Flash memory device and storage control method
a flash memory and control method technology, applied in the field of flash memory devices, can solve the problems of reducing the quality of flash memory, reducing the number of correctable bits of flash memory, and reducing the production efficiency of large-capacity nand flash memory, so as to increase the number of correctable bits and increase the number of
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Benefits of technology
Problems solved by technology
Method used
Image
Examples
first embodiment
[0043]Firstly, a computer system according to a first embodiment will be described below.
[0044]FIG. 1 is a schematic structure figure of a computer system including an SSD according to a first embodiment.
[0045]The computer system comprises a higher-level device 10 and an SSD (Solid State Drive) 20 as an example of a flash memory device. The SSD 20 is communicatively coupled to the higher device 10 via a communication network (e.g., a LAN (Local Area Network)). For example, the higher-level device 10 may be a host computer or a controller of a storage system. In the following description, a host computer is taken as an example of the higher device 10, which will be denoted a host computer 10.
[0046]For example, the host computer 10 is an application server. The host computer 10 is installed with control software (not shown), which is executing on the host computer 10 for issuing control commands, such as write command or read command, to the SSD 20.
[0047]The SSD 20 includes an SSD con...
second embodiment
[0188]Next, a second embodiment will be described below. Incidentally, description will be made of the difference from the first embodiment.
[0189]In the first embodiment, segments of the SCM FM chip 222 are mapped to all of the physical pages included in the NAND FM chip 221. In the second embodiment, segments are mapped to particular physical pages, rather than all of the physical pages, i.e., to only valid physical pages storing important data (management information such as the address conversion table 1122). This allows a plurality of segments to be mapped to one particular physical page. In this manner, an increased capacity may be provided for storing error correction information of the data stored in a particular physical page. Consequently, a larger amount of error correction information may be transferred to the bit inversion circuit 2152 when reading data stored in a particular physical page, as compared with the first embodiment. That is, the correctable limit number of b...
third embodiment
[0193]Next, a third embodiment will be described below. Incidentally, description will be made of the difference from the first embodiment.
[0194]In the first embodiment, since no bit error occurs in the write data and the ECC for the write data (hereinafter, the write ECC) when data is written to the NAND FM chip 221 for the first time, the ECC circuit 2153 generates an initial value as error correction information. In this case, assuming that the initial value of error correction information is all zeros, the bit inversion circuit 2152 cannot correct bit errors by using the initial value of error correction information. Thus, for example, in a read process at a first point in time, if the total number of bit errors that have been occurred in the write data and the write ECC exceeds the correctable limit number by the ECC circuit 2153, uncorrectable errors result.
[0195]In contrast, in the third embodiment, when writing data to the NAND FM chip 221 for the first time, the ECC circuit...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


