Error correction method based on raid information, computer-readable storage medium and processor

Abstract

The invention discloses an error correction method based on RAID information, a computer readable storage medium and a processor. The error correction method comprises the steps: determining the address of uncorrectable error data A when a BCH or RS uncorrectable error occurs in a flash memory particle; calculating a value DRAID obtained through RAID recovery; reading the flash memory particles for three times; selecting three reading thresholds op, op + and op-, wherein op is the optimal threshold of flash memory particles under the current condition, and op + and op- are the threshold on theright side of op and the threshold on the left side of op respectively; obtaining Dop, Dop + and Dop- according to the reading thresholds op, op + and op-rereading error data A; performing exclusive-OR operation on the data Dop + obtained by the second reading and the data Dop-obtained by the third reading according to bits, and judging whether an exclusive-OR result is 1 or not: if the exclusive-OR result is 1, replacing the original data with the corresponding bits of the DRAID; and if the result of exclusive OR is 0, keeping the corresponding bit of the Dop. On the basis of not changing the existing flash memory controller architecture, the error correction capability is improved.

Description

technical field [0001] The invention relates to the technical field of data storage, in particular to an error correction method based on RAID information. Background technique [0002] SSD (Solid State Drive), commonly known as solid-state hard drive, is a hard disk made of solid-state electronic storage chip arrays. It usually includes three major parts, namely SSD main control chip, flash memory particle array for storing data, and cache chip. Solid-state drives have the characteristics of fast reading and writing, light weight, low energy consumption, and small size that traditional mechanical hard drives do not have, making them widely used in consumer markets, data centers, and enterprise markets. [0003] One of the characteristics of flash memory particles is that different degrees of bit inversion will occur during the life cycle. In order to further improve the life of SSD disks, storage manufacturers will pass ECC (Error Correction Code) on the flash memory partic...

AI Technical Summary

Problems solved by technology

Flash memory manufacturers will set up an error-checking code space (out-of-band, OOB space) in the flash memory granules. The error correction capability of the error correction algorithm BCH or RS will be limited by the size of the OOB, and it is becoming more and more difficult to meet the requirements of TLC and QLC flash memory. Error Correction Capability Requirements

Images