KR101270777B1 - System and method for writing data using a PRAM in a device based on input-output of block unit - Google Patents

Abstract

The present invention relates to a data recording system and method using a PRAM in a block unit input and output device.

A data recording system using a pram in a block unit input / output device according to another embodiment of the present invention is a file system for managing input and output of data in block units, a file system for storing the data and a predetermined block of the file system from the file system. Receiving a write command for one data, and transmits a write command to the block of the FRAM in the sub-block unit of the variation data that is different from the second data stored in the block of the FRAM among the first data It includes a filter layer.

Flash Memory, PRAM, Block Units

Description

System and method for writing data using a PRAM in a device based on input-output of block unit}

The present invention relates to a data recording system and method using a pram, and more particularly, to a data recording system and method using a pram in a block unit input and output device.

Recently, digital devices such as digital cameras, MP3 players, mobile phones, personal digital assistants (PDAs) have been used a lot. In such digital devices, a flash memory capable of storing a large amount of data is applied.

Flash memory is widely used as a storage device of the above-mentioned portable digital devices because of low power, non-volatile, high performance, physical stability, portability, etc. In particular, as the capacity of the flash memory is greatly increased, the disk is replaced by the flash memory. .

However, flash memory does not support random access in units of bytes supported by memories such as SRAM, DRAM, PRAM, MRAM, and FeRAM. In addition, the flash memory reads data in units of pages.

Flash memory performs erase-before-write operations because of its physical characteristics. When a write operation is performed on a sector of a flash memory, the write operation is performed after an erase operation of a block to which the sector belongs. Therefore, it may take more time for input / output (I / O) than a hard disk capable of performing an overwrite operation on a sector.

In addition, when the block of the flash memory performs about 100,000 erase operations, the probability that the memory elements on the block fail is significantly increased. Due to this characteristic, when performing a write operation on a specific sector of the flash memory, the flash memory searches for an empty area in the currently allocated block or allocates a block with a small number of erase operations. The layer that performs this operation is called a Flash Translation Layer (hereinafter referred to as FTL). The FTL performs the function of mapping the logical sector address of the file system to the physical sector address of the flash memory.

The performance of flash memory is affected by the FTL algorithm and the access pattern of the file system using FTL. More random accesses to the file system can increase the overhead of the FTL, leading to faster flash memory life due to slower flash memory performance and increased write / erase cycles.

The workload of a file system can be largely divided into an access for processing user data of the file system and an access for processing meta data of the file system itself. Here, data change of metadata of the file system may frequently cause random access to the flash memory.

However, Flash memory and FTL algorithms that perform write operations on a block basis perform rewrite operations on a block basis even if there is a slight change in user data or metadata. The amount of data must be changed, which can overload the device.

As a temporary solution to this problem, if the file system supporting block I / O is changed to support I / O by byte, the file system must be changed in a large scale.

Accordingly, there is a need for a system and method capable of receiving data in a block unit I / O request of a file system supporting block unit I / O without modifying a file system or FTL, and controlling data in a unit smaller than the block unit.

An object of the present invention is to provide a system and method for recording data in sub-block units, which are smaller units than block units, in a device supporting data input / output in block units.

In addition, an object of the present invention is to provide a system and a method for writing data in sub-block units using a PRAM without changing a file system in a device supporting data input / output in a block unit.

The objects of the present invention are not limited to the above-mentioned objects, and other objects not mentioned can be clearly understood by those skilled in the art from the following description.

In order to achieve the above object, a data recording system using a PRAM in a block unit input / output device according to an embodiment of the present invention includes a file system for managing input and output of data in units of blocks; A flash memory for writing first data among the data in units of blocks; A PRAM for writing second data among the data in sub-block units; And a filter layer that receives a write command for the second data from the file system to a predetermined block of the FRAM and writes a difference portion from the third data stored in the FRAM block to the blocks of the FRAM in sub-block units. (Filter layer) is included.

