CN116820339A - Method and device for determining disk state, storage medium and electronic device - Google Patents
Method and device for determining disk state, storage medium and electronic device Download PDFInfo
- Publication number
- CN116820339A CN116820339A CN202310787899.5A CN202310787899A CN116820339A CN 116820339 A CN116820339 A CN 116820339A CN 202310787899 A CN202310787899 A CN 202310787899A CN 116820339 A CN116820339 A CN 116820339A
- Authority
- CN
- China
- Prior art keywords
- target
- disk
- determining
- state
- dimension reduction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 230000009467 reduction Effects 0.000 claims abstract description 86
- 238000012545 processing Methods 0.000 claims abstract description 33
- 238000004590 computer program Methods 0.000 claims description 18
- 230000015654 memory Effects 0.000 claims description 16
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000012423 maintenance Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 abstract description 7
- 238000005516 engineering process Methods 0.000 abstract description 4
- 230000000694 effects Effects 0.000 abstract description 2
- 239000006185 dispersion Substances 0.000 description 9
- 230000006870 function Effects 0.000 description 9
- 230000002159 abnormal effect Effects 0.000 description 7
- 239000011159 matrix material Substances 0.000 description 7
- 238000012544 monitoring process Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000007405 data analysis Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000036541 health Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000001010 compromised effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000000696 magnetic material Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012567 pattern recognition method Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/0614—Improving the reliability of storage systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/061—Improving I/O performance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0629—Configuration or reconfiguration of storage systems
- G06F3/0634—Configuration or reconfiguration of storage systems by changing the state or mode of one or more devices
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Debugging And Monitoring (AREA)
Abstract
The embodiment of the application provides a method and a device for determining a disk state, a storage medium and an electronic device, wherein the method comprises the following steps: acquiring target parameters of a target disk, wherein the target parameters comprise data on a plurality of data dimensions, and one data dimension corresponds to one type of parameter; performing dimension reduction processing on the target parameters by using a target model to obtain target dimension reduction parameters; and determining the state of the target disk based on the target dimension reduction parameter. The application solves the problem of low disk fault detection efficiency in the related technology, and further achieves the effect of comprehensively, accurately and objectively determining the state of the disk.
Description
Technical Field
The embodiment of the application relates to the field of computers, in particular to a method and a device for determining a disk state, a storage medium and an electronic device.
Background
In the related art, it is often necessary to use a disk to store data, which may have serious consequences if the disk fails.
First, disk failures may cause data loss on the disk and may affect the proper operation of the computer. For example, a disk failure may cause the computer system to crash, and may even cause the computer to fail to boot.
Second, disk failure may also cause damage to the disk, affecting the life of the disk. Magnetic disks are one of the important components of a computer, and their life is directly related to the performance and reliability of the computer. If the disk is damaged, both the performance and reliability of the computer can be compromised. If the computer performance is degraded, one may take more time to complete a task and may also face more work risks.
Finally, disk failures can also be inconvenient for people to work. For example, if a computer system crashes due to a disk failure, one cannot work with the computer. In addition, if a disk failure causes data loss, one may take a lot of time and effort to recover the lost data, thereby affecting the working efficiency.
In the related art, although there are some methods capable of analyzing and predicting the failure, these methods cannot detect the failure of the disk comprehensively, precisely and objectively, and therefore, there is a problem that the failure detection efficiency of the disk is low.
In view of the above problems in the related art, no effective solution has been proposed at present.
Disclosure of Invention
The embodiment of the application provides a method and a device for determining a disk state, a storage medium and an electronic device, which are used for at least solving the problem of low disk fault detection efficiency in the related technology.
According to an embodiment of the present application, there is provided a method for determining a disk state, including: acquiring target parameters of a target disk, wherein the target parameters comprise data on a plurality of data dimensions, and one data dimension corresponds to one type of parameter; performing dimension reduction processing on the target parameters by using a target model to obtain target dimension reduction parameters; and determining the state of the target disk based on the target dimension reduction parameter.
In an exemplary embodiment, performing the dimension reduction processing on the target parameter by using a target model, to obtain a target dimension reduction parameter includes: and performing dimension reduction processing on the target parameters by utilizing a fisher linear discriminant analysis FLDA model to obtain the one-dimensional target dimension reduction parameters.
In one exemplary embodiment, determining the state of the target disk based on the target dimension reduction parameter comprises: comparing the target dimension reduction parameter with a pre-configured target threshold under the condition that the target dimension reduction parameter is one-dimensional data; and determining the state of the target disk based on the comparison result.
In one exemplary embodiment, determining the state of the target disk based on the comparison result includes: under the condition that the target dimension reduction parameter is greater than or equal to the target threshold value, determining the state of the target disk as a fault disk; and under the condition that the target dimension reduction parameter is smaller than the target threshold value, determining the state of the target disk as a normal disk.
