JP2014063358A - Information processor, information processing method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To enable an NV memory to be used as a main memory and a storage without discriminating between an area used as the main memory and an area used as the storage.SOLUTION: An information processor includes: an NV memory that is a nonvolatile storage medium; a file system unit that reads and writes data to and from the NV memory for each predetermined unit; and a memory management unit that allocates a predetermined area of the NV memory to a process which is requested to be executed. Thus, the NV memory can be used as a main memory and a storage without discriminating between an area used as the main memory and an area used as the storage.

Description

  The present invention relates to an information processing apparatus using a nonvolatile memory.

  Conventionally, a non-volatile memory (Non-Volatile Memory, hereinafter referred to as NV memory as appropriate) such as a so-called USB memory (see Patent Document 1) and Flash SSD (see Patent Document 2) has been developed.

Non-Patent Document 1: “What is USB Memory”, [online], IT Glossary of Terms e-Words, [Search August 6, 2012], Internet [URL: http://e-words.jp/w/USBE383A1E383A2E383AA .html] Non-Patent Document 2: “What is SSD?”, [Online], IT Glossary of Terms e-Words, [searched August 6, 2012], Internet [URL; http://e-words.jp/w/SSD. html]

  In recent years, NV memory has been divided into two areas, an area used as a main memory and an area used as a storage, by research using the NV memory as a main memory and research using the main memory as a storage. The area can be used as main memory and storage. The ability to use NV memory as both main memory and storage means that both can be merged into one. However, in the conventional research and the like, the NV memory cannot be used as the main memory and storage without distinguishing between the area used as the main memory and the area used as the storage.

  The information processing apparatus according to the first aspect of the present invention includes an NV memory that is a non-volatile recording medium, a file system unit that reads and writes data in a predetermined unit from the NV memory, and a process that is requested to execute. An information processing apparatus includes a memory management unit that allocates a predetermined area of the NV memory.

  With such a configuration, the NV memory can be used as the main memory and storage without distinguishing between the area used as the main memory and the area used as the storage.

  In the information processing apparatus according to the second aspect of the present invention, in contrast to the first aspect, the file system unit is a file having a file identifier for identifying one or more files and one or more logical addresses corresponding to the files. File management information storage means for storing management information, conversion information storage means for storing conversion information for converting logical addresses into physical addresses, and one or more logical addresses corresponding to one or more files , An address conversion unit that converts the information into one or more physical addresses using the conversion information, a writing unit that writes a file in the area of the NV memory corresponding to the physical address acquired by the address conversion unit, and a physical unit acquired by the address conversion unit An information processing apparatus includes reading means for reading a file from an NV memory area corresponding to an address.

  With such a configuration, data stored in the NV memory can be handled as a file.

  In the information processing apparatus according to the third aspect of the present invention, in contrast to the second aspect of the invention, the file system unit manages the NV memory as blocks each having a predetermined size, and the memory management unit manages the NV memory. This is an information processing apparatus that manages a page as a region for each predetermined size, and has the same block size and page size.

  With such a configuration, memory allocation and release processing can be performed efficiently.

  In the information processing apparatus according to the fourth aspect of the present invention, in contrast to any one of the first to third aspects, the memory management unit releases the NV memory area allocated to the process at a predetermined timing, and The system unit detects area information storage means for storing one or more area information indicating a free area or a used area of the NV memory, and detects an area released by the memory management section as a free area, and stores area information indicating the free area. The file system unit writes data to the free area indicated by the area information, and the memory management unit applies the free area indicated by the area information to the process requested to be executed. It is an information processing apparatus to be assigned to.

  With such a configuration, the released NV memory free area can be registered as a free area in the file system. Thereby, the consistency of the file system can be maintained.

  The information processing apparatus according to the fifth aspect of the present invention further includes a volatile memory that is a volatile recording medium as compared with any one of the first to fourth aspects, and the memory management unit is an NV memory. An area determination unit that determines whether there is a free area, and a memory that allocates a predetermined area on the volatile memory to a process requested to be executed when the area determination unit determines that there is no free area in the NV memory. And an information processing apparatus including management means.

  With such a configuration, even when the NV memory has no free space, the volatile memory can be used as the main memory.

  According to the information processing apparatus and the like according to the present invention, the NV memory can be used as the main memory and the storage without distinguishing between the area used as the main memory and the area used as the storage.

Block diagram of information processing apparatus 1 according to Embodiment 1 A flowchart for explaining the overall operation of the information processing apparatus 1 Flowchart explaining the detection of the free area and the area release process The figure which shows the example of the conversion information The figure which shows the example of the same area information The figure which shows the example of the same file management information The figure which shows the example of the same area information The figure which shows the example of the starting command of the same QEMU Diagram showing an example of placement in the same physical address space Diagram showing the relationship of the virtual storage system, etc. A figure showing a screen dump when the same area is allocated and released Figure showing the benchmark results The figure which shows the same performance comparison result Diagram showing an example of the same circuit configuration Block diagram of the information processing apparatus 1 Overview of the computer system in the above embodiment Block diagram of a computer system in the above embodiment

  Hereinafter, embodiments of an information processing apparatus and the like according to the present invention will be described with reference to the drawings. In addition, since the component which attached | subjected the same code | symbol in embodiment performs the same operation | movement, description may be abbreviate | omitted again. In addition, the format, content, and the like of each information described in this embodiment are merely examples, and the format, content, and the like are not limited as long as the meaning of each information can be indicated.

(Embodiment 1)
In the present embodiment, the information processing apparatus 1 used as a storage and main memory without dividing the NV memory into an area used as storage and an area used as main memory will be described. Here, the storage is a so-called secondary storage device or a storage device called an auxiliary storage device. The main memory is a so-called primary storage device or a storage device called a main storage device.

  FIG. 1 is a block diagram of an information processing apparatus 1 in the present embodiment. The information processing apparatus 1 includes an NV memory 11, a volatile memory 12, a reception unit 13, a file system unit 14, and a memory management unit 15. The file system unit 14 includes a file management information storage unit 141, a conversion information storage unit 142, a region information storage unit 143, an address conversion unit 144, a writing unit 145, a reading unit 146, and a region detection unit 147. In addition, the memory management unit 15 includes an area determination unit 151 and a memory management unit 152.

  In addition, the file system unit 14 and the memory management unit 15 included in the information processing apparatus 1 according to the present embodiment are, for example, a so-called OS or what is called a kernel of the OS.

