Server downtime processing method and device, equipment and medium

Abstract

The invention discloses a server downtime processing method and device, equipment and a medium, and relates to the technical field of servers. According to the scheme, when the server is down, first current data of the server before the server is down are obtained, and second current data of all parts of the server under different loads are obtained; and matching the first current data with the second current data, determining the load condition of the target component of the server within a period of time before downtime, and further performing downtime scene simulation on the server according to the target component and the load condition thereof, thereby realizing server downtime scene reproduction, and improving the server downtime scene simulation efficiency. Therefore, a user can conveniently analyze the downtime reason and the pre-event of the server according to the simulated server downtime scene and finally determine the downtime event, and the maintenance efficiency of the server is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of servers, and in particular to a method, device, equipment and medium for processing server downtime. Background Art

[0002] In modern life, the key role of the Internet is becoming increasingly prominent, and server manufacturers have made ensuring server stability and reducing downtime events their top priority. Currently, by collecting server power module status signals and server standby power supply signals in real time and recording them in logs for maintenance personnel to analyze the cause of the fault, the probability of subsequent downtime can be reduced.

[0003] However, although this solution can retain some power analysis logs for situations such as complete power outages, the overall analysis remains at a qualitative level. It can only detect whether the primary and standby power supplies and redundant modes are working properly, and cannot quantitatively analyze or restore the cause of the downtime and its preceding events. Therefore, operation and maintenance and testing personnel can only understand the general cause, and it is difficult to quickly analyze the site and determine the exact cause of the downtime, and then reproduce the downtime scenario and finally quantify the event. This limits the in-depth understanding and effective improvement of server stability.

[0004] In view of the above, how to solve the problem that when the current server crashes, the cause of the crash and its preceding events cannot be restored, the crash scenario cannot be reproduced and the event cannot be finally characterized, is an urgent problem to be solved by technical personnel in this field. Summary of the invention

[0005] The purpose of the present invention is to provide a server downtime processing method, device, equipment and medium to solve the problem that when the current server downtime occurs, the cause of the downtime and its preceding events cannot be restored, the downtime scenario cannot be reproduced and the event cannot be finally characterized.

[0006] In order to solve the above technical problems, the present invention provides a server downtime processing method, comprising:

[0007] When the server crashes, obtain the first current data of the server before the crash;

[0008] Acquire a plurality of second current data, wherein each second current data is current data of each component of the server under different loads;

[0009] Matching the first current data with each second current data, and determining the target component and the load to which the successfully matched second current data corresponds;

[0010] A server downtime scenario simulation is performed based on the target component and the load on the target component to analyze the server downtime cause based on the simulated server downtime scenario.

[0011] On the one hand, before the server goes down, it also includes:

[0012] Collecting first current data of the server according to a first preset period;

[0013] storing the first current data within a second preset period before the current moment into the storage space;

[0014] The first preset period is smaller than the second preset period.

[0015] On the other hand, it also includes:

[0016] Determining a component to be collected in the server that is involved in collecting the second current data;

[0017] Performing a pressure test on the component to be collected, and collecting current data of the component to be collected under different loads based on the pressure test to obtain a plurality of second current data of the component to be collected;

[0018] The second current data of the components to be collected are stored in a database.

[0019] On the other hand, obtaining the first current data of the server before the downtime includes:

[0020] Obtaining the first current fluctuation frequency of the server before the crash;

[0021] Correspondingly, a plurality of second current data are obtained, including:

[0022] A plurality of second current fluctuation frequencies are obtained, wherein each current fluctuation frequency is a current fluctuation frequency of each component of the server under different loads.

[0023] On the other hand, obtaining the first current fluctuation frequency of the server before the crash includes:

[0024] Get the current function curve of the server before the crash;

[0025] The current function curve is cut according to the trough moment in the current function curve to obtain current function curve segments in multiple time neighborhoods;

[0026] Performing periodic image splicing on the current function curve segments in each time neighborhood to obtain a current function curve segment with a complete period;

[0027] According to each current function curve segment and the Fourier series expansion, multiple groups of current fluctuation frequencies of the current function are determined to obtain a first current fluctuation frequency of the server.