In one exemplary embodiment, determining the state of the target disk based on the comparison result includes: determining a difference value between the target dimension reduction parameter and the target threshold value based on a comparison result; determining a normal level of the target disk based on the difference value when the difference value is less than 0, wherein the smaller the difference value is, the higher the level of the normal level is; and determining the fault level of the target disk based on the difference value when the difference value is greater than or equal to 0, wherein the greater the difference value is, the higher the level of the fault level is.
In an exemplary embodiment, the method further comprises: adjusting the target threshold under a target trigger condition, wherein the target trigger condition comprises at least one of: receiving an adjustment request sent by other equipment; and detecting that the fault tolerance of the disk changes.
In one exemplary embodiment, after determining the state of the target disk based on the target dimension reduction parameter, the method further comprises: and executing an alarm operation under the condition that the state of the target magnetic disk is determined to be a fault state, wherein the alarm operation comprises at least one of the following steps: sending a first alarm message to a background server to instruct the server to inform an operation and maintenance person to replace the target disk, wherein the first alarm message carries first multimedia alarm information; and sending a second alarm message to the target terminal to instruct a user of the target terminal to replace the target disk, wherein the second alarm message carries second multimedia alarm information.
According to another embodiment of the present application, there is provided a disk state determining apparatus including: the system comprises an acquisition module, a storage module and a storage module, wherein the acquisition module is used for acquiring target parameters of a target disk, the target parameters comprise data on a plurality of data dimensions, and one data dimension corresponds to one type of parameter; the processing module is used for performing dimension reduction processing on the target parameters by utilizing the target model to obtain target dimension reduction parameters; and the determining module is used for determining the state of the target disk based on the target dimension reduction parameter.
In one exemplary embodiment, the processing module includes: and the processing unit is used for performing dimension reduction processing on the target parameters by utilizing a fisher linear discriminant analysis FLDA model to obtain the one-dimensional target dimension reduction parameters.
In one exemplary embodiment, the determining module includes: the comparison unit is used for comparing the target dimension reduction parameter with a preset target threshold value under the condition that the target dimension reduction parameter is one-dimensional data; and the determining unit is used for determining the state of the target disk based on the comparison result.
In an exemplary embodiment, the determining unit includes: the first determining subunit is used for determining the state of the target disk as a fault disk under the condition that the target dimension reduction parameter is greater than or equal to the target threshold value; and the second determining subunit is used for determining the state of the target disk as a normal disk under the condition that the target dimension reduction parameter is smaller than the target threshold value.
In an exemplary embodiment, the determining unit includes: a third determining subunit, configured to determine a difference value between the target dimension reduction parameter and the target threshold based on a comparison result; a fourth determining subunit, configured to determine, based on the difference value, a normal level of the target disk, where the smaller the difference value is, the higher the level of the normal level is, if the difference value is less than 0; and a fifth determining subunit, configured to determine, based on the difference, a failure level of the target disk if the difference is greater than or equal to 0, where the greater the difference, the higher the level of the failure level.
In an exemplary embodiment, the apparatus further comprises: an adjustment module, configured to adjust the target threshold under a target trigger condition, where the target trigger condition includes at least one of: receiving an adjustment request sent by other equipment; and detecting that the fault tolerance of the disk changes.
In an exemplary embodiment, the apparatus further comprises: the warning module is used for executing warning operation after determining the state of the target disk based on the target dimension reduction parameter and under the condition that the state of the target disk is determined to be a fault state, wherein the warning operation comprises at least one of the following steps: sending a first alarm message to a background server to instruct the server to inform an operation and maintenance person to replace the target disk, wherein the first alarm message carries first multimedia alarm information; and sending a second alarm message to the target terminal to instruct a user of the target terminal to replace the target disk, wherein the second alarm message carries second multimedia alarm information.
According to a further embodiment of the application, there is also provided a computer readable storage medium having stored therein a computer program, wherein the computer program is arranged to perform the steps of any of the method embodiments described above when run.
According to a further embodiment of the application there is also provided an electronic device comprising a memory having stored therein a computer program and a processor arranged to run the computer program to perform the steps of any of the method embodiments described above.
The application adopts the following scheme to determine the state of the target disk: acquiring target parameters of a target disk, wherein the target parameters comprise data on a plurality of data dimensions, and one data dimension corresponds to one type of parameter; performing dimension reduction processing on the target parameters by using a target model to obtain target dimension reduction parameters; and determining the state of the target disk based on the target dimension reduction parameter. By the method, the data of the plurality of dimensions of the magnetic disk can be subjected to dimension reduction processing, and then the state of the magnetic disk is determined based on the data obtained after dimension reduction, namely, when the state of the magnetic disk is determined, the data of the plurality of dimensions of the magnetic disk are comprehensively considered, namely, in the application, the state of the magnetic disk is actually comprehensively determined based on the data of the plurality of dimensions, so that the state of the magnetic disk can be comprehensively, accurately and objectively determined, and the problem of low fault detection efficiency of the magnetic disk in the related art is effectively solved.
