JP2010271933A - Distributed storage system, node device, node processing program, and data file storage method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a distributed storage system for distributing loads on storage control of data files to a plurality of node devices. <P>SOLUTION: The distributed storage system including a plurality of node devices for distributing and storing data files transmitted and received to and from the plurality of node devices communicable with one another via a network includes: a first storage capacity for showing a total sum of a storage capacity in a node device smaller than node numbers of the respective node devices; a means for determining a proportion of a total sum storage capacity showing a total sum of the storage capacity as a storage ratio; a means for determining a position of a prescribed data file identification number from the total number and the storage ratio; a means for determining the number of the data file identification numbers which the respective node devices are in charge of according to the storage capacity and the total sum storage capacity of the respective node devices; a means for determining the data file identification numbers the respective node devices store from positions and the number of data files in charge; and a storage control means for storing data files corresponding to the identification numbers to the respective node devices. <P>COPYRIGHT: (C)2011,JPO&INPIT

Description

  The present invention relates to a technical field of a peer-to-peer (P2P) type communication system including a plurality of node devices that can communicate with each other via a network.

  This type of peer-to-peer communication system (P2P network) distributes and stores (arranges) duplicate data files (replicas) of a plurality of data files in a plurality of node devices. Each data file is a data file of various contents such as movies and music. A distributed storage system in which the above-described data file can be used between node devices is known. This improves fault tolerance and access dispersibility. The location of the data file thus distributed and stored can be efficiently searched using a distributed hash table (hereinafter referred to as DHT (Distributed Hash Table)) as disclosed in Patent Document 1.

JP 2006-197400 A

  By the way, in such a distributed storage system, a large amount of data files may be stored biased to a specific node device. In the above case, it is necessary to store the data file without unevenness between the node devices so that the usage rate of the storage area (cache) of each node device is as uniform as possible between the node devices. In order to solve the above problem, a method in which a management server is installed in a distributed storage system can be considered. The management server controls (manages) data files stored in each node device so that the cache usage rate of each node device is equalized. In this case, each node device periodically notifies the management server of the data file stored in each node device and the cache usage rate. The management server can control the storage of the data file by grasping the data file and the cache usage rate of each node device.

  However, such a method places an excessive processing burden on the management server. As the number of data files provided in the distributed storage system increases and the number of node devices connected to the distributed storage system increases, the processing load on the management server increases.

  The present invention has been made in view of the above-described problems and the like, and a distributed storage system, a node device, a node processing program, and a data file in which a load applied during the storage control of the data file is distributed to a plurality of node devices. It is an object to provide a storage method.

  In order to solve the above problem, the invention according to claim 1 is a storage means for storing data files transmitted and received between a plurality of node devices that can communicate with each other via a network, and the plurality of data files. Total number acquisition means for acquiring the total number of data file identification numbers associated with each of the plurality of node devices, and each of the plurality of node devices constituting a distributed storage system that distributes and stores the data files among the plurality of node devices. A distributed storage system comprising a node device comprising: a node number acquisition unit that acquires the obtained node number; and a storage capacity acquisition unit that acquires a storage capacity of the storage unit of each of the plurality of node devices, In the distributed storage system, in each of the plurality of node devices, the node number is higher than the node number of each of the node devices. A storage ratio determining means for determining, as a storage ratio, a ratio of a first storage capacity indicating the sum of the storage capacities in the storage node apparatus, and a total storage capacity indicating a sum of the storage capacities of the plurality of node apparatuses; Each node device itself is in charge of the position determination means for determining the position of the predetermined data file identification number in the total number from the storage ratio, and the storage capacity and the total storage capacity of each node device. A determination unit for determining the number of data file identification numbers; a storage data file determination unit for determining a data file identification number stored in each node device from the position and the number of the data; and determination of the stored data file The data file corresponding to the data file identification number determined by the means is stored in the storage means of each node device. And control means, a distributed storage system comprising: a.

  In order to solve the above-mentioned problem, the invention according to claim 2, the node device constituting the distributed storage system, the storage ratio determination means, the position determination means, the storage data file determination means, The storage control means, wherein the storage ratio determining means includes a first storage capacity indicating a sum of the storage capacities in a node device having a node number smaller than a node number of the node device, and the plurality of node devices. A ratio of the total storage capacity indicating the sum of the storage capacities is determined as a storage ratio, and the responsible determination means determines a data file identification number assigned to the node apparatus from the storage capacity of the node apparatus and the total storage capacity. The storage data file determination means determines a data file identification number stored by the node device from the location and the number of the charges. The storage control unit stores the data file corresponding to the data file identification number determined by the storage data file determination unit in the storage unit of the node device. It is a node device.

  In order to solve the above problem, according to a third aspect of the present invention, in the node device according to the second aspect, the total number obtaining means is associated with each data file divided by a uniform capacity. A node device that acquires a data file identification number and a total number of the data file identification numbers.

  In order to solve the above problem, the invention according to claim 4 is the node device according to claim 2 or 3, wherein the node of the leaving node device is separated from the leaving node device leaving the distributed storage system. Leaving message receiving means for receiving a leaving message including a number, and when the leaving message is received by the leaving message receiving means, the node number acquisition means is configured such that the node number included in the leaving message is If the node number is smaller than the node number of the node device itself, the node number of the node device itself is updated and acquired, and the storage capacity acquisition unit acquires the storage capacity of the plurality of node devices other than the leaving node device. The storage ratio determining means acquires a node number smaller than the node number acquired by the node device itself. Determining the storage ratio between the first storage capacity indicating the sum of the storage capacities in the storage device and the sum storage capacity indicating the sum of the storage capacities of the plurality of node devices other than the leaving node device; and The determination means determines the position from the total number and the storage ratio determined by the storage ratio determination means, and the responsible determination means determines the storage capacity of the node device itself and the other than the leaving node device. From the total storage capacity of a plurality of node devices, the number of data file identification numbers handled by the node device itself is determined, and the stored data file determining means determines the node device from the position and the number of charges. The data file identification number stored by itself is determined, and the storage control means is the data file determined by the storage data file determination means A node apparatus, characterized in that to store the data file corresponding to a different number in the memory means.

  In order to solve the above-mentioned problem, the invention according to claim 5 is the node device according to any one of claims 2 to 4, wherein the new node device newly connected to the distributed storage system includes: It has a participation message receiving means for receiving the participation message including the storage capacity of the new node device itself, and the storage capacity acquisition means acquires the storage capacity of the new node device and the plurality of node devices, The storage ratio determining means includes the first storage capacity indicating the sum of the storage capacities in a node device having a node number smaller than the node number acquired by the node device itself, the new node device, and the plurality of node devices. The storage ratio with the total storage capacity indicating the sum of the storage capacities is determined, and the position determining means is the total number and the storage ratio determining means. The position is determined from the storage ratio determined from the storage ratio, and the responsible determination means determines the node from the storage capacity of the node device itself and the total storage capacity of the new node device and the plurality of node devices. The number of data file identification numbers handled by the device itself is determined, and the stored data file determining means determines the data file identification number handled by the node device itself from the position and the number of the data, and the storage The control means is a node device characterized in that the storage means stores the data file corresponding to the data file identification number determined by the stored data file determination means.

