JP2006146294A - Data storage control system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To usably fetch data stored distributedly in different storage devices in a short time. <P>SOLUTION: Voice/animation data given from a data processor 10 are divided to a plurality of files by a division processing part 120, and distributedly stored in a plurality of storage devices X, Y and Z by a storage processing part 130. The data fetching rate of each data storage device X, Y or Z is recorded in a storage device list 160, and a storage destination determination part 150 assigns a division file located closer to the top to the data storage device with a higher fetching rate as a storage destination. Upon receipt of a data fetching request, a fetching processing part 190 performs data fetching processing from each data storage device X, Y or Z in parallel. Since each divided file arrives at the fetching processing part 190 in the order of the fetching rate, and is successively provided from a data providing part 170 to a data processor 110, the divided file can be reproduced in the order of arrival. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to a data storage control system, and more particularly to a data storage control system having a function of dividing storage target data into a plurality of divided files and distributing and storing the divided files in different data storage devices.

  Transferring and storing data from an electronic device such as a computer to an external storage device and reading and using the data as needed is widely performed for various purposes. ing. In particular, with the development of a network between computers, the created data is transferred to and stored in other file servers connected via the network, and the necessary data is retrieved via the network when necessary. Usage forms are widespread.

Further, in Patent Document 1 below, in order to ensure the security of stored data, only the person who has deposited the data or a specific person who is permitted to access the data normally performs the data retrieval. A technique for enabling the above is disclosed. According to the technique disclosed in this document, the storage target data is divided into a plurality of divided files and distributed and stored in a plurality of storage locations on the network. If such a storage method is adopted, even if the security of each individual divided file stored in each storage location is low, unless the original division method of the file to be stored and the storage location of each individual divided file can be recognized, It is difficult to restore the original file to be stored, and sufficient security can be ensured.
PCT International Publication No. WO01 / 46808

  The point of the technique disclosed in the above-mentioned patent document is to improve security by dividing one data file into a plurality of divided files and distributing and storing each divided file in a plurality of storage locations. In the point. However, with this method, when it becomes necessary to take out and use stored data, it is necessary to read out individual divided files from a plurality of storage locations. The problem of taking time will arise. In particular, when individual divided files are distributed and stored in a plurality of file servers distributed all over the world using the Internet, the time for retrieving each divided file varies. The speed at which data is retrieved from the file server via the network depends on the data transmission speed of the transmission path constituting the network rather than the performance of the file server itself, and the slowest transmission path becomes the so-called bottleneck. This is a factor that reduces the typical take-out speed. For this reason, in order to retrieve and use a distributed data file, it is necessary to wait for the arrival of a split file from the file server with the slowest retrieval speed, and in some cases, a very long waiting time is required. .

  Therefore, the present invention makes it possible to use the original storage target data as quickly as possible when the storage target data is divided into a plurality of divided files and each divided file is distributed and stored in different data storage devices. An object of the present invention is to provide a data storage control system that can be used.

  (1) According to a first aspect of the present invention, there is provided a data storage control system having a function of dividing storage target data into a plurality of divided files and distributing and storing the divided files in different data storage devices. The divided files that are closer to the beginning of the file are assigned to the data storage device with a higher extraction speed for storage.

(2) According to a second aspect of the present invention, in the data storage control system according to the first aspect described above,
When receiving a request that requires data to be stored that is distributed and stored in multiple data storage devices, the process of extracting the split files from the multiple data storage devices is performed in parallel. The function to provide in order from the one near the head of the data to be stored is provided.

(3) According to a third aspect of the present invention, there is provided a data archiving control system having a function of dividing storage target data given from a data processing device into a plurality of divided files and storing the divided data in a plurality of data archiving devices. In
A data receiving unit for receiving data to be stored from the data processing device;
A division processing unit that divides the received storage target data into a plurality of division files based on a predetermined division method;
A storage device list indicating the locations of a plurality of data storage devices prepared for storing the split files; and
A storage location determination unit for determining the storage location of each divided file from the data storage devices listed in the storage device list;
A storage processing unit that performs processing for storing each divided file in the determined storage destination;
A management data creation unit that creates management data indicating the division method performed by the division processing unit and the storage destination determined by the storage destination determination unit for each storage target data;
Provided,
The storage device list includes information on the data extraction speed from each data storage device, and the divided file whose storage destination determination unit is closer to the beginning of the original data to be stored is the extraction speed. The storage destination is determined so that it can be assigned to a fast data storage device.