[0028] On the other hand, matching the first current data with each second current data to determine the target component and the load thereof corresponding to the successfully matched second current data includes:

[0029] Matching the plurality of groups of first current fluctuation frequencies of the server with the second current fluctuation frequencies respectively to determine the second current fluctuation frequency that matches successfully;

[0030] The corresponding target component and the load of the target component are determined according to the successfully matched second current fluctuation frequency.

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

[0032] Obtaining a preset range of current fluctuation frequency pre-set for each target component;

[0033] Determine the components among the target components whose corresponding second current fluctuation frequency exceeds the preset range of the corresponding current fluctuation frequency to obtain abnormal components;

[0034] Perform fault diagnosis on abnormal components based on the server logs.

[0035] In order to solve the above technical problems, the present invention also provides a server downtime processing device, comprising:

[0036] A first acquisition module, used for acquiring first current data of the server before the server crashes when the server crashes;

[0037] A second acquisition module is used to acquire a plurality of second current data, wherein each second current data is current data of each component of the server under different loads;

[0038] A matching module, used to match the first current data with each second current data, and determine the target component and the load thereof corresponding to the second current data that matches successfully;

[0039] The execution module is used to perform a downtime scenario simulation on the server according to the target component and the load thereof, so as to analyze the downtime cause of the server according to the simulated downtime scenario of the server.

[0040] In order to solve the above technical problems, the present invention also provides a server downtime processing device, comprising:

[0041] Memory for storing computer programs;

[0042] The processor is used to implement the steps of the above-mentioned server downtime processing method when executing a computer program.

[0043] In order to solve the above technical problems, the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above server downtime processing method are implemented.

[0044] The server downtime processing method provided by the present invention specifically obtains the first current data of the server before the downtime when the server downtime; obtains multiple second current data, wherein each second current data is the current data of each component of the server under different loads; matches the first current data with each second current data, and determines the target component and the load corresponding to the successfully matched second current data; performs a downtime scenario simulation of the server according to the target component and the load, so as to analyze the cause of the server downtime according to the simulated server downtime scenario.

[0045] The beneficial effect of the present invention is that, when a server crashes, the first current data of the server before the crash is obtained, and the second current data of each component of the server under different loads is obtained; the first current data is matched with the second current data to determine the load condition of the target component of the server within a period of time before the crash, and then the server crash scenario is simulated according to the target component and its load condition, thereby achieving the reproduction of the server crash scenario, so that the user can analyze the cause of the server crash and its preceding events according to the simulated server crash scenario, and finally quantify the crash event, thereby improving the maintenance efficiency of the server.

[0046] On the other hand, the present invention specifically collects the first current data of the server according to the first preset period, and stores the first current data within the second preset period before the current moment into the storage space, thereby improving the collection efficiency of the first current data of the server and saving storage space. By determining the components to be collected in the server involved in the collection of the second current data, performing a stress test on the components to be collected, and collecting the current data of the components to be collected under different loads based on the stress test, a plurality of second current data of the components to be collected are obtained, and each second current data of the components to be collected is stored in the database, thereby realizing the collection and storage of the second current data of each component of the server.

[0047] In addition, the present invention also provides a server downtime processing device, equipment and medium, with the same effect as above. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0049] Figure 1 A flow chart of a method for processing server downtime provided by an embodiment of the present invention;

[0050] Figure 2 A schematic diagram of a current function curve of a server provided in an embodiment of the present invention;

[0051] Figure 3 A schematic diagram of a current function curve of a server after cutting provided by an embodiment of the present invention;

[0052] Figure 4 A schematic diagram of a server downtime processing device provided by an embodiment of the present invention;

[0053] Figure 5 A schematic diagram of a server downtime processing device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] The core of the present invention is to provide a server downtime processing method, device, equipment and medium to solve the problem that when the current server crashes, the cause of the downtime and its preceding events cannot be restored, the downtime scenario cannot be reproduced and the event cannot be finally characterized.