  In order to solve the above-described problem, the invention according to claim 6 is the node device according to any one of claims 2 to 5, wherein the node device is newly connected to the distributed storage system. It has participation message transmission means for transmitting a participation message including its own storage capacity to the other node devices constituting the distributed storage system, and the storage capacity acquisition means includes the storage capacities of the plurality of node devices. And the storage ratio determination means includes the first storage capacity indicating the sum of the storage capacities in the node device having a node number smaller than the node number acquired by the node device itself, and the storage of the plurality of node devices. The storage ratio with the total storage capacity indicating the sum of capacity is determined, and the position determination means is determined by the total number and the storage ratio determination means. The position is determined from the storage ratio, and the determination unit determines the data file identification number assigned to the node device from the storage capacity of the node device itself and the total storage capacity of the plurality of node devices. The stored data file determining means determines a data file identification number assigned to the node device from the position and the assigned number, and the storage control means is the saved data file determining means. The node device is characterized in that the data file corresponding to the data file identification number determined by (2) is stored in the storage means.

  In order to solve the above-mentioned problem, according to a seventh aspect of the present invention, in the node device according to any one of the second to sixth aspects, when the storage of the data file is completed by the storage control means A storage completion message transmitting unit for transmitting a storage completion message to the other node device, a storage completion message receiving unit for receiving the storage completion message from the other node device, and the storage completion message receiving unit, After receiving the save completion message from another node device, deletes from the storage means a data file different from the data file corresponding to the data file identification number in charge among the data files stored in the storage means And a deleting unit.

  In order to solve the above problem, an invention according to an eighth aspect is a node processing program that causes a computer to function as the node device according to any one of the second to seventh aspects.

  In order to solve the above problems, the invention according to claim 9 is a storage means for storing data files transmitted and received between a plurality of node devices that can communicate with each other via a network, and the plurality of data files. Total number acquisition means for acquiring the total number of data file identification numbers associated with each of the plurality of node devices, and each of the plurality of node devices constituting a distributed storage system that distributes and stores the data files among the plurality of node devices. Data file storage in a distributed storage system comprising a node device comprising: node number acquisition means for acquiring the obtained node number; and storage capacity acquisition means for acquiring the storage capacity of the storage means of each of the plurality of node devices The node device is a node of each of the node devices in each of the plurality of node devices. Determining, as a storage ratio, a ratio of a first storage capacity indicating the sum of the storage capacities in the node device having a node number smaller than the number and a sum storage capacity indicating the sum of the storage capacities of the plurality of node devices; The node device determines a position of a predetermined data file identification number in the total number from the total number and the storage ratio, and the node device stores the storage capacity and the total storage capacity of each node device. Determining the number of data file identification numbers in charge of each node device itself, and the node device determines the data file identification number stored in each node device from the location and the number of charges. A storage data file determination step to be determined, and data determined by the node device in the storage data file determination step A step of storing in the storage unit of each node device the data file corresponding to Airu identification number is a data file storage method characterized by having a.

  According to the present invention, each node device can autonomously store and control the load of data file storage in each node device so that the usage rate of the storage means of each node device is stochastically uniform. .

It is a figure which shows an example of the connection aspect of each node apparatus in the distributed storage system S which concerns on this embodiment. It is a table | surface which shows matching of the node number of each node Nn, the storage capacity of HD, node ID, and the storage charge range. It is explanatory drawing of node ID and file ID in ID space. It is explanatory drawing which shows the mode that the new node N4 connects to the distributed storage system S. It is a block diagram which shows the example of a schematic structure of the node Nn. 4 is a processing flow when a new node Nn is connected to the distributed storage system S, (A) is a process of the control unit 11 in the new node Nn, and (B) is a control in the node Nn already connected to the distributed storage system S. This is processing of the unit 11. 4 is a processing flow when the node Nn leaves the distributed storage system S. (A) is a process of the control unit 11 in the leaving node Nn that is a node leaving the distributed storage system S, and (B) is a node other than the leaving node Nn. There is processing of the control unit 11 in the node Nn.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings.

1. Configuration and Operation Overview of Distributed Storage System First, the configuration and operation overview of the distributed storage system according to the present embodiment will be described with reference to FIG.

  FIG. 1 is a diagram illustrating an example of a connection mode of each node device in the distributed storage system according to the present embodiment.

  As shown in the lower frame 101 of FIG. 1, the distributed storage system S is configured by connecting a plurality of node devices Nn via the Internet. Further, as shown in the lower frame 101 of FIG. 1, IX (Internet eXchange) 3, ISP (Internet Service Provider) 4a, 4b, DSL (Digital Subscriber Line) line operators (devices) 5a, 5b, FTTH ( A network 8 is constructed by a fiber operator (device) 6 and a communication line 7. The communication line 7 is a telephone line or an optical cable. The network 8 is a real world network such as the Internet. A router for transferring data (packets) is appropriately inserted in the network 8 in the example of FIG.

  A plurality of node devices Nn (n = 1, 2, 3,...) Are connected to such a network 8. Hereinafter, the node device is referred to as a “node”. Each node Nn is assigned a unique manufacturing number and an IP (Internet Protocol) address. The distributed storage system S according to the present embodiment includes a peer-to-peer network system formed by connecting any of a plurality of nodes Nn as shown in the upper frame 100 of FIG. It has become.

  The network 9 shown in the upper frame 100 of FIG. 1 is an overlay network 9 that configures a virtual link formed using the existing network 8. The overlay network 9 is a logical network and is realized by a specific algorithm, for example, an algorithm using DHT. A node ID is assigned to each node Nn connected to the distributed storage system S, in other words, connected to the overlay network 9.

  The node ID is unique identification information obtained by a node ID determination method described later. The node ID is an example of node device identification information. Each node ID has the same bit length as a file ID described later. Each node ID is defined so as to be distributed and distributed in the same ID space as the file ID.

  Each node Nn holds a routing table using DHT. This routing table defines various message transfer destinations on the distributed storage system S. Specifically, the routing table registers a plurality of pieces of node information including node IDs and address information of nodes Nn that are moderately separated in the ID space. The address information includes an IP address and a port number. By communicating with each other, each node Nn can know each other's node information via another node Nn, or via a management server or the like.

  By the way, in the distributed storage system S, various data files having different contents are distributed and stored (stored) in a plurality of nodes Nn in a predetermined file format. The data file can be used between the nodes Nn. For example, in the node N5, a data file of a movie whose title is XXX is stored as an example of a data file. On the other hand, a data file of a movie whose title is YYY is stored in the node N3 as an example of a data file. In the following description, a node Nn that stores a data file is referred to as a “data file holding node”.