(4) According to a fourth aspect of the present invention, in the data storage control system according to the third aspect described above,
Each data storage device is further provided with a speed measurement unit that performs processing for measuring the data extraction speed and recording the measurement result in the storage device list.

(5) According to a fifth aspect of the present invention, in the data storage control system according to the third or fourth aspect described above,
An extraction processing unit that performs parallel processing to extract divided files for configuring the same storage target data from a plurality of data storage devices indicated as storage destinations by management data;
By referring to the division method indicated by the management data, a sequential organization unit that recognizes the order of each divided file extracted by the extraction processing unit;
A data providing unit for providing each divided file to the data processing device in accordance with the recognized order;
Is further provided.

(6) According to a sixth aspect of the present invention, in the data storage control system according to the fifth aspect described above,
The division processing unit has a function of encrypting the divided file, the storage processing unit has a function of storing the encrypted divided file, and the extraction processing unit has a function of taking out the encrypted divided file, The sequential organization unit has a function of decrypting the encrypted divided file.

(7) According to a seventh aspect of the present invention, in the data storage control system according to the fifth or sixth aspect described above,
The division processing unit has a function of adding dummy data to the division file, the storage processing unit has a function of storing the division file to which dummy data is added, and the extraction processing unit has the function of storing the division file to which dummy data is added. The sequential organization unit has a function of removing dummy data from a divided file to which dummy data is added.

(8) According to an eighth aspect of the present invention, in the data storage control system according to the sixth or seventh aspect described above,
The management data creation unit has a function of creating management data including information indicating an encryption processing method or dummy data addition method, and the sequential organization unit refers to the management data to perform decryption processing or dummy Data removal processing is performed.

(9) According to a ninth aspect of the present invention, in the data storage control system according to the first to eighth aspects described above,
For a data storage device accessible via a network, the storage destination is determined in consideration of the extraction speed including the data transfer speed on the network.

  (10) A tenth aspect of the present invention provides a program for causing a computer to function as the data storage control system according to the first to ninth aspects described above, and records the program on a computer-readable recording medium So that it can be distributed.

  According to the data storage control system of the present invention, when the storage target data is divided into a plurality of divided files and each divided file is distributed and stored in different data storage devices, the original storage target data is kept as short as possible. Can be made available at

  Hereinafter, the present invention will be described based on the illustrated embodiments. FIG. 1 is a block diagram for explaining the configuration and operation of a data storage control system 100 according to an embodiment of the present invention. This data archiving control system 100 divides the data to be archived given from the data processing device 10 into a plurality of divided files and distributes them to a plurality of data archiving devices X, Y, Z, and data Each of the divided files stored in the storage devices X, Y, and Z is extracted and provided to the data processing device 10.

  The data processing device 10 may be any device as long as it has a data processing function. Specifically, a personal computer, a mobile phone, a PDA device, or the like is used as a general data processing device 10, but other devices that reproduce and present digital content data may also be used. On the other hand, the data storage devices X, Y, and Z are devices having a function of storing and storing data. In the illustrated example, an example in which a data server is used as the data storage device is shown. In this example, the data storage control system 100 and the data storage devices X, Y, and Z are connected to each other via the network N.

  An operator using the data processing apparatus 10 performs an operation of taking data to be stored in and out of the data storage control system 100, so that the data storage apparatuses X, Y, and Z connected via the network N are operated. Data can be stored and retrieved. In addition, since the data to be stored is divided into a plurality of divided files and then stored in each data storage device X, Y, Z, security can be improved as compared with the storage by the normal method.

  FIG. 2 is a diagram showing a concept of storing the storage target data D by dividing it into three divided files D1, D2, and D3. In the illustrated example, the storage target data D given from the data processing device 10 is divided into three divided files D1, D2, and D3, which are distributed and stored in the data storage devices Y, Z, and X, respectively. If such distributed storage is performed, even if data is taken out from any of the data storage devices by an illegal method, only a part of the original storage target data D is stored. Since it only needs to be leaked, higher security can be ensured compared to the method of storing all data in one place. When it is necessary to use the storage target data D, when the data processing device 10 gives a use request to the data storage control system 100, the data storage control system 100 stores the data in the data storage devices X, Y, and Z. A process of extracting the divided files D1, D2, and D3 that have been performed is executed, and a process of providing the divided files to the data processing apparatus 10 is performed.

