Method and system for optimizing the number of memory unit scans based on data movement timing

By calculating the comprehensive instability coefficient of the UFS storage unit and dynamically adjusting the data migration timing and scanning times, the problem of unreasonable setting of the UFS storage unit scanning times is solved, and data stability and reliability are improved.

CN120353413BActive Publication Date: 2025-10-17合肥康芯威存储技术有限公司
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202510869554.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-06-26
Publication Date
2025-10-17
Estimated Expiration
2045-06-26

AI Technical Summary

Technical Problem

In existing UFS storage technology, the number of scan times for storage units lacks adaptability to dynamic environments and cannot effectively cope with the nonlinear growth of bit error rates, leading to retention and read disturbance problems.

Method used

By obtaining the temperature, scanning times and decoding time of the storage unit, the comprehensive instability coefficient is calculated, the data migration timing and scanning times are dynamically adjusted, and the maximum scanning times of the storage unit are optimized.

Benefits of technology

The number of scans can be dynamically adjusted according to the ambient temperature and reading frequency, avoiding the retention and read disturbance problems caused by unreasonable scan threshold settings, and improving data stability and reliability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120353413B_ABST
    Figure CN120353413B_ABST
Patent Text Reader

Abstract

The storage unit scanning frequency optimization method and system based on data migration timing, for any one storage unit: according to the starting record time, the time period corresponding to the current time is obtained; according to the temperature of the storage unit at each time in the time period corresponding to the current time, the decoding time and the scanning frequency of each reading of the storage unit, the comprehensive instability coefficient of the current time is obtained, and then it is judged whether the data migration of the storage unit is carried out at the current time, so as to control the maximum scanning frequency of the storage unit; when data migration is needed, the starting record time is updated, and it is judged whether the data migration of the storage unit is carried out at the next time. By comprehensively considering the temperature, scanning frequency and maximum decoding time of each storage unit, the data migration timing is determined, so that the maximum scanning frequency of the storage unit is more reasonable, and the problems of data storage capacity and read interference caused by too high or too low scanning threshold are avoided.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of UFS storage, and particularly relates to a storage unit scanning frequency optimization method and system based on data migration timing. BACKGROUND

[0002] UFS (Universal Flash Storage) uses NAND Flash as the storage medium, and its data retention capability will gradually deteriorate over time. Specifically, the error bit rate of each storage unit will gradually increase, and when the error bit rate exceeds the error correction threshold of UFS, data loss will occur. In order to solve the retention problem, UFS usually performs a storage unit scanning task periodically, that is, by reading each storage unit to detect the error bit rate, the storage unit with a high error bit rate is found, and the data is reprogrammed to ensure data correctness.

[0003] However, frequent read operations, although helpful in discovering and correcting data errors, can cause read disturb problems in NAND Flash. Read disturb mainly reflects the possibility of disturbing other storage units in the same physical block, thereby affecting the stability of the stored data.

[0004] In existing methods, in order to balance data reliability and read disturb risk, the scanning frequency of the storage unit is often limited by setting a threshold value, so that when the read frequency of the storage unit reaches the scanning threshold, the data is moved to a new NAND Flash block to avoid further data instability caused by read disturb.

[0005] However, the existing method ignores the individual differences of NAND Flash and lacks dynamic environmental adaptability, and cannot adjust the set scanning threshold in real time according to the environmental conditions such as temperature of the individual storage unit, making it difficult to cope with the nonlinear growth of error bit rate.

[0006] Therefore, it is necessary to design a method that can make the maximum scanning frequency of the storage unit more reasonable, to avoid the Retention problem and the Read Disturb problem caused by unreasonable setting of the scanning threshold. SUMMARY

[0007] The technical problem solved by the present application is how to make the maximum scanning frequency of each storage unit more reasonable.