Drawings
FIG. 1 is a block diagram of a hardware configuration of a mobile terminal according to a method for determining a disk status according to an embodiment of the present application;
FIG. 2 is a flow chart of a method of determining disk status according to an embodiment of the present application;
FIG. 3 is a schematic representation of a disk failure affecting factor indicator according to an embodiment of the present application;
fig. 4 is a block diagram of a disk state determining apparatus according to an embodiment of the present application.
Detailed Description
Embodiments of the present application will be described in detail below with reference to the accompanying drawings in conjunction with the embodiments.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order.
First, some terms related to the present application will be described:
magnetic disk: is a storage device that may be used to store data, information, files, etc. Magnetic disks are typically composed of a plurality of platters, each platter having a layer of magnetic material that is readable and writable by a magnetic head. The capacity of the magnetic disk is generally larger and the speed is higher, so that a large amount of storage space and higher data reading and writing speed can be provided. Magnetic disks are an important component of computer systems, playing an important role in computer storage and data processing.
Disk failure: the disk failure refers to the failure of the disk in the use process, so that the disk cannot work normally. Disk failures may be due to hardware problems with the disk itself, or due to data corruption on the disk. In either case, disk failures may result in data loss on the disk and may affect the proper operation of the computer.
Monitoring disk data: disk monitoring tools, which are special software that can monitor the operating state of a disk in real time and provide relevant information, can be used to monitor the disk data. For example, the disk monitoring tool may provide information about the operating temperature, load rate, error rate, etc. of the disk.
Fisher linear discriminant analysis (abbreviated as FLDA): is a commonly used pattern recognition method for projecting data into a low dimensional space and maximizing the distance between different classes as much as possible. The main idea of FLDA is to project data onto a straight line so that sample points inside the same class are closely clustered, and the distance between different classes is as large as possible, so as to distinguish the different classes.
In order to predict disk failure, some prediction methods are also proposed in the related art, specifically as follows:
1. traditional chart data analysis. A large amount of data needs to be collected and then sorted into tables and the data presented using the charts. Through the graphs and tables, people can quickly look up the distribution situation and trend of the data and conduct deeper analysis. Charts and tables cannot show a large amount of data because the amount of data is limited. In addition, one needs to spend a lot of time and effort to sort the data and make charts and tables, which may affect the efficiency of data analysis. Therefore, the conventional chart data analysis method is suitable for a data analysis scene with a smaller scale.
2. And setting a disk fault parameter condition, and identifying an abnormality when information such as INQUIRY fault is retrieved from data. The method is simple and rough, and meanwhile, a large number of disks have no obvious error information, but the failed disk is likely to miss the scene, and the method does not analyze the disk failure rule.
3. Taking the number of damaged sectors as a damaged sector threshold; and a certain parameter of the magnetic disk is selected too one-sided to serve as the basis of the magnetic disk fault, and the effect of other parameters is ignored, so that the detection accuracy is low.
4. Based on a neural network model, such as a long-short term memory neural network LSTM. But has the following problems: first, neural network models require a large amount of data to learn and take a large amount of time to train the model, otherwise the accuracy of the model cannot be guaranteed. In addition, the model has numerous parameters, and the accuracy of the model can be greatly influenced by the setting of the parameters. Finally, the neural network prediction model is easily affected by noise and abnormal values, and the disc fault data just belong to the noise and the abnormal values, so that the model is inaccurate.
In summary, it has been difficult to detect disk failures comprehensively, accurately, and objectively.
Based on the above problems, a new disk failure detection method is provided in the embodiments of the present application, which can process a large amount of data in a short time, detect abnormal values in the data, and also can work well for high-dimensional data, and does not require human intervention to adjust parameters. Therefore, the fault disk and the high-risk disk are identified, and the safety and stability of the system are improved.
The following describes embodiments of the present application and the schemes involved in the preferred embodiments in detail:
the method embodiments provided in the embodiments of the present application may be performed in a mobile terminal, a computer terminal or similar computing device. Taking the mobile terminal as an example, fig. 1 is a block diagram of a hardware structure of the mobile terminal according to a method for determining a disk state according to an embodiment of the present application. As shown in fig. 1, a mobile terminal may include one or more (only one is shown in fig. 1) processors 102 (the processor 102 may include, but is not limited to, a microprocessor MCU or a processing device such as a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 for communication functions and an input-output device 108. It will be appreciated by those skilled in the art that the structure shown in fig. 1 is merely illustrative and not limiting of the structure of the mobile terminal described above. For example, the mobile terminal may also include more or fewer components than shown in fig. 1, or have a different configuration than shown in fig. 1.