  The NV memory 11 is a non-volatile recording medium. The NV memory 11 is, for example, PCM (Phase Change Memory), MRAM, ReMAM, EEPROM, flash memory, or the like. In addition, the NV memory 11 is not particularly limited in shape or type as long as it is a nonvolatile memory. For example, if the NV memory 11 is a nonvolatile memory that can be accessed in byte units, it can be accessed by a physical address. Further, for example, even if the NV memory 11 is a non-volatile memory that cannot be accessed in byte units, it can be accessed by a physical address via a buffer RAM as shown in FIG.

  In addition, the NV memory 11 has one or more areas (hereinafter referred to as unit areas as appropriate) in which data of a predetermined unit is stored. The predetermined unit is usually a so-called size (capacity), such as 4 KB (kilobytes) or 512 B (bytes). The size may or may not be predetermined. Further, the one unit area is used as, for example, a “block” from the file system unit 14 described later. The one unit area is used as, for example, a “page” from the memory management unit 15 described later. That is, the one unit area is usually called by two or more names. The predetermined unit may be, for example, a block, a page, two or more blocks, or two or more pages. In the present embodiment, the size of the block and the size of the page are the same. The size is preferably 4 KB.

  The volatile memory 12 is a volatile recording medium. The volatile memory 12 is usually a so-called DRAM, but may be an SRAM or the like. The volatile memory 12 is not particularly limited in shape or type as long as it is a so-called volatile memory.

  Further, the volatile memory 12 has one or more unit areas, like the NV memory 11. The one unit area is normally used as a “page” from the memory management unit 15 described later. The one unit area is not normally used as a “block” from the file system unit 14 described later.

  Further, the NV memory 11 and the volatile memory 12 are usually arranged in one physical address space. The physical address space usually has one or more consecutive physical addresses. Further, “arranged in the physical address space” means that one or more unit areas of each of the NV memory 11 and the volatile memory 12 are associated with a physical address. That is, the one unit area is identified by the physical address. Further, the one unit area may be indirectly identified by a logical address (also referred to as a virtual address), for example. Note that the one unit area is called a block or a page, and therefore, the physical address and the logical address are hereinafter appropriately referred to as a block identifier or a page identifier.

  Further, the placement of the NV memory 11 in the physical address space is performed by, for example, the file system unit 14 or the memory management unit 15 described later. Further, the arrangement may be performed by, for example, an address space arrangement unit (not shown).

  Further, the NV memory 11 and the volatile memory 12 are normally not assigned overlapping physical addresses.

  The receiving unit 13 receives instructions and information. The instructions are, for example, a program execution instruction, a process execution instruction, a memory allocation instruction to the program or process, a file operation instruction, or the like. The information is, for example, a so-called command or an argument given to the command. These instructions and information are usually output by a program that outputs the instructions and information.

  The file system unit 14 is a so-called file system. The file system is, for example, PRAMFS (Persistent and Protected RAM File System), Ext2 (Second Extended System), or SCMFS (A File System for Storage Class). In addition, the file system supports XIP (eXecute-In-Place), and any file system that targets the NV memory 11 may be used. That is, the file system unit 14 uses the NV memory 11 as so-called storage. In addition, the file system unit 14 usually divides the NV memory 11 into one or more unit areas, and uses the one unit area as a block.

  For example, when writing one file to the NV memory 11, the file system unit 14 first determines to which one or more blocks the one file is assigned. Then, the file system unit 14 divides the one file into the assigned blocks, and writes the divided file into the NV memory 11.

  Further, when one file is written in the NV memory 11, the file system unit 14 normally associates the identifier of the written file (hereinafter referred to as file identifier as appropriate) with the block identifier for identifying the write destination block. The file management information shown is accumulated in an arbitrary storage area or a predetermined storage area. The file identifier is, for example, an ID or a so-called file name. The file identifier may be any format or content as long as the file can be identified.

  For example, when reading one file from the NV memory 11, the file system unit 14 first acquires a block identifier for identifying one or more blocks in which the one file is written from the file management information. Then, the file system unit 14 acquires data of the file divided into one or more from the block indicated by the acquired identifier of the one or more blocks. Then, the file system unit 14 combines the acquired one or more data to acquire a file.

  For example, when deleting one file from the NV memory 11, the file system unit 14 first acquires a file identifier that identifies one or more blocks in which the one file is written from the file management information. . Then, the file system unit 14 erases data from the block indicated by the acquired identifier of one or more blocks. Note that “erasing” usually includes deleting the file management information. The “erase” may be, for example, updating area information to be described later (rewriting area information indicating a used area to area information indicating a free area).

  When one file is deleted from the NV memory 11, the file system unit 14 normally stores information indicating the correspondence between the file identifier for identifying the deleted file and the block identifier for identifying the block to be deleted. The information is deleted from an arbitrary storage area in which the information is stored or a predetermined storage area.

  Since the file system is a well-known technique, description of processing and operations performed by the file system unit 14 will be omitted as appropriate. In addition, the file system unit 14 usually performs, for example, each means described below for managing a file in the NV memory 11, managing a free area, writing a file to the NV memory 11, and reading a file from the NV memory 11. To do.

  The file management information storage unit 141 stores one or more file management information having a file identifier for identifying a file and one or more logical addresses corresponding to the file. The logical address may be a physical address.

  The conversion information storage unit 142 stores conversion information for converting a logical address into a physical address. The conversion information includes, for example, a conversion formula for calculating a physical address by substituting a logical address, a correspondence table between one logical address and one physical address, an offset with respect to one logical address, and the like. The conversion information is information used by an address conversion unit 144 described later to convert one logical address to one physical address. The conversion information is not limited in its format or content as long as it is information that can convert a logical address into a physical address. The conversion information may be information for converting a physical address into a logical address, for example.

  The area information storage unit 143 stores one or more area information. The area information is information indicating a free area that is one or more unit areas that are not used in the NV memory 11. The area information may be information indicating a used area that is one or more unit areas used in the NV memory 11. That is, the area information may indicate a free area or a used area.

  The area information usually has one logical address and a flag. The logical address may be a physical address. The flag indicates whether the unit area identified by the one logical address is an empty area or a used area. The flag is, for example, “0” when indicating a free area and “1” when indicating a used area. The flag is, for example, “◯” when indicating a free area, and “X” when indicating a used area. Further, the area information may have two logical addresses. In this case, the area information indicates that the unit area corresponding to the range of the logical address indicated by the two logical addresses is an empty area or a used area.

