Solid state disk global wear leveling system

Abstract

The invention relates to the technical field of solid state disks, and discloses a solid state disk global wear leveling system, which comprises an SSD data acquisition module, an SSD data analysis module, an SSD evaluation module and an SSD leveling module, and is characterized in that the SSD data acquisition module is used for being connected with a built-in tool of an operating system to acquire temperature data, state data and performance data of an SSD; the SSD data analysis module calculates an SSD temperature index, an SSD state index and an SSD performance index according to the collected data, then the values are evaluated through the SSD evaluation module, whether wear leveling needs to be carried out or not is judged, signals are sent to the SSD leveling module under the condition that wear leveling needs to be carried out, multi-aspect comprehensive analysis is carried out, potential problems are found in time, and the service life of the SSD is prolonged. The state of the SSD is known more comprehensively, the misjudgment risk caused by only depending on a single index is reduced, system faults caused by performance reduction or hardware problems are avoided, unnecessary read-write operation is reduced, abrasion balance is optimized, and the overall service life of the SSD is prolonged.

Description

Technical Field

[0001] The present invention relates to the technical field of solid state hard disks, and in particular to a global wear leveling system for solid state hard disks. Background Art

[0002] The main function of the global wear leveling system of the solid-state drive is to extend the service life of the SSD. Since the number of times the flash memory can be erased and written is limited, some data blocks may prematurely exhaust their service life due to frequent modifications, rendering the entire disk unusable. To avoid this, the global wear leveling system spreads the erase and write operations evenly across the data blocks to prevent some blocks from being exhausted prematurely. The global wear leveling system not only performs balancing within a single hard disk, but also includes all hard disks in the system in the balancing range to ensure that the data blocks of each hard disk can be used evenly, thereby increasing the overall life. This design is more complex and has a larger system overhead, but it provides better protection for the disk.

[0003] Since the storage cells of the solid-state drive have a certain limit on the number of erase and write times, frequently used storage cells will quickly reach their life limit due to frequent erase and write operations, causing these storage cells to be damaged prematurely. As some storage cells are damaged, the data on the SSD may be lost or erroneous. When the number of damaged storage cells increases, the data integrity and reliability of the entire SSD will be affected. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a global wear leveling system for solid-state drives, which has the advantages of more comprehensive understanding of the state of the SSD through multi-dimensional data analysis, reducing the risk of misjudgment by relying on a single indicator, ensuring the accuracy of the analysis, and conducting comprehensive analysis from multiple aspects to timely discover potential problems, avoid system failures caused by performance degradation or hardware problems, reduce unnecessary read and write operations, optimize wear leveling, and extend the overall life of the SSD.

[0005] To achieve the above object, the present invention provides the following technical solutions: a global wear leveling system for a solid state drive, comprising an SSD data acquisition module, an SSD data analysis module, an SSD evaluation module and an SSD leveling module; The SSD data acquisition module is used to connect to the operating system built-in tool to collect temperature data of the SSD. Collect the status data of SSD Collect performance data of SSD The SSD data acquisition module collects the collected data into an SSD temperature data set, an SSD status data set, and an SSD performance data set, respectively, and then saves the data and sends them to the SSD data analysis module; The SSD data analysis module calculates the SSD temperature index based on the SSD temperature data set , calculate the SSD status index based on the SSD status data set , calculate the SSD performance index based on the SSD performance data set , the SSD data analysis module sends the above calculation results to the SSD evaluation module; The SSD evaluation module is preset with an SSD temperature balance threshold, an SSD state balance threshold, and an SSD performance balance threshold, and the above thresholds are respectively compared with the SSD temperature index. , SSD status index , SSD performance index Evaluate and determine whether wear leveling is needed, and send a signal to the SSD balancing module if wear leveling is needed; The SSD balancing module is internally provided with an SSD balancing mechanism, and after receiving the signal, the SSD balancing mechanism is started to perform global wear balancing.

[0006] Preferably, the expression of the SSD temperature data set is: ,in, This is the SSD temperature data collected for the first time in the SSD temperature dataset. It is the SSD temperature data collected last time in the SSD temperature dataset. The data collected in the SSD temperature dataset is , upper right Indicates the time when the corresponding SSD temperature data is collected.