  In the figure, for convenience of explanation, an example using only three data storage devices X, Y, and Z is shown. However, in practice, operation using a large number of data storage devices connected to the network N is shown. Will be done. In particular, if the Internet is used as the network N, operation using a huge number of data storage devices installed all over the world becomes possible. Therefore, the storage destinations of the individual divided files D1, D2, and D3 constituting one storage target data D are some of a large number of data storage devices connected to the network N.

  Next, functions of individual components constituting the data storage control system 100 will be described with reference to the block diagram of FIG. First, the data receiving unit 110 is a component having a function of receiving the storage target data D from the data processing device 10. The storage target data D given from the data processing device 10 is first input to the data receiving unit 110.

  The division processing unit 120 is a component that performs processing for dividing the storage target data D input to the data receiving unit 110 into a plurality of divided files based on a predetermined division method. For example, in the example shown in FIG. 2, the storage target data D is divided into three equal parts and divided into three divided files D1, D2, and D3. The division processing method executed by the division processing unit 120 can be arbitrarily set. In order to improve security, a variation is given to the division method, and each time new storage target data is given, It is preferable to perform the division by different division methods. For example, it may be possible to change the number of halves at random, such as 3 equals in some cases and 7 equals in other cases, or the data length may be changed for each part without being divided equally. It doesn't matter.

  For example, if the operation of dividing the storage target data D into 10 MB, 15 MB, and 8 MB is repeated so as to cut the sheep, multiple divisions that periodically repeat the data length of 10 MB, 15 MB, and 8 MB are performed. A file will be formed. Of course, if the pattern of the data length and its cycle are changed randomly each time, the variation of the division method will spread infinitely.

  The storage processing unit 130 is a component that performs processing for transferring and storing a plurality of divided files generated by the division processing in the division processing unit 120 to respective predetermined storage destinations. For example, in the example shown in FIG. 2, the division processing unit 120 generates three division files D1, D2, and D3, and the storage processing unit 130 stores these data via the network N, respectively. It fulfills the function of transferring and storing to the devices Y, Z, X.

  When such storage is performed for the storage target data D, the management data creation unit 140 stores information indicating the division method performed by the division processing unit 120 and the individual divided files D1, D2, and D3. The management data including the information indicating the destination is created. Specifically, in the case of the above-described example, with respect to the storage target data D, information indicating a division method of “dividing into three equal parts and generating divided files D1, D2, and D3 in order from the top” and “D1 → Y , D2-> Z, D3-> X ", and management data including the information indicating the storage locations are created. This management data becomes information necessary when the storage target data D is retrieved later.

  The storage destination determination unit 150 is a component that performs a process of determining the storage destination of each divided file generated by the division processing unit 120. When determining the storage destination, the storage destination determination unit 150 refers to the storage device list 160. . The storage device list 160 is a list indicating the locations of a plurality of data storage devices prepared for storing the divided files. In the case of the illustrated example, for each of the data storage devices X, Y, and Z, the storage device list 160 is stored. Identification information (for example, symbols X, Y, and Z) and location information for access via the network N are prepared as a list. When the Internet is used as the network N, it is convenient to use a URL as the location information of each data storage device. As will be described later, the storage device list 160 includes information regarding the data extraction speed when data is extracted from the individual data storage devices X, Y, and Z. The speed measurement unit 165 stores each data The storage devices X, Y, and Z have a function of measuring the data extraction speed and recording the measurement result in the storage device list 160.

  Each of the above components is a component for performing data storage processing. Next, components for performing data extraction processing will be described. If there is a use request from the data processing apparatus 10 for the specific storage target data D that has been subjected to storage processing in the past, the data providing unit 170 eventually sends the storage processing data to the data processing apparatus 10. D is provided, and for this purpose, the following processing is performed by the sequential organization unit 180 and the extraction processing unit 190.

  First, when there is a use request for the storage target data D from the data processing device 10, the management data for the storage target data D for which the use request has been made is sent from the management data creation unit 140 to the sequential organization unit 180 and the extraction process. Given to part 190. As described above, when data is stored, management data including information indicating the division method performed by the division processing unit 120 and information indicating the storage destination determined by the storage destination determination unit 150 is generated as management data. Created in part 140. At the time of data extraction, information indicating the storage destination of the management data is provided to the extraction processing unit 190, and information indicating the division method is provided to the sequential organization unit 180.