[0056] In order to enable those skilled in the art to better understand the solution of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0057] Given the key role of the Internet in modern life, server manufacturers have made ensuring server stability and reducing downtime a top priority. To achieve this goal, intelligent detection and remote diagnosis technologies are currently used. In general, servers are equipped with sensors and intelligent detection mechanisms to monitor hardware status in real time, such as temperature, voltage, current and other key parameters. Once an abnormality is found, measures can be automatically taken, such as reducing performance, shutting down some functions or starting backup hardware, to avoid unexpected downtime. In addition, through the baseboard management controller or operating system, server manufacturers or technical support teams can remotely access server hardware for troubleshooting and repair, significantly shortening fault recovery time and improving server availability.

[0058] At present, the server power module status signal and server standby power supply signal can be collected in real time and recorded in a log for maintenance personnel to analyze the cause of the fault, thereby reducing the probability of subsequent downtime. However, although this solution can retain some power analysis logs for situations such as complete power outages, the overall analysis still remains at a qualitative level. It can only detect whether the main and standby power supplies and redundant modes are working normally, and it is impossible to quantitatively analyze or restore the cause of the downtime and its preceding events. Therefore, operation and maintenance and testing personnel can only understand the general reasons, and it is difficult to quickly analyze the scene and derive the exact cause of the downtime, and then reproduce the downtime scenario and finally quantify the event. This limits the in-depth understanding and effective improvement of server stability. Therefore, in order to solve the above problems, the present invention provides a server downtime processing method.

[0059] Figure 1 A flow chart of a method for processing server downtime provided by an embodiment of the present invention. Figure 1 As shown, specifically including:

[0060] S10: When the server crashes, obtain the first current data of the server before the crash.

[0061] Specifically, the solution continuously monitors and stores the first current data of the server when the server is running. When the server crashes, the first current data of the server before the crash is obtained for subsequent reproduction of the server crash scenario.

[0062] It should be noted that in this embodiment, there is no restriction on the specific type of the first current data of the server. For example, it can be the current value, current amplitude, current phase, current stability or current fluctuation frequency of the entire server, depending on the specific implementation situation.

[0063] In addition, in this embodiment, there is no limitation on the monitoring method of the first current data of the server. For example, the first current data may be monitored continuously or in a cycle, depending on the specific implementation situation.

[0064] S11: Acquire a plurality of second current data.

[0065] The second current data are current data of various components of the server under different loads.

[0066] Further, multiple second current data are obtained. It should be noted that each second current data is the current data of each component of the server under different loads. In other words, each component in the server should contain multiple second current data. This embodiment does not limit the specific components of the server involved, such as a central processing unit, a memory, a disk, an image processor, and a network card.

[0067] On the other hand, considering the impact characteristics of server startup and shutdown, it is necessary to sample the current data of each component at least when starting, stopping, and running (different loads), so as to provide reference second current data when different servers are equipped with this component in the future. It should be noted that the specific collection process of the second current data of each component of the server is not limited in this embodiment, and the second current data provided by the server component manufacturer can be used, depending on the specific implementation situation.

[0068] In this embodiment, there is no restriction on the specific type of the second current data, for example, it can be component current value, current amplitude, current phase, current stability or current fluctuation frequency. It only needs to be the same type as the first current data, depending on the specific implementation situation.

[0069] S12: Match the first current data with each second current data, and determine the target component and the load to which it is located corresponding to the successfully matched second current data.

[0070] After obtaining the first current data and the second current data, the first current data is matched with each second current data; when it is confirmed that the first current data and the second current data are the same, it is confirmed that the two current data are matched successfully, and at this time, the target component corresponding to the successfully matched second current data and its load are determined.

[0071] S13: simulating a server downtime scenario according to the target component and its load, so as to analyze the server downtime cause according to the simulated server downtime scenario.

[0072] Finally, the server downtime scenario simulation is performed based on the determined target components and their loads. At this point, the server hardware equipment has been disconnected, and the server downtime cause can be analyzed based on the simulated server downtime scenario, and all work of monitoring and reproducing the downtime scenario can be done.

[0073] It is worth noting that when there are multiple combinations of the matched target components, it is necessary to fully reproduce the server downtime scenario in combination with the target components, so as to help R&D, testing and operation and maintenance personnel quickly analyze and reproduce the downtime scenario, thereby improving the stability and reliability of the server.