The memory 104 may be used to store a computer program, for example, a software program of application software and a module, such as a computer program corresponding to a method for determining a disk state in an embodiment of the present application, and the processor 102 executes the computer program stored in the memory 104 to perform various functional applications and data processing, that is, implement the above-mentioned method. Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory remotely located relative to the processor 102, which may be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 106 is used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, simply referred to as NIC) that can connect to other network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is configured to communicate with the internet wirelessly.
In this embodiment, a method for determining a disk state is provided, and fig. 2 is a flowchart of a method for determining a disk state according to an embodiment of the present application, as shown in fig. 2, where the flowchart includes the following steps:
step S202, obtaining target parameters of a target disk, wherein the target parameters comprise data on a plurality of data dimensions, and one data dimension corresponds to one type of parameter;
step S204, performing dimension reduction processing on the target parameters by using a target model to obtain target dimension reduction parameters;
step S206, determining the state of the target disk based on the target dimension reduction parameter.
The main execution body of the steps may be a processor, a processing module, or other devices with similar processing capability.
In the above embodiment, the target parameters may include disk parameters in multiple dimensions, that is, may include multiple types of disk parameters, for example, a disk temperature, a lifetime margin, a number of link errors, a working time, a number of power-on times, a number of bad blocks, a number of PEs, a read amount, a write amount, and the like, where the disk parameters may be acquired at one time, part of the parameters may be an average value obtained after a plurality of acquisitions (for example, acquired according to a fixed period), or the part of the parameters may be an average value obtained after a plurality of acquisitions to remove a part of the parameters that is significantly unreasonable, and the determination manners of different parameters may be different, that is, the number of acquisitions or the acquisition period of different parameters may be different as long as each parameter that is capable of expressing the disk performance most can be acquired.
In the above embodiment, the target model may be an FLDA model, but may be any other model capable of performing a dimension reduction process. When the target model is an FLDA model, the model can utilize a large amount of data to conduct supervised learning before application, namely, multidimensional parameters of a magnetic disk with known states can be utilized to adjust various parameters in the FLDA model, and then the FLDA model capable of outputting accurate results is obtained.
In the above embodiment, the target dimension reduction parameter may be a one-dimensional parameter, or may be a two-dimensional or more-dimensional parameter, and the more the dimension of the data dimension is, the more complex the calculation mode is required in determining the disk state, and the more preferred mode is to process the target parameter into a one-dimensional parameter.
In the above embodiment, the states of the target disk may include a normal state and a fault state, and further, the states of the target disk may be further divided into a health state, a general state, a risk state and an abnormal state, where the health state may be further subdivided, the abnormal state may be further subdivided, and in particular, to what extent, may be adjusted based on the actual requirement. Further, after the states are subdivided, further adjustments may be made to the subdivided states, including increasing the number of states, decreasing the number of states, and so forth.
The disk failure impact factor indicator is shown in FIG. 3, wherein the disk failure criteria include the aforementioned various disk parameters and the disk health status includes the aforementioned individual disk status.
By the method, the data of the plurality of dimensions of the magnetic disk can be subjected to dimension reduction processing, and then the state of the magnetic disk is determined based on the data obtained after dimension reduction, namely, when the state of the magnetic disk is determined, the data of the plurality of dimensions of the magnetic disk are comprehensively considered, namely, in the application, the state of the magnetic disk is actually comprehensively determined based on the data of the plurality of dimensions, so that the state of the magnetic disk can be comprehensively, accurately and objectively determined, and the problem of low fault detection efficiency of the magnetic disk in the related art is effectively solved.
In an exemplary embodiment, performing the dimension reduction processing on the target parameter by using a target model, to obtain a target dimension reduction parameter includes: and performing dimension reduction processing on the target parameters by utilizing a fisher linear discriminant analysis FLDA model to obtain the one-dimensional target dimension reduction parameters. By reducing the target parameters to one-dimensional data, the subsequent comparison calculation amount can be simplified, and the state of the magnetic disk can be conveniently and rapidly determined.
In the above embodiment, before performing the dimension reduction processing on the target parameter using the FLDA, the FLDA may be subjected to supervised learning in the following manner to obtain an FLDA model after completion:
1) Determining the number of categories
First, the number of two categories into which the sample is to be divided needs to be determined, and the categories are divided into normal disks and failed disks. Let the sample set f contain N d-dimensional samples x 1 ,x 2 ,…,x N Wherein N is 1 Are of omega 1 The samples of the class are noted as subset f 1 ，N 2 Are of omega 2 The samples of the class are noted as subset f 2 . If to x n The components of (a) are linearly combined to obtain a scalar:
y n ＝w T x n ,n＝1,2,…,N
thus N one-dimensional samples y are obtained n A set of components and can be divided into two subsets f 1 ' and f 2 ’。
2) Basic parameters in Fisher criterion function
1. In d-dimensional X space
Average value vector m of various samples i The method comprises the following steps:
sample in-class dispersion matrix S i And a total sample intra-class dispersion matrix S w The method comprises the following steps:wherein S is w Is a symmetric semi-positive (eigenvalue is equal to or greater than zero) matrix.