In order to achieve the above object, a data recording system using a PRAM in a block unit input / output device according to another embodiment of the present invention includes a file system for managing input and output of data in units of blocks; A pram for storing the data; And receiving the write command for the first data from the file system to a predetermined block of the FRAM, and converting the variation data that is different from the second data stored in the FRAM block among the first data in sub-block units. And a filter layer for transmitting a write command to the block of the fram.

According to another aspect of the present invention, there is provided a data writing method using a pram in a block unit input / output device, the method comprising: receiving a write command for first data from a file system to a predetermined block of the pram; Detecting variation data among the first data that is different from the second data stored in the block of the PRAM; And writing the variation data in the block of the PRAM in sub-block units.

According to another aspect of the present invention, there is provided a data writing method using a pram in a block unit input / output device, the method comprising: receiving a write command for first data from a file system to a predetermined block of the pram; Reading second data stored in a predetermined block of the PRAM in block units; Comparing the first data with the second data to detect variation data; And writing the variation data in a sub-block within a predetermined block of the piram in which the variation data is located.

Specific details of other embodiments are included in the detailed description and the drawings.

According to an embodiment of the present invention as described above, a device supporting input / output in block units may support input / output of data in sub-block units.

In addition, a device supporting data input / output may support a function of writing data in sub-block units using a PRAM.

In addition, it is possible to support data input in sub-block units without changing the file system supporting data input / output in block units.

Advantages and features of the present invention and methods for achieving them will be apparent with reference to the embodiments described below in detail with the accompanying drawings. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art. To fully disclose the scope of the invention to those skilled in the art, and the invention is only defined by the scope of the claims.

Hereinafter, the present invention will be described with reference to a block diagram or a flowchart illustrating a data recording system and method using a PRAM in a block unit input / output device according to embodiments of the present invention. At this point, it will be understood that each block of the flowchart illustrations and combinations of flowchart illustrations may be performed by computer program instructions. Since these computer program instructions may be mounted on a processor of a general purpose computer, special purpose computer, or other programmable data processing equipment, those instructions executed through the processor of the computer or other programmable data processing equipment may be described in flow chart block (s). It creates a means to perform the functions. These computer program instructions may also be stored in a computer usable or computer readable memory capable of directing a computer or other programmable data processing apparatus to implement the functionality in a particular manner so that the computer usable or computer readable memory The instructions stored in the block diagram (s) are also capable of producing manufacturing items containing instruction means for performing the functions described in the flowchart block (s). Computer program instructions may also be stored on a computer or other programmable data processing equipment so that a series of operating steps may be performed on a computer or other programmable data processing equipment to create a computer- It is also possible for the instructions to perform the processing equipment to provide steps for executing the functions described in the flowchart block (s).

In addition, each block may represent a portion of a module, segment, or code that includes one or more executable instructions for executing a specified logical function (s). It should also be noted that in some alternative implementations, the functions mentioned in the blocks may occur out of order. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending on the functionality involved.

As used herein, the term 'module' refers to software or a hardware component such as an FPGA or an ASIC, and a module plays a role. However, a module is not limited to software or hardware. A module may be configured to reside on an addressable storage medium and configured to play back one or more processors. Thus, by way of example, a module may include components such as software components, object-oriented software components, class components and task components, and processes, functions, attributes, procedures, Microcode, circuitry, data, databases, data structures, tables, arrays, and variables, as will be appreciated by those skilled in the art. The functionality provided within the components and modules may be combined into a smaller number of components and modules or further separated into additional components and modules.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a block diagram of a data recording system using a PRAM in a block unit input / output device according to an embodiment of the present invention.

Referring to FIG. 1, a data recording system 100 using a PRAM in a block unit input / output device according to an embodiment of the present invention may include an application execution unit 110, an operating system unit 120, a file system 130, and a filter layer. 140, the FTL 170, the PRAM 150, and the flash memory 180 may be included.

The application executor 110 executes a general user program driven by the operating system 120. For example, various application execution units 110 may be included, such as an execution unit for playing an MP3 file, an execution unit for playing a video file, an execution unit for executing a game, and an execution unit for searching for content.

The operating system 120 is a set of programs that manages the file system 130 and provides an interface for a user to easily use hardware. The operating system 120 includes resources such as a processor, a memory device, an input / output device, a communication device, and data. Manage.