[0074] In this embodiment, when the server crashes, the first current data of the server before the crash is obtained, and the second current data of each component of the server under different loads is obtained; the first current data is matched with the second current data to determine the load condition of the target component of the server within a period of time before the crash, and then the server crash scenario is simulated according to the target component and its load condition, thereby achieving the reproduction of the server crash scenario, so that the user can analyze the cause of the server crash and its preceding events according to the simulated server crash scenario, and finally quantify the crash event, thereby improving the maintenance efficiency of the server.

[0075] In order to improve the collection efficiency of the first current data of the server and save storage space, based on the above embodiment, in some embodiments, before the server crashes, the method further includes:

[0076] S14: collecting first current data of the server according to a first preset period;

[0077] S15: storing the first current data within a second preset period before the current moment into a storage space;

[0078] The first preset period is smaller than the second preset period.

[0079] Specifically, before the server crashes, the first current data of the server is collected according to the first preset period. In this embodiment, there is no restriction on the first preset period, which depends on the specific implementation. Considering the validity of the first current data, the first current data can be collected at the second level in the specific implementation.

[0080] Furthermore, when storing the first current data, in order to save storage space, the storage space specifically adopts a queue data structure, and specifically stores the first current data within the second preset period before the current moment into the storage space, thereby ensuring that the storage space always retains the latest first current data within the second preset period before the current moment, avoiding the storage of full data occupying a large amount of storage space. It should be noted that in this embodiment, there is no restriction on the second preset period, and it is necessary to ensure that the first preset period is less than the second preset period, for example, 10 minutes, depending on the specific implementation situation.

[0081] In this embodiment, the first current data of the server is collected according to the first preset period, and the first current data within the second preset period before the current moment is stored in the storage space, which improves the collection efficiency of the first current data of the server and saves storage space.

[0082] In order to collect the second current data of each component of the server, based on the above embodiment, in some embodiments, the method further includes:

[0083] S16: Determine a component to be collected in the server that is involved in collecting the second current data;

[0084] S17: performing a pressure test on the component to be collected, and collecting current data of the component to be collected under different loads based on the pressure test to obtain a plurality of second current data of the component to be collected;

[0085] S18: storing the second current data of the components to be collected into a database.

[0086] Specifically, firstly, related components are determined in the server, such as a central processing unit, a memory, a hard disk, etc., and these components are determined as components to be collected involving the second current data collection. Further, a stress test is performed on the components to be collected, and the current data of the components to be collected under different loads is collected based on the stress test to obtain multiple second current data of the components to be collected. The following example illustrates:

[0087] When the server is powered on and idle, perform a 30-minute maximum stress test on the CPU, collect the current data before the test starts as the second current data under no load on the CPU, and collect the current data in the last 10 minutes after the test starts as the second current data under full load on the CPU. When the server is powered on and idle, perform a 30-minute maximum stress test on the memory, collect the current data before the test starts as the second current data under no load on the memory, and collect the current data in the last 10 minutes after the test starts as the second current data under full load on the memory. The stress-ng tool can be used as the stress tool for the CPU and memory. At the same time, when the server is powered on and idle, collect the current data before the test starts as the second current data under no load on the disk, and collect the current data in the last 10 minutes after the test starts as the second current data under full load on the disk. The fio tool can be used for the disk, and the read-write ratio can be determined based on the actual user usage.

[0088] The above is an example of the second current data acquisition process of the central processing unit, memory and disk. The second current data acquisition process of the graphics processor and the network card is similar to the above process and will not be repeated in this embodiment. On this basis, the central processing unit, memory, disk and other components can also be stress tested while the server is in an idle state. The current data before the test is started is collected as the current data of the server under no load, and the current data within the last 10 minutes after the test is started is used as the current data of the server under full load, as the current data of the normal operation of the server, for reference in downtime analysis.

[0089] Finally, the second current data of the components to be collected are stored in a database, so that when the server crashes, the second current data can be directly read from the database and then matched with the first current data.