  The address conversion unit 144 converts one logical address into one physical address using the conversion information stored in the conversion information storage unit 142. The “conversion” usually includes obtaining one physical address corresponding to one logical address using the conversion information. Further, the address converting unit 144 normally converts one or more logical addresses corresponding to one file into one or more physical addresses using the conversion information. The file is, for example, a file requested to be written to the NV memory 11 or a file requested to be read from the NV memory 11. Note that the receiving unit 13 normally receives an instruction to request the writing and an instruction to request the reading. The instruction usually has a file identifier.

  For example, the address conversion unit 144 first acquires the file identifier included in the instruction received by the receiving unit 13. Then, the address conversion unit 144 acquires a logical address corresponding to the acquired file identifier from the file management information storage unit 141. Then, the address conversion unit 144 acquires a physical address from the acquired logical address using the conversion information stored in the conversion information storage unit 142.

  For example, when the conversion information is a conversion formula, the address conversion unit 144 substitutes a logical address into the conversion formula and acquires a physical address. For example, when the conversion information is a correspondence table, the address conversion unit 144 acquires a physical address corresponding to the logical address from the correspondence table. Further, for example, when the conversion information is an offset, the address conversion unit 144 adds the offset to the logical address and acquires the physical address.

  Further, the address conversion unit 144 may convert a physical address into a logical address using, for example, conversion information. The method and procedure for converting a physical address to a logical address are the same as the method and procedure for converting a logical address to a physical address, and thus description thereof is omitted.

  The writing unit 145 writes the file requested to be written into the NV memory. This is, for example, writing the data corresponding to the file identifier included in the file writing instruction received by the receiving unit 13 as a file in the NV memory.

  For example, the writing unit 145 determines which one or more blocks of the free area indicated by the area information stored in the area information storage unit 143 to write the file requested to be written. The determination is to obtain one or more logical addresses corresponding to one or more blocks to be written to. Moreover, the method of the said determination is not ask | required. For example, the writing unit 145 searches for one or more continuous free areas or one or more non-consecutive (non-contiguous) free areas corresponding to the size of the file requested to be written, and corresponds to the free areas. Get logical address. Then, the writing unit 145 passes the acquired one or more logical addresses to the address conversion unit 144, and acquires one or more physical addresses corresponding to the one or more logical addresses from the address conversion unit 144. Then, the writing unit 145 divides the file into blocks corresponding to the acquired one or more physical addresses, and writes the divided file into each block. Then, the writing unit 145 creates file management information by associating the file identifier for identifying the written file with the logical address corresponding to each of the written one or more blocks. Then, the writing unit 145 accumulates the file management information in the file management information storage unit 141. In this case, for example, the writing unit 145 may pass one or more logical addresses corresponding to the written file to the area detecting unit 147 described later to the area detecting unit 147 described later.

  The reading unit 146 reads the file requested to be read from the NV memory. For example, the data corresponding to the file identifier included in the file read instruction received by the receiving unit 13 is read from the NV memory as a file.

  For example, the reading unit 146 acquires one or more logical addresses corresponding to the file identifier for identifying the file requested to be read from the file management information storage unit 141. Then, the reading unit 146 passes the acquired one or more logical addresses to the address conversion unit 144, and acquires one or more physical addresses corresponding to the one or more logical addresses from the address conversion unit 144. Then, the reading unit 146 reads data from the block corresponding to the one or more physical addresses. Then, the reading unit 146 combines the read one or more data and acquires it as a file.

  Further, the reading unit 146 may delete, for example, a file requested to be deleted from the NV memory. In this case, the method or procedure for acquiring one or more physical addresses corresponding to the file to be deleted is the same as the method or procedure for acquiring one or more physical addresses corresponding to the file to be read. Since there is, description is abbreviate | omitted. Then, the reading unit 146 erases data from the block corresponding to the acquired one or more physical addresses. Then, the reading unit 146 deletes the file management information corresponding to the file to be deleted from the file management information storage unit 141. In this case, for example, the reading unit 146 may pass one or more logical addresses corresponding to the deleted file to the area detecting unit 147 described later to the area detecting unit 147 described later. The file may be deleted by a file deletion unit (not shown).

  The area detection unit 147 detects an empty area in the NV memory 11. Then, the area detection unit 147 accumulates area information indicating the empty area in the area information storage unit 143. For example, the area detection unit 147 determines whether one or more unit areas of the NV memory 11 are free areas. Then, the area detection unit 147 acquires one or more physical addresses corresponding to one or more unit areas determined to be free areas. Then, the area detection unit 147 passes the one or more physical addresses to the address conversion unit 144, and acquires one or more logical addresses corresponding to the one or more physical addresses. Then, the area detection unit 147 creates area information by associating the one or more logical addresses with a flag indicating a free area. Then, the area detection unit 147 accumulates the area information in the area information storage unit 143. The accumulation is a concept including so-called appending, overwriting, updating, and the like. Further, the area detection unit 147 may detect the used area instead of the empty area.

  Further, the area detection unit 147 may detect, for example, a unit area that has become a new empty area or a unit area that has newly become a use area. When detecting a unit area that has newly become a free area, the area detection unit 147 specifies one or more unit areas that are used areas from, for example, area information stored in the area information storage unit 143. Then, the area detection unit 147 determines whether or not one or more unit areas that are used areas are free areas. Then, the area detection unit 147 creates one or more pieces of area information corresponding to one or more unit areas determined to be free areas, and accumulates the area information in the area information storage unit 143. In addition, when detecting a unit area that is newly used, the area detection unit 147 specifies one or more unit areas that are free areas from the area information stored in the area information storage unit 143, for example. . Then, the area detection unit 147 determines whether or not one or more unit areas that are free areas are used areas. Then, the area detection unit 147 creates one or more area information corresponding to one or more unit areas determined to be used areas, and accumulates the area information in the area information storage unit 143. Note that the region information creation method and procedure are the same as described above, and thus the description thereof is omitted.

  In addition, the area detection unit 147 may, for example, after the writing unit 145 writes a file, after the reading unit 146 deletes the file, after the memory management unit 15 described later allocates an area to the process, An empty area is detected at a predetermined timing such as after the management unit 15 releases the area.

  For example, when one or more logical addresses are received from the writing unit 145, the area detecting unit 147 associates each of the one or more logical addresses with a flag indicating that the area is a used area. Area information is created, and the area information is stored in the area information storage unit 143. Further, for example, when one or more logical addresses are received from the reading unit 146, the area detecting unit 147 associates each of the one or more logical addresses with a flag indicating that it is a free area. Information is created and the region information is stored in the region information storage unit 143.

