric field acceleration, v h Indicates the actual voltage of the floating gate oxide layer, v n Indicates the standard voltage of the floating gate oxide layer, t ox Represents the thickness of the floating gate oxide layer.

13. The method according to claim 7, characterized in that The parameter information corresponding to the main fault factor includes: current, and the steps of establishing the fault physical model corresponding to the main fault factor based on the parameter information corresponding to the main fault factor include: The fault physics model corresponding to hot carrier injection is established by the following formula: in, AF HCI represents the fault physics model corresponding to hot carrier injection, I subh represents the actual substrate current, I subn Indicates the substrate standard current.

14. The method according to claim 7, characterized in that The parameter information corresponding to the main fault factor includes: temperature, and the steps of establishing the fault physical model corresponding to the main fault factor based on the parameter information corresponding to the main fault factor include: The physical model of failure corresponding to solder joint fatigue is established by the following formula: in, AF T represents the failure physics model corresponding to solder joint fatigue, T n Indicates the operating temperature of the disk when the environment dimension is c. T h Indicates the actual operating temperature of the disk.

15. The method according to claim 1, characterized in that The step of determining the common mode failure factor of the server to be tested based on the failure model comprises: Obtain parameter information corresponding to the server to be tested and the main failure factors; Based on the parameter information and the corresponding fault model, a common mode failure factor of the server to be tested is determined.

16. The method according to claim 15, characterized in that The obtaining of parameter information corresponding to the server to be tested and the main failure factor includes: The parameter information of the measuring server corresponding to the main fault factor is obtained in an offline and / or online manner.

17. A server-based hard disk common mode failure analysis device, characterized in that: The device comprises: A component determination module, used to determine the fault-related components according to the pre-collected data on the type and failure mode of the hard disk of the server; A factor determination module, used for determining a main fault factor based on the fault-related components; The model building module is used to analyze the main fault factors, build fault models corresponding to the main fault factors, and determine the common mode fault factors of the server to be tested based on the fault models.

18. The device according to claim 17, characterized in that The device further comprises: An information acquisition module, used to acquire parameter information corresponding to the server to be tested and the main failure factors; The common mode factor determination module is used to determine the common mode failure factor of the server to be tested based on the parameter information and the corresponding failure model.

19. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the server-based hard disk common mode failure analysis method according to any one of claims 1 to 16 by executing the computer instructions.

20. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the server-based hard disk common mode failure analysis method according to any one of claims 1 to 16.

Images