JP2018147143A - Information processing apparatus, information processing program and information processing method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To make it possible to efficiently use a semiconductor memory device.SOLUTION: An information processing apparatus includes: a division processing unit 21 for dividing compression target character string data into a plurality of partial regions; a compression processing unit 22 for compressing region data included in each of the plurality of partial regions to an access unit size or less and generating compressed partial data; and a storage processing unit 22 for storing the generated compressed partial data in an access unit area of a semiconductor memory device 14.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an information processing apparatus, an information processing program, and an information processing method.

  Grammar compression is known as one of data compression methods for reducing the amount of character string data.

  FIG. 11 is a diagram for explaining a conventional grammar compression method.

  In grammar compression, two consecutive characters (2 characters) are repeatedly replaced (converted and compressed) with one character, and finally the remaining one character and a dictionary indicating the conversion history are recorded. .

  In FIG. 11, an example of compressing the character string “abcabc” is represented by a tree structure. In this tree structure, the characters in which nodes (nodes, vertices) are replaced are shown.

  Hereinafter, the upper (upper layer) in the tree structure is simply referred to as the upper, and the lower (lower) is simply referred to as the lower.

  First, the character string “abcabc” is converted to the character string “XcXc” by replacing the character string “ab” with the character “X”.

  Next, the character string “Xc” is converted to the character string “YY” by replacing the character string “Xc” with the character “Y”.

  Further, the character string “YY” is converted to the character “Z” by replacing the character string “YY” with the character “Z”.

  Then, information on replacement performed until the character string “abcabc” is converted to “Z” is recorded as a dictionary together with the finally remaining one character “Z”.

  In addition, the compressed character “Z” is expanded (expanded) into the character string “abcabc” before compression by performing the reverse process.

  In grammar compression, information indicating how many characters exist below each node (hereinafter referred to as a label) is added to expand a character string in a specific range with a small number of steps. be able to. A tree structure with a label attached to a node may be referred to as a labeled tree structure.

  FIG. 12 is a diagram illustrating a labeled tree structure, in which a label is attached to the tree structure shown in FIG.

  In the labeled tree structure illustrated in FIG. 12, since there are two characters “a” and “b” under the character “X”, the label “2” is attached to the character “X”. ing. Similarly, under the character “Y”, there are three characters “a”, “b”, and “c”, and the label “3” is attached to the character “Y”. Note that the characters “X” and “Y” used for replacement are not counted in the label.

  The labeled tree structure dictionary illustrated in FIG. 12 can be expressed as follows. The dictionary represents character substitution performed in the process of grammar compression.

“Z”: “Z (6)-> YY”, “Y (3)-> Xc”, “X (2)-> ab”
In the dictionary, the symbol “->” represents a correspondence relationship by replacement. In the dictionary, labels are indicated using numbers with parentheses (for example, “(6)”). Further, in the labeled tree structure, a node between the uppermost character (character “Z” in the example shown in FIG. 12) and the lowermost character (character “abcabc” in the example shown in FIG. 12) is intermediate. Sometimes called a node.

  Here, in the character string “abcabc” represented by the labeled tree structure illustrated in FIG. 12, for example, when the fifth to sixth characters are referred to (expanded), the following procedure is performed.

  Hereinafter, for example, a character string from the a-th character to the b-th character of the character “X” is represented as “X [a, b]”. Both a and b are natural numbers.

  A method for expanding Z [5,6] is shown below.

  In the labeled tree structure shown in FIG. 12, Z can be expanded to Y (3) and Y (3), so Z [5,6] can be represented as Y [2,3]. That is, the second and third characters in Y correspond to the fifth and sixth characters in Z.

  Similarly, Y can be expanded to X (2) and c (1), so Y [2,3] becomes X [2,2] and c. Further, since X can be expanded to a (1) and b (1), Y [2,2] can be represented as b.

  Therefore, the grammar-compressed X [5,6] can be obtained as bc.

  In the labeled tree structure shown in FIG. 12, the nodes referred to for extending Z [5,6] are represented by broken lines as described above.

JP-A-6-202844 JP 2010-26884 A

  Generally, intermediate nodes to be accessed when decompressing grammar-compressed data are scattered in a storage area. Therefore, as described above, data decompression by accessing only a part of nodes in the tree structure means that random access occurs in some areas when considering addresses in the data storage area. Means.

  On the other hand, in recent years, AFA (All Flash Array) using SSD (Solid State Drive) has been developed as a storage product for realizing high-speed data access. The SSD has a characteristic that data access is performed in units of areas called pages.

  Therefore, when grammar-compressed data is stored in the SSD, it is necessary to read a large number of pages constituting the storage area when the data is decompressed. As a result, data in many areas is read in the SSD. There is a need. This shortens the life of the SSD.

  In one aspect, an object of the present invention is to enable efficient use of a semiconductor memory device.

  For this reason, this information processing apparatus compresses the compression target character string data into a plurality of partial areas and the area data included in each of the plurality of partial areas up to an access unit size or less. A compression processing unit that generates compressed partial data, and a storage processing unit that stores the generated compressed partial data in an access unit area in a semiconductor storage device.

  According to one embodiment, a semiconductor memory device can be used efficiently.

