JP2010277495A - Compressive recording device and compressive recording method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a compressive recording device which can make compatible the improvement of a compression rate when an execution file is compressed, and the high-speed execution of a program. <P>SOLUTION: A compressive recording device includes a page request-recording part 202, a compression unit-requiring part 205, an operational section-recording part 209, a page arrangement-determining part 208, and a page arrangement-recording part 210. An operation of a system is partitioned into sections, programs and data which are read out for each section are compressed as compression units to improve the compression rates, and data required for each section are collectively registered in a cache 204 when the data are extended to provide high random access performance. Thus, the improvement of the compression rates and the high-speed execution of the programs are made compatible. <P>COPYRIGHT: (C)2011,JPO&INPIT

Description

  The present invention relates to a compression recording method for recording a compressed program and data on a storage medium, and particularly to a lossless compression recording apparatus that does not involve data loss.

  In recent years, with the informatization of embedded devices such as mobile phones and personal digital assistants, the software scale of embedded systems has been on the rise with the momentum exceeding the capacity of the storage device. On the other hand, in an embedded device, it is necessary to reduce the capacity of a storage device due to price and size restrictions. Therefore, not only data such as images and sounds but also files that store execution objects such as program text and data that are system programs and application programs are generally compressed and recorded. On the other hand, embedded devices are limited in terms of computing power due to product cost and power consumption. The importance of data compression technology that enables more efficient input and output, and data management methods that manage compressed data, There is an increasing trend. Hereinafter, system programs and application programs are referred to as applications. A file storing execution objects such as program text and data is referred to as an object file.

  Object file compression is not possible due to the loss of data during decompression, making it impossible to execute the correct program. Therefore, a compression method using lossless data compression technology that does not involve data loss (hereinafter referred to as lossless compression method) Use.

  In the lossless compression method, when the compressed data is decompressed, the data before compression can be completely reproduced. On the other hand, the compression rate at the time of data compression changes depending on the content of the data to be compressed. The compression rate is unknown. Due to the above nature, for random access in which only a portion of the compressed data is read from an arbitrary position, the entire compressed data is temporarily expanded to a temporary memory secured in the main storage area, etc. The whole expansion method is cut out. For example, even when 1-byte data is read, the entire expansion method requires a main storage area for temporarily storing the entire expanded data at the time of execution and an operation processing time for expanding the entire compressed data.

  When executing a program, it is extremely rare that the file is executed from the beginning to the end in order, and usually the file is randomly accessed by conditional branching or loop processing. In addition, a large number of random accesses for a plurality of object files occur due to function calls of the self and the library and the simultaneous execution of a plurality of programs.

  Usually, a core part of a system program including an operating system (hereinafter referred to as an OS) that is configured around a single file is called a kernel. An executable file that constitutes the kernel is an overall decompression method that eliminates the need for random access to the compressed data by compressing the entire file and recording it in a flash ROM, etc., and expanding the entire program to the main storage area when the system is started. Widely used. Similarly, it is conceivable to use the entire expansion method for applications running on the OS. However, in general, an embedded system has a limitation on the main storage capacity to be mounted. Further, in an embedded system that does not have an area (hereinafter referred to as swap) for saving the contents of the main memory when the main memory is insufficient, it is difficult to apply the entire expansion method to the application.

  Considering these characteristics, the data to be compressed is divided and compressed in a fixed unit, and the entry to the compression unit is managed, so that the data at an arbitrary position before compression can be quickly extracted from the compressed data. There is a division compression method that enables extraction. For example, it is possible to use the division compression method in an OS having a demand paging function that takes out necessary pages from a file when necessary. By dividing and compressing the object file for each page, which is the smallest unit in which the OS manages the memory area, it is possible to expand any page requested by the OS from the compressed file at high speed. Since the division unit is a memory management unit, the process of expanding the entire compressed file into the memory area at once and cutting out the necessary pages from there is no longer necessary, and memory consumption and expansion processing time can be reduced (for example, patents). Reference 1).