[0090] In this embodiment, by determining the components to be collected in the server that are involved in the second current data collection, stress testing is performed on the components to be collected, and based on the stress test, the current data of the components to be collected under different loads are collected to obtain multiple second current data of the components to be collected, and the second current data of the components to be collected are stored in a database, thereby realizing the collection and storage of the second current data of each component of the server.

[0091] Based on the above embodiment, in some embodiments, obtaining the first current data of the server before the downtime includes:

[0092] S100: Obtaining a first current fluctuation frequency of the server before the server crashes.

[0093] In a specific implementation, the first current data of the server is specifically the first current fluctuation frequency. The current fluctuation frequency refers to the number of times the current fluctuates within a unit time. In order to collect the first current fluctuation frequency of the server, the current sensor in the server can be used to collect the current of the entire server, and the corresponding first current fluctuation frequency can be determined by the current of the entire server. An independent current collection device (such as an ammeter) can also be connected in series to the server circuit to continuously collect the server current value to determine the corresponding first current fluctuation frequency. It should be noted that when an independent current collection device is used, the device is powered by the server cabinet power supply; it is also necessary to equip the current collection device with a redundant power supply to ensure that all collected data is recorded when the server is powered off.

[0094] Correspondingly, a plurality of second current data are obtained, including:

[0095] S110: Acquire multiple second current fluctuation frequencies.

[0096] The current fluctuation frequencies are current fluctuation frequencies of various components of the server under different loads.

[0097] It is understandable that, since the first current data and the second current data are of the same type, when the first current data is the first current frequency, the second current data should be the second current fluctuation frequency. It is understandable that each current fluctuation frequency is the current fluctuation frequency of each component of the server under different loads, so as to ensure the matching of the two current data.

[0098] In order to obtain the first current fluctuation frequency of the server before the downtime, based on the above embodiment, in some embodiments, obtaining the first current fluctuation frequency of the server before the downtime includes:

[0099] S101: Obtaining a current function curve of the server before the server crashes;

[0100] S102: cutting the current function curve according to the valley moments in the current function curve to obtain current function curve segments in multiple time neighborhoods;

[0101] S103: performing periodic image splicing on the current function curve segments in each time neighborhood to obtain a current function curve segment with a complete period;

[0102] S104: Determine multiple groups of current fluctuation frequencies of the current function according to each current function curve segment and the Fourier series expansion to obtain a first current fluctuation frequency of the server.

[0103] Figure 2 Schematic diagram of the current function curve of the server provided by the embodiment of the present invention. Figure 2 As shown, first obtain the current function curve of the server before the downtime, assuming that the time is , then the current function is fitted as It should be noted that there may be multiple peaks for the current function curve, and each peak may have different practical significance. In order to determine the specific situation of the server, it is necessary to segment and fit all the current function curves.

[0104] Figure 3 A schematic diagram of a current function curve of a server after cutting provided by an embodiment of the present invention. Figure 3 As shown, the current function curve is cut according to the trough moment in the current function curve to obtain the current function curve segments in multiple time neighborhoods. It can be understood that in each time neighborhood There is a point in the current function curve segment below , satisfying the condition .

[0105] Furthermore, the current function curve segments under each time neighborhood are periodically spliced ​​to obtain a current function curve segment with a complete period. At this time, since the peaks and troughs of the current function curve have been split, the characteristics of the original non-periodic function have been disassembled. , the current graph already has a finite number of extreme points in the neighborhood (Dirichlet condition), and the function in each time neighborhood obviously satisfies the condition .

[0106] Finally, according to each current function curve segment and the Fourier series expansion, multiple groups of current fluctuation frequencies of the current function are determined to obtain the first current fluctuation frequency of the server. The specific formula is as follows:

[0107] ;

[0108] in, is the current function, is a constant term, which fills in the time neighborhood before the cycle The current value at the start time; is the first fluctuation frequency, is the second wave frequency, is the number of arrays; It is the complete cycle after the periodic splicing of the fragment image of the current function curve, and its size is twice the time neighborhood Length; It is the time starting point after the current function curve segment images are periodically spliced.

[0109] For each function By adjusting the length of the array, a specific preset value or adjusting according to the fitting length, until the fitting degree reaches a satisfactory expected value, the server machine is finally obtained. The first current fluctuation frequency of the group includes Group and Group .