It is a figure which shows typically the structure of the information processing apparatus as an example of embodiment. It is a figure for demonstrating the process by the division | segmentation process part in the information processing apparatus as an example of embodiment. It is a figure for demonstrating the process by the compression process part in the information processing apparatus as an example of embodiment. It is a figure for demonstrating the process by the expansion | extension process part in the information processing apparatus as an example of embodiment. It is a flowchart explaining the compression process of the message in the information processing apparatus as an example of embodiment. It is a flowchart explaining the expansion | extension process in the information processing apparatus as an example of embodiment. It is a figure which shows the data compression method in the information processing apparatus as an example of embodiment compared with the conventional grammar compression method. It is a figure which shows the modification of the function structure of the information processing apparatus as an example of embodiment. It is a figure for demonstrating the compression process and the compression effect with respect to the compression object message in the information processing apparatus as a modification. It is a flowchart explaining the compression process of the message in the information processing apparatus as a modification. It is a figure for demonstrating the conventional grammar compression method. It is a figure which illustrates a labeled tree structure.

  Hereinafter, embodiments of the information processing apparatus, an information processing program, and an information processing method will be described with reference to the drawings. However, the embodiment described below is merely an example, and there is no intention to exclude application of various modifications and techniques not explicitly described in the embodiment. In other words, the present embodiment can be implemented with various modifications (combining the embodiments and modifications) without departing from the spirit of the present embodiment. Each figure is not intended to include only the components shown in the figure, and may include other functions.

(A) Configuration FIG. 1 is a diagram schematically illustrating a configuration of an information processing apparatus 1 as an example of an embodiment.

  The information processing apparatus 1 is, for example, a CM (Controller Module) or a personal computer in a storage system.

  For example, as shown in FIG. 1, the information processing apparatus 1 includes a CPU (Central Processing Unit) 11, a RAM (Random Access Memory) 12, a ROM (Read Only Memory) 13, an SSD 14, a graphic processing device 20, an input interface 15, The optical drive device 16, the device connection interface 17, and the network interface 18 are included as components. These components 11 to 18 and 20 are configured to be able to communicate with each other via a bus 19.

  The information processing apparatus 1 includes a data compression function for compressing data (character string data, compression target character string data) composed of character strings and storing the SSD 14 in a state where the data size is reduced.

  The SSD 14 is a recording device that uses a semiconductor memory as a storage medium, and stores various data and programs.

  Hereinafter, an SSD 14 including a flash memory as a semiconductor memory will be described.

  The storage area of the flash memory includes a plurality of (for example, 4200) blocks, and a plurality of (for example, 256) pages are formed in each block. Each page has a storage capacity of 4 KB (KiloByte), for example. Hereinafter, the size of one page is referred to as a page size or an alignment size. In this example, the page size is 4 KB.

  In the flash memory, data reading and writing are performed in units of pages, but erasing is performed in units of blocks.

  For example, a file system executed in the information processing apparatus 1 controls operations, access, and retrieval with respect to data stored in the SSD 14, and controls reading and writing of data with respect to the SSD 14.

  Since read / write input / output access to the storage area of the SSD 14 is performed in units of pages as described above, a page can be referred to as an access unit. The page size can be referred to as an access unit size.

  The ROM 13 is a storage device that stores various data and programs. The RAM 12 is a storage device that temporarily stores data, programs, and the like when the CPU 11 performs arithmetic processing and the like.

  The RAM 12 may temporarily store data stored in the SSD 14 or data read from the SSD 14.

  The CPU 11 performs various calculations and controls by executing an OS (Operating System) and various programs stored in the ROM 13 and the SSD 14. In the information processing apparatus 1, when the CPU 11 executes a program (compression processing program, information processing program) stored in the SSD 14 or the like, the division processing unit 21, the compression processing unit 22, and the decompression processing shown in FIG. Functions as the unit 23 and the storage processing unit 25.

  A program for realizing the functions as the division processing unit 21, compression processing unit 22, decompression processing unit 23, and storage processing unit 25 is, for example, a flexible disk, CD (Compact Disc; CD-ROM, CD-R). (Recordable), CD-RW (ReWritable, etc.), DVD (Digital Versatile Disc; DVD-ROM, DVD-RAM, DVD-R, DVD + R, DVD-RW, DVD + RW, HD DVD, etc.), Blu-ray disc, magnetic disc, It is provided in a form recorded on a computer-readable recording medium such as an optical disk or a magneto-optical disk. Then, the computer reads the program from the recording medium, transfers it to the internal storage device or the external storage device, and uses it. The program may be recorded in a storage device (recording medium) such as a magnetic disk, an optical disk, or a magneto-optical disk, and provided from the storage device to the computer via a communication path.

  When realizing the functions as the division processing unit 21, compression processing unit 22, decompression processing unit 23, and storage processing unit 25, the program stored in the internal storage device (RAM 12 or ROM 13 in this embodiment) is stored in the microcomputer. It is executed by a processor (CPU 11 in this embodiment). At this time, the computer may read and execute the program recorded on the recording medium.

  In the present embodiment, the computer is a concept including hardware and an operating system, and means hardware that operates under the control of the operating system. Further, when an operating system is unnecessary and hardware is operated by an application program alone, the hardware itself corresponds to a computer. The hardware includes at least a microprocessor such as a CPU and means for reading a computer program recorded on a recording medium. In the present embodiment, the information processing apparatus 1 has a function as a computer. ing.

