A method, device and medium for improving first read success rate of NAND flash in SSD

Abstract

The application provides a method, device and medium for improving the first reading success rate of NAND flash in SSD, and belongs to the technical field of solid-state storage. The method first groups the blocks at the first level according to the wear degree, and then groups them at the second level according to the writing temperature; all retry axis readings are recorded as a and b type axes and the wear degree is recorded when the charge is unstable after writing and the block is not full and the error correction requirement is met; within the maximum storage time, test at different temperatures in different time periods, and record the axes that meet the error correction requirement as c, d and e type axes according to the relationship between the writing and reading temperatures, and record the wear degree and the time length; after reaching the maximum reading interference number, test and record the axes that meet the requirement as f type axes and record the related parameters; select the optimal axis from the same type of axis, build a lookup table, and select the optimal axis according to the scene, so that the first reading success rate in different scenes is effectively improved. The application effectively improves the first reading success rate in different scenes.

Description

Technical Field

[0001] This invention relates to a method, apparatus, and medium for improving the first read success rate of NAND Flash in SSDs, belonging to the field of solid-state storage technology. Background Technology

[0002] In the field of solid-state storage technology, NAND Flash, as a non-volatile memory, is widely used in various electronic devices due to its characteristics of data retention after power loss, small size, and ability to achieve inexpensive, efficient, and large-capacity storage. Generally, a NAND Flash chip consists of numerous blocks, each block contains multiple word lines, and each word line contains several pages. Users can perform erase, write, and read operations on NAND Flash. A block is usually the smallest addressable unit for an erase operation, a word line is the smallest addressable unit for a write operation, and a page is the smallest addressable unit for a read operation.

[0003] As NAND Flash storage density continues to increase, a series of problems are becoming increasingly prominent. First, the threshold voltage distribution offset problem is becoming more severe, posing a challenge to accurate data reading. Second, read disturbances occur frequently, meaning that multiple read operations can interfere with the storage cells, affecting data stability. Furthermore, NAND Flash is extremely sensitive to temperature changes; temperature fluctuations can significantly impact its performance. Traditionally, NAND Flash uses a fixed voltage axis strategy for data reading. However, this strategy is difficult to adapt to today's complex and ever-changing application scenarios.

[0004] In practical applications, the unstable charge after writing can lead to read errors due to the incomplete stabilization of the charge in newly written data. Open blocks, due to their incomplete structure and differing charge distribution from closed blocks, also affect read accuracy. Furthermore, temperature variations, differences in NAND process technology, and voltage shifts caused by multiple reads further reduce the success rate of data reads. Due to the limitations of traditional fixed voltage axis strategies, multiple retry mechanisms are often required to correct errors when the first read fails. However, this retrying approach not only increases data read latency but also significantly increases system power consumption, failing to meet the demands of modern electronic devices for efficient, low-power storage. Therefore, there is an urgent need for an innovative method that can adapt to different scenarios and improve data read success rates to address the read performance bottleneck faced by NAND Flash in complex application environments. Summary of the Invention

[0005] The purpose of this invention is to provide a method, apparatus, and medium for improving the first read success rate of NAND Flash in SSDs. By accurately collecting and analyzing pre-data, the first read success rate in different scenarios can be improved.

[0006] To achieve the above objectives, the present invention employs the following technical solution: A method to improve the first read success rate of NAND Flash in SSDs includes the following steps: The SSD is first grouped according to the wear level of the NAND Flash blocks inside the SSD, and then second grouped according to the temperature range when writing data based on the results of the first grouping. Read all retry axes, identify retry axes that meet the error correction requirements under the condition of unstable charge within a certain period after writing and record them as type A axes, and identify retry axes that meet the error correction requirements under the condition that the block is not yet full within a certain period after writing and record them as type B axes, and record the wear degree at the same time. Test the read voltage axis under different data retention times and temperature scenarios. During the maximum retention time, read all retry axes at different temperatures in different time periods to find the retry axes that meet the error correction requirements. Record them as Class C, Class D, or Class E axes according to the relationship between write and read temperatures. At the same time, record the wear degree and retention time. Under the test of read interference scenario, read voltage axis. After reaching the maximum number of read interferences, read all retry axes, find the retry axis that meets the error correction requirements and record it as class f axis. At the same time, record the wear degree and storage time. For axes of the same wear level and storage duration, class A, B, C, D, E, and F are sorted out, and the optimal reading voltage axis is selected based on whether there are identical axes. A lookup table is built based on the optimal read voltage axis under different wear levels, storage durations, and scenarios, and the optimal axis is selected according to the usage scenario.

[0007] Preferably, the primary grouping is based on the number of programmed erases and is grouped according to an interval of 1000 erases / writes.