  Also, information such as a data file name and a file ID is added to each of these data files. This file ID is unique identification information for each data file. The file ID is an example of a data file identification number in the present invention.

  File IDs are generated so as to be stochastically equal in the ID space. The file ID in this embodiment is generated by hashing “data file name + arbitrary numerical value” with a hash function such as SHA-1. Further, the first several bytes of data constituting the data file may be generated by hashing. Alternatively, the system administrator may randomly assign ID values that are unique ID values for each data file and are stochastically equal in the ID space. The file ID has the same bit length as the node ID so that the file ID is defined in the same ID space as the node ID. In this embodiment, the bit length is 160 bits. Such a data file is stored in a node Nn having a node ID determined as a person in charge of storage based on each file ID.

1-2. Node ID determination and storage charge range determination method A node ID determination and a storage charge range determination method for each node Nn will be described below.

  Based on the ratio of the storage capacities of the storage means for storing the data file of each node Nn, a value obtained by dividing the ID space is used as the node ID of each node Nn. In the following description, the storage capacity of the storage means for storing the data file of the node Nn is referred to as “HD (hard disk) storage capacity”.

  FIG. 2 is a table showing the correspondence between the node number of each node Nn connected to the distributed storage system S, the HD storage capacity of each node Nn, the node ID, and the data storage range of the data file. . FIG. 3 is an explanatory diagram of a node ID and a file ID in the ID space. In the figure, a white circle (◯) indicates a node ID, and a black circle (●) indicates a file ID.

  2 and 3 are examples in the case where the three nodes Nn of the node N1, the node N2, and the node N3 are connected to the distributed storage system S. FIG. In addition, each node ID and file ID are arranged in an ID space constituting a 4-digit hexadecimal number (0000 to ffff). In the present embodiment, the total number of ID spaces is 10,000 (∵ffff + 1).

  The node number is a number assigned to each node Nn connected to the distributed storage system S. In the example shown in FIG. 2, the node number of the node N1 is “1”, the node number of the node N2 is “2”, and the node number of the node N3 is “3”. When a node Nn is newly connected to the distributed storage system S, the node number of the new node Nn is set to “4”.

  The node ID is determined based on the total storage capacity and the first storage capacity. The total storage capacity is the sum of the HD storage capacities of all the nodes Nn connected to the distributed storage system S. The first storage capacity is the sum of the HD storage capacities of the nodes Nn having a node number smaller than the node number of the node Nn itself that determines the node ID.

  In the case of the example shown in FIG. 2, the HD storage capacity of the node N1 is 60 GB (gigabytes). The storage capacity of the HD of the node N2 is 70 GB. The storage capacity of the HD of the node N3 is 30 GB. Therefore, the total storage capacity is 160 GB (∵60 + 70 + 30 = 160).

For example, when determining the node ID of the node N3, the sum of the HD storage capacities (first storage capacities) of the nodes N1 and N2, which are node numbers smaller than the node number “3” of the node N3, is 130 GB (∵ 60 + 70 = 130). Then, a storage ratio that is a ratio between the determined first storage capacity and the total storage capacity (160 GB) is determined by Expression (1).
130 GB / 160 GB = 13/16 Equation (1)

Then, the position based on the storage ratio of the total ID space of 10,000 (∵ffff + 1) is determined by Expression (2).
10000 × (13/16) = d000 (2)

  The determined position “d000” is set as the node ID of the node N3. The node ID determined as described above may be a value that cannot be divided. In this case, a value that could not be divided may be rounded up. In addition, a value that could not be divided may be discarded. Whether rounding up or down should be used consistently.

  Similarly, the node ID of each node Nn can be obtained based on the ratio between the total storage capacity and the first storage capacity.

  When determining the node ID of the node N1, since there is no node number smaller than the node number “1” of the node N1, the first storage capacity becomes zero. Then, the position “0000” based on the storage ratio of the total number of ID spaces 10000 (∵ffff + 1) is determined as the node ID of the node N1.

When determining the node ID of the node N2, the total storage capacity (first storage capacity) of the HD of the node N1, which is a node number smaller than the node number “2” of the node N2, is 60 GB. A storage ratio, which is a ratio between the capacity and the total storage capacity (160 GB), is determined by Expression (1).
60GB / 160GB = 6/16 ... Formula (1)

Then, the position based on the storage ratio of the total ID space of 10000 is determined by Expression (2).
10000 × (6/16) = 6000 Formula (2)

  The determined position “6000” is set as the node ID of the node N2.

  Next, the file ID of the data file that each node Nn is responsible for storage is determined.

  The file ID of the data file that is in charge of storage includes the total storage capacity, the HD storage capacity of the node Nn that determines the file ID that is in charge of storage, and the node ID of the node Nn that determines the file ID that is in charge of storage Can be determined based on

For example, for the file ID of the data file handled by the node N2, the ratio between the total storage capacity and the storage capacity of the node N2HD is determined by equation (3).
70GB / 160GB = 7/16 ... Formula (3)

Then, a position (an example of the number of persons in charge) moved from the node ID “6000” of the node N2 by 7/16 of the total number of ID spaces of 10000 is determined by Expression (4).
6000 + 10000 × (7/16) = cfff Equation (4)

  The node N2 is in charge of storing the data file corresponding to the file ID from the node ID “6000” of the node N2 to the position “cfff” determined by Expression (4). Then, the node N2 acquires the data file in charge of storage and stores it in the HD of the node N2.

In summary, the node ID of each node Nn is determined by the following equation (5), and the number in charge of the storage charge range of each node Nn is determined by the equation (6).
Node ID of node Nn = (total number of ID spaces) × (first storage capacity) / (total storage capacity) Expression (5)
Number of nodes in charge of storage range of node Nn = (node ID of node Nn) + (total number of ID spaces) × (storage capacity of HD of node Nn) / (total storage capacity) (6)

  The node ID and storage range (from the node ID to the number in charge) of each of the nodes N1 to N3 are determined according to equations (5) and (6).

  According to the example shown in FIGS. 2 and 3, the node N1 stores a data file having a file ID of an ID (0000 to 5fff) area in the ID space. For example, a data file such as a file ID “2fff” is stored.

  The node N2 stores a data file having a file ID in the ID (6000 to cfff) area in the ID space. For example, a data file such as a file ID “6500” or “9000” is stored.

  The node N3 stores a data file having a file ID in the ID (d000 to ffff) area in the ID space. For example, a data file such as a file ID “e000” is stored.

  As described above, the storage charge range of the data file of each node Nn is determined so that the ratio of the HD storage capacity of each node Nn is equal to the ratio of the data file charge range of each node Nn. Therefore, the load of data file storage in each node Nn can be distributed so that the HD usage rate of each node Nn is stochastically uniform.