  The CPU 11 may be a multiprocessor. Further, instead of the CPU 11, for example, any one of MPU (Micro Processing Unit), DSP (Digital Signal Processor), ASIC (Application Specific Integrated Circuit), PLD (Programmable Logic Device), FPGA (Field Programmable Gate Array) is used. You may prepare. Further, in place of the CPU 11, two or more types of elements of CPU, MPU, DSP, ASIC, PLD, and FPGA may be used in combination.

  A monitor 20 a is connected to the graphic processing device 20. The graphic processing device 20 displays an image on the screen of the monitor 20a in accordance with a command from the CPU 11. Examples of the monitor 20a include a display device using a CRT (Cathode Ray Tube) and a liquid crystal display device.

  A keyboard 15a and a mouse 15b are connected to the input interface 15. The input interface 15 transmits signals sent from the keyboard 15a and the mouse 15b to the CPU 11. The mouse 15b is an example of a pointing device, and other pointing devices can also be used. Examples of other pointing devices include a touch panel, a tablet, a touch pad, and a trackball.

  The optical drive device 16 reads data recorded on the optical disc 16a using laser light or the like. The optical disc 16a is a portable non-temporary recording medium on which data is recorded so as to be readable by reflection of light. Examples of the optical disk 16a include DVD, DVD-RAM, CD-ROM, CD-R / RW).

  The device connection interface 17 is a communication interface for connecting peripheral devices to the information processing apparatus 1. For example, the device connection interface 17 can be connected to a memory device 17a or a memory reader / writer 17b. The memory device 17a is a non-temporary recording medium equipped with a communication function with the device connection interface 17, for example, a USB (Universal Serial Bus) memory. The memory reader / writer 17b writes data to the memory card 17c or reads data from the memory card 17c. The memory card 17c is a card-type non-temporary recording medium.

  The network interface 18 is connected to a network (not shown). The network interface 18 transmits / receives data to / from other computers or communication devices via the network.

  The division processing unit 21 divides compression target data (compression target character string data) described as a character string into a plurality of regions. Hereinafter, the data to be compressed may be referred to as a message or a message to be compressed. Hereinafter, dividing the compression target message into a plurality of regions may be expressed as dividing or partitioning.

  Each region contains one or more pages. In other words, the division processing unit 21 divides the message into regions including one or more pages. One region preferably includes two or more pages, and the region size (region size) is preferably a multiple of the page size. It is desirable that the number of pages included in each region is the same.

  Hereinafter, data included in a region may be referred to as region data. In addition, a region to be processed by the compression processing unit 22 and the decompression processing unit 23 to be described later may be referred to as a target region or simply a target. A plurality of regions may be referred to as a target group.

  In addition, a message divided into a plurality of regions by the division processing unit 21 may be referred to as a partitioned message.

  FIG. 2 is a diagram for explaining processing by the division processing unit 21 in the information processing apparatus 1 as an example of the embodiment.

  In FIG. 2, a symbol (a) indicates a message before division by the division processing unit 21, and indicates a message having a length of 8 pages.

  Hereinafter, in the message shown in the figure, portions corresponding to individual pages in the state before compression are denoted by reference numerals P1 to P8.

  In FIG. 2, reference numeral (b) indicates a message that is divided into a plurality of regions by the division processing unit 21. In the example illustrated in FIG. 2, the division processing unit 21 displays the message as follows: A plurality (four in the example shown in FIG. 2) of regions R1 to R4 are generated by dividing every two continuous pages.

  In the example shown in FIG. 2, the region R1 includes data of pages P1 and P2 as region data. Similarly, region R2 includes data of pages P3 and P4, region R3 includes data of pages P5 and P6, and region R4 includes data of pages P7 and P8 as region data.

  The division processing unit 21 assigns messages to the regions in order from the beginning. If the message data size is not a multiple of the page, the fractional part of the message may be stored in the last region.

  Since the region data of each region has a data size that is an integral multiple of the page, the boundary between adjacent regions matches the boundary between pages in the message. Accordingly, it can be said that each region data is aligned with a page in the storage area of the SSD 14.

  The compression processing unit 22 compresses the data of each region divided (generated) by the division processing unit 21.

  The compression processing unit 22 compresses the region data of each region using a grammatical compression method until each region becomes equal to or smaller than the page size.

  That is, the compression processing unit 22 extracts two consecutive characters that appear most frequently in the compression target message as a replacement target character string, and sets a replacement character for the replacement target character string. Then, the compression processing unit 22 performs compression processing (grammar compression processing) by replacing the replacement target character string with the post-replacement character for the entire compression target message.

  Hereinafter, the data generated by compressing the region data by the compression processing unit 22 may be referred to as compressed partial data. Further, the compressed partial data may be referred to as compressed data.

  FIG. 3 is a diagram for explaining processing by the compression processing unit 22 in the information processing apparatus 1 as an example of the embodiment.

  In FIG. 3, the code (a) indicates a message before being compressed by the compression processing unit 22 (message to be compressed), and the code (b) indicates a message after being compressed by the compression processing unit 22. In FIG. 3, as indicated by reference numeral (b), reference numerals S1 to S4 are attached to the compressed partial data, and reference numeral D1 is attached to the dictionary information.