[0110] In this way, the calculation and acquisition of the first current fluctuation frequency of the server is realized. In addition, the calculation method of the second current fluctuation frequency of each component is different from the above process in that the current function curve of the component needs to be obtained first, and the rest of the process is the same as the above content; therefore, the calculation process of the second current fluctuation frequency is not repeated in this embodiment.

[0111] Based on the above embodiments, in some embodiments, matching the first current data with each second current data, and determining the target component and the load corresponding to the successfully matched second current data includes:

[0112] S121: Matching the plurality of groups of first current fluctuation frequencies of the server with the second current fluctuation frequencies respectively, to determine a successfully matched second current fluctuation frequency;

[0113] S122: Determine the corresponding target component and the load of the target component according to the successfully matched second current fluctuation frequency.

[0114] Specifically, for the configuration of the downed server model, the second current fluctuation frequency of each component is retrieved in the database, and then the collected first current fluctuation frequency of the server is used to match the component power record in the database. Finally, the corresponding target component and the load of the target component are determined based on the successfully matched second current fluctuation frequency.

[0115] It should be noted that if there are different possible combinations of target components, the full amount will be reproduced to provide multiple server configurations for analyzing the cause of server downtime.

[0116] In order to improve the efficiency of analyzing the reasons for server downtime, based on the above embodiments, in some embodiments, the method further includes:

[0117] S19: Obtaining a preset range of current fluctuation frequency that is pre-set for each target component;

[0118] S20: determining the components among the target components whose corresponding second current fluctuation frequency exceeds the preset range of the corresponding current fluctuation frequency, so as to obtain abnormal components;

[0119] S21: Perform fault diagnosis on abnormal components according to the server log.

[0120] Specifically, first obtain the preset range of current fluctuation frequency pre-set for each target component, which indicates the normal range of the current fluctuation frequency of the target component. In this embodiment, there is no restriction on the specific data of the preset range of current fluctuation frequency, which depends on the specific implementation situation. Further, determine the components in each target component whose corresponding second current fluctuation frequency exceeds the preset range of the corresponding current fluctuation frequency to obtain abnormal components. Finally, perform fault diagnosis on the abnormal components according to the log of the server, thereby effectively improving the efficiency of analyzing the cause of server downtime.

[0121] In addition, in the specific implementation, based on the recurring server crash scenario, the cause of the crash can be analyzed in the following steps: First, distinguish between true and false crashes. A true crash means that the server is completely unresponsive, while a false crash is caused by temporary resource exhaustion. Next, analyze the system log and kernel log to find error information and kernel crash records. Then, through resource monitoring, observe the usage of the CPU, memory, disk, and network bandwidth to determine whether there is resource exhaustion or abnormal surge; at the same time, check the running status and logs of each service through service monitoring to find service anomalies or critical errors. The kernel crash dump tool (Kdump) and the kernel crash analysis tool (Crash Utility) can be used to further analyze the memory image when the kernel crashes. In summary, the cause of the crash can be accurately located.

[0122] In the above-mentioned embodiment, the server downtime processing method is described in detail. The present invention also provides a corresponding embodiment of the server downtime processing device.

[0123] Figure 4 A schematic diagram of a server downtime processing device provided by an embodiment of the present invention. Figure 4 As shown, the device comprises:

[0124] A first acquisition module 10 is used to acquire first current data of the server before the server crashes when the server crashes;

[0125] A second acquisition module 11 is used to acquire a plurality of second current data, wherein each second current data is current data of each component of the server under different loads;

[0126] A matching module 12, used to match the first current data with each second current data, and determine the target component and the load corresponding to the successfully matched second current data;

[0127] The execution module 13 is used to perform a downtime scenario simulation on the server according to the target component and the load thereof, so as to analyze the downtime cause of the server according to the simulated downtime scenario of the server.

[0128] In some embodiments, it also includes:

[0129] A collection module, used for collecting first current data of the server according to a first preset period;

[0130] A first storage module, used for storing first current data within a second preset period before a current moment into a storage space;

[0131] The first preset period is smaller than the second preset period.

