CN102024497B - Method for storing data and storage device - Google Patents

Abstract

The embodiment of the present invention discloses a method for storing data and a storage device. The method includes: obtaining data and an error correction code of the data; The codes are respectively stored in different pages of the flash memory. Because the technical scheme of the present invention stores the error correction codes of the data in independent pages, the pages of the storage space are divided into two types, including: one type of page is used to store data, and one type of page is used to store the error correction code of the data. Therefore, the data and all the error correction codes of the data can be obtained through fewer reading times, thereby obtaining correct data, reducing the probability of errors in the storage device, and making the storage device safe and stable when storing data.

Description

Method and storage device for storing data

technical field

The invention relates to the field of electronic technology, in particular to a data storage method and a storage device.

Background technique

Storage devices play a very important role in people's lives today. People use them to store text materials, pictures, videos, etc. A commonly used storage device, such as a solid state drive (SSD, Solid State Disk), plays an important role in people's daily life because of its large storage capacity, small size, and easy portability. An SSD may be composed of flash memory (Flash), such as NAND Flash. Due to the NAND Flash manufacturing process, random bit (bit) flips may occur during data reading, writing, and storage, resulting in data errors. With the continuous improvement of the Flash manufacturing process, more data is stored in a unit storage space, and the probability of errors in the stored data is greater.

Error Checking and Correcting (ECC, Error Checking and Correcting,) technology can perform error checking and correction on data read from Flash, and reduce the error rate of data read from Flash. The specific operation methods include:

First, the data is encoded, and the specific implementation includes: calculating the data written into the Flash chip, so as to obtain the error correction code (ECC, Error Correction Code) of the stored data. The process of obtaining the error correction code is also called encoding. The space of the error correction code is also called the check bit. The stored ECC and data are written into the Flash chip together. The calculation of the error correction code is based on the sector (Sector). When the data stored in a sector is obtained When the check digit occupied by the error correction code is greater than the maximum allowable check digit in a Sector, the error correction code of the data stored in the Sector is stored in the check digits of multiple Sectors;

Secondly, for data decoding, the specific implementation includes: when the data stored on the Flash chip is to be read, the error correction code of the data stored on the data and the check digit is read out, and according to the read error correction code and the read The error-correcting code generated when reading the data corrects the read data, so as to achieve the purpose of reading the correct data.

The allocation of storage space in a sector in the prior art is shown in FIG. 1 , and data is written into the Flash or read from the Flash in units of sectors. A Sector can store up to 528 bytes (B, Bytes) of data, but 512B of it is used as data space for storing data, and 16B is used as redundant space. In the 16B redundant space, there is at least 4B space for storing Logical Block Address (LBA, Logic Block Address) addresses, so the space for storing error correction codes is only 12B at most.

During the research and practice of the prior art, the inventors of the present invention have found that for one sector in the prior art, a 13-bit error correction code is usually required for correcting 1 bit (bit) data, that is, 13-bit error correction codes are required. Check bit, therefore, the check bit of 12B space in a sector can correct up to 8 bits of erroneous data. When more bits of data are to be corrected, the error correction code needs to be stored in more Sector check bits. A page includes multiple Sectors, where a page is the smallest unit for writing and reading data in a storage device. Therefore, when the storage device reads data, it cannot obtain the error correction code corresponding to the data in time, so that the storage device It is not safe and stable enough to store data.

Contents of the invention

Embodiments of the present invention provide a data storage method and a storage device, which can improve the security and stability of stored data.

An embodiment of the present invention provides a method for storing data, including:

Obtaining data and an error correction code for the data;

The data and the error correction codes of the data are respectively stored in different pages of the flash memory through a data channel connected to the flash memory.

An embodiment of the present invention provides a storage device, which includes: a data channel, a flash memory, a first acquisition unit, a second acquisition unit, and a control storage unit;

The first acquisition unit is used to acquire data;

The second obtaining unit is configured to obtain an error correction code of the data;

The control storage unit is configured to respectively store the data and the error correction code of the data in different pages of the flash memory through the data channel connected to the flash memory.