  The compression processing unit 22 repeatedly performs replacement (compression replacement, conversion) of two consecutive characters (two characters) with one character for each region data, thereby compressing the size of the data. To do.

  The compression processing unit 22 compresses the data in each region until it becomes equal to or smaller than the page size, and stops the compression and replacement of the region data when the data becomes smaller than the page size.

  In the example shown in FIG. 3, as indicated by reference numeral (a), the message before compression (message to be compressed) includes the character string “abcabc” in the region R1, the character string “bcbcaa” in the region R2, The character string “aabbcc” is included in R3, and the character string “abccba” is included in the region R1.

  The compression processing unit 22 converts the character string “bc” to the character “P”, the character string “aP” to the character “Q”, the character string “aa” to the character “R”, and the character string “Pc” to the character “ Replace the character string “cb” with the character “T” in S ”.

  Thereby, for example, the character string “abcabc” in the region R1 is converted into the character string “QQ” as shown in the code (b) (see the code S1). The data size of the converted character string “QQ”, which is compressed partial data, is equal to or smaller than the page size and fits in one page.

  Similarly, the character string “bcbcaa” in the region R2 is converted into the character string “PPR” (compressed partial data) as shown in the code (b) (see the code S2). The data size of the converted character string “PPR” (compressed partial data) is also equal to or smaller than the page size and fits in one page. Similarly for the character strings of the other regions R3 and R4, the data size of the compressed partial data after conversion is within one page.

  The compression processing unit 22 performs data compression for each region, and performs data compression within each region. That is, the compression processing unit 22 does not perform data compression beyond the boundary (alignment) between regions.

  That is, the compression processing unit 22 performs character compression on the data of each region.

  The storage processing unit 25 described later stores each compressed partial data generated by the compression processing unit 22 so as to fit in one page in the storage area of the SSD 14. As a result, the data of one region is compressed and stored in one page of the SSD 14 as compressed partial data.

  Therefore, the compressed partial data generated by the data of each region is in a state in which the so-called alignment is aligned without crossing the boundary between adjacent pages in the state stored in the SSD 14.

  In addition, regarding the replacement of the data in each region by the compression processing unit 22 described above, information (generation rule) indicating the correspondence between the character string before replacement and the character string after replacement is stored in the dictionary element by the storage processing unit 25 described later. Is stored as dictionary information D1. The dictionary information D1 is stored together at, for example, the head positions of a plurality of compressed partial data, as indicated by reference numeral (b) in FIG. In the example indicated by reference numeral (b) in FIG. 3, the dictionary information D1 is stored in an area for two pages preceding a plurality of compressed partial data.

  A message to be compressed that has been compressed by the compression processing unit 22 is referred to as a “compressed message”, and is denoted by reference numeral E1. The compressed message E1 includes dictionary information D1 and a plurality of compressed partial data S1 to S4.

  The storage processing unit 25 stores the compressed partial data generated by the compression processing unit 22 in each page constituting the storage area of the SSD 14.

  As described above, since each compressed partial data has a data size equal to or smaller than the page size, each compressed partial data is stored without protruding onto the page.

  The storage processing unit 25 stores each compressed partial data generated by the compression processing unit 22 so as to fit in one page. For example, the storage processing unit 25 stores the compressed partial data with the head thereof aligned with the head position of the page. Thereby, the data of one region is compressed and stored in one page as compressed partial data.

  Therefore, the compressed partial data generated by the data of each region is in a state in which the so-called alignment is aligned without crossing the boundary between adjacent pages in the state stored in the SSD 14. In other words, in the SSD 14, each compressed partial data is stored in a state of being aligned with each page constituting the storage area.

  Further, the storage processing unit 25 uses the compression processing unit 22 to replace data in each region with dictionary information using information (generation rules) indicating correspondence between the character string before replacement and the character string after replacement as a dictionary element. Store as D1. The dictionary information D1 is stored together at, for example, the head positions of a plurality of compressed partial data, as indicated by reference numeral (b) in FIG.

  The storage processing unit 25 desirably stores the compressed partial data in a storage area of the SSD 14 at a position close to other compressed partial data or dictionary information generated from the same message to be compressed.

  The decompression processing unit 23 decompresses (decompresses and restores) the data compressed by the compression processing unit 22.

  The decompression processing unit 23 reads the dictionary information D1 and decompresses the compressed partial data stored in each page using the read dictionary information.

  For example, the decompression processor 23 decompresses the compressed partial data for each region by performing a process opposite to the process in which the compression processor 22 compresses the region data into the compressed partial data using the dictionary information. Restore data to.

  FIG. 4 is a diagram for explaining processing by the decompression processing unit 23 in the information processing apparatus 1 as an example of the embodiment.

  In FIG. 4, symbol (a) indicates a compressed message compressed by the compression processing unit 22, and symbol (b) indicates a part of the message expanded by the expansion processing unit 23.

  The decompression processing unit 23 reads dictionary elements (generation rules) with reference to the dictionary information D1, and decompresses each compressed partial data S using the dictionary elements.

  In the example illustrated in FIG. 4, an example in which the decompression processing unit 23 decompresses the compressed partial data S3 is illustrated. In the example shown in FIG. 4, the compressed partial data S3 compressed to one page size or less and decompressed is decompressed, thereby restoring the data (region data) of the two-page region R3. Indicates the state that has been performed.