  In the technique described in Patent Document 1, the text area of an object file is stored in a format that is divided and compressed into size units that are demand-paged by the OS.

JP 2003-330770 A

  However, in the conventional configuration, division is performed in units of the size of demand paging, and compression in units of pages is compared with batch compression over the entire file or division compression in units of several pages (a larger unit). Since the compression rate is low, the size after compression has increased. For this reason, there is a problem that the required storage capacity increases in an embedded device having a limited storage capacity.

  SUMMARY OF THE INVENTION The present invention solves the above-described conventional problems, and an object thereof is to provide a compression recording apparatus capable of improving the compression rate of a compressed object file and executing an arbitrary page at high speed.

  In order to solve the above-described conventional problems, a compression recording apparatus according to the present invention compresses and records a program and data necessary for system operation in an information processing system capable of simultaneously executing a plurality of programs. The operation monitoring state of the operation sequence from the start of the system, the operation monitoring sequence dividing the operation sequence into one or more sections, and the operation of storing the section information divided by the sequence monitoring means Section recording means, and compression unit determining means for determining the program and data required for each section as a compression unit in the section, dividing the system operation into sections, and calculating the total number of pages required in each section Use compression unit.

  This configuration reduces the overhead associated with random access by expanding all the pages required in each operation section from the compressed file and registering the expanded pages in the file system or OS cache function. By compressing a plurality of pages together, the compression rate can be improved.

  According to the compression recording apparatus of the present invention, since the data is divided and compressed in a unit, the compression efficiency can be improved as compared with the compression in page units, and necessary pages can be quickly expanded and expanded on the memory. It is possible to speed up the startup of the system and program.

1 is a basic configuration diagram of an information processing system according to an embodiment of the present invention. The block diagram which shows the structure of the information processing system in embodiment of this invention The figure which shows an example of the request | requirement log | history of the page in embodiment of this invention The figure which shows an example of the request | requirement log | history of the compression unit in embodiment of this invention The block diagram which shows the structure of the page arrangement | positioning determination means in embodiment of this invention. The figure which shows an example of the data format of the compression file system in embodiment of this invention The figure which shows an example of the data format of the compression block in embodiment of this invention The figure which shows an example of a mode starting system in embodiment of this invention

  Embodiments of the present invention will be described below with reference to the drawings.

(Embodiment 1)
FIG. 1 is a basic configuration diagram of an information processing system according to an embodiment of the present invention.

  The information processing system has hardware resources such as a CPU (Central Processing Unit) 1, a memory 2 as a main storage device, a device 3 as an auxiliary storage device, and various I / O devices (not shown). is doing. Various I / O devices are controlled by this information system, such as a communication device, an input device, a display device, and the like.

  The compression recording apparatus of the information processing system according to the present embodiment is suitable for an electronic information device having a limited main storage capacity and a relatively small auxiliary storage capacity for file storage. Hereinafter, a case where the information processing system is a portable electronic information device such as a mobile phone or a smartphone will be described as an example.

  The CPU 1 may be composed of a single CPU or a plurality of CPUs. The memory 2 includes a RAM (Random Access Memory). The device 3 stores a computer program and data that define the operation of the CPU 1.

  The CPU 1 executes processing specified by the computer program while writing the computer program and data stored in the device 3 to the memory 2 as necessary.

  The memory 2 also functions as a medium for temporarily storing data generated as the CPU 1 executes processing. The memory 2 includes a volatile memory and a storage medium whose stored contents are not retained when the power is turned off. The device 3 includes a nonvolatile memory and a storage medium that can be written like a flash ROM and can retain stored contents even when the power is turned off.

  On the memory 2, a user application 101, an OS (Operating System) 102, and a device driver 103 are provided.

  The user application 101 is composed of a computer program and data, and provides individual defined functions to the user of the information processing system. The OS 102 is basic software that manages system resources such as CPU time, memory capacity, file system, and device and arbitrates system resources between user programs. The device driver 103 processes a computer program and data read request transmitted from the OS 102 and a write request to the device 3.