  The extraction processing unit 190 recognizes a plurality of data storage devices indicated as storage destinations based on the management data given from the management data creation unit 140, and configures the same storage target data therefrom. The process of retrieving the divided files is performed in parallel. In the case of the above example, the divided files D1, D2, and D3 are based on the information indicating the storage destinations “D1 → Y, D2 → Z, D3 → X” in the management data generated for the storage target data D. Are taken out from the data storage devices Y, Z, and X via the network N, respectively.

  On the other hand, the sequential organization unit 180 refers to the division method applied to the storage target data D requested to be used, based on the management data given from the management data creation unit 140, by the take-out processing unit 190. It fulfills the function of recognizing the order of each extracted divided file. In the case of the above-described example, based on the information indicating the division method of the management data generated for the storage target data D, “generate a divided file of D1, D2, and D3 in three equal parts in order from the beginning” It can be recognized that the three divided files D1, D2, and D3 extracted by the extraction processing unit 190 are divided files that form the order of D1 → D2 → D3.

  When the recognition of the order is completed in this way, finally, the data providing unit 170 provides each divided file to the data processing device 10 according to the recognized order. In the above example, the divided files D1, D2, and D3 are provided to the data processing device 10 in this order, and the data processing device 10 connects these divided files D1, D2, and D3 in this order. Thus, the original storage target data D can be obtained.

  In the above-described example, the management data created for the storage target data D at the time of data storage is stored as it is in the management data creation unit 140, and this management data is sequentially transmitted from the management data creation unit 140 at the time of data retrieval. Although it is provided to the organization unit 180 and the extraction processing unit 190, the management data created at the time of data storage may be returned to the data processing device 10. In this case, the returned management data functions as a receipt for the storage target data D. That is, when making a use request for the storage target data D from the data processing apparatus 10 side, the management data functioning as the receipt is sent to the data storage control system 100. On the data storage control system 100 side, the management data thus sent may be provided to the sequential organization unit 180 and the extraction processing unit 190 to execute the above-described extraction processing.

  A feature of the present invention resides in a method for determining the storage destination of each divided file when data storage processing is performed by the data storage control system 100. As described above, the storage destination determination process is performed by the storage destination determination unit 150 that has received information notifying the number of generated divided files from the division processing unit 120, data stored in the storage device list 160. This is done with reference to the storage device. In principle, an arbitrary algorithm can be adopted for determining the storage location. For example, the storage location can be determined at random using a random number or the like. However, in the present invention, when the storage destination is determined, the divided file that is closer to the head of the original storage target data D is allocated to the data storage device with a higher extraction speed and stored. A rule is provided, and the storage location determination unit 150 determines the storage location according to this rule.

  As described above, the storage device list 160 includes information regarding the data extraction speed from each data storage device. Therefore, the storage destination determination unit 150 refers to the information on the speed, and stores the divided file that is located closer to the head of the original data to be stored so that it can be assigned to the data storage device having a higher extraction speed. It is possible to make a prior decision. For example, assuming that the data extraction speeds for the three data storage devices X, Y, and Z shown in FIG. 1 are Vx, Vy, and Vz, the storage device list 160 includes data Vy> Vz> Vx. As shown in FIG. 2, with respect to the divided file D1 located at the head of the original storage target data D, the data storage device Y having the fastest extraction speed is assigned and the divided file D2 located in the middle is allocated. In this case, the data storage device Z having an intermediate extraction speed may be assigned, and the data storage device X having the slowest extraction speed may be assigned to the divided file D3 located at the end.

  The only rule for determining the storage destination according to the present invention is that the divided file located at the position closer to the head of the original storage target data D is allocated to the data storage device with a higher extraction speed for storage. As long as this rule is satisfied, the individual storage destinations may be determined by any algorithm. For example, if there are a total of 100 data storage devices, and three of them are selected and three divided files D1, D2, and D3 are stored, the data storage devices are randomly selected from the 100 data storage devices. The three data storage devices are selected, the divided file D1 is assigned to the one with the fastest extraction speed, the divided file D2 is assigned to the second one, and the divided file D3 is assigned to the slowest one. Then, the object of the present invention can be achieved.