Sample inter-class dispersion matrix S b The method comprises the following steps: s is S b ＝(m 1 -m 2 )(m 1 -m 2 ) T Wherein S is b Is a symmetric semi-positive definite matrix.
2. In one dimension Y space
Average value of various samplesThe method comprises the following steps: />
Sample in-class dispersionAnd the dispersion in the total sample class +.>The method comprises the following steps of:
three) criterion function
After projection is needed, various samples are separated as far as possible in a one-dimensional Y space, namely, the larger the difference between two average values is, the better; while it is desirable that the sample interior be as dense as possible, i.e., the smaller the intra-class dispersion, the better. The Fisher criterion function can thus be defined as:
wherein,,is the difference between the two kinds of mean values->Is the dispersion within the sample class. Obviously, should make J F The numerator of (w) is as large as possible and the denominator as small as possible, i.e. one should find that J is F (w) w as large as possible is taken as the projection direction. However, since w is not apparent in the above formula, it is necessary to try to find J F (w) becomes a explicit function of w.
From the average of each type of sample, it can be deduced that:
thus, the numerator of Fisher criterion function JF (w) can be written as:
let us now review J F Relationship of denominator of (w) to w:
thus, the first and second substrates are bonded together,
substituting the above formulae into J F (w) obtainable:
wherein S is b For the matrix of the dispersion among sample classes, S w Is a matrix of dispersions within the total sample class.
Fourth) determination of optimal transformation vector w
w is the Fisher criterion function J F (w) the solution at maximum, i.e. the optimal projection direction of d-dimensional X space into one-dimensional Y space. With w, the d-dimensional sample x can be projected into one dimension, which is effectively a mapping of multi-dimensional space to one-dimensional space whose direction w is relative to Fisher criterion function J F (w) is most preferable.
In the above embodiment, when the monitoring data of the disk is acquired, as many disk parameter data as possible are selected based on all possible principles. This is because the method used in embodiments of the present application can be used to process high-dimensional data, independent of the linear relationship of the data, and without the need for pre-processing (e.g., normalization or regularization) the data. Therefore, all parameter data which can be collected and each condition are considered as far as possible, so that the whole model is more comprehensive and accurate. Or selecting part of the dimension data according to actual needs or experience.
Most of the current memories such as ATA/SATA, SCSI/SAS and solid state disk are built with SMART systems (Self-Monitoring Analysis and Reporting Technology, automated inspection analysis and reporting technology) or worm systems (Field Accessibility Reliability Metrics) for collecting and monitoring disk data. Disk SMART data/far data contains a number of parameters such as disk temperature, margin of life, number of link errors, operating time, number of power-ups, number of bad blocks, number of PEs, read amount, write amount, etc.
In the above embodiment, sample data may be put into the sample space to analyze the disk failure rule: disk failure data is analyzed based on Fisher linear discriminant analysis (i.e., FLDA). Wherein the FLDA can assign each data point a label, i.e. which category it belongs to. Specifically, FLDA first calculates the overall covariance between different classes, and then by projecting the data onto a straight line, the sample points within the same class are more closely distributed, maximizing the distance between the different classes. This can be achieved by calculating the distance of each sample point to the straight line at the time of classification, thereby judging to which class each sample point belongs.
The FLDA model obtained in the above manner can determine the state of the disk, and in addition, it should be noted that the above manner is equally applicable to determining the state of the actual disk in the actual application stage.
In one exemplary embodiment, determining the state of the target disk based on the target dimension reduction parameter comprises: comparing the target dimension reduction parameter with a pre-configured target threshold under the condition that the target dimension reduction parameter is one-dimensional data; and determining the state of the target disk based on the comparison result.
In the above embodiment, the target threshold may be predetermined, may be determined based on historical experience, may be determined based on performance of the disk, may be determined based on fault tolerance, and may, of course, be determined based on other considerations.
In the above embodiment, the reduced-dimension parameter may be compared with the target threshold, and the state of the target disk may be determined based on the magnitude relation with the target threshold, and by comparing with the predetermined threshold, whether the disk parameter is abnormal may be determined quickly and accurately, so as to determine the state of the disk effectively and accurately.