  Then, when a new node Nn is connected to the distributed storage system S or when the node Nn is disconnected from the distributed storage system S, it depends on the HD storage capacity of the new node Nn and the HD storage capacity of the departure node Nn. Thus, each node Nn autonomously recalculates the node ID of each node Nn itself. Then, the assigned range of each node Nn is changed. Therefore, it is possible to quickly cope with the change of the storage charge range caused by the leaving node or the newly connected node Nn.

  FIG. 4 is an explanatory diagram showing a state in which the new node N4 is connected to the distributed storage system S.

  The number obtained by adding 1 to the number of nodes Nn connected to the distributed storage system S before the new node Nn connects to the distributed storage system S is determined as the node number of the new node Nn. In the case of the example shown in the figure, the number “4” obtained by adding 1 to the number “3” of the node Nn before the new node N4 is connected to the distributed storage system S is determined as the node number of the new node N4. .

  The storage capacity of the HD of the new node N4 is 40 GB.

  The new node N4 transmits to the nodes N1, N2, and N3 connected to the distributed storage system S a participation message including information on the storage capacity of the new node N4 itself (HD capacity information) <1>. The state of transmission of the participation message is indicated by a one-dot chain line in the figure.

  Upon receiving the participation message, each of the nodes N1, N2, and N3 returns information on the storage capacity of the HD of the new node N4 to the new node N4 <2>. The state of transmission of HD storage capacity information is indicated by a two-dot chain line in the figure.

  The new node N4 calculates the node ID of the new node N4 <3>. Specifically, the sum of the HD storage capacities (first storage capacity) (160 GB) of the nodes N1, N2, and N3 having a node number smaller than the node number “4” of the new node N4, and the storage of all the nodes Nn A ratio 16/20 with the total capacity (total storage capacity) (200 GB) is determined as the storage ratio. And the value which determined the position based on the storage ratio of the total number (10000) of ID space is determined as node ID.

The total storage capacity (first storage capacity) of the HDs of the nodes N1, N2, and N3 having a node number smaller than the node number “4” of the new node N4 is 160 GB. A storage ratio that is a ratio between the first storage capacity and the total storage capacity (200 GB) is determined by Expression (1).
160 GB / 200 GB = 16/20 Formula (1)

And the position based on the storage ratio of the total number 10000 of ID space is determined by Formula (2).
10000 × (16/20) = cccc (2)

  The determined position “cccc” is set as the node ID of the new node N4.

  In addition, since the total storage capacity of each node N1, N2, and N3 is changed due to the addition of the new node N4, each node N1, N2, and N3 re-establishes the node ID of each node N1, N2, and N3 itself. Calculate <4>.

  Then, each of the nodes N1, N2, N3, and N4 acquires the data file of the assigned range determined based on the node ID and stores it in the storage unit <5>.

  The storage capacity of the HD of the node N1: The storage capacity of the HD of the node N2: The storage capacity of the HD of the node N3: The ratio of the storage capacity of the HD of the node N4 is 6: 7: 3: 4. The data file storage range is also 6: 7: 3: 4.

  After all the nodes N1 to N4 store the data file that is in charge of storage, each node N1 to N4 stores the data file outside the storage charge range if there is a data file outside the storage charge range in the storage means. Delete from means <6>.

  Even when the node Nn leaves the distributed storage system S, the leaving node Nn transmits a leaving message including the node number of the leaving node Nn itself and the storage capacity information of the HD of the leaving node Nn to each node Nn. To do. When each node Nn receives the leaving message, it recalculates the node ID of each node Nn itself based on the information of the storage capacity of the HD of the leaving node Nn included in the leaving message. Therefore, it is possible to reacquire the data file that has become the storage charge range. Specifically, each node Nn updates the total storage capacity and the first storage capacity based on the HD storage capacity information of the leaving node Nn, and recalculates the node ID of each node Nn itself. Then, a new assigned range is determined.

  In this way, even when a new node Nn connects to the distributed storage system S or when the node Nn leaves the distributed storage system S, each node Nn autonomously assigns a node ID of each node Nn itself. Recalculate and determine the memory range. That is, each node Nn itself can perform storage control of the data file in charge of storage.

  Further, each node Nn is configured to delete the data file outside the storage charge range from the storage means after storing the data file in which all nodes Nn are newly assigned to the storage due to the change of the charge range. As a result, even when the assigned range changes, the data file can be reliably relocated to the storage responsible node without affecting the data file exchange performed in the distributed storage system S. .

1-3. Data File Input and Acquisition Data files that can be used in the distributed storage system S can be input from the management server, the data file input server, or each node Nn. The management server manages the distributed storage system S. The data file input server manages data file distribution. When the node Nn inputs the data file, only the node Nn that has received permission to input the data file from the management server, the data file input server, or the like may be configured to input the data file. Hereinafter, a case where the node Nn inputs a data file will be described as an example.

  When inputting a data file, first, the node Nn determines the file ID of the data file. As described above, the file ID has the same bit length as the node ID. In addition, a random value or a hash value that is probabilistically uniformly distributed in the ID space is used as the file ID.

  Then, the node Nn that inputs the data file transmits the data file to the node Nn that is responsible for storing the data file. As shown in FIG. 2, the node Nn responsible for storing the data file is a node Nn that does not exceed the file ID of the data file to be input and has a node ID closest to the file ID.

  The node Nn responsible for storing the data file is described in the catalog information distributed to each node Nn from the management server, the data file input server, or the like. Specifically, the correspondence between the file ID of the data file and the node information of the node Nn in charge of storage is described in the catalog information. Alternatively, the node Nn that inputs the data file may transmit the data file ID to all the nodes Nn of the distributed storage system S and inquire of each node whether or not it is in charge of storage. Or you may inquire to the management server etc. which manage the node ID of all the nodes Nn.

  The node Nn to which the data file is input may not know the address information of all the nodes Nn of the distributed storage system S, but passes through each node Nn by DHT routing described in JP-A-2006-197400. Thus, it is possible to make an inquiry to another node Nn.

  Thus, the node Nn that inputs the data file transmits the data file to the node Nn that is responsible for storing the data file. The transmitted data file is received by the node Nn in charge of storage. The received data file is stored in the storage means of the node Nn that has received the data file and is responsible for storing the data file. The input of the data file is completed by the above operation.

  Each node Nn can obtain a data file from another node Nn.

  A user node which is a node Nn requesting a data file refers to catalog information distributed to each node Nn from a management server, a data file input server, or the like. Then, the user node acquires the file ID of the data file to be acquired based on the catalog information. The catalog information includes attribute information of the data file. As this attribute information, for example, the file ID of the data file, the node information of the node Nn in charge of storing the data file, the evaluation value of the data file, the release period of the data file, the data file name, the genre, the artist name, the appearance Name, director name, etc.

  Thus, each node Nn transmits a new data file to the node Nn that is in charge of storage. Each node Nn can input a new data file to the distributed storage system S, or can acquire a data file desired to be acquired from the node Nn in charge of storage.

