KR101041837B1 - Control aparatus and method for storing file - Google Patents

Abstract

PURPOSE: A file storage control device and a method thereof are provided to prevent elimination of a block during SPOR(Sudden Power off Recovery) by proceeding duplication writing if the last page of a file is LSB while storing the file in an MLC(Multi-Level Cell) NAND flash memory. CONSTITUTION: An MLA(Memory Linked Architecture) driver(32) approaches to a buffer area of the first memory which a file is temporarily stored during a file write request. A memory driver(33) approaches to the second memory which the file is to be stored. If the last page of the file is an LSB(Least Significant Bit) page, an FTL(Flash Translation Layer) unit(31) writes the LSB page on the first page of a block which the last page is to be stored and proceeds duplication write or emptying of the LSB page on the second page.

Description

CONTROL APARATUS AND METHOD FOR STORING FILE}

The present invention relates to a file storage control apparatus and method.

As multimedia terminals have been diversified due to the development of multimedia technology, interest in storage devices for storing multimedia data is increasing. The storage device includes a volatile storage device or a nonvolatile storage device, and recently, a nonvolatile storage device has been widely used in a small portable terminal. Nonvolatile storage devices include NAND flash memory and NOR flash memory.

NAND flash memory is widely used due to its advantages of easy integration, low cost, fast operation speed, and low power consumption compared to NOR flash memory.

Such a NAND flash memory may include a plurality of identical blocks, and each block may include a plurality of pages. Data stored in a conventional NAND flash memory is stored in each block by a FTL (Flash Translation Layer). In particular, in the case of a NAND flash of a multi-level cell type, since a 2-bit value is stored in each cell, the LSB page and the MSB page are sequentially stored in one block.

In this case, when the last page of the file is an LSB page, the MSB page of the next file may be stored in a block in which the last LSB page is stored. Here, while the MSB page of the next file is stored, the corresponding block is erased during the Sudden Power off Recovery (SPOR), thereby corrupting the previously stored file.

An object of the present invention is to provide a file storage control apparatus and method that can prevent damage to a pre-stored file even if a SPOR (Sudden Power off Recovery) occurs when the file is stored in the nonvolatile memory.

According to an aspect of the present invention, in the file storage control device for controlling the file storage of the memory, MLA (Memory Linked Architecture) for accessing the buffer area of the first memory where the file is temporarily stored when a file write request; "Driver"; A memory driver accessing a second memory in which the corresponding file is to be stored; And if the last page of the corresponding file is an LSB by determining whether the last page is a LSB (Least Significant Bit) page or a Most Significant Bit (MSB) page; Perform a write operation of the last LSB page, which is the last page of the file, to the first page of the block to be stored, and overwrite or write the last LSB page of the file to the second page of the block in which the last page is stored; A file storage control apparatus may include a FTL (Flash Translation Layer) unit for controlling to empty the second page.

When the last page of the corresponding file is an MSB page, the FTL unit may perform a file write on a second page of a block in which the LSB page is stored.

The FTL unit checks a physical block address corresponding to a logical block address included in the file information received when the file write request is requested, and checks whether data stored in the page corresponding to the physical block address is present to store data stored in the block page. If not, the last LSB page can be stored.

The FTL unit may further include a log block table in which the logical block address and the physical block address are mapped.

The FTL unit may perform overwriting when there is data stored in a block in which the file is to be stored.

The overwrite operation checks the presence of a temporary block, and if there is a temporary block, writes the file to an empty block, determines whether the last page is an LSB page, and performs an overwrite when the LSB page is a log block. You can update the table.

If there is no temporary block, the FTL unit may allocate a new block or allocate a victim block to write a file of the file to the block.

If there is no physical block address corresponding to the logical block address included in the file information received at the file request, the FTL unit allocates an empty block of the second memory and includes physical block address information corresponding to the empty block. You can update the log block table information as much as possible.

According to another aspect of the present invention, a file storage control device for controlling file storage of a memory, comprising: an MLA driver for accessing a buffer region of a first memory in which a corresponding file is temporarily stored when a file write request is made; A memory driver accessing a second memory in which the corresponding file is to be stored; And store the corresponding file in a first storage area of the second memory, and determine whether the last page of the file is an LSB page or an MSB page and if the last page of the file is an LSB page, the last LSB page. A file storage control device may include an FTL unit configured to perform redundant writing on a second storage area of the second memory.