  The OS 102 includes a VFS (Virtual File System) 111, a compressed file system 112, and a program loader 113.

  The VFS 111 is a layer for abstracting the file system, and a conventional type can be applied. The compressed file system 112 is a main part of the present invention, and provides a compressed file recording system for computer programs and data that define the user application 101. The compressed file system 112 provides a data input / output function for an object file in which computer programs and data are recorded in a data format defined by the present invention.

  The program loader 113 expands the executable computer program and data on the VFS 111 into the memory 2 in a form executable by the CPU 1.

  With the above configuration, for example, when the CPU 1 executes a certain page of the user application 101, if it is detected that the page has not yet been expanded and read in the memory 2, the following processing is performed. First, the CPU 1 stops the user application 101 and requests a corresponding page from the program loader 113. The program loader 113 specifies the object file to which the page belongs and the position (hereinafter referred to as offset) within the file in which the page is located from the page request of the CPU 1. After specifying, the program loader 113 requests the VFS 111 to read the page, and waits until the page is acquired. The VFS 111 specifies the file system to which the object file storing the page belongs, and requests the file system to read the page at the offset position of the object file. In the present embodiment, the case where the file system is the compressed file system 112 will be described as an example. The compressed file system 112 receives a page read request from the VFS 111 and searches a cache held in the compressed file system 112. If the page does not exist, the compressed file system 112 identifies the position inside the device where the compression unit including the page is stored, and issues a read request for the compression unit to the device 3. The device 3 receives the compression unit read request from the compression file system 112, reads the compression unit recorded on the flash ROM or HDD, stores it on the memory 2, and notifies the compression file system of the completion of data transfer. . Upon receiving a transfer completion notification from the device 3, the compressed file system 112 decompresses the compression unit stored in the memory 2, acquires a page requested by the VFS 111, and notifies the VFS 111 of the completion of reading. Upon completion of reading, the VFS 111 returns control to the program loader 113. The program loader 113 that has returned to control resumes the user application 101.

  In the present embodiment, the page cache is stored in the compressed file system 112 as an example. However, the page cache may be stored in the VFS 111 or the OS 102.

  FIG. 2 is a block diagram illustrating a configuration of an information processing system including the compression recording apparatus according to the embodiment of the present invention. In FIG. 2, the same components as those in FIG.

  In FIG. 2, the compressed file system 112 of the information processing system includes a page request processing unit 201, a page request recording unit 202, a cache management unit 203, a cache 204, a compression unit request unit 205, a compression unit request recording unit 206, and an expansion unit 207. , A page arrangement determining unit 208, an operation section recording unit 209, a page arrangement recording unit 210, and a file system updating unit 211.

  The page request processing unit 201 records a page read request from the VFS 111 in the page request recording unit 202 and requests the requested page from the cache management unit 203. The page request recording unit 202 holds a history of page requests for object files transmitted from the VFS 111.

  FIG. 3 shows an example of a page request history stored in the page request recording unit 202. In the example of FIG. 3, a file ID 301, an offset 302, and an access time 303 are managed as a set. The file ID 301 is information for specifying the object file from all files held by the file system. The offset 302 indicates the position of the requested page in the object file. The access time 303 indicates the time when the page is requested and the elapsed time from the system startup. Here, it is indicated that a page at the position of the offset O1 from the head of the file F1 is requested at the time T1.

  The cache management unit 203 searches the cache 204, and when the requested page exists in the cache 204, returns the cached page to the page request processing unit. When the page does not exist in the cache 204, the page is requested to the compression unit request unit 205.

  The compression unit request unit 205 searches the position of the compression unit corresponding to the requested page, and requests the device driver 103 for the compression unit. The compression unit requesting unit 205 requests a compression unit, specifies a current system operation section from information held in the system operation section recording unit 209, and requests a history of the request of the operation section and the compression unit as a compression unit request. Records in the recording unit 206.