[0007] Preferably, the expression of the SSD status data set is: ,in, The number of times the wear leveling mechanism is executed in the SSD status dataset. is the number of erase / write operations performed on each flash memory cell in the SSD status data set. is the number of spare flash memory cells in the SSD status data set, The remaining lifespan of the SSD in the SSD status dataset is estimated. is the number of abnormal errors in the SSD status dataset, subscript The data above are the collected quantities of corresponding values, and can be obtained through tools provided by SSD manufacturers.

[0008] Preferably, the expression of the SSD performance data set is: ,in, This is the read and write speed data in the SSD performance dataset. Write speed data to the SSD performance data set. This is the random read speed data in the SSD performance dataset. This is the random write speed data in the SSD performance dataset. is the average latency of read and write operations in the SSD performance dataset. is the corresponding data collection quantity. The above data can be obtained through the system task manager.

[0009] Preferably, the SSD temperature index The calculation formula is as follows:

[0010] In the above formula, is the sum of the last five temperature data in the SSD temperature dataset. It is the mean of the sum of the last five temperature data in the SSD temperature dataset.

[0011] Preferably, the SSD status index The calculation formula is as follows:

[0012] In the above formula, the superscript , , , , They are the number of times the wear leveling mechanism is executed in the SSD status dataset, the number of erases and writes performed on each flash memory cell, the number of spare flash memory cells, the estimated remaining life of the SSD, and the corresponding weights of the number of abnormal errors.

[0013] Preferably, the SSD performance index The calculation formula is as follows:

[0014] In the above formula, It is a general standard index in the SSD performance data set.

[0015] Preferably, when the SSD temperature index When the temperature is greater than the SSD temperature balance threshold, a signal is sent to the SSD balance module.

[0016] Preferably, when the SSD status index When the value is greater than the SSD status balancing threshold, a signal is sent to the SSD balancing module.

[0017] Preferably, when the SSD performance index When the value is greater than the SSD performance balancing threshold, a signal is sent to the SSD balancing module.

[0018] Compared with the prior art, the present invention provides a global wear leveling system for solid state drives, which has the following beneficial effects: 1. The present invention monitors the temperature data of SSD And forming an SSD temperature data set helps to adjust the write strategy, which can reduce the impact of high temperature on the life of the SSD, thereby extending the service life of the SSD. At the same time, in a high temperature environment, the wear rate of certain storage units will accelerate. By monitoring the temperature, a solid and powerful data foundation is provided for the global wear leveling of the solid-state drive, which facilitates the system to balance in time when abnormal high temperature is found.