According to another aspect of the present invention, a file storage control method for controlling file storage in a memory, the method comprising: (a) receiving a file write request; (b) checking the physical block address of the file to be stored in the memory; (c) determining the presence or absence of data stored in a block of the memory corresponding to the physical block address if the physical block address exists as a result of the checking; (d) performing file writing when there is no data stored in the block corresponding to the physical block address as a result of the determination; And (e) determining whether the last page of the file on which the file write is performed is an LSB page or an MSB page, and if the last page is an LSB page, performs a duplicate write on the last LSB page, or the rest of the block in which the last LSB page is stored. It is possible to provide a file storage control method including the step of emptying an area.

The step (e) may be a step in which the last LSB page is stored in a second page after the last LSB page is stored in a first page among pages set for each block of the flash memory.

Step (b) may further include the step of converting to a physical block address corresponding to the logical block address received in the step of receiving the file write request.

After step (b), if there is no physical block address, allocating an empty block to the memory and updating a block table; And writing the file to the empty block.

If there is data stored in the block corresponding to the physical block address in step (d), the method may further include overwriting.

The overwriting may include checking whether a log block exists in a log block table; And writing a file to an empty log block when the log block exists.

The overwriting may include checking whether a log block exists in a log block table; If there is no log block, checking for the presence of an empty log block; Allocating the empty log block and updating the log block table if the empty log block exists; And writing a file to the empty log block.

Selecting at least one block from a log block if there is no empty log block; And writing a file to the selected block.

According to another aspect of the present invention, a file storage control method for controlling file storage in a memory, the method comprising: (a) receiving a file write request; (b) checking the physical block address of the file to be stored in the memory; (c) determining the presence or absence of data stored in a block of the memory corresponding to the physical block address if the physical block address exists as a result of the checking; (d) writing a file to a first storage area of the memory when there is no data stored in a block corresponding to the physical block address as a result of the determination; And (e) determining whether the last page of the file on which the file writing is performed is an LSB page or an MSB page, and if the LSB page is an LSB page, storing the last LSB page in a second storage area of the memory. Can be provided.

The step (d) may further include storing the LSB page in a first page of the first storage area and storing the MSB page in a second page.

According to an embodiment of the present invention, when a file is stored in an MLC NAND flash memory, when the last page of the file is an LSB, the last LSB page may be overwritten to prevent the block from being erased during the SPOR.

According to an embodiment of the present invention, when the file is stored in the MLC NAND flash memory, when the last page of the file is the LSB, the second page of the block in which the last LSB page is stored may be emptied to prevent the block from being erased at the SPOR. .

According to an embodiment of the present invention, when a file is stored in an MLC NAND flash memory, when the last page of the file is an LSB, the last LSB page is repeatedly stored in the second storage area to prevent the block from being erased during the SPOR. .

1 is a block diagram illustrating an embodiment of a memory control system having a file storage control apparatus according to an embodiment of the present invention.
FIG. 2 is a block diagram showing an embodiment of a file storage control device shown in FIG. 1; FIG.
3 is a block diagram schematically showing the structure of the MLC NAND shown in FIG.
4 is a block diagram illustrating that a file is stored in an MLC NAND according to one embodiment of the present invention.
5 is a block diagram illustrating that a file is stored in an MLC NAND according to another embodiment of the present invention.
6 is a flowchart illustrating a file storage control method according to a first embodiment of the present invention.
Figure 7 is a block diagram showing a terminal having a file storage control device according to a second embodiment of the present invention.
FIG. 8 illustrates an example in which data is stored in a first storage area and a second storage area of the second memory shown in FIG. 7.
9 is a flowchart sequentially illustrating a file storage control method according to a second embodiment of the present invention.

The present invention may be variously modified and have various embodiments, and specific embodiments will be illustrated in the drawings and described in detail with reference to the accompanying drawings. However, this is not intended to limit the present invention to specific embodiments, it should be understood to include all modifications, equivalents, and substitutes included in the spirit and scope of the present invention.

In describing the present invention, when it is determined that the detailed description of the related known technology may unnecessarily obscure the subject matter of the present invention, the detailed description thereof will be omitted. In addition, numerals (eg, first, second, etc.) used in the description process of the present specification are merely identification symbols for distinguishing one component from another component.