  If the node information of the node Nn responsible for storing the data file is not described in the catalog information, the index information may be stored in each root node. The index information is information indicating where the data files are stored. The root node is a node Nn that stores index information and manages the location of the data file. Specifically, the index information is information including a set of node information of the node Nn storing the data file and a file ID of the data file. The root node can be determined according to a predetermined rule. For example, the node Nn that is closest to the file ID and has a node ID that does not exceed the file ID may be determined as the root node, or the node ID that is a predetermined value or more away from the file ID is the most file ID. A node Nn or the like having a close node ID may be determined as the root node. Each data file is configured to be managed by one of the root nodes.

  In such a distributed storage system S, when a data file is downloaded (acquired), the user node sends a message inquiring about the location of the desired data file toward the root node according to the routing table. Hereinafter, a message for inquiring the node Nn in charge of storing the data file is referred to as “query”.

  When receiving the query, the root node transmits address information of the data file holding node that stores (holds) the queried data file to the user node. The data file holding node is a node Nn responsible for storing data files.

  The user node receives the address information of the data file holding node that holds the data file from the root node.

  Then, the user node accesses the data file holding node based on the received node information. The user node transmits a data file transmission request message to the data file holding node, and downloads the data file from the data file holding node. Alternatively, the root node that has received the query can transmit a data file transmission request message to the data file holding node, and the data file holding node can transmit the data file to the user node. Note that the routing table using DHT and the message transfer between the nodes Nn using the routing table are publicly known in Japanese Patent Application Laid-Open No. 2006-197400 and the like, which is an example of a data file. Because there are, detailed explanation is omitted.

2. Configuration and Function of Node Nn Next, the configuration and function of the node Nn will be described with reference to FIG.

  FIG. 5 is a block diagram illustrating a schematic configuration example of the node Nn.

  Each node Nn includes a control unit 11, a storage unit 12, a buffer memory 13, a decoder unit 14, a video processing unit 15, a display unit 16, an audio processing unit 17, a speaker 18, and a communication unit 20. , And an input unit 21. The control unit 11, the storage unit 12, the buffer memory 13, the decoder unit 14, the communication unit 20, and the input unit 21 are connected to each other via a bus 22.

  The control unit 11 includes a CPU having a calculation function, a working RAM, a ROM that stores various data and programs, and the like. The control unit 11 functions as a computer of this embodiment. The storage unit 12 includes a hard disk (HD) that stores and stores data files, various data, various programs, and the like. For example, the storage unit 12 stores a data file and a routing table in charge of storage. The buffer memory 13 temporarily stores received data files and the like. The decoder unit 14 decodes (data expansion, decoding, etc.) encoded video data (video information), audio data (audio information), and the like. When the data file includes video and audio, the decoder unit 14 decodes encoded video data and audio data included in the data file. The video processing unit 15 performs a predetermined drawing process on the decoded video data or the like and outputs it as a video signal. The display unit 16 is a CRT, a liquid crystal display, or the like that displays an image based on the video signal output from the image processing unit 15. The sound processing unit 17 performs D (Digital) / A (Analog) conversion of the decoded audio data into an analog audio signal, and then amplifies the signal by an amplifier and outputs the amplified signal. The communication unit 20 that outputs the audio signal output from the sound processing unit 17 as a sound wave performs communication control of information between other nodes Nn and the like through the network 8. The input unit 21 receives an instruction from the user and communicates an instruction signal corresponding to the instruction to the control unit 11. The input unit 21 is, for example, a keyboard, a mouse, or an operation panel. As the node Nn, a personal computer, an STB (Set Top Box), a communication karaoke apparatus, a TV receiver, or the like is applicable.

  The storage unit 12 stores address information of the node Nn itself.

  After the node Nn is connected to the distributed storage system S, the storage unit 12 stores information on the node number of the node Nn itself and the HD of the node Nn that is a node number smaller than the node number of the node Nn itself. Information on the total storage capacity (first storage capacity) and information on the total storage capacity (total storage capacity) of all nodes Nn connected to the distributed storage system S are stored.

  The storage unit 12 also stores information on the storage capacity of the HD for storing the data file, and information on the node ID of the determined node Nn itself and the file ID of the storage charge range after determining the node ID. ing. Note that the information on the storage capacity of the HD for storing the data file is information acquired when necessary in the processing of the node Nn described later.

  Further, the storage unit 12 stores a management table. Information (title, file ID, release period, etc.) related to the data file stored in the storage unit 12 is registered in the management table.

  Furthermore, the storage unit 12 stores index information. The index information is information including a set of node information of the node Nn, which is a data file holding node managed by the node Nn itself, and a file ID of the data file. When the control unit 11 receives a query from the user node, the control unit 11 refers to the index information. Then, the control unit 11 returns the node information of the data file holding node corresponding to the request included in the query to the user node.

  In such a configuration, the control unit 11 performs overall control by the CPU reading and executing a program stored in the storage unit 12 or the like. When the node Nn is connected to the distributed storage system S and the program is executed, processing as at least one of the user node, the relay node, the root node, and the data file holding node described above is performed. ing.

  In addition, the control unit 11 executes the node processing program of the present invention, so that the storage unit, the total number acquisition unit, the node number acquisition unit, the storage capacity acquisition unit, the storage ratio determination unit, the position determination unit, and the determination of charge Means, storage data file determination means, storage control means, leave message reception means, participation message reception means, participation message transmission means, storage completion message transmission means, storage completion message reception means, deletion means and the like. The node processing program may be downloaded from a predetermined server on the network 8, for example, or recorded on a recording medium such as a CD-ROM and read via a drive of the recording medium. You may do it.

3. Processing in the node Nn at the processing node Nn will be described in detail with reference to the drawings.

3-1. Process Flow of Each Node Nn When New Node Nn is Connected FIG. 6 is a process flow when the new node Nn is connected to the distributed storage system S. FIG. 6A shows processing of the control unit 11 in the new node Nn. FIG. 6B shows the processing of the control unit 11 in the node Nn already connected to the distributed storage system S.

  The processing of the new node Nn will be described with reference to FIG.

  First, the control unit 11 of the new node Nn sets the node number of the new node Nn itself (step S10). Specifically, the number obtained by adding 1 to the number of nodes Nn before the new node Nn connects to the distributed storage system S is set as the node number of the new node Nn itself. Information on the set node number is stored in the storage unit 12. The information on the number of nodes Nn connected to the distributed storage system S is inquired of the management server or the like by the new node Nn or described in the catalog information, and the new node Nn refers to the catalog information. Get it.

  Next, the control unit 11 functions as a storage capacity acquisition unit, and acquires information on the storage capacity of the HD of the new node Nn (step S11). Specifically, information on the storage capacity of the HD for storing the data file in the storage unit 12 is acquired.

  And the control part 11 functions as a participation message transmission means, and transmits a participation message to all the other nodes Nn connected to the distributed storage system S (step S12). The control unit 11 includes the node number information of the new node Nn itself and the HD storage capacity information of the new node Nn acquired in step S11 in the participation message.

