Search

CN-121979446-A - Control method of flash memory device and flash memory device

CN121979446ACN 121979446 ACN121979446 ACN 121979446ACN-121979446-A

Abstract

The application discloses a control method of flash memory equipment and the flash memory equipment, the control method comprises the steps of obtaining hardware information of the flash memory equipment, dividing a preset storage space of the flash memory equipment into a plurality of independent disk redundant array preparation members according to independent disk redundant array construction rules, carrying out risk assessment of unrecoverable errors on the independent disk redundant array preparation members, determining an initial independent disk redundant array group from the independent disk redundant array preparation members according to risk assessment results, and executing read-write operation of service data based on the initial independent disk redundant array group, wherein the initial independent disk redundant array group comprises at least N independent disk redundant array preparation members, and N is a natural number greater than or equal to 2. The application improves the probability of single failure under the expected use condition by adjusting the construction mode of the RAID group member, thereby improving the data reconstruction power and avoiding the data loss.

Inventors

  • QIU JIAYANG

Assignees

  • 深圳市时创意电子股份有限公司

Dates

Publication Date
20260505
Application Date
20251231

Claims (10)

  1. 1. A method for controlling a flash memory device, comprising the steps of: acquiring hardware information of the flash memory device; dividing a preset storage space of the flash memory device into a plurality of RAID preparation panelists according to RAID construction rules; Performing risk assessment of unrecoverable errors on a plurality of Redundant Array of Independent Disks (RAID) preparation members; Determining an initial RAID group from a plurality of RAID preparation panelists according to the risk assessment result; performing read-write operation of service data based on the initial RAID group; The initial RAID group comprises at least N continuous RAID preparation members, wherein N is a natural number greater than or equal to 2.
  2. 2. The method for controlling a flash memory device according to claim 1, wherein the step of performing risk assessment of unrecoverable errors on the plurality of redundant array of independent disks preparation members comprises: analyzing the error bit behavior of each RAID preparation member, and generating an error behavior index for each RAID preparation member; And calculating the risk that a plurality of RAID preparation members become a virtual RAID group to generate unrecoverable errors according to the error behavior index of each RAID preparation member.
  3. 3. The method for controlling a flash memory device according to claim 2, wherein, The step of determining the initial RAID group from the plurality of RAID preparation panelists according to the risk assessment result comprises the following steps: And when the risk of unrecoverable errors of the continuous n RAID preparation panelists is lowest, taking the continuous n RAID preparation panelists as the initial RAID group, wherein n is a natural number greater than or equal to 2.
  4. 4. The method for controlling a flash memory device according to claim 2, wherein the step of calculating the risk of an unrecoverable error of a plurality of spare raid members becoming a virtual raid group according to the error behavior index of each spare raid member comprises: Randomly selecting a continuous Redundant Array of Independent Disks (RAID) preparation members as a virtual RAID group, wherein a is a natural number greater than or equal to 2; Calculating virtual redundant array groups of which the number of the redundant array of independent disks preparation members of unrecoverable errors in the multiple virtual redundant array groups simultaneously does not exceed 1 according to the error behavior index of each redundant array of independent disks preparation member, and marking the virtual redundant array groups as candidate groups; The step of determining the initial RAID group from the plurality of RAID preparation panelists according to the risk assessment result comprises the following steps: comparing the number of spare members of the RAID of the plurality of candidate groups; and selecting the candidate group with the largest number of spare members of the RAID as the initial RAID group.
  5. 5. The method for controlling a flash memory device according to claim 1, wherein after the step of performing the read/write operation of the service data based on the initial redundant array of independent disks, further comprises: When an unrecoverable error occurs to one RAID preparation team member in the initial RAID group, carrying out risk assessment of the unrecoverable error by a plurality of RAID preparation team members again; and reorganizing the initial RAID group from the plurality of RAID preparation members according to the risk assessment result.
  6. 6. The method for controlling a flash memory device according to claim 1, wherein the redundant array of independent disks construction rule includes: A plurality of independent storage units for dividing a preset storage space according to a physical structure in hardware information of the flash memory device; the RAID preparation team comprises an independent storage unit.
  7. 7. The method for controlling a flash memory device according to claim 4, wherein the step of dividing the preset storage space of the flash memory device into a plurality of spare raid groups according to the raid group creation rule comprises: Dividing a preset storage space of the flash memory device into a plurality of logic storage unit groups according to an independent disk redundant array construction rule, wherein each logic storage unit group comprises a plurality of independent storage units, and each independent storage unit is used as an independent disk redundant array preparation member; The step of arbitrarily selecting the continuous a Redundant Array of Independent Disks (RAID) preparation members as a virtual RAID group comprises the following steps: And randomly selecting a continuous independent storage units from each logic storage unit group as a virtual independent disk redundant array group, and exhausting a plurality of virtual independent disk redundant array groups by adopting a greedy method model.
  8. 8. The method of claim 7, wherein the memory space is divided into a plurality of independent memory cells according to a word line parameter in hardware information of the flash memory device, wherein one word line is used as one independent memory cell; When the number of the logic memory cell groups is b, taking the remainder of the word line sequence numbers and b, and taking the word lines with the same remainder as the same logic memory cell group, wherein b is a natural number greater than or equal to 2; the N continuous word lines in the same logic memory cell group are used as an initial RAID group.
  9. 9. The method according to claim 4, wherein the error bit behavior includes an error amount that can be corrected by the error correction mechanism in the read operation, a trend of variation of the error amount with time or the number of uses, and a frequency at which the error amount approaches an upper limit of the error correction capability.
  10. 10. A flash memory device for storing program data executable to implement the method of controlling a flash memory device of any one of claims 1 to 9.