In the embodiment of the present invention, the error correction code of the data is stored in an independent page, that is, the pages of the storage space are divided into two types, including: one type of page is used to store data, and one type of page is used to store the error correction code of the data; Therefore, the data and all the error correction codes of the data can be obtained through fewer reading times, thereby obtaining correct data, reducing the probability of errors in the storage device, and making the storage device safe and stable when storing data.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. For those skilled in the art, other drawings can also be obtained according to these drawings without any creative effort.

Fig. 1 is an allocation diagram of storage space in a sector in the prior art;

FIG. 2 is a schematic flowchart of a method for storing data provided by Embodiment 1 of the present invention;

FIG. 3 is a schematic flowchart of a method for storing data provided by Embodiment 2 of the present invention;

FIG. 4 is a schematic diagram of a storage space allocation in Embodiment 2 of the present invention;

FIG. 5 is a schematic flowchart of a method for storing data provided by Embodiment 3 of the present invention;

FIG. 6 is a schematic diagram of a storage space allocation in Embodiment 3 of the present invention;

FIG. 7 is a schematic diagram of a logical unit of a storage device provided in Embodiment 4 of the present invention.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

Embodiment one,

The embodiment of the present invention provides a method for storing data, as shown in Figure 2, the method includes:

Step 1: Obtain the data and the error correction code (ECC) of the data;

Wherein, the data obtained in step 1 may be received data sent by other devices and needs to be stored, and the error correction code of the data obtained in step 1 may be the error correction code of the data calculated according to a specific algorithm. For the specific operation of the error correction code, reference may be made to the prior art.

Step 2: Store the data and the error correction code of the data in different pages of the flash memory through the data channel connected to the flash memory.

Wherein, it should be noted that, when the storage device reads data and writes data, it operates in units of pages (Page). In step 2, the data is stored in one or more than one page, and the error correction code of the data is also stored in one or more than one page, wherein the page storing data and the page storing data error correction code are different pages. That is, it can be understood that the pages in the storage device are divided into two parts, including: pages storing data and pages storing data error correction codes.

Through the description of a method for storing data provided by the embodiment of the present invention, the method stores the error correction code of the data in an independent page, that is, the page of the storage space is divided into two types, including: one type of page is used for storing Data, a type of page is used to store the error correction code of the data; therefore, the data and all the error correction codes of the data can be obtained through fewer readout times, thereby obtaining correct data and reducing the probability of errors in the storage device. The storage device is safe and stable when storing data.

Embodiment two,

The embodiment of the present invention provides a method for storing data, which is similar to the method provided in Embodiment 1, including: storing the error correction code of the data separately in the unit of Page, and the Page for storing the error correction code of the data is not Store data, and at the same time, the Page that stores the data does not store the error correction code of the data; however, the embodiment of the present invention provides a more specific method for storing data and the error correction code of the data, which is convenient to use fewer steps and more quickly Get all the error correction codes of the data, so as to get the correct storage data.

As shown in Figure 3, the method includes:

Step A1: the same as Step 1 in Embodiment 1, that is, to obtain the data and the error correction code (ECC) of the data;

Step A2: through the data channel connected to the flash memory, store the data and the error correction code of the data in different pages of the flash memory respectively; wherein, the above-mentioned data channel includes at least one; the above-mentioned data channel connected to the flash memory includes: one or more At least one data channel connected to one flash memory; when the different pages of the flash memory are different pages with the same number in the flash memory, the error correction code is the error correction code of the data stored in the page with the same number in the flash memory.

The instructions for easy understanding include: the storage device stores the acquired data and the error correction code of the data in different pages, when there is more than one flash memory, and the data channels connected to the flash memory (Flash) include more than one , Flash is divided into more than one page, in all the pages with the same number in Flash, there is a page for storing error correction code, the error correction code is the error correction code of the data stored in the pages with the same number in all Flash .

It should be understood that the data channel is used to input data and error correction codes to the storage space in the storage device, or to output data and error correction codes from the storage space. The storage space described here is usually composed of multiple flash memories. A data channel is usually connected to one or more than one flash memory. The flash memory is divided into multiple pages. The flash memory outputs the data stored in the page or error correction in units of pages. Code, write data or error correction code in units of pages.