  For example, when decompressing the compressed partial data S3 and restoring the data of the region R3, the decompression processing unit 23 accesses the dictionary information D1 (dictionary element) and the compressed partial data S3 stored in the SSD 14. .

  That is, the decompression processing unit 23 achieves decompression of the compressed partial data S3 by accessing only the storage area (page) in which the compressed partial data S3 to be decompressed and the dictionary information D1 are stored. . That is, the storage area of the compressed partial data S3 other than the decompression target is not accessed.

(B) Operation Message compression processing in the information processing apparatus 1 as an example of the embodiment configured as described above will be described with reference to a flowchart (steps A1 to A7) shown in FIG. In the example shown below, the division processing unit 21 divides a message every two consecutive pages.

  In the following processing, a message to be compressed (compression target message) is input by an operator or the like. The operator may specify the region size and page size. Note that predetermined values set in advance may be used for these region sizes and page sizes. The compression target message is recorded in a storage area such as the RAM 12 as a code word.

  In step A1, the division processing unit 21 divides the processing target message every two times the page size, and generates a plurality of regions (target groups). As a result, each region includes two adjacent pages.

  In step A2, the compression processing unit 22 selects one region (target) from a plurality of regions. When the data (region data) stored in the target region is equal to or smaller than the page size, the compression processing unit 22 converts the data (compressed data, compressed partial data) to 1 in the storage area of the SSD 14. Store in one page.

  In step A <b> 3, the compression processing unit 22 checks whether there is a region (target) in the target group that has not been compressed until the region data is equal to or smaller than the page size.

  If there is a region (target) that has not been compressed to the page size or less (see YES route in step A3), the process proceeds to step A4. In the processing of steps A4 to A6 below, the compression processing unit 22 performs compression (grammar compression) processing on the processing target message.

  In step A4, the compression processing unit 22 extracts region data of a region (target) that has not been compressed as compression target data, and extracts two consecutive characters that appear most frequently in the compression target data as replacement target character strings. The compression processing unit 22 sets a character after replacement (character after replacement) for the replacement target character string. In this example, the replaced character is “X”.

  In step A5, the compression processing unit 22 registers a dictionary element (generation rule) in which the replacement target character string and the replaced character (for example, X) are associated with each other in the dictionary information D1.

  In step A <b> 6, the compression processing unit 22 performs compression processing by replacing the replacement target character string with the replaced character “X” for the entire compression target message. Thereafter, the process returns to step A2. It should be noted that the characters after replacement are appropriately changed.

  In addition, as a result of the confirmation in step A3, when there is no region that has not been compressed to the page size or less, that is, when all the compressed partial data of the region data of all regions is compressed to the page size or less. (Refer to the NO route in step A3), the process proceeds to step A7.

  In step A7, the compression processing unit 22 outputs the dictionary information D1 and each compressed partial data as a compressed message (codeword). That is, a compressed message obtained by compressing the compression target message is output. Thereafter, the process ends.

  Next, decompression processing in the information processing apparatus 1 as an example of the embodiment will be described with reference to a flowchart (steps B1 to B5) illustrated in FIG.

  In the following processing, a compressed message (also referred to as a code word) and a block number indicating the compressed partial data to be decompressed are input, and a part of the decompressed message (for two pages) is output.

  In step B1, the decompression processing unit 23 extracts the compressed partial data to be decompressed from the compressed message and sets it as the decompression target.

  In step B2, the decompression processing unit 23 checks whether there is an unprocessed dictionary element for the decompression target in the dictionary information D1.

  If there is an unprocessed dictionary element (see YES route in step B2), the process proceeds to step B3.

  In step B3, the decompression processing unit 23 extracts one dictionary element that has not yet been used for data decompression, corresponding to the compressed data, from the dictionary information D1 and sets it as the dictionary element X.

  In step B4, the decompression processing unit 23 decompresses the compressed partial data of the decompression target using the dictionary element X. Thereafter, the process returns to step B2.

  If there is no unprocessed dictionary element as a result of the confirmation in step B2 (see NO route in step B2), the process proceeds to step B5.

  In step B5, the decompression processing unit 23 outputs decompressed data (for two pages), and thereafter ends the process.

(C) Effect As described above, according to the information processing apparatus 1 as an example of the embodiment, the division processing unit 21 divides the compression target message into a plurality of regions including one or more pages, and the compression processing unit 22 Compress the data in each region until it is less than the page size.

  As a result, the compressed partial data generated by compressing each region data fits within the page and is aligned for each page.

  Therefore, when decompressing specific compressed partial data, the decompression processing unit 23 accesses only the page storing the compressed partial data to be decompressed and the dictionary information D1, thereby obtaining the decompression target data. The compressed partial data can be expanded.

  As a result, when decompressing a part of the compressed message, the page range accessed in the storage area of the SSD 14 can be reduced, and the life of the SSD 14 can be extended. Therefore, the SSD 14 can be used efficiently.

  The data storage area in the SSD 14 can also be efficiently used by compressing the message to be compressed using the grammar compression technique.

  The division processing unit 21 partitions the compression target message so that each region includes the same number of pages, so that the size of the compressed partial data generated by the compression processing unit 22 can be made substantially uniform and uniform. This also allows the compressed partial data to be easily aligned on the page.