File system 130 provides methods and functions for writing, reading, and using data. The file system 130 performs a function for efficient management of a file, which is a collection of data, and provides fast search, recovery, and support of large data. The file system 130 reduces the bottleneck caused by a storage medium having a relatively slow processing speed compared to a processor such as a CPU to the system, facilitates file processing, and improves the performance of the entire system.

The Flash Translation Layer (FTL) 170 performs a function of mapping a logical sector address of the file system 130 to a physical sector address of the flash memory. When the FTL performs a write operation on a specific sector of the flash memory, the flash memory software controls to find an empty area in the currently allocated block or to perform a write operation by allocating a block with a low number of erase operations. It performs the function.

The file system 130 according to an exemplary embodiment of the present invention performs data input / output in units of blocks formed of a plurality of byte aggregates. Here, a block means a basic input / output unit of a file system or an FTL. For example, a block can be 512 bytes or multiples of 512 bytes in size. However, the size of the block is not limited to the number of 512, 128, and the like, and may be referred to as a block, a collection of a plurality of byte units that can be changed by those skilled in the art. However, the data block may be used as another term meaning an input / output unit of data such as a cluster, a sector, and a page.

The filter layer 140 acts as an intermediary for the file system 130 or the FTL 170 to perform a write operation on the pram 150. The filter layer 140 performs a write operation on the pram 150 in units of sub blocks that are smaller in size than blocks. Here, the sub-block means a data size unit that is relatively smaller than the data size of the block, and means a small data size in multiples of the size of the data of the block. For example, if the data size of the block is 1024 bytes, the sub block may be 512 bytes, 256 bytes, ..., 1 byte. For example, if I / O is controlled by byte unit, the byte unit may be a sub block unit.

In the file system 130 that supports input and output in block units, a write operation is generally performed in block units with respect to the flash memory 180. If there is a data change for only some data in the block unit, the entire block must be rewritten. However, because of the nature of the program, the write operation is slower than the read operation, so writing the entire block can significantly slow down the overall system.

Therefore, by introducing the filter layer 140, an operation of writing only changed data may be performed on the PRAM 150 storing data in a file system that performs input and output in units of blocks. The filter layer 140 receives a write command for a predetermined block from the file system 130 or the FTL 170, and allows the pram 150 to perform a write operation on a subblock basis only for the changed part of the block. .

The filter layer 140 is a kind of filtering layer. The filter layer 140 may perform a write operation to the memory in a sub-block unit, which is a data unit smaller than the block unit, without modifying the file system 130 or the FTL 170 that performs input / output in block units. The filter layer 140 may filter a block with respect to a block write operation command of the file system 130 or the FTL 170 to perform a write operation in units of sub-blocks.

The PRAM 150 may also be referred to as a phase change memory, a state change memory, or a phase change memory. It has both the advantages of flash memory, which does not erase stored information even when the power is cut off, and the advantages of DRAM, which has a high processing speed. However, since the write speed is relatively slower than the read speed, the write speed may be slow.

The flash memory 180 is a nonvolatile memory having a characteristic that stored information is maintained even when the power is turned off. The flash memory 180 also freely inputs and outputs data and is widely used in digital camcorders, mobile phones, digital cameras, personal digital assistants, MP3 players, and the like. The flash memory 180 is inputted and outputted in units of blocks through an FTL, and may be suitable for reading and writing a large amount of data.

2 illustrates an operation of a data recording system using a PRAM in a block unit input / output device according to an embodiment of the present invention.

Referring to FIG. 2, an application execution unit 110 or an operating system unit 120 may attempt to access data stored in the PRAM 150 or the flash memory 180. For example, assume that user data is stored in the flash memory 180, and metadata of the file system 130 and / or the FTL 170 is stored in the piram 150. Here, the metadata of the file system is data representing information about the user data file, and the metadata of the FTL 170 is data representing mapping information between logical addresses and physical addresses, state information of a physical device, and the like. The metadata is smaller in capacity than user data and can be changed frequently.