  FIG. 4 shows an example of a compression unit request history held by the compression unit request recording unit 206. In the example of FIG. 4, the address 401, the access time 402, the operation section 403, the previous access section 404, and the previous access section 405 are managed as a set.

  An address 401 indicates a position inside the device in which a compression unit serving as an identifier of a compression unit including the requested page is recorded. The access time 402 indicates the time when the compression unit is requested and the elapsed time since the system startup. An operation interval 403 indicates an operation interval of the system when a compression unit is requested. A previous access section 404 indicates an operation section when the address is accessed in the previous system activation. The last access section 405 indicates an operation section when the address is accessed in the last system activation. Here, it is shown that the compressed block at the position of the address A1 is requested from the section D1 at the time T1, and that the address A1 is requested by D1 at the previous activation and the previous activation.

  When the compression unit request unit 205 receives the compression unit from the device driver 103, the compression unit request unit 205 requests the decompression unit 207 to decompress the compressed data.

  Upon receiving a request from the compression unit request unit 205, the decompression unit 207 decompresses the compressed data and registers the expanded single or plural pages in the cache 204.

  When a new page is registered by the decompression unit 207, the cache 204 notifies the cache management unit 203 of a cache update.

  When an update is notified from the cache 204, the cache management unit 203 returns the requested page to the page request unit 201.

  The page arrangement unit 208 is configured to determine the operation interval and the interval in consideration of the page request recording unit 202, the compression unit request recording unit 206, the operation interval recording unit 209, the execution status of the user program executed by the CPU 1, and the like. Determine the page layout for each page. The page layout unit 208 records the page layout information in the page layout recording unit 210 and requests the file system update unit 211 to update the file system.

  The file system update unit 211 collects page information necessary for the compression unit from the page arrangement information held by the page arrangement recording unit 210, and reconfigures the compression unit. The file system update unit 211 records the updated file system and the page arrangement information for the device driver 103.

  The operation section recording unit 209 holds an operation section in which the system is divided by the characteristics of the access pattern of the device 3 and an operation section to which the current system belongs.

  FIG. 5 is a block diagram showing the configuration of the page arrangement determining unit 208 in the information processing system including the compression recording apparatus according to the embodiment of the present invention.

  In FIG. 5, the page arrangement determination unit 208 includes an activation sequence monitoring unit 501, a compression unit determination unit 502, a compression unit arrangement unit 503, and a compressed image generation unit 504.

  The activation sequence monitoring unit 501 monitors the progress of the activation sequence of the system. This progress is determined from the history of page requests held by the page request recording unit 202, the access pattern to the device 3 held by the compression unit request recording unit 206, and the elapsed time from the system startup. In addition, the activation sequence monitoring unit 501 divides the system activation sequence into sections based on the operation state of the application that is the page request source and the characteristics of access to the device 3 and records them in the operation interval recording unit 209.

  The compression unit determination unit 502 determines the size of the compression unit that can hold all the pages required in the section of the activation sequence for each object file. This size determination is performed based on the page request history held by the page request recording unit 202 and the division of the activation sequence held by the operation interval recording unit 209. Further, the compression unit determination unit 502 requests the compression unit arrangement unit 503 to create a compression unit based on the determined size.

  The compression unit arrangement unit 503 first determines page arrangement information for the compression unit for each object file. Next, the compression unit arrangement unit 503 determines the arrangement position in the device 3 of the compression unit so that the compression units in the same section can be sequentially read out in the device 3, and stores the compression unit in the page arrangement recording unit 210. Record the placement information.

  The compressed image generation unit 504 collects page data for each compression unit based on the arrangement information held by the page arrangement recording unit 210, performs compression processing, and generates compressed data. The compressed image generation unit 504 constructs a binary image of the file system according to the arrangement information determined by the compression unit arrangement unit 503.