In addition, in the present specification, when one component is referred to as "connected" or "connected" with another component, the one component may be directly connected or directly connected to the other component, but in particular It is to be understood that, unless there is an opposite substrate, it may be connected or connected via another component in the middle.

Hereinafter, an apparatus for storing data in a memory according to embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a block diagram illustrating a terminal having an apparatus for storing data in a memory according to an embodiment of the present invention. The computing system of FIG. 1 may be a multimedia terminal such as a mobile terminal, MP3, navigation, PMP, or the like.

Referring to FIG. 1, another terminal according to an exemplary embodiment may include a host processor 10, a first memory 20, a file storage control device 30, and a second memory 40.

Here, the first memory 20 is described as a volatile memory (Dynamic Random Access Memory) (DRAM) as an example, the second memory 40 is a non-volatile memory as a multi-level cell NAND Flash memory ) As an example. However, the first memory 20 and the second memory 40 are not limited thereto.

In detail, the host processor 10 may perform functions such as transmission and reception communication signal processing, signal compression processing, error correction, and communication system control. In addition, the host processor 10 may perform a multimedia function.

For example, the host processor 10 may perform an multimedia process by performing an application through an interface with a user.

The host processor 10 may perform a function such as writing, reading, or erasing a file in the first memory 20. To this end, the host processor 10 may include a file system. The file system may perform a function such as writing or reading a file in the first memory 20.

The first memory 20 may store a program, data, and the like. The first memory 20 may be divided into a processor region 21, a buffer region 22, and a driver region 23.

The processor region 21 may store file data, a program, and the like input from the host processor 10 or an external device.

In the buffer area 22, data to be stored in the second memory 40 may be temporarily stored. The buffer area 22 may be a dual port memory area that is accessible between the host processor 10 and the file storage control device 30. The buffer area 22 may be divided into an area in which an instruction is to be stored and an area in which data is to be stored. The command storage area may store a command to be executed in the file storage control device, and the data storage area may temporarily store data to be stored in the second memory 40.

The driver area 23 may store a program performed by the file storage control device 30 and the file storage control device 30.

The second memory 40 may store an application program, data, and the like. The second memory 40 may include a nonvolatile memory. According to the present embodiment, the second memory 40 stores data in units of pages, and data is erased in units of blocks. For example, as illustrated in FIG. 3, the second memory 40 may divide and store data into the first page 51 and the second page 52 in one block 41. In this case, a first page 51 may store a least significant bit (LSB) page, and a second page may store an MSB page (most significant bit).

The file storage control device 30 may access the second memory 40 and store a data temporarily stored in the buffer area 22.

The file storage control device 30 may convert the logical address of the data input from the buffer area 22 into a physical address to store the file at the physical address of the second memory 40. When the last page of the corresponding file to be stored is the LSB page, the file storage control device 30 may control to store the last LSB page redundantly on the next page of the second memory 40.

In addition, the file storage controller 30 may control to empty the next page in the second memory 40 when the last page of the corresponding file to be stored is the LSB page.

On the other hand, the file storage control device 30 may write the file to another empty storage block when other data is stored at the corresponding physical address in the second memory 40.

The file storage control device 30 will be described in more detail with reference to FIGS. 2 to 5 below.

FIG. 2 is a block diagram schematically illustrating a hierarchy between a host processor and a file storage control device shown in FIG. 1.

Referring to FIG. 2, the host processor 10 may include an application 11, a file system 12, a first Memory Linked Architecture (MLA) driver 13, and a file. The storage controller 30 may include a Flash Translation Layer (FTL) unit 31, a second MLA driver 32, and a NAND driver 33.

As described above, the application 11 may perform various applications of the terminal. For example, the application 11 may perform application functions such as communication, games, and multimedia communication.

The file system 12 may perform functions such as reading, writing, and erasing a file or data. For example, when writing data, the file system 12 may divide the file into a number of files to store the file. The divided file is temporarily stored in the buffer area of the first memory. In this case, the first memory may be accessed through the first MLA driver 13.

The first MLA driver 13 is responsible for the interface between the buffer area and the file storage control device 30. The first MLA driver 13 may access the buffer area 22. When the first MLA driver 13 receives a file transfer request from the file storage control device 30, the first MLA driver 13 may provide a command or data temporarily stored in the buffer area 22.