  For example, it is assumed that the area information “(0x00000000 | 0), (0x00000001 | 0), (0x00000002 | 0)” is already stored in the area information storage unit 143. The area information means that blocks corresponding to logical addresses “0x00000000” to “0x00000002” are free areas. Further, it is assumed that the area detection unit 147 acquires area information “(0x00000000 | 0), (0x00000001 | 1), (0x00000002 | 1)”. The area information means that only blocks corresponding to the logical address “0x00000000” are free areas in the blocks corresponding to the logical addresses “0x00000000” to “0x00000002”. In such a case, the area detection unit 147 overwrites the already stored area information with the acquired area information.

  Further, for example, it is assumed that the area information “0x00000000 to 0x00000002” is already stored in the area information storage unit 143. The area information means that blocks corresponding to logical addresses “0x00000000” to “0x00000002” are free areas. Further, it is assumed that the area detection unit 147 acquires area information “0x00000003 to 0x00000005”. Since the meaning of the area information is the same as described above, the description thereof is omitted. In such a case, the area detection unit 147 rewrites the already stored area information to “0x00000000-0x00000005”.

  As described above, the area information is normally accumulated in the area information storage unit 143 by the area detection unit 147. Thus, for example, when data is stored in a unit area but apparently the unit area is used as an empty area (data is not deleted from the unit area, but the unit area is used as an empty area for management purposes) The reading means 146 obtains one or more logical addresses corresponding to the file to be deleted, and the area detecting means 147 sets a flag indicating that the one or more logical addresses are free areas. The information is stored in the association and area information storage unit 143.

  The memory management unit 15 performs so-called memory management. Memory management refers to, for example, allocating one or more unit areas of the NV memory 11 to a process requested to be executed, or one or more unit areas of the NV memory 11 in response to a request from the executing process. And one or more unit areas of the NV memory 11 that are no longer needed are released as free areas. That is, the memory management unit 15 uses the NV memory 11 as a so-called main memory. In addition, the memory management unit 15 normally divides the NV memory 11 into one or more unit areas, and manages the one unit area as a page.

  Note that since memory management is a known technique, description of processing and operations performed by the memory management unit 15 will be omitted as appropriate. In addition, the memory management unit 15 normally performs, for example, allocation of pages to processes, release of allocated pages, and the like by means described below.

  The area determination unit 151 determines whether there is a free area in the NV memory 11. At this time, the area determination unit 151 normally determines whether or not there is a free area having the same size as that requested by the process requested to be executed. The area determination unit 151 normally determines whether or not the file system unit 14 is using all areas of the NV memory 11. The area determination unit 151 normally determines these determinations using the file management information stored in the file management information storage unit 141 and the area information stored in the area information storage unit 143. In other words, the area determination unit 151 normally determines whether all areas of the NV memory 11 are used areas based on the area information stored in the area information storage unit 143. Then, if all the areas of the NV memory 11 are used areas, the area determining means 151 determines whether the files are written in all the used areas based on the file management information stored in the file management information storage means 141. Judge whether or not.

  The memory management unit 152 allocates one or more pages of the NV memory 11 to the process requested to be executed. The process is usually a user process requested by a so-called user. In addition, the “assignment” includes securing the one or more pages for the process, permitting the process to use the one or more pages, and the like. At this time, the memory management unit 152 normally transmits a logical address for identifying the one or more pages to the process. The logical address may be a physical address.

  Also, the memory management unit 152 releases one or more pages allocated to the process at a predetermined timing, for example. “Release” means to make the one or more pages free. The predetermined timing is, for example, at the end of the process execution, at the normal end, or at the restart. Further, for example, the memory management unit 152 may notify the area detection unit 147 that the page has been released after the page is released. For example, the memory management unit 152 may store area information indicating that the page is an empty area in the area information storage unit 143 after the page is released.

  For example, if the area determination unit 151 determines that there is no free area in the NV memory 11, the memory management unit 152 allocates one or more pages of the volatile memory 12 to the process requested to be executed. .

  Further, the memory management unit 152 may be considered to include, for example, a memory management unit (MMU), or may not be considered as such. Further, the memory management unit 152 may secure and release an area on the NV memory via the file system unit 14, for example.

  Further, the file system unit 14, the file management information storage unit 141, the conversion information storage unit 142, the area information storage unit 143, the address conversion unit 144, the writing unit 145, the reading unit 146, the region detection unit 147, the memory management unit 15, The area determination unit 151 and the memory management unit 152 can be usually realized by an MPU, a memory, or the like. The processing procedure of the file system unit 14 is usually realized by software, and the software is recorded on a recording medium such as a ROM. However, it may be realized by hardware (dedicated circuit).

  Next, the overall operation of the information processing apparatus 1 will be described using the flowchart of FIG.

  (Step S201) The file system unit 14 arranges the NV memory 11 and the volatile memory 12 in the same physical address space. The arrangement may be performed by the memory management unit 15.

  (Step S202) The writing unit 145 determines whether the receiving unit 13 has received an instruction. If accepted, the process proceeds to step S203, and if not, the process proceeds to step S215.

  (Step S203) The writing unit 145 determines whether or not the instruction received in step S202 is a file writing instruction. If it is a file write instruction, the process proceeds to step S204, and if not, the process proceeds to step S208.

  (Step S204) The writing unit 145 secures one or more blocks for writing a file corresponding to the file write instruction received in step S202. “Securing” means obtaining one or more logical addresses corresponding to the one or more blocks.

  (Step S205) The address conversion unit 144 uses the conversion information stored in the conversion information storage unit 142 to convert the one or more logical addresses acquired in Step S204 into one or more physical addresses.

  (Step S206) The writing unit 145 writes the file in the unit area identified by one or more physical addresses acquired in step S205.

  (Step S207) The writing unit 145 associates the identifier of the file written in step S206 with one or more logical addresses acquired in step S204, and accumulates them in the file management information storage unit 141 as file management information.

  (Step S208) The reading unit 146 determines whether or not the instruction received in step S202 is a file reading instruction. If it is a file read instruction, the process proceeds to step S209, and if not, the process proceeds to step S212.

  (Step S209) The reading unit 146 acquires one or more logical addresses corresponding to the file reading instruction received in step S202 from the file management information storage unit 141.

  (Step S210) The address conversion unit 144 converts the one or more logical addresses acquired in Step S209 into one or more physical addresses.

  (Step S211) The reading unit 146 reads a file from the unit area identified by one or more physical addresses acquired in Step S210.

  (Step S212) The reading unit 146 determines whether or not the instruction received in step S202 is a file deletion instruction. If it is a file deletion instruction, the process proceeds to step S213, and if not, the process proceeds to step S217.