  Next, the control unit 11 functions as a storage capacity acquisition unit, and receives HD storage capacity information from all other nodes Nn connected to the distributed storage system S (step S13). Here, the control unit 11 stands by until information on the storage capacity of the HD is received from all other nodes Nn. If the HD storage capacity information cannot be received from all the other nodes Nn even after the predetermined time has elapsed, the control unit 11 inquires the management server to check the HD storage capacity information of all the other nodes Nn. To get.

  Subsequently, the control unit 11 determines the first storage capacity and the total storage capacity, and stores the determination result in the storage unit 12 (step S14). In this embodiment, the number obtained by adding 1 to the number of participating nodes Nn before the new node Nn connects to the distributed storage system S is set as the node number of the new node Nn itself. Therefore, all the other nodes Nn are nodes having a node number smaller than that of the new node Nn itself.

  The control unit 11 functions as a storage ratio determination unit and a position determination unit. Specifically, the control unit 11 determines the position in the total number of ID spaces based on the first storage capacity and the total storage capacity stored in the storage unit 12 and the total number of ID spaces (for example, 10000). decide. Next, the control unit 11 determines the determined position as the node ID of the new node Nn itself (step S15).

  Next, the control unit 11 functions as a charge determination unit, a stored data file determination unit, and a storage control unit.

  First, the control unit 11 stores a storage charge range based on the storage capacity of the HD for storing the data file in the storage unit 12, the total storage capacity, and the node ID of the node Nn itself determined in step S15. To decide. Then, the control unit 11 acquires a data file corresponding to the file ID in the storage charge range and stores it in the storage unit 12 (step S16). Specifically, when node information indicating the storage responsibility of each data file is described in the catalog information, the control unit 11 refers to the catalog information. And the control part 11 acquires the node information of the node Nn in charge of memory | storage. Then, the control unit 11 transmits a data file request message including the file ID of the data file desired to be acquired to the node Nn in charge of storage in accordance with the address information included in the acquired node information. Then, the control unit 11 acquires a data file from the node Nn in charge of storage. On the other hand, if the node information of the node Nn responsible for storing the data file is not described in the catalog information, a query including the data file ID may be transmitted to the root node to acquire the data file. When there is a data file already stored in the storage unit 12 among the data files in the storage charge range, only the data file that is not stored is acquired from the other node Nn and stored in the storage unit 12. . This is to prevent duplicate memory.

  Then, when all the data files in the storage charge range are stored in the storage unit 12, the control unit 11 functions as a storage completion message transmission unit and notifies that the storage (storage) has been completed. The control unit 11 transmits a storage completion message indicating that the storage is complete to all the other nodes Nn connected to the distributed storage system S (step S17). For example, the storage completion message transmitted in step S17 is received in the process of step S24 described later.

  Next, the control unit 11 functions as a storage completion message receiving unit, and receives a storage completion message from all other nodes Nn connected to the distributed storage system S (step S18). At this time, the control unit 11 stands by until a storage completion message is received from all the other nodes Nn connected to the distributed storage system S.

  When the storage unit 11 receives the storage completion message from all the nodes Nn, the control unit 11 functions as a deletion unit. If a data file outside the storage area of the node Nn itself is stored in the storage unit 12, the storage unit 12 stores the data file. The data file outside the assigned range is deleted from the storage unit 12 (step S19), and the process ends.

  Next, the processing of the control unit 11 in the node Nn connected to the distributed storage system S will be described with reference to FIG. The processing of the control unit 11 in the node Nn already connected to the distributed storage system S is started when the control unit 11 functions as a participation message receiving unit and receives a participation message from the new node Nn.

  First, the control unit 11 returns information on the storage capacity of the HD in the storage unit 12 to the new node Nn (step S20). The new node Nn receives the HD storage capacity information of the storage unit 12 transmitted at this time in step S13.

  Next, the control unit 11 updates the total storage capacity stored in the storage unit 12 based on the information on the HD storage capacity of the new node Nn included in the participation message. Furthermore, the control unit 11 recalculates the node ID of the node Nn itself (step S21). Specifically, the control unit 11 updates the total storage capacity stored in the storage unit 12 by adding the HD storage capacity of the new node Nn. The control unit 11 stores the updated node ID in the storage unit 12 again. In step S21, the same process as step S14 is performed.

  Next, based on the recalculated node ID, the control unit 11 acquires the data file that is in the storage charge range from another node Nn and stores it in the storage unit 12 (step S22). Specifically, for example, when node information in charge of storage of each data file is described in the catalog information, the control unit 11 refers to the catalog information and obtains node information of the node Nn in charge of storage. To do.

  Then, the control unit 11 transmits a data file request message including the file ID of the data file desired to be acquired to the node Nn in charge of storage in accordance with the address information included in the acquired node information. Then, the control unit 11 acquires a data file from the node Nn in charge of storage. When the node information of the node Nn responsible for storing the data file is not described in the catalog information, the control unit 11 may acquire a data file by transmitting a query including the data file ID to the root node. . If there is a data file that is already stored in the storage unit 12 among the data files in the storage charge range, the control unit 11 determines that only the unstored data file is stored in another node in order to prevent duplicate storage. Obtained from Nn and stored in the storage unit 12.

  When the storage unit 12 stores all data files in the storage charge range, the control unit 11 transmits a storage completion message to all other nodes Nn connected to the distributed storage system S (step S23). ). The new node Nn receives the storage completion message transmitted at this time in step S18. Note that the storage completion message transmitted in step S23 is also received in step S24 of the processing flow in FIG. 6B executed by each of the other nodes Nn.

  Next, the control unit 11 functions as a storage completion message receiving unit, and receives a storage completion message from all other nodes Nn connected to the distributed storage system S (step S24). At this time, the control unit 11 stands by until a storage completion message is received from all the other nodes Nn connected to the distributed storage system S.

  When the storage unit 11 receives the storage completion message from all the nodes Nn, the control unit 11 functions as a deletion unit, and deletes the data file that is out of the storage charge range from the storage unit 12 due to the change of the charge range (step S25). ), The process is terminated.

  In step S16 and step S22, when the data file in charge cannot be acquired from another node Nn, the control unit 11 acquires the data file from a data file input server or the like that manages the distribution of the data file. Also good. When it is not possible to acquire from another node Nn, there is no description of the node Nn in charge of storage in the catalog information, or when a data file holding node is not found or there is no response even if a query is sent to another node Nn It is.

  In step S10, the number obtained by adding “1” to the number of nodes Nn connected to the distributed storage system S is used as the node number of the new node Nn, but the node number of the new node Nn is also set to “1”. Good. When the node number of the new node Nn is “1”, each node Nn connected to the distributed storage system S updates the node number by incrementing the node number of each node Nn by “1”. It may be configured.

  In this case, the new node Nn notifies the set node number of the node Nn itself to the other nodes Nn, and each node Nn has a node number that does not overlap with other nodes Nn within a range of 1 or more and the number of participating nodes or less. Set. Each node Nn may transmit the set node number together with the HD storage capacity. Then, the first storage capacity, the total storage capacity, the storage ratio, etc. are determined at each node Nn, and the assigned range of each node Nn is determined at each node Nn.