[0008] Preferably, the secondary grouping is based on the temperature range when the data is written, and grouped at 10°C intervals.

[0009] Preferably, for blocks that are not fully written within a certain period of time after being written, invalid data of one layer of WL is written into the unwritten block to stabilize the charge of the valid data.

[0010] Preferably, the maximum storage time is divided into ten segments, and all retry axes are read at different temperatures within each time segment.

[0011] Preferably, the c-type axis is an axis with the same writing and reading temperature, the d-type axis is an axis with low-temperature writing and high-temperature reading, and the e-type axis is an axis with high-temperature writing and low-temperature reading.

[0012] Preferably, the specific method for selecting the optimal axis is as follows: if there are identical axes among different types of axes, then use the same axis as the optimal axis; otherwise, select different optimal axes according to different scenarios.

[0013] An apparatus for improving the first-read success rate of NAND Flash in an SSD includes a processor and a memory storing program instructions, the processor being configured to execute the method for improving the first-read success rate of NAND Flash in an SSD when running the program instructions.

[0014] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for improving the first read success rate of NAND Flash in an SSD.

[0015] The advantages of this invention are as follows: This invention fully considers various complex scenarios encountered by NAND Flash in practical applications, covering situations such as unstable charge after writing, incomplete blocks, different temperature conditions, long-term storage, and read interference. Through precise pre-data acquisition and analysis, corresponding dynamic voltage axis adjustment strategies are formulated for different scenarios, effectively improving the first-read success rate under different scenarios. Attached Figure Description

[0016] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof.

[0017] Figure 1 This is a schematic diagram of the method flow of the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Example 1 like Figure 1 As shown, a method to improve the first read success rate of NAND Flash in SSD includes the following steps: S1: Group the SSD according to the wear level of the NAND Flash blocks in the SSD, and then group it according to the temperature range when writing data based on the results of the first grouping. S2: Read all retry axes, identify retry axes that meet the error correction requirements under the condition of unstable charge within a certain period after writing and record them as type a axes, identify retry axes that meet the error correction requirements under the condition that the block is not yet full within a certain period after writing and record them as type b axes, and record the wear degree at the same time. S3: Test the read voltage axis under different data retention times and temperature scenarios. During the maximum retention time, read all retry axes at different temperatures in different time periods to find the retry axis that meets the error correction requirements. Record it as a Class C axis, Class D axis or Class E axis according to the relationship between the write and read temperatures. At the same time, record the wear degree and retention time. S4: Test the reading voltage axis under the reading interference scenario. After reaching the maximum number of reading interferences, read all retry axes, find the retry axis that meets the error correction requirements and record it as a class f axis. At the same time, record the wear degree and the storage time. S5: Organize the axes of type a, b, c, d, e, and f with the same wear level and storage time, and select the optimal reading voltage axis based on whether there are identical axes; S6: Build a lookup table based on the optimal read voltage axis under different wear levels, storage durations and scenarios, and select the optimal axis according to the usage scenario.

[0020] As a refinement of the above embodiment, the first-level grouping in step S1 is based on the number of programmed erases and is grouped according to an interval of 1000 erases and writes.

[0021] Based on the different levels of wear within the SSD, the blocks are grouped into i primary groups. Specifically, during primary grouping, the wear level ranges from PE0 to the end of the NAND Flash lifespan, initially divided into PE0, PE1000, PE2000, PE3000, etc., with an interval of 1000 write cycles.

[0022] The secondary grouping is based on the temperature range when the data is written, and is grouped at 10°C intervals.

[0023] Based on the results of the first-level grouping, the data is then grouped a second time according to the temperature range during SSD data writing. Each first-level group is further divided into j second-level groups. Specifically, during the second-level grouping, the temperature during data writing ranges from 60℃ to 80℃, initially in 10℃ increments: 60℃, 70℃, 80℃, etc.

[0024] As a refinement of the above embodiment, for blocks that are not fully written within a certain period of time after being written, invalid data of one layer of WL is written into the unwritten block to stabilize the charge of the valid data.

[0025] As a refinement of the above embodiment, step S3 specifically involves: long-term storage during power-on and power-off, with the storage period being the maximum storage time provided by the manufacturer. Based on the maximum storage time, the storage time is divided into ten segments. At each time interval, under different temperatures (60℃, 70℃, 80℃), all retry axes provided by the NAND manufacturer are read to identify all retry axes that meet the error correction requirements. Records written and read at the same temperature are classified as Class C axes; records written at low temperatures and read at high temperatures are classified as Class D axes (low-temperature write, high-temperature read); and records written at high temperatures and read at low temperatures are classified as Class E axes (high-temperature write, low-temperature read). The degree of wear and storage duration are recorded simultaneously.