In one exemplary embodiment, determining the state of the target disk based on the comparison result includes: under the condition that the target dimension reduction parameter is greater than or equal to the target threshold value, determining the state of the target disk as a fault disk; and under the condition that the target dimension reduction parameter is smaller than the target threshold value, determining the state of the target disk as a normal disk. In this embodiment, the states of the magnetic disk may be divided into two states, that is, a normal state and a failure state, and it may be determined which state is the current state of the target magnetic disk based on the size relationship between the target dimension reduction parameter and the target threshold. Of course, in practical applications, the states of the magnetic disk may be more than two, and there may be more kinds, or more levels, for example, determining the state of the target magnetic disk based on the comparison result may further include: determining a difference value between the target dimension reduction parameter and the target threshold value based on a comparison result; determining a normal level of the target disk based on the difference value when the difference value is less than 0, wherein the smaller the difference value is, the higher the level of the normal level is; and determining the fault level of the target disk based on the difference value when the difference value is greater than or equal to 0, wherein the greater the difference value is, the higher the level of the fault level is. In the above embodiment, the Fisher criterion is used to convert the d-dimensional classification problem into a one-dimensional classification problem, then determine a threshold T, and compare the projection point (i.e., the one-dimensional data) with T, so as to classify and distinguish the normal disk from the failed disk. At the same time, the anomaly level can be further refined according to y n Determining abnormal level, setting and adjusting threshold value of health state of magnetic disk according to actual situation to distinguish health, general, risk and abnormalOften times. Through the embodiment, the disk state can be further divided, so that the accurate state of the disk state is determined, and when the critical state (namely, to-be-failed) of disk processing is determined, the disk can be replaced in advance, and unnecessary loss is avoided.
In an exemplary embodiment, the method further comprises: adjusting the target threshold under a target trigger condition, wherein the target trigger condition comprises at least one of: receiving an adjustment request sent by other equipment; and detecting that the fault tolerance of the disk changes. In this embodiment, after the target threshold is determined, the target threshold may be flexibly adjusted, so that the setting of the target threshold may be matched with the actual situation, and the problem that the disk state is inaccurate due to the excessively large or excessively small set target threshold is avoided.
In one exemplary embodiment, after determining the state of the target disk based on the target dimension reduction parameter, the method further comprises: and executing an alarm operation under the condition that the state of the target magnetic disk is determined to be a fault state, wherein the alarm operation comprises at least one of the following steps: sending a first alarm message to a background server to instruct the server to inform an operation and maintenance person to replace the target disk, wherein the first alarm message carries first multimedia alarm information; and sending a second alarm message to the target terminal to instruct a user of the target terminal to replace the target disk, wherein the second alarm message carries second multimedia alarm information. It should be noted that the above-described alarm operation is only an exemplary illustration, and is not limited to this in practical application.
From the description of the above embodiments, it will be clear to a person skilled in the art that the method according to the above embodiments may be implemented by means of software plus the necessary general hardware platform, but of course also by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present application.
The embodiment also provides a device for determining a disk state, which is used for implementing the foregoing embodiments and preferred embodiments, and is not described in detail. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
Fig. 4 is a block diagram of a disk state determining apparatus according to an embodiment of the present application, as shown in fig. 4, including:
an obtaining module 42, configured to obtain a target parameter of a target disk, where the target parameter includes data on a plurality of data dimensions, where one data dimension corresponds to a type of parameter; the processing module 44 is configured to perform dimension reduction processing on the target parameter by using a target model to obtain a target dimension reduction parameter; a determining module 46, configured to determine a state of the target disk based on the target dimension reduction parameter.
In one exemplary embodiment, the processing module 44 includes: and the processing unit is used for performing dimension reduction processing on the target parameters by utilizing a fisher linear discriminant analysis FLDA model to obtain the one-dimensional target dimension reduction parameters.
In one exemplary embodiment, the determination module 46 includes: the comparison unit is used for comparing the target dimension reduction parameter with a preset target threshold value under the condition that the target dimension reduction parameter is one-dimensional data; and the determining unit is used for determining the state of the target disk based on the comparison result.
In an exemplary embodiment, the determining unit includes: the first determining subunit is used for determining the state of the target disk as a fault disk under the condition that the target dimension reduction parameter is greater than or equal to the target threshold value; and the second determining subunit is used for determining the state of the target disk as a normal disk under the condition that the target dimension reduction parameter is smaller than the target threshold value.
In an exemplary embodiment, the determining unit includes: a third determining subunit, configured to determine a difference value between the target dimension reduction parameter and the target threshold based on a comparison result; a fourth determining subunit, configured to determine, based on the difference value, a normal level of the target disk, where the smaller the difference value is, the higher the level of the normal level is, if the difference value is less than 0; and a fifth determining subunit, configured to determine, based on the difference, a failure level of the target disk if the difference is greater than or equal to 0, where the greater the difference, the higher the level of the failure level.
In an exemplary embodiment, the apparatus further comprises: an adjustment module, configured to adjust the target threshold under a target trigger condition, where the target trigger condition includes at least one of: receiving an adjustment request sent by other equipment; and detecting that the fault tolerance of the disk changes.