  The file system update unit 211 records the compressed file system image created by the compressed image generation unit 504 on the device 3 via the device driver 103.

  When the system is started with a predetermined operation every time the power is turned on, the present embodiment uses the compression unit request history, the address 401 and the access time 402 stored in the compression unit request recording unit 206 to determine the compression unit. The determination and the arrangement of the compression units may be determined.

  In the case where there are pages or access units with fluctuations in access timing every time the system is activated, this embodiment may add access records of the past two compression units to the sorting condition. That is, the access record of the past compression unit, the previous access section 404, and the previous access section 405 recorded by the compression unit request recording unit 206 are referred to.

  FIG. 6 shows an example of the data format of the compressed file system 112 recorded in the device 3. In the example of FIG. 6, the data format of the compressed file system 112 includes compressed blocks 601 to 603, a header 604, and a block management information array 605. The compression blocks 601 to 603 are computer programs and data compressed for each compression unit. The header 604 includes information indicating that the data format is a compressed file system. The block management information array 605 manages the arrangement information of the compressed blocks and the pages held by the compressed blocks as an array.

  FIG. 7 shows an example of the block management information array 605.

  The block management information array 605 includes a size 701 for each compressed block, an offset 702, a file ID 703, and a page offset 704. An offset 702 indicates the position of the compressed block within the file system image. The file ID 703 is information for specifying the file to which the page recorded in the compressed block belongs. A page offset 704 indicates the position of the page recorded in the compressed block within the object file.

  The block management information array 605 is used when the compression unit request unit 205 specifies a compressed block. The compression unit request unit 205 first uses the block management information array 605 to specify, from the file ID 703, the compressed block in which the object file to which the page requested by the cache management unit 203 belongs is recorded. Next, the page offset 704 is used to determine the position within the object file, and the compressed block in which the requested page is recorded is specified. Finally, the identified compressed block can be read from the device 3 via the device driver 103 and the page can be registered in the cache 204 using the decompression means 207.

  Next, the section division process performed by the activation sequence monitoring unit 501 will be described with reference to FIG.

  Here, in a relatively large-scale information processing system that has an OS 102 and a plurality of user applications 101 perform processing in cooperation with each other, the system startup from power ON to the steady state of the system is taken as an example. Will be explained.

  FIG. 8 shows an example in which a plurality of user applications operate when the system is started. In the example of FIG. 8, the system activation is defined as starting from the power ON 801 until the steady state 802. System activation can be divided into sections 805 to 807 by checkpoints 803 to 804 based on the characteristics of user application behavior.

  A section 805 represents an operation section in which the applications 811 to 813 that are user application programs are sequentially activated. In this example, the application 810, which is an application management program, activates the application 811 and activates the next application 812 when the processing of the application 811 ends or reaches a certain state. A section 805 is an operation section in which a plurality of programs are sequentially activated.

  A section 806 shows an example in which the applications 820 to 822 are activated simultaneously and operate in parallel. In such a case, a plurality of user applications advance processing while frequently switching tasks with each other.

  A section 807 indicates a section where the operation of the application 830 is dominant.

  In the section illustrated in section 805, where a plurality of applications start sequentially while operating in a relatively short time, pages requested by the applications 810 to 813 are collectively compressed as a compressed block unit. As a result, the applications 810 to 813 can be expanded at the same time when the section 805 starts. The system starts executing the application 810 immediately after the power is turned on 801. At this time, the application 810 requests the program loader 113 for the first page. The program loader issues a page request to the compressed file system 112 via the VFS 111. Since the corresponding page is included in the compressed block collected in the section 805, the compressed block is decompressed, and all pages required in the section 805 are registered in the cache 204. As a result, the pages necessary for the remaining operation in the section 805 exist in the cache 204, and the page request is completed up to the VFS 111, so that the overhead of file system processing can be reduced. Furthermore, since the pages required by the applications 811 to 813 operating in the same section 805 are already registered in the cache 204, all file system overhead that would have been required for these application programs can be reduced.