  (Step S213) The reading unit 146 acquires one or more logical addresses corresponding to the file deletion instruction received in Step S202 from the file management information storage unit 141.

  (Step S214) The address conversion unit 144 converts the one or more logical addresses acquired in Step S213 into one or more physical addresses.

  (Step S215) The reading unit 146 deletes the file from the unit area identified by the one or more physical addresses acquired in Step S214.

  (Step S216) The reading unit 146 deletes the file management information having the identifier of the file deleted in Step S215 and the one or more logical addresses acquired in Step S213 from the file management information storage unit 141.

  (Step S217) The memory management unit 15 determines whether or not the instruction received in Step S202 is a process execution instruction. If it is a process execution instruction, the process proceeds to step S218; otherwise, the process returns to step S202.

  (Step S <b> 218) The area determination unit 151 determines whether there is a free area in the NV memory 11. When it exists, it progresses to step S219, and when that is not right, it progresses to step S220.

  (Step S219) The memory management unit 152 secures one or more pages from the NV memory 11 for executing the process corresponding to the process execution instruction received in Step S202. “Securing” means obtaining one or more logical addresses corresponding to one or more pages of the NV memory 11.

  (Step S220) The memory management unit 152 reserves one or more pages from the volatile memory 12 for executing the process corresponding to the process execution instruction received in Step S202. “Securing” means obtaining one or more logical addresses corresponding to one or more pages of the volatile memory 12.

  (Step S221) The address conversion unit 144 converts one or more logical addresses acquired in Step S219 or Step S220 into one or more physical addresses.

  (Step S222) The memory management unit 152 assigns one or more unit areas identified by one or more physical addresses acquired in Step S221 to a process corresponding to the process execution instruction received in Step S202, and allocates the process. Run.

  (Step S223) The area detection means 147 and the memory management means 152 detect a free area and release the area. Details of this processing will be described with reference to the flowchart of FIG.

  In the flowchart of FIG. 2, the process may be terminated by powering off or a process termination interrupt.

  In the flowchart of FIG. 2, the area determination unit 151 does not need to determine whether or not there is a free area in the NV memory 11. In this case, when the instruction received in step S202 is a process execution instruction in step S217 of FIG. 2, the process proceeds to step S219.

  FIG. 3 is a flowchart showing the free area detection and area release processing in step S223 of the flowchart of FIG.

  (Step S <b> 301) The area detection unit 147 determines whether or not it is the timing for detecting an empty area in the NV memory 11. If it is the timing of detection, the process proceeds to step S302, and if not, the process proceeds to step S304.

  (Step S302) The area detection unit 147 detects an empty area in the NV memory 11, and acquires area information indicating the empty area.

  (Step S303) The region detection unit 147 accumulates the region information acquired in Step S302 in the region information storage unit 143.

  (Step S304) The memory management unit 152 determines whether it is the timing for releasing the allocation area, which is one or more unit areas allocated to the process. If it is the release timing, the process proceeds to step S305, and if not, the process returns to the upper process.

  (Step S305) The memory management unit 152 releases an allocation area that is one or more unit areas allocated to a process. Then, the process returns to the upper process.

(Concrete example)
Next, a specific example of the operation of the information processing apparatus 1 will be described. In this specific example, it is assumed that the NV memory 11 and the volatile memory 12 are arranged in the same physical address space. The NV memory 11 and the volatile memory 12 each have one or more unit areas each having a size of 4 KB.

(Example 1)
In this example, it is assumed that the conversion information storage unit 142 stores the conversion information shown in FIG. The conversion information includes an ID for uniquely identifying a record, a logical address, and a physical address. Further, it is assumed that the region information storage unit 143 stores the region information shown in FIG. The area information includes an ID for uniquely identifying a record, a logical address, and a flag (item name: empty) indicating whether the area is an empty area. The flag indicates that “0” is a free area and “1” is not a free area (used area). Further, one logical address (physical address) in FIGS. 4 and 5 identifies one unit area (hereinafter referred to as a block as appropriate) of the NV memory 11.

  First, it is assumed that the user operates the information processing apparatus 1 and performs an operation for creating a 10 KB file whose file name is “v_img”. Then, the accepting unit 13 accepts a file writing instruction having the file name.

  Next, since the size of the file to be written is 10 KB, the writing unit 145 uses the blocks identified by the three logical addresses “ID = 011” to “ID = 013” in FIG. 5 as the area of the file to be written. Secure. At this time, the writing unit 145 associates the three logical addresses with the flag “1” indicating the used area, creates area information, and stores the area information in the area information storage unit 143. May be.

  Next, the address conversion unit 144 acquires physical addresses corresponding to the three logical addresses “ID = 011” to “ID = 013” in FIG. 5 from the conversion information in FIG. Then, the address conversion unit 144 acquires three physical addresses “ID = 011” to “ID = 013” in FIG.

  Next, the writing unit 145 writes the file to be written in the unit area identified by each of the three physical addresses “ID = 011” to “ID = 013” in FIG. For example, the writing unit 145 divides a file to be written into 4 KB data (divided into three data of 4 KB, 4 KB, and 2 KB). Then, the writing unit 145 writes the three data in each of the three unit areas.

  Next, the writing unit 145 associates the file name “v_img” of the file with the three secured logical addresses “0xF0000001”, “0xF0000002”, and “0xF00000003”, and stores the file management information as file management information. 141. The file management information is, for example, FIG.

  Next, since the writing unit 145 has written the file to the NV memory, the area detecting unit 147 determines that it is the detection timing of the free area, and detects the free area of the NV memory 11. Then, the area detecting unit 147 acquires area information indicating that the unit area identified by each of the three physical addresses “0x10000001”, “0x10000002”, and “0x10000003” is a used area. Then, the area detection unit 147 accumulates the acquired area information in the area information storage unit 143. As a result, the region information stored in the region information storage unit 143 is as shown in FIG. In FIG. 7, the area information from “ID = 011” to “ID = 013” is the area information acquired by the area detecting unit 147.

  Next, it is assumed that the user operates the information processing apparatus 1 and performs an operation for reading a file whose file name is “v_img”. Then, the accepting unit 13 accepts a file reading instruction having the file name.

  Next, the reading unit 146 acquires the logical address corresponding to the file name “v_img” from the file management information of FIG. Then, the reading unit 146 acquires three logical addresses “0xF0000001”, “0xF0000002”, and “0xF00000003” from the file management information of FIG.

  Next, the address conversion unit 144 acquires physical addresses corresponding to the three logical addresses included in the record of “ID = 001” in FIG. 6 from the conversion information in FIG. Then, the address conversion unit 144 acquires three physical addresses “ID = 011” to “ID = 013” in FIG.