In an exemplary embodiment, the apparatus further comprises: the warning module is used for executing warning operation after determining the state of the target disk based on the target dimension reduction parameter and under the condition that the state of the target disk is determined to be a fault state, wherein the warning operation comprises at least one of the following steps: sending a first alarm message to a background server to instruct the server to inform an operation and maintenance person to replace the target disk, wherein the first alarm message carries first multimedia alarm information; and sending a second alarm message to the target terminal to instruct a user of the target terminal to replace the target disk, wherein the second alarm message carries second multimedia alarm information.
It should be noted that each of the above modules may be implemented by software or hardware, and for the latter, it may be implemented by, but not limited to: the modules are all located in the same processor; alternatively, the above modules may be located in different processors in any combination.
Embodiments of the present application also provide a computer readable storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the method embodiments described above when run.
In the present embodiment, the above-described computer-readable storage medium may be configured to store a computer program for performing the steps of:
s1, acquiring target parameters of a target disk, wherein the target parameters comprise data on a plurality of data dimensions, and one data dimension corresponds to one type of parameter;
s2, performing dimension reduction processing on the target parameters by using a target model to obtain target dimension reduction parameters;
s3, determining the state of the target disk based on the target dimension reduction parameter.
In one exemplary embodiment, the computer readable storage medium may include, but is not limited to: a usb disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing a computer program.
An embodiment of the application also provides an electronic device comprising a memory having stored therein a computer program and a processor arranged to run the computer program to perform the steps of any of the method embodiments described above.
In an exemplary embodiment, the above-mentioned processor may be arranged to perform the following steps by means of a computer program:
s1, acquiring target parameters of a target disk, wherein the target parameters comprise data on a plurality of data dimensions, and one data dimension corresponds to one type of parameter;
s2, performing dimension reduction processing on the target parameters by using a target model to obtain target dimension reduction parameters;
s3, determining the state of the target disk based on the target dimension reduction parameter.
In an exemplary embodiment, the electronic device may further include a transmission device connected to the processor, and an input/output device connected to the processor.
Based on the above process, the state of the disk can be obtained, so that the high-risk disk and the fault disk can be prevented and processed in a targeted manner, such as timely replacement. The data and business safety is ensured, and an improvement direction is provided for disk hardware manufacturers. In addition, reducing disk failures can bring many economic benefits to enterprises, and first, reducing disk failures can reduce maintenance costs. Disk failures frequently result in maintenance costs for engineers, which can all affect the financial aspects of the enterprise. Secondly, reducing disk faults can also improve the reliability of the disk, thereby improving the business efficiency of enterprises. When the failure rate of the disk is low, the reliability of the disk is improved. Therefore, the normal operation of the magnetic disk can be ensured, and the influence on the normal operation of the service due to the fault of the magnetic disk is avoided. Therefore, the business efficiency of the enterprise can be effectively improved, and the economic benefit of the enterprise is improved. Finally, reducing disk failures may also increase the reputation of the enterprise. When the enterprise can reduce the disk faults and ensure the normal operation of the service, the trust degree of the client to the enterprise is improved.
Specific examples in this embodiment may refer to the examples described in the foregoing embodiments and the exemplary implementation, and this embodiment is not described herein.
It will be appreciated by those skilled in the art that the modules or steps of the application described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, they may be implemented in program code executable by computing devices, so that they may be stored in a storage device for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than that shown or described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple modules or steps of them may be fabricated into a single integrated circuit module. Thus, the present application is not limited to any specific combination of hardware and software.
The above description is only of the preferred embodiments of the present application and is not intended to limit the present application, but various modifications and variations can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the principle of the present application should be included in the protection scope of the present application.
Claims (10)
1. A method for determining a state of a disk, comprising:
acquiring target parameters of a target disk, wherein the target parameters comprise data on a plurality of data dimensions, and one data dimension corresponds to one type of parameter;
performing dimension reduction processing on the target parameters by using a target model to obtain target dimension reduction parameters;
and determining the state of the target disk based on the target dimension reduction parameter.
2. The method of claim 1, wherein performing the dimension reduction on the target parameter using a target model to obtain a target dimension reduction parameter comprises:
and performing dimension reduction processing on the target parameters by utilizing a fisher linear discriminant analysis FLDA model to obtain the one-dimensional target dimension reduction parameters.
3. The method of claim 1, wherein determining the state of the target disk based on the target dimension reduction parameter comprises:
comparing the target dimension reduction parameter with a pre-configured target threshold under the condition that the target dimension reduction parameter is one-dimensional data;
and determining the state of the target disk based on the comparison result.
4. The method of claim 3, wherein determining the state of the target disk based on the comparison result comprises:
under the condition that the target dimension reduction parameter is greater than or equal to the target threshold value, determining the state of the target disk as a fault disk;
and under the condition that the target dimension reduction parameter is smaller than the target threshold value, determining the state of the target disk as a normal disk.