[0008] According to a first aspect, in an embodiment, a storage unit scanning frequency optimization method based on data migration timing is provided, comprising:

[0009] For any one storage unit: obtaining a starting recording time, obtaining a time period corresponding to a current time according to the starting recording time; obtaining a temperature instability coefficient of each time in the time period corresponding to the current time according to the temperature of each time in the time period and the first mapping table;

[0010] obtaining a scanning instability coefficient of the time period corresponding to the current time according to the scanning times in the time period and the instability increment;

[0011] obtaining a comprehensive instability coefficient of the current time according to the scanning instability coefficient of the time period corresponding to the current time, the temperature instability coefficient of each time and the decoding time consumption of each reading of the storage unit; judging whether data migration of the storage unit is needed at the current time according to the comprehensive instability coefficient of the current time, so as to control the maximum scanning times of the storage unit;

[0012] when the data migration of the storage unit is not needed at the current time, continuing to judge whether data migration of the storage unit is needed at the next time according to the starting recording time;

[0013] when the data migration of the storage unit is needed at the current time, performing data migration, updating the starting recording time, and judging whether data migration of the storage unit is needed at the next time according to the updated starting recording time.

[0014] According to the second aspect, an embodiment provides a storage unit scanning times optimization system based on data migration time, comprising:

[0015] a target parameter obtaining unit configured to obtain a target parameter of any one storage unit, wherein the target parameter comprises the temperature of the storage unit at each time, the decoding time consumption of each reading of the storage unit and the scanning times of the storage unit in a time period corresponding to a current time;

[0016] and a processor configured to:

[0017] For any one storage unit: obtaining a starting recording time, obtaining a time period corresponding to a current time according to the starting recording time; obtaining a temperature instability coefficient of each time in the time period corresponding to the current time according to the temperature of each time in the time period and the first mapping table;

[0018] obtaining a scanning instability coefficient of the time period corresponding to the current time according to the scanning times in the time period and the instability increment;

[0019] According to the scan instability coefficient of the storage unit in the time period corresponding to the current time, the temperature instability coefficient of each time, and the decoding time consumption when reading the storage unit each time, a comprehensive instability coefficient of the current time is obtained; according to the comprehensive instability coefficient of the current time, it is judged whether data migration is needed for the storage unit at the current time, so as to control the maximum scan times of the storage unit;

[0020] When data migration is not needed for the storage unit at the current time, it is continued to be judged whether data migration is needed for the storage unit at the next time according to the starting recording time;

[0021] When data migration is needed for the storage unit at the current time, data migration is performed, the starting recording time is updated, and it is judged whether data migration is needed for the storage unit at the next time according to the updated starting recording time.

[0022] According to the storage unit scan times optimization method and system based on data migration time in the above embodiment, the comprehensive instability coefficient of the current time is obtained according to the temperature of each time in the time period corresponding to the current time of the storage unit, the decoding time consumption when reading the storage unit each time, and the scan times; then, according to the comprehensive instability coefficient of the current time, it is judged whether data migration is needed for the storage unit at the current time, so as to determine the time of data migration and control the maximum scan times of the storage unit; the temperature instability coefficient is adjusted according to the temperature of the storage unit, so that the maximum scan times of the storage unit are smaller when the ambient temperature is higher, and the maximum scan times of the storage unit are larger when the ambient temperature is lower; the scan instability coefficient is adjusted according to the scan times of the storage unit in the time period corresponding to the current time, so as to ensure the stability of the data in the storage unit, especially the storage unit which needs to be frequently read; the decoding instability coefficient is adjusted according to the maximum decoding time consumption of the storage unit in the time period corresponding to the current time, so as to ensure the reliability of the data in the storage unit; thus, by comprehensively considering the temperature of the environment where each storage unit is located, the scan times of the storage unit, and the maximum decoding time consumption generated in the process of reading the storage unit, the maximum scan times of the storage unit are more reasonable, and the Retention problem and the Read Disturb problem caused by the too high or too low of the scan threshold value are avoided. BRIEF DESCRIPTION OF DRAWINGS

[0023] Figure 1 The method flow chart of the storage unit scan times optimization method based on data migration time;

[0024] Figure 2 The system block diagram of the storage unit scan times optimization system based on data migration time. DETAILED DESCRIPTION