Typically multiple data channels pass data into or out of the storage device in parallel. As shown in FIG. 4 , taking four data channels in the storage device as an example, they include: the zeroth channel (Channel0 ), the first channel (Channel1 ), the second channel (Channel2 ), and the third channel (Channel3 ). Wherein, the numbering of each Page in the Flash connected to each channel is different, as shown in the figure, the consecutive pages with numbers from Page0 to Page7 in the Flash connected to each channel are shown. Wherein, said in step A2 " in all the pages with the same number in the Flash, there is a page for storing the error correction code, and the error correction code is the error correction code of the data stored in the pages with the same number in all the Flash", The understanding of Figure 4 is that among the pages numbered Page0 in the Flash connected to Channel0 to Channel3, there is a page (ie, Page0 of Channel0) used to store the error correction of the data in all Page0 in the Flash connected to Channel1 to Channel3 code. The data stored in Page0 of all Flash connected to the data channel is defined as data0, the data stored in Page1 of all Flash connected to the data channel is defined as data1, and so on; the error correction code of data0 is stored in Page0 In a page (that is, the page where the parity bit Parity0 is located in Figure 4), the error correction code of data1 is stored in a page of Page1 (ie, the page where the parity bit Parity1 is located in Figure 4), and so on.

It also needs to be understood that the physical addresses of pages with the same number in all data are usually continuous, for example: page0 in Flash connected to Channel0, page0 in Flash connected to Channel1, page0 in Flash connected to Channel2 , which is continuous with the physical address of page0 in the Flash connected to Channel3.

Through the above description of a method for storing data provided by the embodiment of the present invention, when reading continuous address data, because the channels are concurrent, the data and the error correction code of the data can be obtained by reading once, so as to perform data verification and output. Therefore, correct data is obtained, the probability of errors in the storage device is reduced, and the storage device is safe and stable when storing data.

Further, in order to ensure that when the address discontinuous data is read, the error correction code corresponding to the data can be read with as few operations as possible, the page for storing the error correction code in step A2 needs to be further restricted, namely: In the flash memory connected to one data channel in at least one data channel, when the different pages in the flash memory connected to one data channel are N pages with consecutive numbers in the flash memory, store the error correction code in the N pages with consecutive numbers In a page of , the value of N is the number of all data channels.

The explanation in the previous paragraph can be understood as, for the page storing the error correction code in step A2, further restrictions include: in all the Flash connected to a data channel, among the N pages with consecutive numbers, only one page is used to store the error correction code code, where N is the number of all data channels.

In order to facilitate the understanding of the previous paragraph, please still refer to Figure 4. Since multiple data channels output data to the storage device in parallel, and the addresses read at the same time are discontinuous, for example: the pages read at the same time include: and Channel0 Page0 in the connected Flash, Page0 in the Flash connected to Channel1, Page1 in the Flash connected to Channel2, Page2 in the Flash connected to Channel3, that is, the order of the read data is: Parity0, data0, data1, data2 .

Since in all the Flashes connected to a data channel, only one page is used to store the error correction code among the consecutively numbered N pages, the error correction code of all the data can be read out by the storage device outputting again, that is, the following The pages read at a moment include at least: Parity1 stored in Page1 in the Flash connected to Channel1, and Parity2 stored in Page2 in the Flash connected to Channel2. If both Parity1 and Parity2 are stored in the same data channel, it is impossible to read the error correction codes Parity1 and Parity2 of data1 and data2 at one time.

By implementing the above method of storing data, as shown in Figure 4, it is a schematic diagram of the distribution of the data finally input in the data channel and the error correction code of the data. It can be seen that only one of the four consecutive pages in each channel is used For storing error correction codes, the other three pages store data. Therefore, the pages used to store the error correction code form a regular step distribution as shown in FIG. 4 .

It should also be noted that the above is an example of a storage device with four data channels. For other numbers of data channels, it can be easily deduced from the description here. Therefore, this should not be construed as limiting the embodiment of the present invention .