The second MLA driver 32 is responsible for interfacing with the first MLA driver 13 included in the host processor 10. Since the second MLA driver 32 may not directly access the buffer area 22 from the FTL part 31, the second MLA driver 32 may access data temporarily stored in the buffer area 22 from the FLT part 31.

The NAND driver 33 may access the second memory 40 as a memory driver. When the control signal or the command signal is input from the FTL unit 31, the NAND driver 33 accesses the second memory to support a function such as reading or writing a file.

When the write command is performed, the FTL unit 31 converts a logical address of the input file information into a physical block address of the nonvolatile memory. The logical address may be the same as a sector of a disk, and the physical block address may be a block number and a page number. The FTL unit 31 retrieves the block address of the second memory 40 and writes data to the corresponding block. In this case, if the last page of the file is the LSB, the last LSB page is overwritten. When the overwrite is performed, the last LSB page write may be performed on the next page or the blank page of the second memory.

If there is no corresponding block address, the FTL unit 31 searches for an empty block and performs data writing. The FTL unit 31 updates the address information of the empty block in the block table.

Meanwhile, when data is already stored in the second memory corresponding to the block address, the FTL unit 31 checks whether there is an empty block of the log block table and writes a file to the empty log block. At this time, if the last page of the file is LSB, the last LSB page is overwritten and the log table is updated.

If there is no empty log block in the log block table, the FTL unit 31 checks the empty log block again, allocates a new block to display the log block, and writes a file to the empty log block. In this case, when there is no empty block, one victim block may be selected from the log block, the data may be written to the victim block, and the existing block may be erased.

The file storage control apparatus according to the above embodiment may be implemented as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

3 is a diagram schematically illustrating a configuration of a second memory.

3 schematically illustrates a second memory according to an embodiment of the present invention, and illustrates an MLC NAND flash memory as an example.

Referring to FIG. 3, the second memory 40 may include a plurality of blocks 41 and 42. Each block may be divided into two pages 51 and 52.

The second memory 40 is performed in units of pages when writing a file and in units of blocks when deleting. For example, the LSB page may be stored in the first page 51 and the MSB page may be stored in the second page 52.

FIG. 4 is a diagram illustrating an embodiment in which a file is stored in a second memory of FIG. 3.

Referring to FIG. 4, the second memory 40 may be composed of a plurality of blocks 41. In this case, each block 41 may be divided into two pages 51 and 52. As described with reference to FIG. 1, the second memory 40 is a flash memory in which writing is performed in units of pages and erased in units of blocks.

In the second memory 40, a file to be stored is divided into an LSB page 61 and an MSB page 62.

The LSB page 61 may be stored in the first page, and the MSB page 62 may be stored in the second page. In this case, when the last page of the file to be stored is the LSB page 63, as shown in FIG. 4, the last LSB page 63 may be duplicated and stored in the second page of the same block 42.

In addition, as shown in FIG. 5, when the last page of the file to be stored is an LSB page, the second page of the block in which the last LSB page 63 is stored is empty, and the first page of the next block when the next file is stored. Can be stored.

6 is a flowchart illustrating a file storing method according to an embodiment of the present invention. In the description of FIG. 6, it will be described with reference to FIGS. 1 to 5.

Referring to FIG. 6, a method of storing data in a memory according to an embodiment of the present disclosure may include receiving a file write request (S100), checking a physical block address (S110), and checking whether a data exists in a corresponding page ( S120), a file writing step (S130), a last page LSB determination step (S140), and a last LSB page duplication writing step (S150).

In detail, in operation S100, a file write request is received from the host processor 10.

In the physical block address checking step (S110), a logical block address is calculated using logical page information included in the file write request information, and a physical block address is checked from a log block table using the calculated logical block address.

The data presence check step (S120) of the corresponding page checks the data storage state of the physical block if the physical block address exists. In this case, the second memory 40 may be divided into a first page in which the LSB page is to be stored and a second page in which the MSB page is to be stored. At this time, the NAND driver 33 or the FTL unit 31 accesses the second memory 40 and checks whether there is data stored in the block in which the corresponding file is to be stored. Here, the NAND driver 33 or the FTL unit 31 checks the presence or absence of data stored in the first page or data stored in the second page.

In the file writing step S130, when there is no data stored in the first page or the second page of the block, file writing is performed.

The last page LSB determination step (S140) writes a file to each block and determines whether the last page of the file is an LSB page or an MSB page.