[0025] The application will be described in further detail below with reference to the drawings. Like elements in different embodiments are denoted by like reference numerals. In the following description, numerous specific details are described to provide a thorough understanding of the application. However, it will be apparent to one skilled in the art that the application can be practiced without these specific details. In other instances, well-known structures have not been shown or described in detail to avoid obscuring aspects of the application. The detailed description is presented largely in terms of elements, procedures, steps, and / or blocks that accomplish certain tasks or accomplish certain abstract

[0026] In addition, features, operations, or steps described in the specification can be combined in any suitable manner without departing from the scope of the application. Similarly, the various steps or acts in a method can be combined, reordered, or omitted without departing from the scope of the application. Accordingly, the specification and drawings are to be regarded as illustrative in nature and not as restrictive.

[0027] The serial numbers of components in the specification, such as "first", "second", etc., are used only to distinguish the described objects and do not have any sequential or technical meaning. The application refers to "connection" and "coupling", unless otherwise specified, which includes direct and indirect connection (coupling).

[0028] In the embodiments of the application, the comprehensive instability coefficient is calculated by comprehensively considering the temperature change, the number of scans, and the decoding time consumption of a single storage unit (NAND Flash) in a period of time, so as to determine the data migration timing and transfer the data to a safe NAND Flash block, thereby avoiding the influence of too high or too low number of scans on the storage unit, and thus making the maximum number of scans of the storage unit more reasonable.

[0029] Please refer to Figure 1 In some embodiments, a storage unit scan number optimization method based on data migration timing is provided, comprising:

[0030] Step S100: For any one storage unit, obtaining a starting recording time, and obtaining a time period corresponding to a current time according to the starting recording time.

[0031] For any one storage unit, the next time of the time corresponding to the last data migration of the storage unit is taken as the starting recording time in the embodiment, and if the storage unit has not undergone data migration, the starting recording time is the first time.

[0032] For example, assuming that the current time is the tth time, if the storage unit is at the mth time corresponding to the last data migration, the m+1th time is taken as the starting recording time of the current time; and the time period from the m+1th time to the tth time is taken as the time period corresponding to the current time. Subsequently, the comprehensive instability coefficient is calculated by analyzing the temperature, scanning times and decoding time consumption in the time period to determine whether data migration is needed at the current time.

[0033] Step S110: According to the temperature of each time in the time period corresponding to the current time of the storage unit, the decoding time consumption and the scanning times when reading the storage unit each time, the comprehensive instability coefficient of the current time is obtained.

[0034] Since the higher the temperature of the environment in which the NAND Flash is located, the faster the data reliability deteriorates over time, the embodiment adds a temperature acquisition unit, such as a temperature sensor, inside the UFS to record the temperature change of the NAND Flash, and when the storage unit experiences a high temperature, it is mapped to a larger temperature instability coefficient, so that the comprehensive instability coefficient of the storage unit approaches the upper limit (i.e. the preset instability threshold) faster; and when the storage unit experiences a low temperature, it is mapped to a larger temperature instability coefficient, so that the comprehensive instability coefficient of the storage unit approaches the upper limit more slowly, thereby obtaining the maximum acceptable scanning times of the storage unit under different temperature environments, realizing that the higher the temperature experienced by the storage unit, the lower the corresponding maximum scanning times; the lower the temperature experienced by the storage unit, the higher the corresponding maximum scanning times, so that the maximum scanning times are more reasonable.

[0035] It should be noted that the temperature reading method can be to add a temperature sensor inside the UFS, or to use the temperature sensor inside the NAND Flash, and the specific temperature acquisition method is not limited.