Embodiment three,

The embodiment of the present invention provides a method for storing data. The embodiment of the present invention provides a method for storing data. This method is similar to the method provided in Embodiment 1, including: the error correction code of the data is separately represented by Page Store as a unit, the Page that stores the data error correction code does not store data, and at the same time, the Page that stores data does not store the error correction code of the data; however, the embodiment of the present invention provides another more specific storage data and the data error correction The code method is convenient to obtain all the error correction codes of the data more quickly through fewer steps, so as to obtain the correct storage data.

As shown in Figure 5, the method includes:

Step B1: the same as Step 1 in Embodiment 1, that is, to obtain the data and the error correction code (ECC) of the data;

Step B2: Store the data and the error correction codes of the data in different pages of the flash memory connected to different data channels; wherein, the above-mentioned data channels include at least one; the above-mentioned data channels connected to the flash memory include: one or more than one At least one data channel connected to a flash memory.

Step B2 can be understood as: storing the obtained data and the error correction code of the data in different pages, wherein, when there is more than one flash memory, and the data channel connected to the flash memory (Flash) includes more than one , Flash is divided into more than one page, the data stored in all Flash connected to one data channel, and the error correction code of the data are stored in flash memory connected to different data channels; one data channel is any data aisle.

Wherein, in step B2, the error correction code of the data stored in the Flash connected to one data channel is stored in different Flashes, and this different Flash refers to the Flash connected to another data channel. When , the data and the error correction code of the data can be output at the same time, so that the correct data can be obtained quickly.

As shown in FIG. 6 , taking four data channels in the storage device as an example, the distribution diagram of the space for storing data and the space for data error correction codes is shown. Among them, a section of address space is defined in each data channel for error correction codes for storing data, that is, as shown in Figure 6, there is a line in each data channel and a section of address space is an error correction code for storing data; for easy understanding, In Figure 6, define all the data stored in the Flash connected to Channel0 as data0, define all the data stored in the Flash connected to Channel1 as data1, define all the data stored in the Flash connected to Channel2 as data2, and define all the data stored in the Flash connected to Channel2 as data2. All data stored in the connected Flash is defined as data3. Store all the error correction codes of data0 in a self-defined address space (i.e. parity0) in the Flash connected to Channel1, and store all the error correction codes of data1 in a self-defined address space in the Flash connected to Channel2 (i.e. parit1 ), store all the error correction codes of data2 in a self-defined address space (ie parity2) in the Flash connected to Channel3, and store all the error correction codes of data3 in a self-defined address space in the Flash connected to Channel0 ( Namely parity3).

Wherein, each customized segment of address space includes at least one page. It should also be understood that the above is the case of the error correction codes of the regularly stored data, that is, as shown in Figure 6, the error correction codes of the data stored in the Flash connected to each data channel are stored in In the user-defined address space in the Flash connected to the adjacent next data channel. In fact, the data stored in the Flash connected to a data channel and the error correction code of the data stored in the Flash connected to the data channel can be stored in the Flash connected to different data channels respectively. When fetching the data stored in the data channel, the error correction code can be read out according to the address of the error correction code storing the data. Wherein, the reading of the data and the error correction code of the data may be performed simultaneously, or may be divided into two steps, including: reading the data once, and reading the error correction code of the data once. For reading data and error correction codes, the fastest strategy for reading data and error correction codes can be selected according to the address of the stored data and error correction codes.

Through the description of a method for storing data provided by an embodiment of the present invention, the method stores the obtained data and the error correction code of the data in different pages, wherein, when there is more than one flash memory, and the flash memory ( When the data channel connected to Flash) includes more than one, Flash is divided into more than one page, and the data stored in all Flash connected to one data channel, and the error correction code of the data, are stored in different data channels In the connected flash memory; a data channel is any data channel; therefore, the data and all the error correction codes of the data can be obtained through fewer readout times, thereby obtaining correct data and reducing the probability of errors in the storage device. The storage device is safe and stable when storing data.