[0019] 2. The present invention improves the accuracy of SSD status analysis by combining the number of times the wear leveling mechanism is executed, the number of erases and writes that have been executed for each flash memory unit, the number of spare flash memory units, the estimated remaining life of the SSD, and the corresponding weights of the number of abnormal errors. Through multi-dimensional data analysis, a more comprehensive understanding of the SSD status is achieved, reducing the risk of misjudgment by relying on only a single indicator, ensuring the accuracy of the analysis. Combined with the SSD read and write speed, write speed, random read speed, random write speed, and the average delay speed of read and write operations, a comprehensive analysis is conducted from multiple aspects to timely discover potential problems, avoid system failures caused by performance degradation or hardware problems, reduce unnecessary read and write operations, optimize wear leveling, and extend the overall life of the SSD. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a schematic diagram of the structural system of the present invention; DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] See also Figure 1 , a solid state drive global wear leveling system, comprising an SSD data acquisition module, an SSD data analysis module, an SSD evaluation module and an SSD leveling module; The SSD data acquisition module is used to connect to the operating system's built-in tools to collect SSD temperature data Collect the status data of SSD Collect performance data of SSD The SSD data acquisition module collects the collected data into an SSD temperature data set, an SSD status data set, and an SSD performance data set, respectively, and then saves the data and sends them to the SSD data analysis module; The expression of the SSD temperature dataset is: ,in, This is the SSD temperature data collected for the first time in the SSD temperature dataset. It is the SSD temperature data collected last time in the SSD temperature dataset. The data collected in the SSD temperature dataset is , upper right Represents the time when the corresponding SSD temperature data is collected; Since high temperature will accelerate the aging and wear of storage units, by monitoring the temperature data of SSD The SSD temperature data set is formed to help adjust the write strategy, reduce the impact of high temperature on the life of the SSD, and thus extend the service life of the SSD. At the same time, in a high temperature environment, the wear rate of some storage units will accelerate. By monitoring the temperature, a solid and powerful data foundation is provided for the global wear leveling of the solid state drive, which facilitates the system to balance in time when abnormal high temperature is found; The expression of the SSD status dataset is: ,in, The number of times the wear leveling mechanism is executed in the SSD status dataset. is the number of erase / write operations performed on each flash memory cell in the SSD status data set. is the number of spare flash memory cells in the SSD status data set, The remaining lifespan of the SSD in the SSD status dataset is estimated. is the number of abnormal errors in the SSD status dataset, subscript The data above can be obtained through tools provided by SSD manufacturers. The overall wear of the SSD can be evaluated by analyzing the number of times the wear leveling mechanism is executed. In the case of too many wear leveling counts, it may mean that some cells have experienced a lot of erasures. By analyzing the number of erasures of each flash memory cell, the wear of the SSD can be understood. If the number of erasures of some cells is close to a large number, it indicates that the health of these cells is poor and may fail. The number of spare flash memory cells and the effective use of spare cells can significantly improve the reliability of data. By analyzing the number of spare flash memory cells, when some cells fail, spare cells can be seamlessly replaced to avoid data loss or damage. The remaining life estimation of the SSD can accurately understand the wear of the SSD and the expected use time, which helps users take measures in advance to avoid sudden failures or data loss due to the exhaustion of the SSD life. The number of abnormal errors is one of the key indicators to measure the health of the SSD. A high number of abnormal errors indicates that there may be faulty or unstable cells inside the SSD. Timely detection of these errors can help users determine whether the SSD needs to be replaced or maintained. The expression of the SSD performance dataset is: ,in, This is the read and write speed data in the SSD performance dataset. Write speed data to the SSD performance data set. This is the random read speed data in the SSD performance dataset. This is the random write speed data in the SSD performance dataset. is the average latency of read and write operations in the SSD performance dataset. is the corresponding data collection quantity. The above data can be obtained through the system task manager; Monitoring the read and write speeds of the SSD can ensure that users get faster responses when accessing data, providing a smoother user experience for daily computing, gaming, or other applications that require high performance. Analyzing the write speed data can timely understand the current write performance of the SSD and identify possible performance bottlenecks or problems. Random read speed data and random write speed data are helpful for comprehensively evaluating the health status and performance of the SSD. The average latency speed of read and write operations can identify areas or units with high latency. These areas may be excessively worn due to frequent read and write operations, or there are other potential hardware problems. After identifying these problem areas, data can be migrated to healthier units through global wear leveling to avoid further deterioration. The SSD data analysis module calculates the SSD temperature index based on the SSD temperature data set. ; SSD Temperature Index The calculation formula is as follows:

[0023] In the above formula, is the sum of the last five temperature data in the SSD temperature dataset. It is the mean of the sum of the last five temperature data in the SSD temperature dataset; The average of the sum of the last five temperature data in the SSD temperature data set and the time of temperature calculation are used to analyze the temperature of the SSD, which effectively reduces the error and makes the temperature data analysis more comprehensive and accurate; The SSD data analysis module calculates the SSD status index based on the SSD status data set. ; SSD Status Index The calculation formula is as follows:

[0024] In the above formula, the superscript , , , , They are the number of times the wear leveling mechanism is executed in the SSD status data set, the number of erases and writes executed for each flash memory cell, the number of spare flash memory cells, the estimated remaining life of the SSD, and the corresponding weights of the number of abnormal errors; By combining the number of times the wear leveling mechanism is executed, the number of times each flash memory unit has been erased and written, the number of spare flash memory units, the estimated remaining life of the SSD, and the corresponding weights of the number of abnormal errors, the accuracy of SSD status analysis is improved. Through multi-dimensional data analysis, a more comprehensive understanding of the SSD status is achieved, reducing the risk of misjudgment by relying on a single indicator, and ensuring the accuracy of the analysis; The SSD data analysis module calculates the SSD performance index based on the SSD performance data set ; SSD Performance Index The calculation formula is as follows:

[0025] In the above formula, It is a general standard index in the SSD performance data set; Combined with the SSD read and write speed, write speed, random read speed, random write speed, and average delay speed of read and write operations, comprehensive analysis from multiple aspects can timely discover potential problems, avoid system failures caused by performance degradation or hardware problems, reduce unnecessary read and write operations, optimize wear leveling, and extend the overall life of the SSD; The SSD data analysis module sends the above calculation results to the SSD evaluation module; The SSD evaluation module has preset SSD temperature balance threshold, SSD status balance threshold, and SSD performance balance threshold, and the above thresholds are respectively compared with the SSD temperature index , SSD status index , SSD performance index Conduct assessments; When the SSD temperature index When the temperature is greater than the SSD temperature balance threshold, a signal is sent to the SSD balance module; When the SSD status index When the value is greater than the SSD status balancing threshold, a signal is sent to the SSD balancing module; When SSD performance index When the value is greater than the SSD performance balancing threshold, a signal is sent to the SSD balancing module; The SSD balancing module is internally provided with an SSD balancing mechanism, which starts the SSD balancing mechanism to perform global wear balancing after receiving the signal.