The file system 130 reads and writes the user data stored in the flash memory 180 in block units. Let user data be referred to as first data. The FTL 170 retrieves the physical sector address of the flash memory mapped to the logical sector address of the file system, and reads and writes block by block to a specific sector of the flash memory.

On the other hand, in order to read the data stored in the FRAM 150, the file system 130 or the FTL 170 is accessed in units of blocks. Accordingly, by accessing data stored in the PRAM 150 in units of blocks, the file system 130 and the FTL 170 that perform input / output of the existing blocks can be used without modification.

However, in order to write data to the PRAM 150, a sub block unit is used. Since the file system 130 and the FTL 170 do not support the input / output of the sub block unit, the file system 130 supports the writing of the sub block unit through the filter layer 140.

The file system 130 or the FTL 170 transmits information, such as an address, a logical block number, and data, of a logical block to be stored in order to write data to a predetermined block of the FRAM 150 to the filter layer. Assume that data to be written by the PRAM 150 in a predetermined block is second data. The second data is made in blocks. Thus, the second data consists of at least one block.

The filter layer 140 searches for a block of the PRAM 150 corresponding to the logical block of the file system 130 or the FTL 170 based on the mapping information. However, the block of the pram 150 refers to a physical medium in which data is substantially stored in the pram 150.

The filter layer 140 reads a block of the retrieved param 150. Let the read data be the third data. The third data has the same number of blocks as the second data, so that the second data and the third data have the same size. The third data may be temporarily stored in a buffer unit (not shown) of the filter layer 140.

The filter layer 140 detects the variation data by comparing with the third data based on the second data. The difference from the third data on the basis of the second data is called variation data. For example, if the second data and the third data are completely different data, the change data becomes the second data. Or if the second data and the third data are the same only in the first half of the block, the variation data becomes the second half of the second data. The unit of the variation data is made in sub-block units.

The filter layer 140 writes the block of the PRAM 150 using the detected variation data. The file system 130 or the FTL 170 instructs the FRAM 150 to write the second data in block units, but writes the fluctuation data in the sub-block units to the blocks of the FRAM 150 through the filter layer 140. . Therefore, writes are performed externally in units of blocks, but internally, writes to the PRAM 150 in units of subblocks. In addition, since the data is written only in the changed part, the data can be efficiently updated, and the data can be read and written without changing the file system 130 and / or the FTL 170 that perform I / O in blocks. can do.

As described above, the flash memory 180 performs input / output in block units, and the pram 150 performs input / output in block units externally, but internally writes data to the pyram 150 in sub-block units. Write This means that user data having a large capacity and infrequently changed in the content is stored in the flash memory 180, and meta data having a small capacity and frequently changed in the content is stored in the pram 150 to perform efficient data management. Can be.

In addition, by introducing the filter layer 140 to the PRAM 150 performing I / O in sub-block units, data is read without changing the file system 130 and / or the FTL 170 which performs I / O in units of blocks. You can write.

In addition, the writing speed is slower than the reading speed, and only the data of the changed part is extracted and written in sub-block units by using the characteristic of PRAM that can write data in sub-block units (for example, byte units) instead of block units. As a result, the flash memory 180 and the fram 150 may be effectively used together.

3 is a block diagram of a data recording system using a pram in a block unit input and output device according to another embodiment of the present invention, Figure 4 is a data recording using a pram in a block unit input and output device according to another embodiment of the present invention Show the operation of the system.

Referring to FIG. 3, a block diagram of a data recording system using a PRAM in a block unit input / output device according to another embodiment of the present invention is an application execution unit 110, an operating system unit 120, a file system 130, and a filter layer. 140 and pyram 150 may be included.

The application executor 110, the operating system 120, the file system 130, the filter layer 140, and the pram 150 have been described in detail in the above-described embodiments, and thus, the filter layer 140 is omitted. An operation of a data recording system using a PRAM in a block unit input / output device according to another embodiment of the present invention will be described.

The filter layer 140 may include a mapping information providing unit 210, a data reading unit 220, and a variation data extraction unit 230.