  As described above, the merit of performing the allocation considering the data extraction speed is that a divided file that is closer to the head of the original storage target data D at the time of extraction can be extracted earlier, The knitting unit 180 is such that each divided file is gathered in order from the divided file located at the position close to the head. As described above, when there is a retrieval request for the predetermined storage target data D from the data processing device 10, the retrieval processing unit 190 retrieves each divided file distributed and stored in a plurality of data storage devices. In parallel. However, the time taken for the extracted divided files to reach the extraction processing unit 190 is different, and arrivals vary. However, if allocation is performed in consideration of the data extraction speed based on the above rules, the arrival order will be the order close to the beginning of the original data D to be stored. The data can be provided from the data providing unit 170 to the data processing apparatus 10.

  For example, when the storage as shown in FIG. 2 is performed, an extraction request for the divided files D1, D2, and D3 is made in parallel from the extraction processing unit 190 to each of the data storage devices X, Y, and Z. However, the time required for the divided files D1, D2, and D3 to reach the extraction processing unit 190 varies. However, when the data extraction speeds for the three data storage devices X, Y, and Z are in a relationship of Vy> Vz> Vx, as shown in FIG. Unless a certain accident occurs or a rapid fluctuation occurs in the take-out speed, first, the divided file D1 from the storage device Y having the fastest take-out speed arrives, and then the divided file D2 from the storage device Z arrives. Finally, the divided file D3 from the storage device X having the slowest extraction speed arrives.

  As described above, if the individual portions from the beginning of the original storage target data D reach the extraction processing unit 190 sequentially with a time difference, depending on the nature of the storage target data D, it is necessary to wait until all the data is available. In some cases, it may be more reasonable to provide the individual parts from the data providing unit 170 when each part is reached. Specifically, when the storage target data D is data that is used in order from the head to the tail, such as music data or moving image data, for example, each part is taken out by the extraction processing unit 190. It is more reasonable to provide the data processing unit 170 from the data providing unit 170 as needed. Since the music data and the moving image data are data that is reproduced along a predetermined time axis, for example, in the example shown in FIG. 2, even if only the data of the first divided file D1 is provided, at least It is possible to reproduce music and moving images related to the head part without any trouble. At the latest, if the next divided file D2 is provided before the end of the reproduction of the end portion of the divided file D1, the data processing apparatus 10 continues to reproduce music and moving images without any trouble. be able to. Similarly, it is sufficient that the last divided file D3 is provided to the data processing apparatus 10 by the time when the reproduction of the end portion of the divided file D2 ends.

  As described above, the method of providing each divided file to the data processing apparatus 10 as it arrives waits for all the divided files to reach the extraction processing unit 190, and completes the storage target data D. Compared with the system provided to the data processing apparatus 10 in a simple manner, it is possible to shorten the waiting time of the operator who operates the data processing apparatus 10 and to realize extremely good responsiveness. . In particular, when the Internet is used as the network N, it often takes a considerable time for the divided file from the slowest data storage device to reach the extraction processing unit 190. In such a case, the method according to the present invention is extremely effective.

  If the arrival order of the individual divided files to the extraction processing unit 190 is always in the expected order, the divided files that have reached the extraction processing unit 190 are immediately provided to the data providing unit 170 without providing the sequential organization unit 180. Can also be provided to the data processing apparatus 10. However, in practice, the divided files do not always arrive in the expected order, so that the order recognition unit 180 performs the order recognition process, and in the unlikely event the divided files are not in the expected order. Is preferably provided from the data providing unit 170 in the correct order. For example, in the case of the example shown in FIG. 2, originally, the divided files D1, D2, and D3 should arrive at the extraction processing unit 190, but if they arrived in the order of D1, D3, and D2. In this case, the sequential organization unit 180 can recognize that the divided file D3 that has reached the second is actually the third divided file from the beginning, so that the divided file D2 waits for the divided file D2 to arrive. The divided file D3 is transferred to the data providing unit 170 after D2, and the correct sequential organization can be performed. Then, each divided file is always provided from the data providing unit 170 in order from the side closer to the head of the storage target data D.