Embodiment four,

An embodiment of the present invention provides a storage device. As shown in FIG. 7 , the storage device includes: a first acquisition unit 100 , a second acquisition unit 101 , a control storage unit 102 , a data channel 103 and a flash memory 104 .

Wherein, the first acquisition unit 100 is used to acquire data;

The second obtaining unit 101 is configured to obtain the error correction code of the data obtained in the first obtaining unit 100;

Wherein, the data obtained in the first obtaining unit 100 may be the data that needs to be stored received from other devices, and the error correction code for obtaining the data in the second obtaining unit 101 may be the correction code of the data calculated according to a specific algorithm. For the specific operation of obtaining the error code and the error correction code of the data, reference may be made to the prior art.

The storage unit 102 is controlled to store the data and the error correction code of the data in different pages of the flash memory through a data channel connected to the flash memory.

The data channel 103 is used to transmit data and the error correction code of the data, which is the same as the data channel in the prior art;

The flash memory 104 is used to store data and error correction codes. The flash memory is divided into pages, which is the same as the flash memory in the prior art.

Wherein, the data is stored in one or more than one page, and the error correction code of the data is also stored in one or more than one page, wherein, the page storing the data is different from the page storing the data error correction code Page.

Through the description of a storage device provided by the embodiment of the present invention, the device stores the error correction code of the data in an independent page, that is, the page of the storage space is divided into two types, including: one type of page is used to store data, One type of page is used to store the error correction codes of the data; therefore, the data and all the error correction codes of the data can be obtained through fewer readout times, thereby obtaining correct data, reducing the probability of errors in the storage device, and making the storage The device is safe and stable when storing data.

Optionally, when the data channel includes at least one; and one or more than one flash memory is connected to each data channel;

Then control the storage unit 102, specifically for storing the data and the error correction codes of the data in different pages of the flash memory through the data channel connected to the flash memory; when the different pages of the flash memory are different pages with the same number in the flash memory, The error correction code is an error correction code for data stored in pages with the same number in the flash memory.

Regarding the description of the control storage unit 102 in the previous two paragraphs, it can also be understood that the control storage unit 102 is specifically used to store the acquired data and the error correction code of the data in different pages, wherein, when there are more than A flash memory, and when the data channel connected to the flash memory (Flash) includes more than one, the Flash is divided into more than one page. Among the pages with the same number in all Flash, one page is used to store the error correction code. The error code is the error correction code of the data stored in the pages with the same number in all Flash.

Wherein, it should be understood that the storage device may include one or more than one Flash, and the Flash provides a storage space, that is, an error correction code for storing data and/or data, and each Flash is divided into multiple pages, A page is the smallest unit for reading or writing to Flash.

Through further description of the control storage unit 102 in the storage device, when the storage device reads continuous address data, because the channels are concurrent, the data and the error correction code of the data can be obtained by reading once, so as to perform data processing. Verify and output. Therefore, correct data is obtained, the probability of errors in the storage device is reduced, and the storage device is safe and stable when storing data.

Further, on the basis of the above further description about the storage device 102, among all the Flashes connected to one data channel in the storage device 102, among the N pages with consecutive numbers, only one page is used to store the error correction code, where , N is the number of the data channels.

The description of the previous paragraph can also be understood as: in the flash memory connected to at least one data channel in the flash memory, when the different pages in the flash memory connected to one data channel are N pages with consecutive numbers in the flash memory, The error correction code is stored in one page of N pages with consecutive numbers, and the value of N is the number of all data channels.

By further adding the description of the control storage unit 102 in the storage device, the storage device can read the error correction code corresponding to the data with as few operations as possible when reading data with discontinuous addresses.

Optionally, when the data channel in the storage device includes at least one; and one or more than one flash memory is connected to each data channel; then the storage unit 102 is controlled, specifically for storing the data and the error correction code of the data respectively to different pages of flash memory connected to different data lanes.