In the last LSB page overwriting step (S150), when the last page is an LSB page in the last page determination step (S140), the last LSB page is overwritten in the same block.

In this case, the last LSB page may be stored in the first page of the corresponding block, and the same last LSB page may be duplicated and stored in the second page.

Meanwhile, in the last LSB page redundancy write operation (S150), the redundancy write is not performed, and the second page of the block in which the last LSB page is stored may be emptied without writing data.

That is, after the writing of the last LSB page is performed on the first page, the second page of the same block may be empty, and other data writing may not be performed later.

As shown in FIG. 5, the second page of the block in which the last LSB page is written may cause no data to be stored.

The next file is stored from the first page of the next block.

On the other hand, if there is no corresponding physical block in the physical block address check step (S110), an empty block may be allocated (S160). After allocating the empty block, the log block table is updated to update the block information in the log block table. (S170)

Next, a file writing step (S130), a last page LSB determination step (S140), and a last LSB page duplicate writing step (S150) may be performed.

According to the first embodiment of the present invention, if the corresponding page is not empty in the data existence check step (S120) of the corresponding page, overwriting may be performed.

The overwriting is a step of checking whether a log block exists in the log block table (S200), a file writing step into an empty log block (S210), a last page LSB determination step (S220), a last page duplicate writing step (S230), and a log mapping table It may include an update step (S240) and the existing block erase step (S250). In addition, if there is no log block in the log block table, the log block table checks whether there is an empty log block (S260), a new block allocation step (S270) and the victim block selection step (S280) in the log block further includes Can be.

In detail, in operation S200, the presence of a log block in the log block table is checked in the presence of a file previously stored in the log block table. If a log block exists in the log block table, a file write is performed on an empty log block (S210). Subsequently, it is determined whether the last page of the file is LSB (S220). At this time, if the last page of the file is LSB, the last page is overwritten. Duplicate writing may be performed on the second page of the corresponding block of the second memory.

Next, the log mapping table is updated (S240) and the existing block is erased (S250).

On the other hand, if there is no log block in the log block table, it is checked whether there is an empty log block (S60). If there is an empty log block, a new block is allocated (S270), the log block is displayed, the file writing, the last page LSB determination, and the last page overwriting are performed.

However, if there is no empty log block, one victim block is selected from the log block (S290). A file write is performed on the selected victim block (S210). After that, the above-described last page LSB determination step (S220), the last page duplicate writing step (S230), the log mapping table updating step (S240), and the existing block are erased. Step S250 is performed sequentially.

As described above, according to an embodiment of the present invention, when the last page of the file stored in the second memory is an LSB page, by storing the last LSB page in the same block or emptying the second page of the same block, Even if a SPOR occurs, the pre-stored file is not damaged.

7 is a block diagram illustrating a terminal having an apparatus for storing data in a memory according to a second embodiment of the present invention. FIG. 8 illustrates an example in which data is stored in a first storage area and a second storage area of the second memory shown in FIG. 7.

Since FIG. 7 is identical to FIG. 1 except that the second storage area is additionally provided, duplicate description of the same elements will be omitted. Here, the second memory and the second storage area are the same memory, and the storage area may be divided.

7 and 8, a terminal according to a second embodiment of the present invention includes a host processor 10, a first memory 20, a file storage control device 30, a first storage area 80, and a second. The storage area 90 may include a divided second memory 40. The second memory 40 will be described using, for example, a multi-level cell NAND flash memory.

The host processor 10 may perform functions such as transmission and reception communication signal processing, signal compression processing, error correction, and communication system control. In addition, the host processor 10 may perform a multimedia function.

For example, the host processor 10 may perform an multimedia process by performing an application through an interface with a user.

The host processor 10 may perform a function such as writing, reading, or erasing a file in the first memory 20. To this end, the host processor 10 may include a file system. The file system may perform a function such as writing or reading a file in the first memory 20.

The first memory 20 may store a booting program, data, and the like. The first memory 20 may be divided into a processor region 21, a buffer region 22, and a driver region 23.

The processor region 21 may store file data, a program, and the like input from the host processor 10 or an external device.

In the buffer area 22, data to be stored in the second memory 40 may be temporarily stored. The buffer area 22 may be a memory area accessible between the host processor 10 and the file storage control device 30. The buffer area 22 may be divided into an area in which an instruction is to be stored and an area in which data is to be stored.