  Further, when decompressing a part of the compressed message, the page range accessed in the SSD 14 is small, so that the processing speed can be improved.

  FIG. 7 is a diagram showing a data compression method in the information processing apparatus 1 as an example of the embodiment in comparison with a conventional grammar compression method.

  In FIG. 7, code (a) shows a data compression example by a conventional grammar compression method in a tree structure, and code (b) shows a data compression example by the compression processing unit 22 of the information processing apparatus 1 of the present application in a tree concept.

  In data compression performed by a conventional grammar compression method, compression and replacement are repeatedly performed until one character ("G" in the example shown in FIG. 7) is finally obtained, as indicated by symbol (a). Thereby, there are many dictionary elements and the dictionary information size becomes large.

  On the other hand, in the information processing apparatus 1, the compression processing unit 22 repeatedly performs compression replacement for each region until the page size is equal to or smaller than the page size. Then, the compression replacement is terminated.

  For example, in FIG. 7, the compressed partial data S1 (R1) indicated by reference numeral (b) has been compressed in the state of the character string “QQ”.

  As a result, compared to the conventional grammatical compression method, the number of dictionary elements accompanying compression replacement is small, and the data size of the dictionary information D1 is small. Thereby, when decompressing the compressed message, the page range to be accessed can be further reduced.

(D) Others The disclosed technology is not limited to the above-described embodiment, and various modifications can be made without departing from the spirit of the present embodiment. Each structure and each process of this embodiment can be selected as needed, or may be combined suitably.

  For example, in the above-described embodiment, the division processing unit 21 divides the compression target message into regions of a predetermined size (number of pages), and the compression processing unit 22 reduces the region data of each region to a page size or less. However, the present invention is not limited to this.

  FIG. 8 is a diagram illustrating a modification of the functional configuration of the information processing apparatus 1 as an example of the embodiment.

  As shown in FIG. 8, in this modification, the CPU 11 functions as the confirmation unit 24 in addition to the functions as the division processing unit 21, compression processing unit 22, decompression processing unit 23, and storage processing unit 25 described above. Realize the function.

  In the figure, the same reference numerals as those already described indicate the same parts, and detailed description thereof is omitted.

  The confirmation unit 24 calculates a compression rate for each data compression process performed by the compression processing unit 22 on the compression target message and the compressed message, and stores the calculated compression rate in a predetermined storage area such as the RAM 12.

  Then, the confirmation unit 24 compares the calculated compression rate with a predetermined threshold value to determine whether or not the compression processing performed by the compression processing unit 22 has a compression effect.

  For example, when the calculated compression rate is equal to or greater than the threshold value, the confirmation unit 24 determines that the evaluation requirement is satisfied and there is a compression effect. On the other hand, when the calculated compression rate is less than the threshold value, the confirmation unit 24 determines that the evaluation requirement is not satisfied and the compression effect is not obtained. That is, the confirmation unit 24 evaluates the compression processing performed by the compression processing unit 22.

  FIG. 9 is a diagram for explaining a compression process and a compression effect for a compression target message in the present modification.

  In FIG. 9, the code (a) indicates a message divided into a plurality of regions by the division processing unit 21. In the example shown in FIG. 9, the division processing unit 21 displays the message every two consecutive pages. It is divided into. Hereinafter, regions R1 to R4 are attached to the regions. In FIG. 9, as shown by reference numerals (b) to (d), reference numerals S01 to S07 are attached to the compressed partial data, and reference numeral D1 is attached to the dictionary information.

  In the example shown in FIG. 9, the data of pages P1 and P2 is included as region data in region R1. Similarly, region R2 includes data of pages P3 and P4, region R3 includes data of pages P5 and P6, and region R4 includes data of pages P7 and P8 as region data.

  In FIG. 9, a code (b) indicates a compressed message E1-1 generated by the compression processing unit 22 by compressing the partitioned message indicated by the code (a).

  The compression processing unit 22 generates compressed partial data S01 to S04 of the compressed message E1-1 by compressing each region data of the regions R1 to R4 of the compression target message until the page size is equal to or smaller than the page size. The data (region data) of each region that is the target of compression processing becomes a compression target by the compression processing unit 22.

  In this modification, the compression processing unit 22 has an additional compression function for performing further compression on the compressed message. That is, the compression processing unit 22 collects a plurality of adjacent compressed partial data in the compressed message and performs compression (additional compression) until the page size is equal to or smaller than the page size.

  In FIG. 9, the code (c) indicates a compressed message E1-2 generated by the compression processing unit 22 by further compressing the compressed message E1-1 shown in the code (b).

  In the compressed message E1-2 indicated by the code (c), the compression processing unit 22 collectively combines the two compressed partial data S01 and S02 in the compressed message E1-1 of the code (b). And Then, the compression processing unit 22 generates the compressed partial data S05 by compressing the generated compression target until it becomes equal to or smaller than the page size.

  Similarly, the compression processing unit 22 collectively sets two compressed partial data S03 and S04 in the compressed message E1-1 with the code (b) as a compression target. Then, the compression processing unit 22 generates the compressed partial data S06 by compressing the generated compression target until it becomes equal to or smaller than the page size.

  When the confirmation unit 24 determines that there is a compression effect, the compression processing unit 22 performs additional compression on the compressed message after the compression. On the other hand, when the confirmation unit 24 determines that there is no compression effect, the compression processing unit 22 does not perform additional compression on the compressed message after the compression. That is, additional compression is prevented from being performed.