[0132] In some embodiments, it also includes:

[0133] A determination module, used for determining a component to be collected in the server that is involved in the second current data collection;

[0134] A testing module, used for performing a pressure test on the component to be collected, and collecting current data of the component to be collected under different loads based on the pressure test to obtain a plurality of second current data of the component to be collected;

[0135] The second storage module is used to store the second current data of the components to be collected into a database.

[0136] In some embodiments, the first acquisition module 10 includes:

[0137] A first acquisition submodule, used to acquire a first current fluctuation frequency of the server before the server crashes;

[0138] Correspondingly, the second acquisition module 11 includes:

[0139] The second acquisition submodule is used to acquire multiple second current fluctuation frequencies, wherein each current fluctuation frequency is a current fluctuation frequency of each component of the server under different loads.

[0140] In some embodiments, the first acquisition submodule includes:

[0141] The third acquisition submodule is used to obtain the current function curve of the server before the downtime;

[0142] A cutting submodule, used for cutting the current function curve according to the trough moment in the current function curve to obtain current function curve segments in multiple time neighborhoods;

[0143] A splicing submodule is used to periodically splice the current function curve segments in each time neighborhood to obtain a current function curve segment with a complete period;

[0144] The calculation submodule is used to determine multiple groups of current fluctuation frequencies of the current function according to each current function curve segment and the Fourier series expansion to obtain a first current fluctuation frequency of the server.

[0145] In some embodiments, the matching module 12 includes:

[0146] A first matching submodule, used for matching the plurality of first current fluctuation frequencies of the server with the second current fluctuation frequencies respectively, so as to determine a second current fluctuation frequency that matches successfully;

[0147] The first determination submodule is used to determine the corresponding target component and the load of the target component according to the successfully matched second current fluctuation frequency.

[0148] In some embodiments, it also includes:

[0149] A range acquisition module, used to acquire a preset range of current fluctuation frequency pre-set for each target component;

[0150] A second determination submodule is used to determine the components of each target component whose corresponding second current fluctuation frequency exceeds the preset range of the corresponding current fluctuation frequency, so as to obtain abnormal components;

[0151] The diagnosis submodule is used to perform fault diagnosis on abnormal components according to the server log.

[0152] Since the embodiments of the apparatus part correspond to the embodiments of the method part, please refer to the description of the embodiments of the method part for the embodiments of the apparatus part, which will not be repeated here.

[0153] In addition, the present invention also provides a computer program product, including a computer program / instruction, which implements the steps of the above-mentioned server downtime processing method when executed by a processor.

[0154] Figure 5 A schematic diagram of a server downtime processing device provided by an embodiment of the present invention. Figure 5 As shown, the server downtime processing equipment includes:

[0155] A memory 20, for storing computer programs;

[0156] The processor 21 is used to implement the steps of the server downtime processing method mentioned in the above embodiment when executing the computer program.

[0157] The server downtime processing device provided in this embodiment may include but is not limited to a smart phone, a tablet computer, a laptop computer, or a desktop computer.

[0158] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 can be implemented in at least one hardware form of a digital signal processor (DSP), a field programmable gate array (FPGA), and a programmable logic array. The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in an awake state, also known as a central processing unit (CPU); the coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 21 may be integrated with a graphics processing unit (GPU), and the GPU is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may also include an artificial intelligence (AI) processor, which is used to process computing operations related to machine learning.

[0159] The memory 20 may include one or more computer-readable storage media, which may be non-transitory. The memory 20 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In this embodiment, the memory 20 is at least used to store the following computer program 201, wherein, after the computer program is loaded and executed by the processor 21, it can implement the relevant steps of the server downtime processing method disclosed in any of the aforementioned embodiments. In addition, the resources stored in the memory 20 may also include an operating system 202 and data 203, etc., and the storage method may be temporary storage or permanent storage. Among them, the operating system 202 may include Windows, Unix, Linux, etc. Data 203 may include but is not limited to data related to the server downtime processing method.

[0160] In some embodiments, the server downtime processing device may further include a display screen 22 , an input / output interface 23 , a communication interface 24 , a power supply 25 , and a communication bus 26 .