[0026] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A global wear leveling system for a solid state drive, characterized in that: Including SSD data acquisition module, SSD data analysis module, SSD evaluation module and SSD balancing module; The SSD data acquisition module is used to connect to the operating system built-in tool to collect temperature data of the SSD. Collect the status data of SSD Collect performance data of SSD The SSD data acquisition module collects the collected data into an SSD temperature data set, an SSD status data set, and an SSD performance data set, respectively, and then saves the data and sends them to the SSD data analysis module; The SSD data analysis module calculates the SSD temperature index based on the SSD temperature data set , calculate the SSD status index based on the SSD status data set , calculate the SSD performance index based on the SSD performance data set , the SSD data analysis module sends the above calculation results to the SSD evaluation module; The SSD evaluation module is preset with an SSD temperature balance threshold, an SSD state balance threshold, and an SSD performance balance threshold, and the above thresholds are respectively compared with the SSD temperature index. , SSD status index , SSD performance index Evaluate and determine whether wear leveling is needed, and send a signal to the SSD balancing module if wear leveling is needed; The SSD balancing module is internally provided with an SSD balancing mechanism, and after receiving the signal, the SSD balancing mechanism is started to perform global wear balancing.

2. A global wear leveling system for a solid state drive according to claim 1, characterized in that: The expression of the SSD temperature data set is: ,in, This is the SSD temperature data collected for the first time in the SSD temperature dataset. It is the SSD temperature data collected last time in the SSD temperature dataset. The data collected in the SSD temperature dataset is , upper right Indicates the time when the corresponding SSD temperature data is collected.

3. The global wear leveling system for a solid state drive according to claim 1, characterized in that: The expression of the SSD status data set is: ,in, The number of times the wear leveling mechanism is executed in the SSD status dataset. is the number of erase / write operations performed on each flash memory cell in the SSD status data set. is the number of spare flash memory cells in the SSD status data set, The remaining lifespan of the SSD in the SSD status dataset is estimated. is the number of abnormal errors in the SSD status dataset, subscript The data above are the collected quantities of corresponding values, and can be obtained through tools provided by SSD manufacturers.

4. The global wear leveling system for a solid state drive according to claim 1, characterized in that: The expression of the SSD performance data set is: ,in, This is the read and write speed data in the SSD performance dataset. Write speed data to the SSD performance data set. This is the random read speed data in the SSD performance dataset. This is the random write speed data in the SSD performance dataset. is the average latency of read and write operations in the SSD performance dataset. is the corresponding data collection quantity. The above data can be obtained through the system task manager.

5. The global wear leveling system for a solid state drive according to claim 2, characterized in that: The SSD Temperature Index The calculation formula is as follows: In the above formula, is the sum of the last five temperature data in the SSD temperature dataset. It is the mean of the sum of the last five temperature data in the SSD temperature dataset.

6. The global wear leveling system for a solid state drive according to claim 3, characterized in that: The SSD status index The calculation formula is as follows: In the above formula, the superscript , , , , They are the number of times the wear leveling mechanism is executed in the SSD status dataset, the number of erases and writes performed on each flash memory cell, the number of spare flash memory cells, the estimated remaining life of the SSD, and the corresponding weights of the number of abnormal errors.

7. A global wear leveling system for a solid state drive according to claim 4, characterized in that: The SSD performance index The calculation formula is as follows: In the above formula, It is a general standard index in the SSD performance data set.

8. The global wear leveling system for a solid state drive according to claim 5, characterized in that: When the SSD temperature index When the temperature is greater than the SSD temperature balance threshold, a signal is sent to the SSD balance module.

9. The global wear leveling system for a solid state drive according to claim 6, characterized in that: When the SSD status index When the value is greater than the SSD status balancing threshold, a signal is sent to the SSD balancing module.

10. The global wear leveling system for a solid state drive according to claim 7, characterized in that: When the SSD performance index When the value is greater than the SSD performance balancing threshold, a signal is sent to the SSD balancing module.

Images