  In FIG. 9, a code (d) indicates a compressed message E1-3 generated by the compression processing unit 22 by further compressing the compressed message E1-2 shown in the code (c).

  The compression processing unit 22 generates a new compression target by combining two consecutive compressed partial data S05 and S06 in the compressed message E1-2 of the code (c), and converts the generated compression target into a page size. Compress until: Thereby, the compression process part 22 has produced | generated the compressed partial data S07 in the compressed partial data of the compressed message E1-3 shown to code | symbol (d).

  In the example shown in FIG. 9, when the compressed message E1-2 is compressed to generate the compressed message E1-3, the capacity of the dictionary information D1 is increased. As a result, the compression rate of the compressed message E1-3 is less than a predetermined threshold value, and it is determined by the confirmation unit 24 described later that there is no compression effect.

  The compression processing unit 22 does not perform additional compression when the confirmation unit 24 determines that there is no compression effect.

  When the confirmation unit 24 determines that there is a compression effect, the compression processing unit 22 performs further compression on the compressed message that has been previously compressed. That is, in the compressed message that has been previously compressed, two consecutive compressed partial data are collected as compression target data.

  Then, the compression processing unit 22 extracts two consecutive characters appearing most in the compression target data as a replacement target character string, and sets a post-replacement character for the replacement target character string. Then, the compression processing unit 22 performs compression processing on the entire compression target message by replacing the replacement target character string with the post-replacement character.

  On the other hand, when the confirmation unit 24 determines that there is no compression effect, the compression processing unit 22 does not perform further compression on the compressed message that has been previously compressed.

  A message compression process in the information processing apparatus 1 as a modified example of the embodiment configured as described above will be described with reference to a flowchart (steps C1 to C10) illustrated in FIG.

  In step C1, the division processing unit 21 divides the processing target message every two times the page size, and generates a plurality of regions (target groups).

  The compression processing unit 22 prepares dictionary information D1 that is empty. The message to be compressed is recorded as a code word.

  In step C2, the compression processing unit 22 selects one region (target) from a plurality of regions. When the data (region data) stored in the target region is equal to or smaller than the page size, the compression processing unit 22 converts the data (compressed data, compressed partial data) to 1 in the storage area of the SSD 14. Store in one page.

  In step C <b> 3, the compression processing unit 22 confirms whether there is a region (target) in the target group that has not been compressed until the region data is equal to or smaller than the page size.

  If there is a region (target) that has not been compressed to the page size or less (see YES route in step C3), the process proceeds to step C4. In the processing of steps C4 to C6 below, the compression processing unit 22 performs compression (grammar compression) processing on the processing target message.

  In step C4, the compression processing unit 22 extracts region data of a region (target) that has not been compressed as compression target data, and extracts two consecutive characters that appear most frequently in the compression target data as replacement target character strings. The compression processing unit 22 sets a character after replacement (character after replacement) for the replacement target character string. In this example, the replaced character is “X”.

  In step C5, the compression processing unit 22 registers a dictionary element (generation rule) in which the replacement target character string and the replaced character (for example, X) are associated with each other in the dictionary information D1.

  In step C <b> 6, the compression processing unit 22 performs compression processing by replacing the replacement target character string with the replaced character “X” for the entire compression target message. Thereafter, the process returns to step C2. It should be noted that the characters after replacement are appropriately changed.

  In addition, as a result of the confirmation in step C3, when there is no region that has not been compressed to the page size or less, that is, all the compressed partial data of the region data of all regions is compressed to the page size or less. (Refer to the NO route in step C3), the process proceeds to step C7.

  In step C7, the confirmation unit 24 calculates a compression rate for the compressed message generated by the data compression processing performed by the compression processing unit 22, compares the calculated compression rate with a predetermined threshold value, and determines the compression effect. It is determined whether or not there has been.

  For example, the confirmation unit 24 determines that there is a compression effect when the calculated compression rate is equal to or greater than a threshold value. The confirmation unit 24 determines that there is no compression effect when the calculated compression rate is less than the threshold value. That is, the confirmation unit 24 evaluates the compression processing performed by the compression processing unit 22.

  As a result of the evaluation by the confirmation unit 24, when it is determined that there is a compression effect (see YES route of Step C7), the process proceeds to Step C8.

  In step C8, the compression processing unit 22 records the dictionary information D1 in which the dictionary elements used for compression are registered and the generated compressed message as codewords in a predetermined storage area such as the RAM 12.

  In step C9, the compression processing unit 22 generates one or more compression targets by combining two consecutive compressed partial data in the compressed message. Thereafter, the process returns to step C2.

  Moreover, when it is determined that there is no compression effect as a result of the evaluation by the confirmation unit 24 in Step C7 (see NO route in Step C7), the process proceeds to Step C10.

  In step C10, the compression processing unit 22 outputs the dictionary information D1 and each compressed partial data as a compressed message (code word). That is, a compressed message obtained by compressing the compression target message is output. Thereafter, the process ends.

  As described above, according to the information processing apparatus 1 as a modified example of the embodiment, it is necessary to obtain in advance the size and size of a region, that is, the size of a page included in the region, in addition to obtaining the same operational effects as the above-described embodiment There is no convenience.