  In the section where a plurality of applications operate at the same time as exemplified in the section 806, the application 821 tries to operate while the application 820 requests and waits for the first page. However, since the system is being activated since the power is turned on, the page storing the program required by the application 821 does not exist in the cache 204 or the memory 2, and the application 821 also requests the page and enters a standby state. Similarly, the application 822 also waits for a page request, and until the end of the section 806, due to the waiting due to the page request, task switching occurs frequently, program execution is excessively divided, and processing time is delayed. In a section in which a plurality of applications operate simultaneously, pages required in the section are collected into a single compression unit, and decompressed and registered in a cache at the start of the section. As a result, not only the file system overhead but also the task switch caused by the waiting due to the page request can be removed, and the processing time and the CPU load can be reduced.

  Further, in the section where the single application 830 operates dominantly as illustrated in the section 807, the single application 830 compresses based on whether a large amount of program code is executed or a large amount of data is accessed. What is necessary is just to determine a unit. That is, when a large amount of program code is executed or a large amount of data is accessed, the pages required in the section are collected into a single compression unit, and decompressed and registered in a cache at the start of the section. As a result, it is possible to reduce waiting time for device access and file system overhead.

  Next, a method of dividing the sections 805 to 807 will be described.

  A section 805 is an example of a pattern in which applications are sequentially activated. Such sequential activation is performed by activation control from an application activation script or an application management program. For this reason, it is possible to previously set a checkpoint 803 that causes a section break in the startup script at the time of system design. For example, in the case of a startup script, the compressed file system 112 may be notified of checkpoint passing via a control command of the OS 102. You may notify directly using the control command of the compressed file system 112. In the case of an application management program, the compressed file system 112 may be notified via a control system call of the OS 102. Further, notification may be made using a control system call of the compressed file system 112.

  A section 806 is an example of a pattern in which a plurality of applications are activated simultaneously. Such parallel activation causes frequent frequent device access and division of task execution by device access. Such parallel activation can be detected from monitoring of a task scheduler that controls the execution order of applications possessed by the OS 102 and the history of page requests recorded in the page request recording unit 202. When it is detected that a plurality of applications simultaneously enter a waiting state with page requests to the device 3 and frequently generate page requests, it can be considered that the section 806 has started. For example, when the activation sequence monitoring unit 501 sets threshold values for the frequency of page requests and the frequency of task switching, and detects the occurrence of requests and switching exceeding the threshold within a certain time, the start of the same section It is possible to judge.

  A section 807 is an example of a pattern in which a specific application operates dominantly. That is, in this section, a page request is generated for the device in a random access manner. When the activation sequence monitoring unit 501 sets a threshold value for the number of page requests generated for each object file within a predetermined time from the history of page requests recorded in the page request storage 202, and detects a request exceeding the threshold value, It can be regarded as the start of the same section.

  Since the end point of a section is also the start point of another section, it can be considered that the same section continues until another type of section starts. When the system is in a steady state, all applications are in a state of waiting for an event due to a user operation or the like, and the system is in an idle state. Therefore, a threshold is set for the continuous occurrence time of the system idle, and the activation sequence monitoring unit 501 can detect the end point of the section by monitoring the idle time.

  As described above, the compression recording apparatus according to the present invention manages the system operation by dividing into sections based on the status of access to the device and the status of program execution by the CPU, and the pages necessary for each section for each object file. Judge the compression unit. As a result, when the sections are switched, all the pages required in the section are decompressed from the compressed file all at once, so that the decompression can be performed at high speed and the system processing time can be shortened.

  In particular, as the system grows in size, the number of pages required when executing an application program tends to increase, and at the start of execution, expanding the entire program is difficult for embedded systems with limited main storage capacity. ,Have difficulty. For this reason, it is more effective to divide into appropriate units by the compression recording apparatus of the present invention.