[0036] The temperature of the storage unit is recorded once every fixed time; then the temperature instability coefficient of each time in the time period corresponding to the current time is obtained according to the temperature of each time in the time period. For example, the temperature instability coefficient of each time is obtained according to the temperature of each time in the time period corresponding to the current time and a first mapping table. The first mapping table is shown in Table 1:

[0037] Table 1

[0038]

[0039] The correspondence between different temperatures and temperature instability coefficients is shown in Table 1. It should be noted that if the temperature of the storage unit at a certain time cannot be directly found in the first mapping table, the corresponding temperature instability coefficient can be obtained by linear interpolation; or the temperature instability coefficient corresponding to the closest temperature is taken as the temperature instability coefficient corresponding to the temperature.

[0040] Generally, the storage unit is scanned once by a fixed frequency, but considering that excessive reading of local hot cells can accelerate data corruption, the number of scans of the storage unit in the time period corresponding to the current time also needs to be further considered; therefore, according to the number of scans in the time period corresponding to the current time, the embodiment obtains the scan instability coefficient of the time period.

[0041] For example, the number of scans in the time period corresponding to the current time is obtained; then the product of the obtained number of scans and the instability increment is calculated, and the obtained product is taken as the scan instability coefficient; wherein the instability increment increases by one for each scan in the time period corresponding to the current time, and the value can be obtained by experimental statistics.

[0042] The decoding time of the storage unit refers to the time required for error correction decoding of the original read data when the UFS (or NAND Flash) reads the data of the storage unit; when the error rate of the storage unit is high, the error correction algorithm needs to process more error bits, resulting in an increase in the number of decoding iterations; and with the increase in the number of Program / Erase cycles, the state of the NAND Flash itself is affected, which also leads to an increase in the error rate; therefore, the larger the decoding time, the more errors there are in the storage unit, and the more reliable the data in the storage unit, the more data migration is needed; therefore, the embodiment further designs a timer in the chip to record the decoding time of each storage unit when reading, and then obtains the decoding instability coefficient of the time period corresponding to the current time according to the decoding time of each reading.

[0043] It should be noted that the method of recording the decoding time can be to add a separate device for timing in the chip, or to time by software, and the specific method of obtaining the decoding time is not limited.

[0044] For example, the maximum decoding time required for each reading of the storage unit in the time period corresponding to the current time is obtained, and the maximum decoding time is obtained; and the decoding instability coefficient is obtained according to the obtained maximum decoding time and the second mapping table. The second mapping table is shown in Table 2.

[0045] Table 2

[0046]

[0047] The correspondence between the range of different decoding time consumption and the decoding instability coefficient is shown in Table 2, and the corresponding decoding instability coefficient is obtained by looking up the range of the maximum decoding time consumption.

[0048] The comprehensive instability coefficient of the current time is obtained according to the scanning instability coefficient of the time period corresponding to the current time, the decoding instability coefficient, and the temperature instability coefficient of each time in the time period; in this embodiment, the sum of the temperature instability coefficient of each time in the time period is added to the scanning instability coefficient and the decoding instability coefficient, and the obtained sum is taken as the comprehensive instability coefficient of the current time.

[0049] Step S120: According to the comprehensive instability coefficient of the current time, it is judged whether the data migration of the storage unit is performed at the current time to control the maximum scanning times of the storage unit.

[0050] After obtaining the comprehensive instability coefficient of the current time, if the comprehensive instability coefficient of the current time is greater than or equal to the preset instability threshold, the data migration of the storage unit is needed at the current time; otherwise, the data migration of the storage unit is not needed at the current time.

[0051] When the data migration of the storage unit is not needed at the current time, it is continued to judge whether the data migration of the storage unit is performed at the next time according to the starting recording time;

[0052] When the data migration of the storage unit is needed at the current time, the data migration is performed, the starting recording time is updated, and it is judged whether the data migration of the storage unit is performed at the next time according to the updated starting recording time. That is, after the completion of one data migration, the scanning times, the temperature of each time, the decoding time consumption and the like are recorded again from the next time, and when the comprehensive instability coefficient corresponding to the subsequent times reaches the preset instability threshold again, the data migration of the storage unit is performed again, and so on.