[0161] Those skilled in the art will understand that Figure 5 The structure shown in the figure does not constitute a limitation on the server crash processing device, and may include more or fewer components than those shown in the figure.

[0162] Finally, the present invention also provides an embodiment corresponding to a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps recorded in the above method embodiment are implemented.

[0163] It is understandable that if the method in the above embodiment is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc. Various media that can store program codes.

[0164] The above is a detailed introduction to a server downtime processing method, device, equipment and medium provided by the present invention. The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referenced to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description. It should be pointed out that for ordinary technicians in this technical field, without departing from the principle of the present invention, several improvements and modifications can be made to the present invention, and these improvements and modifications also fall within the scope of protection of the present invention.

[0165] It should also be noted that, in this specification, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

Claims

1. A method for processing server downtime, characterized in that: include: When the server crashes, obtaining first current data of the server before the crash; Acquire a plurality of second current data, wherein each of the second current data is current data of each component of the server under different loads; Matching the first current data with each of the second current data, and determining a target component and a load corresponding to the second current data that matches successfully; A downtime scenario simulation of the server is performed according to the target component and the load thereof, so as to analyze the downtime cause of the server according to the simulated downtime scenario of the server.

2. The server downtime processing method according to claim 1, characterized in that: Before the server goes down, the method further includes: Collecting the first current data of the server according to a first preset period; storing the first current data within a second preset period before the current moment into a storage space; Wherein, the first preset period is smaller than the second preset period.

3. The server downtime processing method according to claim 1, characterized in that: Also includes: Determining a component to be collected in the server that is involved in collecting the second current data; Performing a pressure test on the component to be collected, and collecting current data of the component to be collected under different loads based on the pressure test to obtain a plurality of second current data of the component to be collected; The second current data of each component to be collected is stored in a database.

4. The server downtime processing method according to claim 1, characterized in that: Acquiring first current data of the server before the server crashes, including: Obtaining a first current fluctuation frequency of the server before the server crashes; Correspondingly, obtaining a plurality of the second current data includes: A plurality of second current fluctuation frequencies are obtained, wherein each of the current fluctuation frequencies is a current fluctuation frequency of each component of the server under different loads.

5. The server downtime processing method according to claim 4, characterized in that: Obtaining a first current fluctuation frequency of the server before the server crashes, including: Obtaining a current function curve of the server before the downtime; Cutting the current function curve according to the trough moments in the current function curve to obtain current function curve segments in multiple time neighborhoods; Performing image periodic splicing on the current function curve segments in each time neighborhood to obtain the current function curve segments with a complete period; According to each of the current function curve segments and the Fourier series expansion, multiple groups of current fluctuation frequencies of the current function are determined to obtain the first current fluctuation frequency of the server.

6. The server downtime processing method according to claim 4, characterized in that: Matching the first current data with each of the second current data, and determining a target component and a load corresponding to the successfully matched second current data, comprises: Matching the plurality of groups of first current fluctuation frequencies of the server with the respective second current fluctuation frequencies to determine the second current fluctuation frequency that matches successfully; The corresponding target component and the load of the target component are determined according to the successfully matched second current fluctuation frequency.

7. The server downtime processing method according to claim 5 or 6, characterized in that: Also includes: Obtaining a preset range of current fluctuation frequency pre-set for each target component; Determine, among the target components, components for which the second current fluctuation frequency corresponds to a preset range of the current fluctuation frequency, to obtain abnormal components; Fault diagnosis is performed on the abnormal component according to the log of the server.

8. A server downtime processing device, characterized in that: include: A first acquisition module, used for acquiring first current data of the server before the server crashes when the server crashes; A second acquisition module is used to acquire a plurality of second current data, wherein each of the second current data is current data of each component of the server under different loads; A matching module, used for matching the first current data with each of the second current data, and determining a target component and a load corresponding to the second current data that matches successfully; An execution module is used to perform a downtime scenario simulation on the server according to the target component and the load thereof, so as to analyze the downtime cause of the server according to the simulated downtime scenario of the server.

9. A server downtime processing device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the server downtime processing method as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the server downtime processing method according to any one of claims 1 to 7 are implemented.

Images