  That is, it is possible to generate compressed partial data that is aligned for each page without prescribing the region size.

(E) Supplementary Notes The following supplementary notes are further disclosed regarding the above embodiment.

(Appendix 1)
A division processing unit that divides compression target character string data into a plurality of partial areas;
A compression processing unit that generates compressed partial data by compressing the area data included in each of the plurality of partial areas to an access unit size or less;
An information processing apparatus comprising: a storage processing unit that stores the generated compressed partial data in an access unit area in a semiconductor storage device.

(Appendix 2)
The information processing apparatus according to appendix 1, wherein the partial area includes a plurality of adjacent access unit areas.

(Appendix 3)
The information processing apparatus according to appendix 1 or 2, wherein the compression processing unit generates the compressed partial data by performing a grammar compression process.

(Appendix 4)
Any one of appendices 1 to 3, further comprising a decompression processing unit that decompresses compressed partial data to be decompressed using dictionary information and restores a part of the character string data to be compressed. The information processing apparatus described.

(Appendix 5)
When the compression rate of the compressed character string data including the compressed partial data generated by the compression processing unit satisfies the evaluation requirement, a plurality of continuous compressed partial data is equal to or smaller than an access unit size (page unit). The information processing apparatus according to any one of supplementary notes 1 to 4, wherein the information processing apparatus is compressed to a minimum.

(Appendix 6)
The compression target character string data is divided into a plurality of partial areas,
The area data included in each of the plurality of partial areas is compressed to an access unit size or less to generate compressed partial data,
An information processing program for causing a computer to execute processing for storing the generated compressed partial data in an access unit area in a semiconductor memory device.

(Appendix 7)
The information processing program according to appendix 6, wherein the partial area includes a plurality of adjacent access unit areas.

(Appendix 8)
The information processing program according to appendix 6 or 7, wherein the compressed partial data is generated by performing grammar compression processing.

(Appendix 9)
The information according to any one of appendices 6 to 8, wherein the computer executes a process of decompressing the compressed partial data to be decompressed using dictionary information and restoring a part of the character string data to be compressed. Processing program.

(Appendix 10)
When the compression rate of the compressed character string data including the generated compressed partial data satisfies the evaluation requirement, the computer is caused to execute a process of compressing a plurality of continuous compressed partial data to an access unit size or less. The information processing program according to any one of appendices 6 to 9.

(Appendix 11)
A process of dividing the compression target character string data into a plurality of partial areas;
Processing for generating compressed partial data by compressing the area data included in each of the plurality of partial areas to an access unit size or less;
And a process of storing the generated compressed partial data in an access unit area in a semiconductor memory device.

(Appendix 12)
12. The information processing method according to appendix 11, wherein the partial area includes a plurality of adjacent access unit areas.

(Appendix 13)
13. The information processing method according to appendix 11 or 12, wherein the compressed partial data is generated by performing grammar compression processing.

(Appendix 14)
14. The method according to any one of appendices 11 to 13, further comprising a process of decompressing the compressed partial data to be decompressed using dictionary information and restoring a part of the compression target character string data. Information processing method.

(Appendix 15)
When the compression rate of the compressed character string data including the generated compressed partial data satisfies the evaluation requirement, the processing includes compressing a plurality of continuous compressed partial data to an access unit size or less. The information processing method according to any one of supplementary notes 11 to 14.

1 Information processing apparatus 11 CPU
12 RAM
13 ROM
14 SSD
DESCRIPTION OF SYMBOLS 15 Input interface 15a Keyboard 15b Mouse 16 Optical drive device 16a Optical disk 17 Device connection interface 17a Memory device 17b Memory reader / writer 17c Memory card 18 Network interface 19 Bus 20 Graphic processing device 20a Monitor 21 Division processing unit 22 Compression processing unit 23 Decompression processing unit 24 Confirmation Unit 25 Storage Processing Unit

Claims (7)

A division processing unit that divides compression target character string data into a plurality of partial areas;
A compression processing unit that generates compressed partial data by compressing the area data included in each of the plurality of partial areas to an access unit size or less;
An information processing apparatus comprising: a storage processing unit that stores the generated compressed partial data in an access unit area in a semiconductor storage device. The information processing apparatus according to claim 1, wherein the partial area includes a plurality of adjacent access unit areas. The information processing apparatus according to claim 1, wherein the compression processing unit generates the compressed partial data by performing a grammar compression process. The decompression processing unit that decompresses the compressed partial data to be decompressed using the dictionary information and restores a part of the character string data to be compressed is provided. The information processing apparatus described in 1. The compression processing unit compresses a plurality of continuous compressed partial data to an access unit size or less when the compression rate of the compressed character string data including the generated compressed partial data satisfies the evaluation requirement. The information processing apparatus according to claim 1, wherein: The compression target character string data is divided into a plurality of partial areas,
The area data included in each of the plurality of partial areas is compressed to an access unit size or less to generate compressed partial data,
An information processing program for causing a computer to execute processing for storing the generated compressed partial data in an access unit area in a semiconductor memory device. A process of dividing the compression target character string data into a plurality of partial areas;
Processing for generating compressed partial data by compressing the area data included in each of the plurality of partial areas to an access unit size or less;
And a process of storing the generated compressed partial data in an access unit area in a semiconductor memory device.

Images