The mapping information provider 210 provides information for mapping a logical block of the file system 130 to a block of the PRAM 150. The mapping information providing unit 210 provides mapping information corresponding to the physical block of the PRAM in the logical block of the file system. In response to the command to write the first data in the predetermined logical block from the file system 130, the block of the PRAM 150 corresponding to the mapping information 210 is searched. Here, the first data refers to data made in units of blocks by a file system managing input / output in units of blocks. For example, even though the data to be written to the PRAM 150 is smaller than a block unit, the first data is loaded in one block. Alternatively, when the data to be written to the pram 150 is larger than one block unit, the first data is loaded in two blocks. However, the mapping information providing unit 210 may be located in the file system 130 or another component or may be an independent component.

The data reading unit 220 reads the retrieved block of the PRAM 150. The data reading unit 220 may read a block of the PRAM in sub-block units. For example, if the sub block is in bytes, the data reading unit 220 may read the blocks of the retrieved params in bytes and temporarily store them in a buffer unit (not shown). Data read by the data reading unit 220 will be referred to as second data.

The variation data extractor 230 compares the first data and the second data to extract the variation data. Here, the variation data refers to data having a difference from the second data based on the first data. For example, if the first data and the second data are completely different data, the variation data is the same as the first data. Or if the first data and the second data are the same as the first half of the block, the variation data becomes the second half of the first data. However, the variation data unit is composed of sub-block units.

Therefore, if the size of the extracted variation data is smaller than the size of the block, the overhead and the writing speed of the device itself can be significantly improved by performing an operation of rewriting only the variation data portion rather than rewriting the block as a whole. When the writing speed such as PRAM is slower than the reading speed, writing of data in block units can be efficiently performed by reducing the writing operation.

Referring to FIG. 4, an operation of a data recording system using a PRAM in a block unit input / output device according to another embodiment of the present invention is as follows.

The file system 130 receives a command from the operating system 120 or the application execution unit 110 to store the first data 430 in the memory. The file system 130 transmits information, such as an address of the logical block, the number of logical blocks, and data, to store the first data 430 to the filter layer 140.

The filter layer 140 searches for the block 400 of the PRAM corresponding to the logic block. The block 400 of the PRAM consists of a plurality of sub blocks 410. The filter layer 140 reads the block 400 of the retrieved param and temporarily stores it as the second data 450. Accordingly, the variation data 420 is extracted by comparing the first data 430 and the second data 450. The filter layer 140 allows the extracted variation data 420 to be written to the pyram in sub-block units.

For example, if the variation data 420 is one subblock 410, an operation of writing only one subblock may have the effect of writing the first data 430 to the pram 150. Therefore, the data can be updated effectively when the data change is small and the data change frequently occurs.

For example, metadata including information about user data or metadata including information about data stored in a flash memory is relatively small in size but changes relatively frequently. This is because the meta data includes not only unique information of the user data such as the size of the user data, attributes of the user data, but also variable information such as a storage time of the user data, recent access time, and mapping information of the FTL.

Therefore, since metadata of small data write requests is frequently changed, excessive overhead may be applied to a device that inputs / outputs data in block units. In addition, waste of the system may be excessive because the entire block is rewritten even with a small data change due to the input / output of each block.

According to an embodiment of the present invention, while maintaining the input and output of the block unit externally while the internally recorded in the sub-block 410 unit in the FRAM 150, without modifying the file system for the input and output of the block unit Data can be recorded in sub-block units.

At the same time, by recording only the changed data portion, the burden of rewriting blocks can be reduced, and the time for writing data can be reduced.

However, when reading data without changing the data, the data may be read in units of blocks instead of through the filter layer 140.

5 is a diagram illustrating a structure and a mapping table of a FRAM in a data recording system using a FRAM in a block unit input / output device according to an embodiment of the present invention.

Referring to FIG. 5, the PRAM 150 is formatted and initialized in units of blocks that are the same input / output units as the file system 130 or the FTL 170. The PRAM 150 may be physically initialized with a plurality of blocks, and may be configured as, for example, P-Block 1, P-Block 2, ..., P-Block n in order.