It can also be understood that the control storage unit 102 in the storage device can be specifically used to store the acquired data and the error correction code of the data in different pages, wherein, when there is more than one flash memory, and the flash memory ( When the data channel connected to Flash) includes more than one, Flash is divided into more than one page, and the data stored in all Flash connected to one data channel, and the error correction code of the data, are stored in different data channels In the connected flash memory; a data channel is any data channel.

The limitation of the control storage unit 102 by the previous paragraph makes the storage device store the error correction code of the data stored in the Flash connected to one data channel in the Flash connected to zero and one data channel. When the data is concurrent, the data and the error correction code of the data can be output at the same time, so that the correct data can be obtained quickly.

It should also be noted that for more detailed description and understanding of the storage device, reference may be made to the descriptions in method embodiments 1, 2, and 3.

Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above-mentioned embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium can include: ROM, RAM, disk or CD, etc.

The method and storage device for storing data provided by the embodiment of the present invention have been described above in detail. In this paper, specific examples are used to illustrate the principle and implementation of the present invention. The description of the above embodiment is only used to help understand the present invention. The method of the invention and its core idea; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation and scope of application. In summary, the content of this specification should not be understood To limit the present invention.

Claims (6)

1. A method for storing data, comprising: Obtaining data and an error correction code for the data; storing the data and the error correction codes of the data in different pages of the flash memory through a data channel connected to the flash memory; Wherein, the data channel includes more than one; the data channel connected to the flash memory includes: at least one data channel connected to more than one flash memory; When the different pages of the flash memory are different pages with the same number in the flash memory, the error correction code is an error correction code for data stored in the pages with the same number in the flash memory. 2. The method for storing data according to claim 1, wherein the data and the error correction codes of the data are respectively stored in different pages of the flash memory through the data channel connected to the flash memory ,include: In the flash memory connected to one of the more than one data channels, when the different pages in the flash memory connected to the one data channel are N pages with consecutive numbers in the flash memory, the error correction code is stored in In one page of N pages with consecutive numbers, the value of N is the number of all data channels. 3. A method for storing data, comprising: Obtaining data and an error correction code for the data; storing the data and the error correction codes of the data in different pages of the flash memory through a data channel connected to the flash memory; Wherein, the data channel includes more than one; the data channel connected to the flash memory includes: at least one data channel connected to more than one flash memory; The storing the data and the error correction code of the data in different pages of the flash memory through the data channel connected to the flash memory includes: respectively storing the data and the error correction code of the data in the same page as the flash memory In different pages of flash memory connected by different data channels. 4. A storage device, comprising: a data channel and a flash memory, further comprising: a first acquisition unit, a second acquisition unit and a control storage unit; The first acquisition unit is used to acquire data; The second obtaining unit is configured to obtain an error correction code of the data; The control storage unit is configured to respectively store the data and the error correction code of the data in different pages of the flash memory through the data channel connected to the flash memory; Wherein, the data channel includes more than one; the data channel connected to the flash memory includes: at least one data channel connected to more than one flash memory; When the different pages of the flash memory are different pages with the same number in the flash memory, the error correction code is an error correction code for data stored in the pages with the same number in the flash memory. 5. The device according to claim 4, wherein the data and the error correction codes of the data are respectively stored in different pages of the flash memory through the data channel connected to the flash memory, comprising: In the flash memory connected to one of the more than one data channels, when the different pages in the flash memory connected to the one data channel are N pages with consecutive numbers in the flash memory, the error correction code is stored in In one page of N pages with consecutive numbers, the value of N is the number of all data channels. 6. A storage device, comprising: a data channel and a flash memory, further comprising: a first acquisition unit, a second acquisition unit and a control storage unit; The first acquisition unit is used to acquire data; The second obtaining unit is configured to obtain an error correction code of the data; The control storage unit is configured to respectively store the data and the error correction code of the data in different pages of the flash memory through the data channel connected to the flash memory; Wherein, the data channel includes more than one; the data channel connected to the flash memory includes: more than one data channel connected to more than one flash memory; The storing the data and the error correction code of the data in different pages of the flash memory through the data channel connected to the flash memory includes: respectively storing the data and the error correction code of the data in the same page as the flash memory In different pages of flash memory connected by different data channels.

Images