[0053] Taking a certain storage unit as an example, the temperature of each minute, whether to scan, the decoding time consumption, and the corresponding temperature instability coefficient, scanning instability coefficient, decoding instability coefficient and comprehensive instability coefficient of the storage unit from the first time (or the next time of the time corresponding to the last data migration) are shown in Table 3:

[0054] Table 3

[0055]

[0056] For example, assume that the preset instability threshold is 110, i.e., when the integrated instability coefficient at a time instant is greater than or equal to 110, data migration needs to be performed at the time instant; in addition, the storage unit needs to be scanned every three minutes; and "NA" represents a missing value.

[0057] If the current time instant is the 4th minute, the time period corresponding to the current time instant is the 1st minute (the starting recording time instant) to the 4th minute, the temperature instabilities of the storage unit at each minute in the time period are 12, 12, 13, and 13 respectively; the storage unit is scanned once in the time period, and if the instability increment is 10, the scanning instability coefficient corresponding to the current time instant is 10; the maximum decoding time consumption in the time period is 6 μs , the decoding instability coefficient of the current time instant is 8, and then the cumulative sum of the temperature instability coefficients of each time instant in the time period is added to the scanning instability coefficient and the decoding instability coefficient to obtain the integrated instability coefficient of the current 4th minute, which is 68.

[0058] If the current time instant is the 7th minute, since the integrated instability coefficient at this time instant is 121, which exceeds the preset instability threshold, data migration needs to be performed on the storage unit at this time instant; the next time instant is updated as a new starting recording time instant, i.e., the 8th minute is taken as the new starting recording time instant, and the time period corresponding to each subsequent time instant is reacquired according to the new starting recording time instant, and whether data migration needs to be performed at each subsequent time instant is determined.

[0059] At the 11th minute and the 20th minute, the integrated instability coefficient exceeds 110 (the preset instability threshold), so data migration needs to be performed on the storage unit at the 11th minute and the 20th minute.

[0060] In addition, in Table 3, the temperature experienced by the storage unit is high from the 8th minute to the 11th minute, indicating that the storage unit is in a high-temperature environment from the 8th minute to the 11th minute, and data migration is performed once after only one scan; the temperature experienced by the storage unit is low from the 12th minute to the 20th minute, indicating that the storage unit is in a low-temperature environment from the 12th minute to the 20th minute, and data migration is performed after a total of three scans; in this example, the corresponding scanning threshold is one time when the storage unit is in a high-temperature environment, and the corresponding scanning threshold is three times when the storage unit is in a low-temperature environment; i.e., the method in this embodiment can be adjusted in real time according to the environmental conditions of each storage unit, so that the maximum number of scans of each storage unit is more reasonable.

[0061] The embodiment obtains the comprehensive instability coefficient of the current time according to the number of scans in the time period corresponding to the current time, and the temperature and decoding time consumption of each time in the time period corresponding to the current time; then judges whether to perform data migration on the storage unit at the current time according to the comprehensive instability coefficient of the current time, so as to determine the timing of data migration and control the maximum number of scans of the storage unit; adjusts the temperature instability coefficient according to the temperature of the storage unit, so as to realize that the maximum number of scans of the storage unit is smaller when the ambient temperature is higher, and the maximum number of scans of the storage unit is larger when the ambient temperature is lower; adjusts the scan instability coefficient according to the number of scans of the storage unit in the time period corresponding to the current time, so as to ensure the stability of data in the storage unit, especially the storage unit that needs to be frequently read; adjusts the decoding instability coefficient according to the maximum decoding time consumption of the storage unit in the time period corresponding to the current time, so as to ensure the reliability of data in the storage unit; thus, by comprehensively considering the temperature of the environment where each storage unit is located, the number of scans of the storage unit, and the maximum decoding time consumption generated in the process of reading the storage unit, the maximum number of scans of the storage unit is more reasonable, and the Retention problem and the Read Disturb problem caused by the excessively high or low setting of the scan threshold value are avoided.