  Of course, depending on the nature of the storage target data D, there is data that does not make sense unless all the data is available. For example, since the data of a general application program is not always used in order from the head portion, in the example shown in FIG. 2, only the head divided file D1 is provided to the data processing device 10 in advance. There is no meaning. However, since most of so-called digital contents such as music data and video data are used in order from the head to the tail, allocation of data storage devices in consideration of the data extraction speed during storage It is sufficiently meaningful to take the method of providing the data processing apparatus 10 for each divided file at the time of extraction. Practically, it is determined whether or not the data to be stored is the type of data that is used in order from the head to the tail (for example, it is possible to make a determination based on the extension of the file name) In this case, the sequential organization unit 180 may wait until the entire data to be stored is complete and decide whether to provide the data in a lump or to provide the data sequentially for each divided file.

  In the embodiment shown in FIG. 1, a speed measurement unit 165 is provided in the data storage control system 100. The speed measuring unit 165 has a function of measuring the data extraction speed for each data storage device X, Y, Z and recording the measurement result in the storage device list 150. Of course, when performing the speed measurement, for the data storage devices X, Y, and Z that are accessible via the network N as shown in the figure, the extraction speed including the data transfer speed on the network N is measured. Become. Specifically, the test data is transmitted from the speed measurement unit 165 to the data storage device to be tested via the network N, and then the test data is extracted. May be processed to measure the time until it reaches the speed measurement unit 165. Depending on the network transmission path, there is an asymmetric transmission path with different transmission speeds in the upstream and downstream directions, but what is important in the present invention is the speed at which data is extracted from each data storage device.

  Of course, in addition to measuring the extraction speed of such test data, if the extraction processing by the extraction processing unit 190 is executed during actual operation, a function for monitoring the extraction processing is provided. It is also possible to measure the arrival speed of data during operation. In practice, since the retrieval speed of each data storage device may vary due to aging, the speed measurement unit 165 periodically measures the speed, and the latest measurement result is stored in the storage device list 160. If written, information related to measurement in the storage device list 160 can be sequentially updated.

  In practice, it is preferable to perform an encryption process in order to further increase the security of each divided file stored in the data storage devices X, Y, and Z. That is, if the division processing unit 120 has a function of encrypting the division file, and the storage processing unit 130 stores the encrypted division file in each data storage device X, Y, Z, Even if each divided file stored in each of the data storage devices X, Y, and Z is illegally taken out, it is still in an encrypted state, so that safety is improved. .

  FIG. 3 is a diagram showing an example of such an encryption process. In this example, after the storage target data D is divided into three divided files D1, D2, and D3 in the storage processing unit 130, each is encrypted, and encrypted divided files D1c, D2c, and D3c are created. The data storage devices Y, Z, and X store the encrypted divided files D1c, D2c, and D3c.

  Of course, when encryption is performed at the time of storage, it is necessary to perform decryption at the time of retrieval. That is, since the extraction processing unit 190 extracts the encrypted divided files, the sequential organization unit 180 has a function of decrypting the encrypted divided files, and each encrypted division The files D1c, D2c, and D3c may be decrypted and returned to the divided files D1, D2, and D3, and then provided to the data processing apparatus 10.

  As a method different from encryption, a method of adding unnecessary dummy data to the original data constituting each divided file is also effective. FIG. 4 is a diagram for explaining the concept of the method of adding the dummy data. For example, as shown in FIG. 4 (a), when dummy data (hatched portion) that is not related to the original data is added, unnecessary data that is originally unnecessary is mixed. The correct data cannot be used. In particular, as shown in FIG. 4 (b), if a method of inserting dummy data in a format in which the original data is divided at a plurality of locations, it becomes almost impossible to use the original data.

  In the case of adopting such a method of adding dummy data, a function for adding dummy data to the divided file may be added to the division processing unit 120. Then, the divided file with the dummy data added is stored by the storage processing unit 130. Further, since the extraction processing unit 190 takes out the divided file to which the dummy data is added, the sequential organization unit 180 removes the dummy data from the divided file to which the dummy data is added. A function to perform processing is added.

  As described above, when encryption processing or dummy data addition processing is performed when data is stored, it is necessary to perform decryption processing or dummy data removal processing when data is extracted. For that purpose, information indicating what kind of encryption was performed at the time of data storage and what kind of dummy data was added was recorded somewhere, and based on this record at the time of data retrieval Therefore, it is necessary to restore the original storage target data D. It is convenient to perform such recording in the management data created by the management data creation unit 140. Eventually, the management data created by the management data creation unit 140 includes information indicating the division method, information indicating the storage destination of each divided file, encryption processing method, and information indicating the dummy data addition method. become. The sequential organization unit 180 refers to the management data, recognizes the order of each divided file, and performs a decoding process and a dummy data removal process.