3-2. Processing flow when a node leaving Figure 7, the node Nn from the distributed storage system S is a process flow upon withdrawal. FIG. 7A shows processing of the control unit 11 in a leaving node that is a node leaving the distributed storage system S. FIG. 7B shows processing of the control unit 11 in the nodes Nn other than the leaving node Nn.

  The process of the leaving node will be described with reference to FIG.

  First, the controller 11 of the leaving node functions as a storage capacity acquisition unit and acquires information on the HD storage capacity of the leaving node (step S30). Specifically, the control unit 11 acquires information on the storage capacity of the HD for storing the data file in the storage unit 12.

  Then, the control unit 11 functions as a leave message transmission unit, and sends a leave message to all other nodes Nn connected to the distributed storage system S (step S31). The control unit 11 includes in the leave message the information on the node number of the leaving node and the information on the HD storage capacity of the leaving node acquired in step S30.

  Next, the control unit 11 functions as a storage completion message receiving unit and receives a storage completion message from all the other nodes Nn connected to the distributed storage system S (step S32). The control unit 11 stands by until a storage completion message is received from all the other nodes Nn connected to the distributed storage system S.

  And the control part 11 will detach | leave from the distributed storage system S, if a storage completion message is received from all the nodes Nn (step S33), and complete | finishes a process.

  When leaving, the control unit 11 performs a deletion process of node number information and node ID information stored in the storage unit 12. Further, the control unit 11 may be configured to delete the catalog information and data file acquired by the distributed storage system S from the storage unit 12.

  As described above, after the storage completion message is received from all the nodes Nn, it is configured to leave in step S33. Thus, even when the node Nn leaves, the data file storage node can be changed reliably and smoothly without affecting the data file exchange performed in the distributed storage system S.

  Next, the processing of the control unit 11 in the node Nn other than the leaving node will be described with reference to FIG. The processing of the control unit 11 in the node Nn other than the leaving node is started when the control unit 11 functions as a leaving message receiving unit and receives a leaving message from the leaving node.

  First, the control unit 11 determines whether or not the node number of the leaving node Nn included in the leaving message is smaller than the node number stored in the storage unit 12 (step S41). As a result of the determination, if the node number of the leaving node Nn is smaller than the node number stored in the storage unit 12, the node number stored in the storage unit 12 is decremented (subtracted) and updated ( Step S42). Then, the first storage capacity stored in the storage unit 12 is updated based on the HD storage capacity information of the leaving node Nn included in the leaving message (step S43). Specifically, the HD storage capacity of the leaving node Nn is subtracted from the first storage capacity and updated.

  Subsequently, the control unit 11 updates the total storage capacity stored in the storage unit 12 based on the information on the storage capacity of the HD of the leaving node Nn included in the leaving message, and further updates the node ID of the node Nn itself. Is recalculated (step S44). Specifically, the HD storage capacity of the leaving node Nn is subtracted from the total storage capacity stored in the storage unit 12 and updated.

  Then, based on the recalculated node ID, the control unit 11 acquires the data file that is in the storage charge range from the other node Nn and stores it in the storage unit 12 (step S45).

  When all the data files in the storage area are stored in the storage unit 12, the control unit 11 functions as a storage completion message transmission unit and connects a storage completion message informing the storage completion to the distributed storage system S. It is transmitted to all other nodes Nn that are currently operating (step S46). For example, the storage completion message transmitted at this time is received by the leaving node Nn in step S32.

  Next, the control unit 11 functions as a storage completion message receiving unit and receives a storage completion message from all the other nodes Nn connected to the distributed storage system S (step S47). The control unit 11 stands by until a storage completion message is received from all the other nodes Nn connected to the distributed storage system S.

  When the storage unit 11 receives the storage completion message from all the nodes Nn, the control unit 11 functions as a deletion unit, and stores the data file that is out of the assigned range by updating the node ID, in other words, the changed assigned range. 12 (step S48), and the process ends.

  With such a configuration, for example, when the usage rate of the storage unit 12 in each node Nn becomes equal to or higher than a predetermined threshold, the management server or the like newly inputs a node Nn with a usage rate of 0 to the distributed storage system S. Thus, the usage rate of the storage unit 12 of each node Nn can be reduced and the load can be reduced. The node Nn whose usage rate is 0 is a node Nn in which no data file is stored in the storage unit 12.

  In the above-described embodiment, the data file that is not in charge of storage is configured to be deleted. However, when the storage unit 12 has a margin, such as when the usage rate of the storage unit 12 is less than a predetermined value, You may memorize it without deleting.

  Further, in the above-described embodiment, in steps S12, S13, S20, S31, etc., the node number information of each node Nn and the HD storage capacity information are mutually transmitted and received between the nodes Nn. May be described in the catalog information. In this case, each node Nn may refer to the catalog information as necessary to obtain the node number of each node Nn and the storage capacity information of the HD.

  For example, when the information on the storage capacity of the HD of each node Nn is described in the catalog information, the leaving node Nn connects all the nodes Nn that connect the leaving message including the node ID and node number to the distributed storage system S. Send to. The node Nn that has received the leave message refers to the catalog information and acquires the HD storage capacity associated with the node ID and node number of the leave node Nn as information on the HD storage capacity of the leave node Nn. . The new node Nn transmits a participation message including the node ID and the node number to all the nodes Nn connected to the distributed storage system S. Then, the node Nn that has received the participation message refers to the catalog information and acquires the HD storage capacity associated with the node ID and node number of the new node Nn from the catalog information. In this case, before connecting each node Nn to the distributed storage system S, the node number of the node Nn itself and information on the storage capacity of the HD are transmitted to a management server or the like that manages catalog information. In addition, when the node Nn adds an HD, it is desirable that the information on the storage capacity of the HD after the addition is transmitted to the management server, and the catalog information always describes the latest HD storage capacity. .

  Note that the present invention can also be applied to a case where the data file is a metadata file composed of a plurality of divided data files. At this time, the plurality of divided data files are divided so that the data capacities are uniform. A file ID is assigned to each divided data file. By uniformly configuring the data capacities of the plurality of divided data files, the HD usage rate of each node Nn can be made probabilistically uniform.

  The distributed storage system S has been described on the assumption that it is formed by an algorithm using DHT, but the present invention is not limited to this.