[0062] Reference is made to Figure 2 In some embodiments, a storage unit scan number optimization system based on data migration timing is provided, comprising:

[0063] The target parameter acquisition unit 200 is configured to acquire the target parameters of any storage unit, wherein the target parameters include the temperature of the storage unit at each time, the decoding time consumption when reading the storage unit each time, and the number of scans of the storage unit in the time period corresponding to the current time.

[0064] The processor 210 is configured to:

[0065] For any storage unit: acquire the starting recording time, and obtain the time period corresponding to the current time according to the starting recording time; obtain the temperature instability coefficient of each time in the time period according to the temperature of each time in the time period corresponding to the current time and the first mapping table; obtain the scan instability coefficient of the time period according to the number of scans in the time period corresponding to the current time and the instability increment; obtain the comprehensive instability coefficient of the current time according to the scan instability coefficient of the time period corresponding to the current time, the temperature instability coefficient of each time, and the decoding time consumption when reading the storage unit each time; and judge whether to perform data migration on the storage unit at the current time according to the comprehensive instability coefficient of the current time, so as to control the maximum number of scans of the storage unit.

[0066] When data migration is not needed for the storage unit at the current time, it is determined whether data migration is needed for the storage unit at the next time according to the start record time;

[0067] When data migration is needed for the storage unit at the current time, data migration is performed, the start record time is updated, and it is determined whether data migration is needed for the storage unit at the next time according to the updated start record time.

[0068] It should be noted that the processor processing process in the embodiment corresponds to the method steps of the storage unit scanning frequency optimization method based on the data migration time, and the specific implementation has been described in the above embodiment, which will not be repeated here.

[0069] Those skilled in the art can understand that all or part of the functions of the various methods in the above embodiments can be realized by hardware or by a computer program. When all or part of the functions in the above embodiments are realized by a computer program, the program can be stored in a computer readable storage medium, which can include read-only memory, random access memory, magnetic disk, optical disk, hard disk, etc. The above functions are realized by executing the program by a computer. For example, the program is stored in the memory of the device, and when the program in the memory is executed by the processor, the above all or part of the functions are realized. In addition, when all or part of the functions in the above embodiments are realized by a computer program, the program can also be stored in a server, another computer, a disk, an optical disk, a flash disk or a mobile hard disk, etc. storage medium, saved to the memory of the local device by downloading or copying, or the system of the local device is updated, and when the program in the memory is executed by the processor, all or part of the functions in the above embodiments are realized.

[0070] The above application of specific examples is used to illustrate the present application, which is only used to help understand the present application and does not limit the present application. For those skilled in the art to which the present application belongs, according to the idea of the present application, several simple deductions, deformations or substitutions can be made.

Claims

1. A method for optimizing the number of storage unit scans based on data migration timing, characterized in that: include: For any storage unit: obtaining a start recording time, obtaining a time period corresponding to the current time according to the start recording time; obtaining a temperature instability coefficient at each time period in the time period corresponding to the current time according to the temperature at each time period and the first mapping table; Obtain the scanning instability coefficient of the time period according to the number of scans and the unstable increment in the time period corresponding to the current moment; Obtaining a comprehensive instability coefficient at the current moment based on the scanning instability coefficient of the storage unit in the time period corresponding to the current moment, the temperature instability coefficient at each moment, and the decoding time consumed when reading the storage unit each time; According to the comprehensive instability coefficient at the current moment, it is determined whether to move data to the storage unit at the current moment to control the maximum number of scans of the storage unit; When data migration is not required for the storage unit at the current moment, determining whether to migrate data for the storage unit at the next moment according to the start recording moment; When data needs to be moved from the storage unit at the current moment, the data is moved, the starting recording time is updated, and based on the updated starting recording time, it is determined whether to move data from the storage unit at the next moment.

2. The method for optimizing the number of storage unit scans based on data migration timing according to claim 1, wherein: The obtaining of the start recording time includes: taking the next moment after the moment corresponding to the last data migration as the start recording time; wherein, if the storage unit has not undergone data migration, the start recording time is the first moment.