  In the embodiment shown in FIG. 1, the data processing apparatus 10 and the data storage control system 100 are directly connected, but it is not always necessary to directly connect them. The embodiment shown in FIG. 5 is an example in which two data processing apparatuses A and B are connected to the data storage control system 100 via a network N. The internal configuration of the data storage control system 100 is the same as that shown in the block diagram of FIG. When storing predetermined data in the data storage devices X, Y, and Z from the data processing device A or B, the storage target data D may be delivered to the data storage control system 100 via the network N. Subsequent processing is exactly the same as in the above-described embodiment.

  In the embodiment shown in FIG. 5, a plurality of data processing devices A and B can be connected to the data storage control system 100 via the network N, so that the specific data stored by the data processing device A is specified. It is also possible to take out the data from another data processing apparatus B. If the Internet is used as the network N, for example, a global usage mode is possible in which specific data stored by the data processing apparatus A installed in Japan is retrieved by the data processing apparatus B installed in the United States.

  Contrary to such a use form on a global scale, the present invention can be applied to a very local system. The example shown in FIG. 6 is an example in which the present invention is applied to a local system including one personal computer and an external storage device. In this example, the data processing apparatus A is a single personal computer, and a plurality of external storage devices are connected to the personal computer A. In the illustrated example, three hard disk recording devices HD1, HD2, and HD3, one magneto-optical disk recording device MO, and one optical disk recording device LD are connected to the personal computer A as an external storage device. . Further, the data storage control system 100 indicated by blocks is a system having the same function as the data storage control system 100 shown in FIG. However, the data storage control system 100 is not prepared as special hardware, but is actually a system realized as a program installed in the personal computer A.

  In general, hard disk recording devices, magneto-optical disk recording devices, and optical disk recording devices have different access speeds. Even hard disk recording devices have different access speeds for each model. Therefore, as shown in FIG. 6, if five external storage devices are connected to the personal computer A, the data reading speed will naturally be different. Therefore, if information on the reading speeds of these five external storage devices is recorded in the storage device list 160 in the data storage control system 100, the data used in the personal computer A can be stored via the data storage control system 100. When the data is divided and distributed and stored in a plurality of external storage devices, the storage destination can be determined in consideration of the reading speed. Specifically, the divided file that is closer to the beginning of the original data to be stored may be stored in a device having a higher reading speed.

  As described above, if the storage destination is determined in consideration of the reading speed, when the stored data is read out and used by the personal computer A, the data is read by the personal computer A when the head portion of the data is read out. You can start using it. Eventually, the stored data can be made available in the shortest possible time, so it is very useful for data that is played back in order from the beginning, such as music data and video data. The point is exactly the same as in the above-described embodiment.

  As described above, the data storage control system according to the present invention is not limited to the case of storing data via the network as in the embodiments shown in FIGS. The same applies to local systems. In the block diagram of FIG. 1, the data storage control system 100 is shown as a component composed of a plurality of blocks. However, these components are all elements that can be realized in the form of a program. Therefore, for example, in the case of the embodiment shown in FIG. 1, the substance of the data storage control system 100 can be realized by a program installed in the data processing apparatus 10, and in the case of the embodiment shown in FIG. The entity of the storage control system 100 can be realized by a program installed in the data processing apparatus A (personal computer).

  Further, all of the components shown in the block diagram of FIG. 1 are not necessarily required for realizing the present invention. For example, as in the embodiment shown in FIG. 6, when the data reading speed of each data storage device is known from the specifications of the external storage device, the speed measuring unit 165 need not be provided. In this case, it is sufficient to write the known reading speed to the storage device list 160 as it is. In addition, the data storage control system 100 in FIG. 1 includes the data providing unit 170, the sequential organization unit 180, and the extraction processing unit 190, which are constituent elements for performing data extraction processing. Since it can also be directly executed by the data processing apparatus 10, it is not always necessary to provide the data storage control system 100.