[0026] As a refinement of the above embodiment, in step S6, a table is created to determine the optimal axis for different wear levels and storage durations under different scenarios. The software selects the optimal axis based on the actual scenario, thereby improving the first read success rate (FirstReadSuccessRate, FRSR) under different scenarios.

[0027] This invention aims to provide a method for optimizing the read success rate of NAND Flash in SSDs based on multi-scenario dynamic voltage axis adjustment. This method can comprehensively consider various scenarios of NAND Flash and improve the first read success rate (FRSR) under different scenarios through precise pre-data acquisition and analysis.

[0028] Example 2 This disclosure also provides an apparatus for improving the first-read success rate of NAND Flash memory in an SSD, including a processor and memory. Optionally, the apparatus may further include a communication interface and a bus. The processor, communication interface, and memory can communicate with each other via the bus. The communication interface can be used for information transmission. The processor can invoke logical instructions in the memory to execute the method for improving the first-read success rate of NAND Flash memory in the SSD described above.

[0029] Furthermore, the logical instructions in the aforementioned memory can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium.

[0030] Memory, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of this disclosure. The processor executes functional applications and data processing by running the program instructions / modules stored in the memory, thereby implementing the method described above for improving the first-read success rate of NAND Flash in the SSD.

[0031] The memory may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the terminal device. Furthermore, the memory may include high-speed random access memory and may also include non-volatile memory.

[0032] This disclosure provides a computer-readable storage medium storing computer-executable instructions configured to execute the above-described method for improving the first-read success rate of NAND Flash in an SSD.

[0033] The aforementioned computer-readable storage medium may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0034] The technical solutions of this disclosure can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes one or more instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in this disclosure. The aforementioned storage medium can be a non-transitory storage medium, including: a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and other media capable of storing program code. It can also be a transient storage medium.

[0035] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for improving the first-read success rate of NAND Flash in SSD, characterized in that, Includes the following steps: The SSD is first grouped according to the wear level of the NAND Flash blocks inside the SSD, and then second grouped according to the temperature range when writing data based on the results of the first grouping. Read all retry axes, identify retry axes that meet the error correction requirements under the condition of unstable charge within a certain period after writing and record them as type A axes, and identify retry axes that meet the error correction requirements under the condition that the block is not yet full within a certain period after writing and record them as type B axes, and record the wear degree at the same time. Test the read voltage axis under different data retention times and temperature scenarios. During the maximum retention time, read all retry axes at different temperatures in different time periods to find the retry axes that meet the error correction requirements. Record them as Class C, Class D, or Class E axes according to the relationship between write and read temperatures. At the same time, record the wear degree and retention time. Under the test of read interference scenario, read voltage axis. After reaching the maximum number of read interferences, read all retry axes, find the retry axis that meets the error correction requirements and record it as class f axis. At the same time, record the wear degree and storage time. For axes of the same wear level and storage duration, class A, B, C, D, E, and F are sorted out, and the optimal reading voltage axis is selected based on whether there are identical axes. A lookup table is built based on the optimal read voltage axis under different wear levels, storage durations, and scenarios, and the optimal axis is selected according to the usage scenario.

2. The method for improving the first read success rate of NAND Flash in SSD according to claim 1, characterized in that, The primary grouping is based on the number of programmed erases and is grouped according to an interval of 1000 erase / write cycles.

3. The method for improving the first read success rate of NAND Flash in SSD according to claim 1, characterized in that, The secondary grouping is based on the temperature range when the data is written, and is grouped at 10°C intervals.

4. The method for improving the first read success rate of NAND Flash in SSD according to claim 1, characterized in that, For blocks that are not fully written within a certain period of time after being written, invalid data of one layer of WL is written into the unwritten block to stabilize the charge of the valid data.

5. The method for improving the first read success rate of NAND Flash in SSD according to claim 1, characterized in that, The maximum retention time is divided into ten segments, and all retry axes are read at different temperatures within each time segment.

6. The method for improving the first read success rate of NAND Flash in SSD according to claim 1, characterized in that, The C-type axis is an axis with the same writing and reading temperature, the D-type axis is an axis with low-temperature writing and high-temperature reading, and the E-type axis is an axis with high-temperature writing and low-temperature reading.

7. The method for improving the first read success rate of NAND Flash in SSD according to claim 1, characterized in that, The specific method for selecting the optimal axis is as follows: if there are identical axes in different categories, then use the same axis as the optimal axis; otherwise, select different optimal axes according to different scenarios.

8. An apparatus for improving the first-read success rate of NAND Flash in an SSD, comprising a processor and a memory storing program instructions, characterized in that, The processor is configured to, when running the program instructions, execute the method for improving the first read success rate of NAND Flash in the SSD as described in any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the method for improving the first read success rate of NAND Flash in an SSD as described in any one of claims 1-7 above.

Images