The driver area 23 may store a program performed by the file storage control device 30 and the file storage control device 30.

The second memory 40 may store a boot program, data, and the like. The second memory 40 may be a NAND flash memory in which data is stored in units of pages and data is erased in units of blocks. For example, as illustrated in FIG. 3, the second memory 40 may divide and store data into the first page 51 and the second page 52 in one block 41. In this case, the LSB page may be stored in the first page 51 and the MSB page may be stored in the second page.

As illustrated in FIG. 8, the second memory 40 may be divided into a first storage area 80 and a second storage area 90. The LSB page and the MSB page of the file may be stored in the first storage area 80.

The second storage area 90 may store the last LSB data when the last page of the stored file is the LSB.

According to the second embodiment of the present invention, the second memory 40 is divided into the first storage area 80 and the second storage area 90. However, the present invention is not limited thereto, and the last page is the LSB. It may have a separate memory for storing the last LSB page.

The file storage control device 30 may access the second memory 40 and store a data temporarily stored in the buffer area 22.

The file storage control device 30 may convert the logical address of the data input from the buffer area 22 into a physical address to store the file at the physical address of the second memory 40. When the last page of the corresponding file to be stored is the LSB page, the file storage control device 30 may control to duplicate the last LSB page in the second storage area 90 of the second memory 40.

On the other hand, the file storage control device 30 may write the file to another empty storage block when the data having a different physical address is stored in the second memory 40.

9 is a flowchart sequentially illustrating a file storage method according to a second embodiment of the present invention.

According to an embodiment of the present invention, a file storing method may include receiving a file write request (S100), checking a physical block address (S110), writing a file to a corresponding block in a first storage area of a second memory (S300), The final page LSB determination step S310 and the last page duplicate writing step S320 may be included in the second storage area of the second memory.

In detail, in operation S100, a file write request is received from the host processor 10. In this case, a file to be stored in the buffer area is temporarily stored, and a file write request may be received through an interface between the first MLA driver 13 and the second MLA driver 32.

In the physical block address checking step (S110), a logical block address is calculated using logical page information included in the file write request information, and a physical block address is checked from a log block table using the calculated logical block address.

The file writing step S300 in the first storage area performs file writing when there is no data stored in the first page or the second page of the block.

In the final page LSB determination step S310, a file is written to each block, and it is determined whether the last page of the file is an LSB page or an MSB page.

In the step S320 of overwriting the last LSB page in the second storage area, when the last page is the LSB page in the last page LSB determination step S310, the last LSB page is overwritten in the second storage area 90. .

Here, the method may further include a step of checking whether data of the corresponding page exists. The data presence check step (S120) of the corresponding page checks the data storage state of the physical block if there is a physical block address in the physical block address check step (S110). In this case, the second memory 40 may be divided into a first page in which the LSB page is to be stored and a second page in which the MSB page is to be stored. At this time, the NAND driver 33 or the FTL unit 31 accesses the second memory 40 and checks whether there is data stored in the block in which the corresponding file is to be stored. Here, the NAND driver 33 or the FTL unit 31 checks the presence or absence of data stored in the first page or data stored in the second page.

On the other hand, if the page is not empty in the data existence check step of the page can be overwritten. Since the overwriting step is the same as the overwriting step described with reference to FIG. 6, duplicate description thereof will be omitted.

As described above, according to an embodiment of the present disclosure, the block may be prevented from being erased during the SPOR by overwriting the last LSB page in the second area of the second memory.

Although the above has been described with reference to embodiments of the present invention, those skilled in the art may variously modify the present invention without departing from the spirit and scope of the present invention as set forth in the claims below. And can be changed.

10: host processor
11: Application
12: file system
13: first MLA driver
20: first memory
21: Processor area
22: buffer area
23: Driver Area
30: file storage controller
31: FTL section
32: second MLA driver
33: NAND driver
40: second memory
41: block
51: first page area
52: second page area
80: first storage area
90: second storage area

Claims (19)