3. The method for optimizing the number of storage unit scans based on data migration timing according to claim 1, wherein: The method of obtaining a comprehensive instability coefficient at the current moment based on the scanning instability coefficient of the storage unit in the time period corresponding to the current moment, the temperature instability coefficient at each moment, and the decoding time consumed when the storage unit is read each time includes: Obtaining a decoding instability coefficient for the time period according to the decoding time consumed when the storage unit is read each time in the time period corresponding to the current moment; The comprehensive instability coefficient at the current moment is obtained according to the scanning instability coefficient and the decoding instability coefficient of the time period corresponding to the current moment and the temperature instability coefficient at each moment in the time period.

4. The method for optimizing the number of storage unit scans based on data migration timing according to claim 1, wherein: The method of obtaining the scanning instability coefficient of the time period based on the number of scans and the unstable increment in the time period corresponding to the current moment includes: obtaining the number of scans in the time period corresponding to the current moment; calculating the product between the number of scans and the unstable increment, and using the obtained product as the scanning instability coefficient.

5. The method for optimizing the number of storage unit scans based on data migration timing according to claim 3, wherein: The decoding instability coefficient of the time period is obtained based on the decoding time consumption when the storage unit is read each time in the time period corresponding to the current moment, including: obtaining the maximum value of the corresponding decoding time consumption when the storage unit is read each time in the time period corresponding to the current moment to obtain the maximum decoding time consumption; and obtaining the decoding instability coefficient based on the maximum decoding time consumption and the second mapping table.

6. The method for optimizing the number of storage unit scans based on data migration timing according to claim 3, wherein: The comprehensive instability coefficient at the current moment is obtained based on the scanning instability coefficient, decoding instability coefficient and temperature instability coefficient of the time period corresponding to the current moment, including: calculating the cumulative sum of the temperature instability coefficient at each moment in the time period, adding the cumulative sum to the scanning instability coefficient and decoding instability coefficient, and using the obtained addition result as the comprehensive instability coefficient.

7. The method for optimizing the number of storage unit scans based on data migration timing according to claim 1, wherein: The method of judging whether to move data of the storage unit at the current moment based on the comprehensive instability coefficient at the current moment includes: if the comprehensive instability coefficient at the current moment is greater than or equal to the preset instability threshold, then data needs to be moved to the storage unit at the current moment; otherwise, data does not need to be moved to the storage unit at the current moment.

8. A system for optimizing the number of storage unit scans based on data migration timing, characterized in that: include: a target parameter acquisition unit, configured to acquire target parameters of any storage unit, wherein the target parameters include the temperature of the storage unit at each moment, the decoding time consumed when reading the storage unit each time, and the number of scans of the storage unit in the time period corresponding to the current moment; and a processor for: For any storage unit: obtain the starting recording time, and obtain the time period corresponding to the current time according to the starting recording time; obtain the temperature instability coefficient at each moment in the time period corresponding to the current time according to the temperature at each moment in the time period and the first mapping table; obtain the scanning instability coefficient of the time period according to the number of scans and the unstable increment in the time period corresponding to the current time; obtain the comprehensive instability coefficient at the current moment according to the scanning instability coefficient of the storage unit in the time period corresponding to the current moment, the temperature instability coefficient at each moment, and the decoding time consumed when the storage unit is read each time; and determine whether to move data to the storage unit at the current moment according to the comprehensive instability coefficient at the current moment, so as to control the maximum number of scans of the storage unit; When data migration is not required for the storage unit at the current moment, determining whether to migrate data for the storage unit at the next moment according to the start recording moment; When data needs to be moved from the storage unit at the current moment, the data is moved, the starting recording time is updated, and based on the updated starting recording time, it is determined whether to move data from the storage unit at the next moment.

9. A computer-readable storage medium, characterized in that The medium stores a computer program, which can be executed by a processor to implement the method for optimizing the number of storage unit scans based on data migration timing according to any one of claims 1 to 7.

Citation Information

Patent Citations

  • Storage error correction method and device for NAND Flash and storage medium

    CN117724888A

  • Method for managing threshold voltage, and method for reading flash data

    US20230298676A1