  Next, the reading unit 146 reads the file from the unit area identified by each of the three physical addresses “ID = 011” to “ID = 013” in FIG. For example, the reading unit 146 acquires data from the three unit areas, combines the three data, and acquires the data as a file.

  Next, it is assumed that the user operates the information processing apparatus 1 and performs an operation for deleting a file whose file name is “v_img”. Then, the reception unit 13 receives a file deletion instruction having the file name. Note that the method for acquiring the physical address corresponding to the file is the same as described above, and thus the description thereof is omitted.

  Next, the reading unit 146 deletes data from the unit area identified by each of the three physical addresses “ID = 011” to “ID = 013” in FIG. At this time, the reading unit 146 associates the three logical addresses corresponding to the three physical addresses with the flag “0” indicating the free area, creates area information, and sets the area information as the area. The information may be stored in the information storage unit 143.

  Next, since the reading unit 146 deletes the file from the NV memory, the area detection unit 147 determines that it is the detection timing of the free area, and detects the free area of the NV memory 11. Then, the area detecting unit 147 displays area information indicating that the unit area identified by each of the three physical addresses “0x10000001”, “0x10000002”, and “0x10000003” has become a new empty area by the above deletion. get. Then, the area detection unit 147 accumulates the acquired area information in the area information storage unit 143. As a result, the area information stored in the area information storage unit 143 is as shown in FIG.

(Example 2)
In this example, it is assumed that the conversion information storage unit 142 stores the conversion information shown in FIG. Further, it is assumed that the region information storage unit 143 stores the region information shown in FIG. In addition, the description of the processing and operation described in Example 1 will be omitted as appropriate.

  First, it is assumed that the user operates the information processing apparatus 1 and performs an operation for executing a program whose program name is “pg_sample” and uses a 10 KB area for execution. For example, the program may be stored in the NV memory or may be stored in the volatile memory 12. Hereinafter, the program is referred to as a process. Then, the reception unit 13 receives a process execution instruction having the program name.

  Next, the area determination unit 151 determines whether there is an empty area in the NV memory 11 and determines that there is an empty area.

  Next, since the area used by the process to be executed is 10 KB, the memory management unit 152 executes the page identified by the three logical addresses “ID = 011” to “ID = 013” in FIG. Reserve as an area used by the process. Then, the address conversion unit 144 acquires three physical addresses corresponding to the three logical addresses.

  Next, the memory management unit 152 allocates a unit area identified by each of three physical addresses “ID = 011” to “ID = 013” in FIG. 4 to a process to be executed. Then, the memory management unit 152 executes a process.

  Next, the area detection unit 147 determines that it is the detection timing of the empty area, detects the empty area of the NV memory, and acquires area information. Then, the area detection unit 147 accumulates the acquired area information in the area information storage unit 143. As a result, the region information stored in the region information storage unit 143 is as shown in FIG.

  Next, it is assumed that the user operates the information processing apparatus 1 and performs an operation of turning off the power of the information processing apparatus 1. Then, the reception unit 13 receives a power-off instruction that is an instruction to turn off the power.

  Next, the memory management unit 152 forcibly terminates the process being executed. Then, the memory management unit 152 releases the unit area that is assigned to the process and is identified by the three physical addresses “ID = 011” to “ID = 013” in FIG.

  Next, the area detection unit 147 determines that it is the detection timing of the empty area, detects the empty area of the NV memory, and acquires area information. Then, the area detection unit 147 accumulates the acquired area information in the area information storage unit 143. As a result, the area information stored in the area information storage unit 143 is as shown in FIG.

  Further, for example, in the above, it is assumed that the area determination unit 151 determines whether there is a free area in the NV memory 11 and determines that there is no free area. In this case, the memory management unit 152 secures three pages of the volatile memory 12 as an area used by the process to be executed. Then, the memory management unit 152 acquires three logical addresses that identify the three pages.

(Example 3)
In this example, a specific method for realizing the information processing apparatus 1 will be described. In this example, the NV memory 11 is simply expressed as “NV memory”, and the volatile memory 12 is a DRAM. The information processing apparatus 1 is assumed to be a Linux (registered trademark) kernel (hereinafter referred to as a kernel).

  First, a system having the NV memory 11 as a main memory is emulated using an emulator. Further, when the NV memory 11 is used as the main memory, it is desirable that the 64-bit environment has a wide physical address space. An emulator that satisfies the condition is, for example, QEMU (http://wiki.qemu.org/Main_Page).

  Next, a file “nvmemory.img” for saving the contents of the NV memory is prepared. Then, the command shown in FIG. 8 is executed to start QEMU. This command secures a 128 MB (megabyte) DRAM area, and starts QEMU with all of the file “nvmemory.img” mapped as an NV memory area from the physical address “0x10000000”. The As a result, the NV memory of the DRAM is arranged in the physical address space as shown in FIG. Here, the kernel is assumed to be stored in the DRAM, expanded on the DRAM, and booted (started).

  Next, FIG. 10 is a diagram showing the relationship between the virtual storage system, the memory allocator, and the file system in the kernel. In FIG. 10, a virtual memory system (Virtual Memory) is a virtual memory used by the file system unit 14 and the memory management unit 15, and is usually a logical address space. The memory allocator corresponds to the memory management unit 15, the conversion information storage unit 142, and the address conversion unit 144. The file system (PRAMFS) corresponds to the file system unit 14 and is normally constructed on the NV memory as shown in FIG. The block size of the file system is 4 KB which is the page size of the main memory.

  The file system is used as a base for NV memory area management. That is, the file system manages the free area of the NV memory, and the area is secured and released by the memory allocator through the file system.

  In addition, the allocation of an area from the file system in a simple block unit has a large effect on performance. Therefore, for example, a method may be adopted in which areas are secured together from the file system and a small number of remaining areas are cached in a free list. In this method, area reservation and release are performed as follows. If there is an empty area in the free list in response to the area allocation request, it is returned. If not, a free area is returned after securing the area as a whole. When releasing, if a certain number of blocks (for example, 128 blocks) or more are in the free list, they are released to the file system, otherwise they are added to the free list.

  The memory allocator first tries to secure an area from the NV memory, not from the DRAM. The memory allocator does not secure the area from the DRAM when the area can be secured from the NV memory. At the time of release, the NV memory needs to be released separately from the DRAM. Therefore, the memory allocator adds “NVmemory” as the attribute of the page when the NV memory area is secured. If the page to be released has this attribute, a function for releasing the NV memory area is called.