Each block 400 of the PRAM may be accessed by a mapping table 500 having mapping information. The mapping table 500 is formed by the mapping information providing unit 210 and has an address of the block 400 of the PRAM corresponding to the logical block of the file system 130 or the FTL 170. Accordingly, the mapping information provider 210 provides the mapping information to the file system 130, the FTL 170, the filter layer 140, or the like by using the mapping table 500, and the file system 130 and the FTL 170. ) Or the filter layer 140 may access the block 400 of the Pram.

6 illustrates a data writing method using a PRAM in a block unit input / output device according to another embodiment of the present invention.

Referring to FIG. 6, first, the OS 120 or the application execution unit 110 transmits a first data write command to the FRAM 150 to the file system 130 or the FTL 170. Here, the first data is data made in units of blocks and is data to be updated. The file system 130 or the FTL 170 transmits a first data write command to the filter layer (S600). At this time, while transmitting the first data write command, the address of the logical block to perform the first data write and the first data are also delivered. In addition, the file system 130, the FTL 170, or the filter layer 140 search for the block 400 of the PRAM corresponding to the logic block using the mapping information (S610). After retrieving the block 400 of the fram using mapping information, the second data stored in the block 400 of the fram is read. Here, the size of the first data and the second data is the same, so the number of blocks is also the same so that the first data and the second data can be compared one-to-one.

After reading the second data, the variation data 420 is detected by comparing the second data with the second data (S630). The detected variation data 420 is formed in sub-block units. The variation data 420 is data obtained by extracting, in sub-block units, a portion that is changed in the first data from the second data stored in the existing PRAM.

When the variation data 420 is detected, the variation data 420 is written in sub-block units in the block of the PRAM where the second data is located (S640). For example, suppose a subblock unit is a byte unit and a block unit is 1024 bytes. If the first data varies by 10 bytes from the second data, the extracted change data 420 becomes 10 bytes. Therefore, instead of writing all 1024 bytes to the PRAM, only 10 bytes of variable data can be written to improve the write speed.

As described above, when the data is frequently changed while the capacity is small, only the changed data can be rewritten, so that the characteristic of the writing speed slower than the reading speed of the PRAM can be efficiently used.

In addition, data can be efficiently updated by writing to the FRAM 150 in sub-block units without changing the file system 130 or the FTL 170 of the device that performs input / output in units of blocks.

FIG. 7 illustrates a method of reading data of a PRAM through a filter layer in a data writing method using a PRAM in a block unit input / output device according to another embodiment of the present invention.

Referring to FIG. 7, the file system 130 or the FTL 170 receives a read command for the data of the PRAM 150 from the operating system 120 or the application execution unit 110. The file system 130 or the FTL 170 receives the information of the logical block address to be read and the number of logical blocks to be read and transmits a read request to the filter layer 140 (S700).

The filter layer 140 searches for the block 400 of the PRAM corresponding to the logical block to be read using the mapping information (S710). The filter layer 140 may request the mapping information provider 210 to search for the block 400 of the PRAM.

After finding the block 400 of the pram, the data stored in the block 400 of the pram is read (S720). At this time, the block 400 of the PRAM is read in sub-block units, and read to the end of the block.

As described above, the data of the PRAM 150 may be read through the filter layer 140, and the variation data 420 may be extracted by comparing the data of the PRAM 150 with the data to be written. By using the faster reading speed than the writing speed, which is a characteristic of the FRAM, the FRAM data access can be faster through the filter layer by reading the entire block and writing only the changed part.

Although embodiments of the present invention have been described above with reference to the accompanying drawings, those skilled in the art to which the present invention pertains may implement the present invention in other specific forms without changing the technical spirit or essential features thereof. You can understand that there is. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive.

1 is a block diagram of a data recording system using a PRAM in a block unit input / output device according to an embodiment of the present invention.

2 is a diagram illustrating an operation of a data recording system using a PRAM in a block unit input / output device according to an embodiment of the present invention.

3 is a block diagram of a data recording system using a PRAM in a block unit input / output device according to another embodiment of the present invention.

4 is a diagram illustrating an operation of a data recording system using a PRAM in a block unit input / output device according to another embodiment of the present invention.