3 IX
4a, 4b ISP
5a, 5b DSL line company 6 FTTH line company 7 Communication line 8 Network 9 Overlay network (P2P network)
11 Control Unit 12 Storage Unit 13 Buffer Memory 14 Decoder Unit 15 Video Processing Unit 16 Display Unit 17 Audio Processing Unit 18 Speaker 20 Communication Unit 21 Input Unit 22 Bus Nn Node

Claims (9)

Storage means for storing data files transmitted and received between a plurality of node devices that can communicate with each other via a network;
Total number acquisition means for acquiring the total number of data file identification numbers associated with each of the plurality of data files;
Node number acquisition means for acquiring a node number allocated to each of the plurality of node devices constituting a distributed storage system that distributes and stores the data file among the plurality of node devices;
Storage capacity acquisition means for acquiring the storage capacity of the storage means of each of the plurality of node devices;
A distributed storage system comprising node devices comprising:
The distributed storage system includes:
In each of the plurality of node devices, a first storage capacity indicating a sum of the storage capacities in a node device having a node number smaller than a node number of each of the node devices, and a sum of the storage capacities of the plurality of node devices. Storage ratio determining means for determining a ratio of the total storage capacity as a storage ratio;
Position determining means for determining a position of a predetermined data file identification number in the total number from the total number and the storage ratio;
From the storage capacity of each node device and the total storage capacity, responsible determination means for determining the number of data file identification numbers that each node device itself is responsible for,
A stored data file determining means for determining a data file identification number stored by each of the node devices from the position and the number in charge;
Storage control means for storing the data file corresponding to the data file identification number determined by the stored data file determination means in the storage means of each node device;
A distributed storage system comprising: The node device constituting the distributed storage system is:
The storage ratio determining means;
The position determining means;
The stored data file determining means;
The storage control means;
With
The storage ratio determining means includes a first storage capacity that indicates a sum of the storage capacities in a node device having a node number smaller than a node number of the node device, and a sum storage that indicates a sum of the storage capacities of the plurality of node devices. The capacity ratio is determined as the memory ratio
The responsible determination means determines the number of data file identification numbers in charge of the node device from the storage capacity of the node device and the total storage capacity,
The storage data file determining means determines a data file identification number stored by the node device from the position and the number of persons in charge,
2. The node device according to claim 1, wherein the storage control unit stores the data file corresponding to the data file identification number determined by the saved data file determination unit in the storage unit of the node device. The node device according to claim 2,
The total number acquisition unit acquires the data file identification number associated with each data file divided by a uniform capacity and the total number of the data file identification numbers. The node device according to claim 2 or claim 3,
Leaving message receiving means for receiving a leaving message including the node number of the leaving node device from a leaving node device that leaves the distributed storage system;
When the leaving message is received by the leaving message receiving unit, the node number obtaining unit is configured to, when the node number included in the leaving message is smaller than the node number of the node device itself, Update and acquire its own node number,
The storage capacity acquisition means acquires the storage capacity of the plurality of node devices other than the leaving node device,
The storage ratio determining means includes the first storage capacity indicating the sum of the storage capacities in the node device having a node number smaller than the node number acquired by the node device itself, and the plurality of node devices other than the leaving node device. Determining the storage ratio with the total storage capacity indicating the total storage capacity;
The position determining means determines the position from the total number and the storage ratio determined by the storage ratio determining means;
The responsible determination means determines the number of data file identification numbers handled by the node device itself from the storage capacity of the node device itself and the total storage capacity of the plurality of node devices other than the leaving node device. And
The stored data file determining means determines a data file identification number stored by the node device itself from the position and the number of persons in charge,
The node control device, wherein the storage control unit stores the data file corresponding to the data file identification number determined by the storage data file determination unit in the storage unit. In the node apparatus as described in any one of Claims 2-4,
A participation message receiving means for receiving the participation message including the storage capacity of the new node device itself from a new node device newly connected to the distributed storage system;
The storage capacity acquisition means acquires the storage capacity of the new node device and the plurality of node devices,
The storage ratio determining means includes the first storage capacity indicating the sum of the storage capacities in a node device having a node number smaller than the node number acquired by the node device itself, the new node device, and the plurality of node devices. Determining the storage ratio with the total storage capacity indicating the total storage capacity;
The position determining means determines the position from the total number and the storage ratio determined by the storage ratio determining means;
The responsible determination means determines the number of data file identification numbers handled by the node device itself from the storage capacity of the node device itself and the total storage capacity of the new node device and the plurality of node devices. ,
The stored data file determining means determines a data file identification number that the node device itself is in charge of from the position and the number of persons in charge,
The node control device, wherein the storage control unit stores the data file corresponding to the data file identification number determined by the storage data file determination unit in the storage unit. In the node apparatus as described in any one of Claims 2-5,
When newly connecting to the distributed storage system, there is a participation message transmission means for transmitting a participation message including the storage capacity of the node device itself to the other node devices constituting the distributed storage system,
The storage capacity acquisition unit acquires the storage capacity of the plurality of node devices,
The storage ratio determining means is configured to calculate the first storage capacity indicating the sum of the storage capacities in the node device having a node number smaller than the node number acquired by the node device itself, and the sum of the storage capacities of the plurality of node devices. Determining the storage ratio with the total storage capacity shown,
The position determining means determines the position from the total number and the storage ratio determined by the storage ratio determining means;
The responsible determination means determines the number of data file identification numbers handled by the node device from the storage capacity of the node device itself and the total storage capacity of the plurality of node devices,
The stored data file determining means determines a data file identification number that the node device is in charge of from the position and the number of persons in charge,
The storage device stores the data file corresponding to the data file identification number determined by the storage data file determination unit in the storage unit. In the node apparatus as described in any one of Claims 2-6,
When the storage of the data file is completed by the storage control unit, a storage completion message transmission unit that transmits a storage completion message to the other node devices;
Storage completion message receiving means for receiving the storage completion message from the other node device;
The data file corresponding to the data file identification number in charge among the data files stored in the storage unit after the storage completion message receiving unit receives the storage completion message from the other node device. Deleting means for deleting different data files from the storage means;
A node device comprising:   A node processing program that causes a computer to function as the node device according to any one of claims 2 to 7. Storage means for storing data files transmitted and received between a plurality of node devices that can communicate with each other via a network;
Total number acquisition means for acquiring the total number of data file identification numbers associated with each of the plurality of data files;
Node number acquisition means for acquiring a node number allocated to each of the plurality of node devices constituting a distributed storage system that distributes and stores the data file among the plurality of node devices;
Storage capacity acquisition means for acquiring the storage capacity of the storage means of each of the plurality of node devices;
A data file storage method in a distributed storage system comprising node devices comprising:
In each of the plurality of node devices, the node device has a first storage capacity indicating a sum of the storage capacities in the node device having a node number smaller than the node number of each of the node devices, and the storage of the plurality of node devices. Determining a ratio of the total storage capacity indicating the total capacity as a storage ratio;
The node device determines a position of a predetermined data file identification number in the total number from the total number and the storage ratio;
The node device determines the number of data file identification numbers handled by each node device itself from the storage capacity and the total storage capacity of each node device;
A storage data file determination step in which the node device determines a data file identification number to be stored in each node device from the position and the number in charge;
The node device storing the data file corresponding to the data file identification number determined in the storage data file determination step in a storage unit of each node device;
A data file storage method characterized by comprising:

Images