  In order to normally terminate the system, generally, a signal is sent to all processes to perform termination processing, and after the file system is unmounted or read-mounted again, kernel termination processing is started. When remounting read-only, the allocation of the area from the NV memory is stopped, so that the pages allocated from the NV memory and in use are eliminated. After remounting read-only, the area is not secured from the NV memory, and at this time, the cached pages for allocation are also released.

(Example 4)
In this example, a result of operating the information processing apparatus 1 realized by the realizing method shown in Example 3 will be described.

  FIG. 11 shows a screen dump when the area is allocated to and released from the main memory and the file. In FIG. 11, the first line indicates that PRAMFS is mounted as a root file system and the kernel is booted. When the kernel is booted, first, a busybox shell is started. Therefore, a program for allocating and releasing the area to the main memory and the file is executed. By specifying “16” as an argument of the program, area allocation up to 16 MB is performed while increasing from 1 MB to twice. From FIG. 11, it can be seen that each time the allocation to the main memory and the creation of the file are performed, the use space of the file system increases correspondingly. Finally, the used space of the file system is reduced by releasing the allocated area and erasing the file. When releasing from the main memory, a certain amount is left as a cache, so it does not return completely to the initial value.

  FIG. 12 is a diagram illustrating a result of executing “fork + exit”, “fork + execve”, and “fork + sh” included in the LMbench3 benchmark suite. In FIG. 12, each value is a value obtained by dividing the number of execution instructions acquired by the RDTSC instruction by “1000”. In FIG. 12, “DRAM” in the item name “benchmark” is a result when the NV memory is not used. The “NV memory (cache)” is a result of using a method in which areas are secured together from the file system and a small number of remaining areas are cached in a free list. The “NV memory (for each page)” is a result when an area is secured in a block unit from the file system without using the method. “Fork + exit” creates a process by a fork system call and ends the process. In addition to “fork + exit”, “fork + exec” is a program for starting another program by an execute system call. “Fork + sh” is for starting another program from the shell.

  From FIG. 12, it can be seen that by caching the area to be allocated to the main memory in the free list, a performance improvement of 23 to 26% can be realized, and a performance equivalent to that of the DRAM can be realized. On the other hand, it can be seen that simply using the file system as a free space management mechanism is inefficient and affects the OS execution performance. By caching a small number of areas, it is possible to reduce the cost of area allocation and conceal the overhead of using the file system as a free area management mechanism.

  FIG. 13 is a diagram showing a result of performance comparison with the paging mechanism. This comparison is a measurement of whether a performance difference occurs when a large amount of memory access occurs between paging and when memory can be directly allocated from the NV memory. In FIG. 13, the horizontal axis represents the allocated memory size, and the vertical axis represents the value obtained by dividing the number of execution instructions acquired by the RDTSC instruction by “1000”.

  From FIG. 13, “DRAM only” (first in the legend) and “NV memory (cache)” (third in the legend) have almost the same performance, but “DRAM only” has insufficient memory. Therefore, allocation of 128 MB or more cannot be performed. The “DRAM and swap file combination” (second in the legend) can be allocated up to 512 MB, but costs about 7.4 times (vertical axis) more than “NV memory (cache)”. ing. The “NV memory (per page)” (fourth in the legend) costs about 1.8 times (vertical axis) the cost of “NV memory (cache)”. Therefore, it can be seen that by using the NV memory for both the main memory and the file system, paging becomes unnecessary and the performance equivalent to that of the DRAM alone can be maintained.

  As described above, according to the information processing apparatus 1 according to the present embodiment, the NV memory can be used as a main memory and a storage without dividing the area. Thus, the NV memory can be used without dividing the main memory area and the storage area, and the memory area that can be used in a single system can be increased. This also eliminates the need for paging, and can improve system processing performance.

  Further, according to the information processing apparatus 1 according to the present embodiment, a free area on the NV memory that is allocated to a process and then released can be registered as a free area in the file system. Thereby, the consistency of the file system can be maintained.

  In the present embodiment, the file management information storage unit 141 may store file management information having a file identifier and one or more physical addresses. In this case, the writing unit 145 normally associates the file identifier of the file requested to be written with a physical address that identifies one or more blocks into which the file has been written, and stores it in the file management information storage unit 141. To do. Further, the reading unit 146 acquires from the file management information storage unit 141 one or more physical addresses corresponding to the file identifier of the file that has been requested to be read or deleted.

  In the present embodiment, the information processing apparatus 1 does not have to include the area information storage unit 143. In this case, the area information may be stored in the file management information storage unit 141 or may be included in the file management information.

  In this embodiment, the memory management unit 15 stores, for example, one or more process management information having a process identifier for identifying a process and one or more logical addresses corresponding to the process. Storage means (not shown) may be provided. In this case, the memory management unit 152 normally associates a process identifier that identifies a process requested to be executed with one or more logical addresses that identify one or more pages assigned to the process, and manages process information Is accumulated in the process management information storage means. The logical address may be a physical address.

  In the present embodiment, the information processing apparatus 1 may include two or more NV memories 11. In this case, it is preferable that the two or more NV memories 11 are normally continuously arranged in one physical address space.

  Further, in the present embodiment, the information processing apparatus 1 may not include the volatile memory 12. A block diagram of the information processing apparatus 1 in this case is shown in FIG. In this case, the file system unit 14 normally uses a predetermined number or less (total size is equal to or less than a predetermined size) of one or more unit areas of the NV memory 11. In other words, the file system unit 14 leaves a predetermined number or more (total size is a predetermined size or more) of one or more unit areas of the NV memory 11 without using them. This is to secure an area used by the memory management unit 15.

  In the present embodiment, the file system unit 14 and the memory management unit 15 are usually configured to use one or more unit areas of the NV memory 11 as an area used by the file system unit 14 and the memory management unit 15. Use without distinguishing from the area to be used. That is, for example, for one unit area, the file system unit 14 uses the area at a certain timing, but the memory management unit 15 may use the area at another timing. It is. In other words, for one unit area, the memory management unit 15 uses the area at a certain timing, but the file system unit 14 may use the area at another timing. That's what it means.

  Further, in the present embodiment, the information processing apparatus 1 reads / writes data from / to the NV memory 11 that is a nonvolatile recording medium having one or more unit areas of a predetermined size. A file system unit 14 and a memory management unit 15 that allocates one or more free areas, which are unused areas among the one or more unit areas, to the process in response to a request from an executing process; The one or more unit areas may be the information processing apparatus 1 used without being distinguished into an area used by the file system unit 14 and an area used by the memory management unit 15.