  Furthermore, the compression recording apparatus of the present invention sequentially reads out the pages required in the section by rearranging and rearranging the positions of the compression units accessed in the section in the device for each section. Make it possible. As a result, random access to an object file associated with program execution can be made sequential, thereby preventing deterioration in program execution time performance caused by random access, and shortening system processing time.

  In addition, since the compression recording apparatus of the present invention compresses a plurality of pages together, the compression rate can be improved and the capacity of the auxiliary storage device can be reduced as compared with the case of compressing in units of pages. It becomes possible and the cost can be reduced.

  Each functional block of the present invention is typically realized as software, but may be realized as an LSI which is an integrated circuit. The name used here is LSI, but it may also be called IC, system LSI, super LSI, or ultra LSI depending on the degree of integration. Further, the method of circuit integration is not limited to LSI's, and implementation using dedicated circuitry or general purpose processors is also possible. An FPGA (Field Programmable Gate Array) that can be programmed after manufacturing the LSI, or a reconfigurable processor that can reconfigure the connection or setting of circuit cells inside the LSI may be used. Furthermore, if integrated circuit technology comes out to replace LSI's as a result of the advancement of semiconductor technology or a derivative other technology, it is naturally also possible to carry out function block integration using this technology. Biotechnology can be applied.

  The compression recording apparatus according to the present invention has a function of determining a compression unit by dividing a system operation into sections, and is useful for an embedded system. Moreover, it can be applied to various home appliances, communication devices such as mobile phones, industrial devices, and passenger equipment.

1 CPU
2 Memory 3 Device 101 User application 102 OS
103 Device driver 111 VFS
DESCRIPTION OF SYMBOLS 112 Compression file system 113 Program loader 201 Page request processing means 202 Page request recording part 203 Cache management means 204 Cache 205 Compression unit request means 206 Compression unit request recording part 207 Decompression means 208 Page arrangement determination means 209 Operation section recording part 210 Page arrangement Recording unit 211 File system update unit 501 Startup sequence monitoring unit 502 Compression unit determination unit 503 Compression unit arrangement unit 504 Compressed image generation unit

Claims (5)

In an information processing system capable of simultaneously executing a plurality of programs, a compression recording apparatus that compresses and records programs and data necessary for system operation,
A sequence monitoring means for monitoring the state of the operation sequence from the start of the system and dividing the operation sequence into one or more sections;
Operation section recording means for storing information of the section divided by the sequence monitoring means;
A compression recording apparatus comprising compression unit determining means for determining a program and data required for each section as a compression unit in the section. Compression unit arrangement means for determining arrangement so that the calling order of page data corresponding to the compression units determined by the compression unit determination means is sequential;
2. A compression generation unit configured to acquire page data corresponding to the compression unit based on the arrangement determined by the compression unit arrangement unit, perform compression processing, and generate compressed data. The compression recording device described. The sequence monitoring means divides the operation sequence into one or more sections based on a history of page requests in the operation sequence from the system startup, an access pattern to the device, and an elapsed time from the system startup. The compression recording apparatus according to claim 1, wherein the compression recording apparatus is divided. In an information processing system capable of simultaneously executing a plurality of programs, a compression recording method for compressing and recording programs and data necessary for system operation,
A sequence monitoring step of monitoring the state of the operation sequence from when the system is started and dividing the operation sequence into one or more sections;
A compression unit determination step for determining a required program and data as a compression unit in the section for each section divided by the sequence monitoring step;
A compression unit arrangement step for determining the arrangement so that the calling order of page data corresponding to the compression units determined by the compression unit determination step is sequential;
A compression recording method comprising: a compression generation step of obtaining compressed data by acquiring page data corresponding to the compression unit based on the arrangement determined in the compression unit arrangement step . In the sequence monitoring step, the operation sequence is divided into one or more sections based on the history of page requests in the operation sequence from the system startup, the access pattern to the device, and the elapsed time from the system startup. 5. The compression recording method according to claim 4, wherein the compression recording method is divided.

Images