FIG. 5 is a diagram illustrating a structure and a mapping table of a FRAM in a data recording system using a FRAM in a block unit input / output device according to an embodiment of the present invention.

6 is a flowchart illustrating a data writing method using a PRAM in a block unit input / output device according to another embodiment of the present invention.

FIG. 7 is a flowchart illustrating a method of reading data of a PRAM through a filter layer in a data writing method using a PRAM in a block unit input / output device according to another embodiment of the present invention.

DESCRIPTION OF THE REFERENCE NUMERALS

100: data recording system using pyram

110: application execution unit

120: operating system

130: file system

140: filter layer

150: piram

170: Flash Translation Layer (FTL)

180: flash memory

Claims (18)

A file system managing input / output of data in block units; A flash translation layer (FTL) for writing first data among the data into a flash memory in units of blocks; A PRAM for writing second data among the data in sub-block units; And A filter layer for receiving a write command for the second data from the file system to a predetermined block of the FRAM and writing a difference portion from the third data stored in the FRAM block to the blocks of the FRAM in sub-block units; Filter layer) And at least one of the file system and the FTL reads the third data in the block unit. The method of claim 1, wherein the filter layer And a variation data extracting unit configured to extract the variation data by reading the third data from the block of the pram and comparing the second data with the second data. The method of claim 1, And the first data is user data, and the second data is meta data. The method of claim 1, wherein the sub-block unit A data recording system using a PRAM in a block unit input / output device, which is a byte unit. The method of claim 1, And a mapping information providing unit configured to provide mapping information between the block of the FRAM and a logical block of the file system to the file system or the filter layer. The method of claim 5, wherein the mapping information providing unit And retrieving a block of the PRAM corresponding to the logical block of the file system using the mapping information. A file system managing input / output of data in block units; A pram for storing the data; And Receiving a write command for the first data from the file system to a predetermined block of the FRAM, the variable data that is different from the second data stored in the block of the FRAM among the first data in the sub-block unit A filter layer for passing a write command to the block of And the file system reads the second data stored in the block of the FRAM in the block unit, and uses the FRAM in the block unit input / output device. Claim 8 was abandoned when the registration fee was paid. The method of claim 7, wherein the sub-block unit A data recording system using a PRAM in a block unit input / output device, which is a byte unit. Claim 9 has been abandoned due to the setting registration fee. The method of claim 7, wherein the pram And an operation of writing the variation data in sub-block units to the block of the pram indicated by the filter layer. The method of claim 7, wherein the pram And a data recording system using a PRAM in a block unit input / output device which is formatted and initialized in the block unit. Claim 11 was abandoned when the registration fee was paid. 8. The method of claim 7, And a mapping information providing unit for retrieving a block of the FRAM corresponding to the logical block of the file system using the mapping information between the logical block of the file system and the block of the FRAM. Data recording system. Receiving a write command for the first data from a file system to a predetermined block of the FRAM; Detecting variation data different from the second data stored in the block of the PRAM among the first data, and reading the second data in block units; And And writing the variation data in the block of the PRAM in sub-block units. Claim 13 was abandoned upon payment of a registration fee. The method of claim 12, wherein the sub-block unit A data writing method using a PRAM in a block unit input / output device, which is a byte unit. delete Claim 15 is abandoned in the setting registration fee payment. The method of claim 12, wherein the pram The data recording method using the PRAM in a block unit input and output device is formatted and initialized in the block unit. Receiving a write command for the first data from a file system to a predetermined block of the FRAM; Reading second data stored in a predetermined block of the PRAM in block units; Comparing the first data with the second data to detect variation data; And And writing the variation data in sub-block units in a sub-block in a predetermined block of the piram in which the variation data is located. Claim 17 has been abandoned due to the setting registration fee. The method of claim 16, wherein the step of transmitting a write command to the first data comprises: And retrieving a block of the FRAM corresponding to a logical block of the file system using mapping information. Claim 18 has been abandoned due to the setting registration fee. The method of claim 16, wherein the first data is A data writing method using a PRAM in a block unit input / output device which is metadata.

Images