In the file storage control device for controlling the file storage of the memory,
A Memory Linked Architecture (MLA) driver accessing a buffer area of the first memory in which the file is temporarily stored when a file write request is requested;
A memory driver accessing a second memory in which the corresponding file is to be stored; And
If the last page of the file is LSB (Least Significant Bit (LSB)) page or MSB (Most Significant Bit (hereinafter, referred to as "MSB") page, the page is LSB, the last page is stored Perform a write operation on the last LSB page, which is the last page of the file, to the first page of the block to be
And a FTL (Flash Translation Layer) section controlling controlling a second write of the last LSB page of the corresponding file or an empty of the second page to a second page of the block in which the last page is stored. File storage controller.
The method of claim 1,
The FTL part is
And writing a file to a second page of a block in which the LSB page is stored, when the last page of the corresponding file is an MSB page.
The method of claim 1,
The FTL part is
Examine a physical block address corresponding to a logical block address included in the file information received in the file write request,
And checking the presence or absence of data stored in the page corresponding to the physical block address and storing the last LSB page when there is no data stored in the block page.
The method of claim 3, wherein
And a log block table in which the logical block address and the physical block address are mapped.
The method of claim 3, wherein
The FTL part is
And, if there is data stored in the block in which the file is to be stored, overwriting is performed.
The method of claim 5, wherein
The overwrite operation is
If there is a temporary block, the file is written to an empty block, if there is a temporary block, it is determined whether the last page is an LSB page, and if it is an LSB page, an overwrite is performed, and then the log block table is updated. File storage control device characterized in that.
The method according to claim 6,
If the temporary block does not exist, a file storage control apparatus for allocating a new block or assigning a victim block to write a file of the file to the block.
The method of claim 1,
The FTL part is
If there is no physical block address corresponding to the logical block address included in the file information received at the file request, the second block allocates a free block of the second memory, and includes a log block to include physical block address information corresponding to the free block. File storage control device, characterized in that for updating the table information.
In the file storage control device for controlling the file storage of the memory,
An MLA driver accessing a buffer area of the first memory in which the file is temporarily stored when a file write request is requested;
A memory driver accessing a second memory in which the corresponding file is to be stored; And
The file is stored in a first storage area of the second memory, and if the last page of the file is an LSB page or an MSB page, the last page of the file is an LSB page. And a FTL unit for controlling to overwrite the second storage area of the second memory.
In the file storage control method for controlling the file storage of the memory,
(a) receiving a file write request;
(b) checking the physical block address of the file to be stored in the memory;
(c) determining the presence or absence of data stored in a block of the memory corresponding to the physical block address if the physical block address exists as a result of the checking;
(d) performing file writing when there is no data stored in the block corresponding to the physical block address as a result of the determination; And
(e) It is determined whether the last page of the file on which the file write is performed is an LSB page or an MSB page, and if the last page is an LSB page, the second LSB page is overwritten or the remaining area of the block in which the last LSB page is stored. File storage control method comprising the step of performing the emptying of the.
The method of claim 10,
Step (e) is
And storing the last LSB page in a second page after the last LSB page is stored in a first page among the pages set for each block of the flash memory.
The method of claim 10,
Step (b) is
And converting to a physical block address corresponding to the logical block address received in the step of receiving the file write request.
The method of claim 10,
After step (b),
If there is no physical block address, allocating an empty block to the memory and updating a block table; And
And writing the file to the empty block.
The method of claim 10,
And performing overwriting when there is data stored in the block corresponding to the physical block address in the step (d).
The method of claim 14,
Performing the overwriting is
Checking the presence or absence of a log block in the log block table; And
And writing a file to an empty log block if the log block exists.
The method of claim 14,
Performing the overwriting is
Checking the presence or absence of a log block in the log block table;
If there is no log block, checking for the presence of an empty log block; And
Allocating the empty log block and updating the log block table if the empty log block exists; And
And performing a file write on the empty log block.
17. The method of claim 16,
Selecting at least one block from a log block if there is no empty log block; And
And writing a file to the selected block.
In the file storage control method for controlling the file storage of the memory,
(a) receiving a file write request;
(b) checking the physical block address of the file to be stored in the memory;
(c) determining the presence or absence of data stored in a block of the memory corresponding to the physical block address if the physical block address exists as a result of the checking;
(d) writing a file to a first storage area of the memory when there is no data stored in a block corresponding to the physical block address as a result of the determination; And
(e) determining whether the last page of the file on which the file writing is performed is an LSB page or an MSB page, and if the LSB page is an LSB page, storing the last LSB page in a second storage area of the memory.
The method of claim 18,
Step (d) is
Storing the LSB page in a first page of the first storage area, and storing the MSB page in a second page.

Images