Description

Control method of flash memory device and flash memory device Technical Field The present application relates to the field of display technologies, and in particular, to a control method of a flash memory device and a flash memory device. Background As a novel storage medium, the NAND flash memory device has the advantages of large capacity, high read-write speed, shock resistance, falling resistance, low power consumption, no noise, low price and the like compared with a mechanical hard disk storage, and is applied in the consumer personal computer field and the enterprise server field in a large scale. Flash memory devices typically include a memory control chip for managing a plurality NAND FLASH of memory cells. The control chip is responsible for processing host data access requests and performing the functions of logical address and physical address mapping, bad area management, write averaging (WEAR LEVELING), error handling, etc. through the flash translation layer (Flash Translation Layer, FTL). Because NAND FLASH memory has unavoidable error behavior in terms of process and physical characteristics, the storage control chip is usually matched with an error correction code (Error Correction Code, ECC) mechanism to correct bit errors generated in the reading process. However, as the number of times NAND FLASH erasures and the data storage time increase, the error rate increases, and the mere reliance on the ECC mechanism may still be at risk of unrecoverable errors (Uncorrectable Error, UECC). To further improve the reliability of data, a part of the storage control chip may internally implement a data redundancy mechanism similar to a redundant array of independent disks (Redundant Array of INDEPENDENT DISKS, hereinafter referred to as RAID). However, the number of members in the current redundant array of independent disks (RAID group) is fixed, and the health status of the members is not considered, so that the redundant array of independent disks is easy to make errors, resulting in data loss. Disclosure of Invention The application aims to provide a control method of a flash memory device and the flash memory device, which can improve the probability of single failure only under the expected use condition by adjusting the construction mode of an independent disk redundant array member, thereby improving the data reconstruction power and avoiding the data loss. The application discloses a control method of flash memory equipment, which comprises the following steps: acquiring hardware information of the flash memory device; dividing a preset storage space of the flash memory device into a plurality of RAID preparation panelists according to RAID construction rules; Performing risk assessment of unrecoverable errors on a plurality of Redundant Array of Independent Disks (RAID) preparation members; Determining an initial RAID group from a plurality of RAID preparation panelists according to the risk assessment result; performing read-write operation of service data based on the initial RAID group; The initial RAID group comprises at least N continuous RAID preparation members, wherein N is a natural number greater than or equal to 2. Optionally, the step of performing risk assessment of unrecoverable errors on the plurality of redundant array of independent disks preparation members includes: analyzing the error bit behavior of each RAID preparation member, and generating an error behavior index for each RAID preparation member; And calculating the risk that a plurality of RAID preparation members become a virtual RAID group to generate unrecoverable errors according to the error behavior index of each RAID preparation member. Optionally, the step of determining the initial raid group from the multiple raid preparation panelists according to the risk assessment result includes: And when the risk of unrecoverable errors of the continuous n RAID preparation panelists is lowest, taking the continuous n RAID preparation panelists as the initial RAID group, wherein n is a natural number greater than or equal to 2. Optionally, the step of calculating the risk of the plurality of spare raid members becoming a virtual raid group for occurrence of unrecoverable errors according to the error behavior index of each spare raid member comprises: Randomly selecting a continuous Redundant Array of Independent Disks (RAID) preparation members as a virtual RAID group, wherein a is a natural number greater than or equal to 2; Calculating virtual redundant array groups of which the number of the redundant array of independent disks preparation members of unrecoverable errors in the multiple virtual redundant array groups simultaneously does not exceed 1 according to the error behavior index of each redundant array of independent disks preparation member, and marking the virtual redundant array groups as candidate groups; The step of determining the initial RAID group from the plurality of RAID preparation panelists