It is a block diagram for demonstrating the structure and operation | movement of the data storage control system 100 which concern on one Embodiment of this invention. It is a figure which shows the concept which divides | segments the preservation | save object data D into three division | segmentation files D1, D2, and D3, and is preserve | saved. It is a figure which shows an example of the process of the encryption performed with the data storage control system 100 shown in FIG. It is a figure for demonstrating the concept of the process which adds the dummy data performed with the data storage control system 100 shown in FIG. 2 is a block diagram showing an embodiment in which two data processing devices A and B are connected to a data storage control system 100 via a network N. FIG. 1 is a block diagram illustrating an embodiment in which the present invention is applied to a local system including one personal computer and an external storage device.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 ... Data processing apparatus 100 ... Data storage control system 110 ... Data reception part 120 ... Division processing part 130 ... Storage processing part 140 ... Management data creation part 150 ... Storage destination determination part 160 ... Storage apparatus list 165 ... Speed measurement part 170 ... Data providing unit 180 ... Sequential knitting unit 190 ... Removal processing unit A, B ... Data processing device (personal computer)
D: Data to be stored D1, D2, D3: Divided files D1c, D2c, D3c ... Encrypted divided files HD1, HD2, HD3 ... Hard disk recording device LD ... Optical disk recording device MO ... Magneto-optical disk recording device N ... Network X, Y , Z ... Data storage device (data server)

Claims (10)

  In a data storage control system having a function of dividing storage target data into a plurality of divided files and distributing and storing each divided file in different data storage devices, the divided files that are closer to the head of the storage target data A data archiving control system characterized in that it is assigned to a data archiving device with a fast take-out speed and stored. The data storage control system according to claim 1,
When receiving a request that requires data to be stored that is distributed and stored in a plurality of data storage devices, the process of extracting the divided files from the plurality of data storage devices is performed in parallel, and the extracted divided files are A data storage control system having a function of providing data in order from the side closer to the head of the storage target data. A data storage control system having a function of dividing storage target data given from a data processing device into a plurality of divided files and storing the divided data in a plurality of data storage devices,
A data receiving unit for receiving data to be stored from the data processing device;
A division processing unit that divides the received storage target data into a plurality of division files based on a predetermined division method;
A storage device list indicating the locations of a plurality of data storage devices prepared for storing the split files; and
A storage location determination unit for determining a storage location of each divided file from the data storage devices listed in the storage device list;
A storage processing unit that performs processing for storing each divided file in the determined storage destination;
A management data creation unit that creates management data indicating the division method performed by the division processing unit and the storage destination determined by the storage destination determination unit for each storage target data;
With
The storage device list includes information on the data extraction speed from each data storage device, and the storage destination determination unit is closer to the beginning of the original storage target data, A data storage control system, wherein a storage destination is determined so as to be assigned to a data storage device having a high extraction speed. The system of claim 3, wherein
A data storage control system, further comprising a speed measurement unit that performs processing for measuring a data extraction speed and recording a measurement result in a storage device list for each data storage device. The system according to claim 3 or 4,
An extraction processing unit that performs parallel processing to extract divided files for configuring the same storage target data from a plurality of data storage devices indicated as storage destinations by management data;
By referring to the division method indicated by the management data, a sequential organization unit that recognizes the order of each divided file extracted by the extraction processing unit;
A data providing unit for providing each divided file to the data processing device in accordance with the recognized order;
A data storage control system further comprising: The system of claim 5, wherein
The division processing unit has a function of encrypting the divided file, the storage processing unit has a function of storing the encrypted divided file, and the extraction processing unit has a function of taking out the encrypted divided file, A data storage control system characterized by having a function of decrypting a divided file in which a sequential organization unit is encrypted. The system according to claim 5 or 6,
The division processing unit has a function of adding dummy data to the division file, the storage processing unit has a function of storing the division file to which dummy data is added, and the extraction processing unit has the function of storing the division file to which dummy data is added. A data storage control system having a function of taking out, and a sequential organization unit having a function of removing dummy data from a divided file to which dummy data is added. The system according to claim 6 or 7,
The management data creation unit has a function of creating management data including information indicating an encryption processing method or dummy data addition method, and the sequential organization unit refers to the management data to perform decryption processing or dummy A data storage control system characterized by performing data removal processing. The system according to any one of claims 1 to 8,
A data storage control system for a data storage device accessible via a network, wherein a storage destination is determined in consideration of an extraction speed including a data transfer speed on the network.   A program for causing a computer to function as the data storage control system according to claim 1, or a computer-readable recording medium on which the program is recorded.