  In the present embodiment, the information processing apparatus 1 includes an NV memory 11 that is a nonvolatile recording medium having one or more unit areas of a predetermined size, and a file system unit 14 that uses the NV memory 11 as a storage. And the memory management unit 15 that uses the NV memory 11 as a main memory, the file system unit 14 uses the one or more unit areas as a block, and the memory management unit 15 includes the one or more unit areas. The information processing apparatus 1 may use the unit area as a page.

  In each of the above embodiments, each process or each function may be realized by centralized processing by a single device or a single system, or distributed by a plurality of devices or a plurality of systems. It may be realized by being processed.

  In each of the above embodiments, each component may be configured by dedicated hardware, or a component that can be realized by software may be realized by executing a program. For example, each component can be realized by a program execution unit such as a CPU reading and executing a software program recorded on a recording medium such as a hard disk or a semiconductor memory.

  Moreover, the software which implement | achieves the information processing apparatus in each said embodiment is the following programs, for example. In other words, this program allows a computer that can access an NV memory, which is a non-volatile recording medium, to a file system unit that reads / writes data in / from the NV memory in a predetermined unit and a process that is requested to be executed. A program for causing a memory management unit to allocate a predetermined area of the NV memory.

  Note that the program does not include at least processing that is performed only by hardware.

  The program may be executed by being downloaded from a server or the like, or a program recorded on a predetermined recording medium (for example, an optical disk such as a CD-ROM, a magnetic disk, a semiconductor memory, or the like) is read out. May be executed. Further, this program may be used as a program constituting a program product.

  Moreover, the computer which performs the said program may be single, and plural may be sufficient as it. That is, centralized processing may be performed, or distributed processing may be performed.

  FIG. 16 is an overview of the computer system 9 that executes the above-described program to realize the information processing apparatus and the like of the above-described embodiment. The above-described embodiments can be realized by computer hardware and a computer program executed thereon.

  In FIG. 16, the computer system 9 includes a computer 901 including a CD-ROM drive 9011 and an FD drive 9012, a keyboard 902, a mouse 903, and a monitor 904.

  FIG. 17 is a block diagram of the computer system 9. In FIG. 17, in addition to the CD-ROM drive 9011 and the FD drive 9012, a computer 901 is connected to an MPU 9013, a ROM 9014 for storing a program such as a bootup program, and an MPU 9013, and temporarily receives instructions of an application program. A bus for mutually connecting a RAM 9015 for storing a temporary storage space, a hard disk 9016 for storing application programs, system programs, and data, a CD-ROM drive 9011, an FD drive 9012, an MPU 9013, etc. 9017. Although not shown here, the computer 901 may further include a network card that provides connection to a LAN.

  A program that causes the computer system 9 to execute the functions of the information processing apparatus and the like of the above-described embodiment is stored in the CD-ROM 9101 or the FD 9102, inserted into the CD-ROM drive 9011 or the FD drive 9012, and further the hard disk 9016. May be forwarded to. Alternatively, the program may be transmitted to the computer 901 via a network (not shown) and stored in the hard disk 9016. The program is loaded into the RAM 9015 when executed. The program may be loaded directly from the CD-ROM 9101, the FD 9102, or the network.

  The program does not necessarily include an operating system (OS) or a third-party program that causes the computer 901 to execute the functions of the information processing apparatus according to the above-described embodiment. The program only needs to include an instruction portion that calls an appropriate function (module) in a controlled manner and obtains a desired result. How the computer system 9 operates is well known and will not be described in detail.

  The present invention is not limited to the above-described embodiments, and various modifications are possible, and it goes without saying that these are also included in the scope of the present invention.

  As described above, the information processing apparatus according to the present invention has an effect that the NV memory can be used as the main memory and the storage without distinguishing between the area used as the main memory and the area used as the storage. It is useful as a function of the operating system.

DESCRIPTION OF SYMBOLS 1 Information processing apparatus 11 NV memory 12 Volatile memory 13 Reception part 14 File system part 15 Memory management part 141 File management information storage means 142 Conversion information storage means 143 Area information storage means 144 Address conversion means 145 Writing means 146 Reading means 147 Area detection means 151 Area determination means 152 Memory management means

Claims (7)

NV memory which is a nonvolatile recording medium;
A file system unit for reading / writing data from / to the NV memory in a predetermined unit;
An information processing apparatus comprising: a memory management unit that allocates a predetermined area of the NV memory to a process requested to be executed. The file system unit is
File management information storage means for storing file management information having a file identifier for identifying the one or more files and one or more logical addresses corresponding to the files;
Conversion information storage means for storing conversion information for converting a logical address into a physical address;
Address conversion means for converting one or more logical addresses corresponding to the one or more files into one or more physical addresses using the conversion information;
Writing means for writing a file into an NV memory area corresponding to the physical address obtained by the address conversion means;
The information processing apparatus according to claim 1, further comprising: a reading unit that reads a file from an NV memory area corresponding to the physical address acquired by the address converting unit. The file system unit is
Managing the NV memory as a block which is an area for each predetermined size;
The memory management unit
The NV memory is managed as a page that is an area for each predetermined size,
The information processing apparatus according to claim 2, wherein a size of the block and a size of the page are the same. The memory management unit
At a predetermined timing, the NV memory area allocated to the process is released,
The file system unit is
Area information storage means for storing one or more area information indicating a free area or a used area of the NV memory;
An area detection unit that detects an area released by the memory management unit as an empty area, and stores area information indicating the empty area in an area information storage unit;
The file system unit is
Write data to the free area indicated by the area information,
The memory management unit
The information processing apparatus according to any one of claims 1 to 3, wherein a free area indicated by the area information is allocated to a process requested to be executed. A volatile memory that is a volatile recording medium;
The memory management unit
Area determination means for determining whether or not there is a free area in the NV memory;
The memory management means for allocating a predetermined area on the volatile memory to a process requested to be executed when the area determination means determines that there is no free area in the NV memory. The information processing apparatus according to claim 4. NV memory which is a nonvolatile recording medium;
An information processing method performed using a file system unit and a memory management unit,
The file system unit is
A file system step for reading and writing data to and from the NV memory in a predetermined unit;
The memory management unit
A memory management step of allocating a predetermined area of the NV memory to a process requested to be executed. A computer that can access an NV memory that is a non-volatile recording medium,
A file system unit for reading / writing data from / to the NV memory in a predetermined unit;
A program for causing a process requested to be executed to function as a memory management unit that allocates a predetermined area of the NV memory.