5. The method of claim 3, wherein determining the state of the target disk based on the comparison result comprises:
determining a difference value between the target dimension reduction parameter and the target threshold value based on a comparison result;
determining a normal level of the target disk based on the difference value when the difference value is less than 0, wherein the smaller the difference value is, the higher the level of the normal level is;
and determining the fault level of the target disk based on the difference value when the difference value is greater than or equal to 0, wherein the greater the difference value is, the higher the level of the fault level is.
6. The method according to any one of claims 3-5, further comprising:
adjusting the target threshold under a target trigger condition, wherein the target trigger condition comprises at least one of:
receiving an adjustment request sent by other equipment;
and detecting that the fault tolerance of the disk changes.
7. The method of any of claims 1-6, wherein after determining the state of the target disk based on the target dimension reduction parameter, the method further comprises:
and executing an alarm operation under the condition that the state of the target magnetic disk is determined to be a fault state, wherein the alarm operation comprises at least one of the following steps:
sending a first alarm message to a background server to instruct the server to inform an operation and maintenance person to replace the target disk, wherein the first alarm message carries first multimedia alarm information;
and sending a second alarm message to the target terminal to instruct a user of the target terminal to replace the target disk, wherein the second alarm message carries second multimedia alarm information.
8. A disk state determining apparatus, comprising:
the system comprises an acquisition module, a storage module and a storage module, wherein the acquisition module is used for acquiring target parameters of a target disk, the target parameters comprise data on a plurality of data dimensions, and one data dimension corresponds to one type of parameter;
the processing module is used for performing dimension reduction processing on the target parameters by utilizing the target model to obtain target dimension reduction parameters;
and the determining module is used for determining the state of the target disk based on the target dimension reduction parameter.
9. A computer readable storage medium, characterized in that a computer program is stored in the computer readable storage medium, wherein the computer program, when being executed by a processor, implements the steps of the method according to any of the claims 1 to 7.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method of any one of claims 1 to 7 when the computer program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310787899.5A CN116820339A (en) | 2023-06-29 | 2023-06-29 | Method and device for determining disk state, storage medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310787899.5A CN116820339A (en) | 2023-06-29 | 2023-06-29 | Method and device for determining disk state, storage medium and electronic device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116820339A true CN116820339A (en) | 2023-09-29 |
Family
ID=88125488
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310787899.5A Pending CN116820339A (en) | 2023-06-29 | 2023-06-29 | Method and device for determining disk state, storage medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116820339A (en) |
-
2023
- 2023-06-29 CN CN202310787899.5A patent/CN116820339A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | Hard drive failure prediction using decision trees | |
| CN108647136B (en) | Hard disk damage prediction method and device based on SMART information and deep learning | |
| CN107025153B (en) | Disk failure prediction method and device | |
| CN110164501B (en) | Hard disk detection method, device, storage medium and equipment | |
| US10147048B2 (en) | Storage device lifetime monitoring system and storage device lifetime monitoring method thereof | |
| CN111966569B (en) | Hard disk health evaluation method and device and computer readable storage medium | |
| KR101948634B1 (en) | Failure prediction method of system resource for smart computing | |
| Lim et al. | Identifying recurrent and unknown performance issues | |
| CN111104293A (en) | Method, apparatus and computer program product for supporting disk failure prediction | |
| CN110119344B (en) | Hard disk health state analysis method based on S.M.A.R.T. parameters | |
| Huang et al. | Characterizing disk failures with quantified disk degradation signatures: An early experience | |
| EP4078380B1 (en) | Behavior-driven die management on solid-state drives | |
| CN111858108B (en) | Hard disk fault prediction method and device, electronic equipment and storage medium | |
| CN113778766B (en) | Hard disk fault prediction model establishment method based on multidimensional characteristics and application thereof | |
| WO2022001125A1 (en) | Method, system and device for predicting storage failure in storage system | |
| CN111813585A (en) | Prediction and processing of slow discs | |
| CN112951311A (en) | Hard disk fault prediction method and system based on variable weight random forest | |
| DE112019005558T5 (en) | USE OF ERROR CORRECTION-BASED METRICS TO IDENTIFY BADLY FUNCTIONING DATA STORAGE DEVICES | |
| CN111949459B (en) | Hard disk failure prediction method and system based on transfer learning and active learning | |
| Zhang et al. | Multi-view feature-based {SSD} failure prediction: What, when, and why | |
| CN117591351A (en) | Disk fault detection model training method and disk fault detection method | |
| Agarwal et al. | Discovering rules from disk events for predicting hard drive failures | |
| CN116820339A (en) | Method and device for determining disk state, storage medium and electronic device | |
| CN115794451A (en) | Execution strategy prediction method, device and system based on health state of storage equipment | |
| CN115617604A (en) | Disk failure prediction method and system based on image pattern matching |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |