JP5157770B2 - Node device, program, and storage instruction method - Google Patents

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.

  In this type of peer-to-peer communication system, copy data (hereinafter referred to as “replica”) of a plurality of content data (content data such as movies and music) is distributed and stored (arranged) in a plurality of node devices. A distributed content storage system that makes it possible to use replicas between node devices is known, and this improves fault tolerance and access dispersibility. The location of the replicas thus distributed and stored can be efficiently searched using a distributed hash table (hereinafter referred to as DHT (Distributed Hash Table)) as disclosed in, for example, Patent Document 1.

  In such a distributed content storage system, when performing a content distribution service, access is concentrated on popular content replicas, so it is desirable to distribute and store a number of replicas corresponding to popularity in a plurality of node devices. According to Patent Document 1, each node device has an evaluation value of the content before publication (before the publication) before making a replica of the content newly input to the system available to other node devices (before publication). Compared with the evaluation value of the content replica that has already been saved), it is saved when the evaluation value of the content before publication is large, but not when it is small Yes.

As described above, when a new content replica before publication is stored in a node device in the system, a node device in the system is randomly selected or a content viewing reservation period is selected as a storage destination node device selection method. And a replica of the content is stored in the node device that has reserved viewing during the period. For example, Patent Document 2 discloses a storage instruction device that stores a replica of a new content in a node device that has reserved the purchase of the content when a replica of the new content before publication is inserted in the system. Is disclosed.
JP 2007-034630 A JP 2008-20938 A

  However, because no consideration is given to the free recording capacity of the storage unit in which the replica of the content of each node device is recorded, a certain node device does not record the content replica in the storage unit such as a hard disk at all. The storage unit of a certain node device is almost used and there is no free recording capacity.

  For this reason, when an instruction to save a new content replica is given to a node device whose free storage capacity in the storage unit is less than the capacity of the new content replica, the node device A situation arises in which such a replica is deleted, a recording location of a new replica is secured, and a new replica is recorded.

The present invention has been made in view of the above problems, and content recording such as a storage unit of each node device participating in the content distributed storage system when content data (replica) is input to the content distributed storage system. based on the information for specifying the free recording capacity means, to the node device free recording capacity is relatively large, the estimation, the node device for storing contents data, programs, to provide a storage instruction method Is an issue.

In order to solve the above-described problem, the invention according to claim 1 is the node device in the content distributed storage system that stores a plurality of content data in a plurality of node devices that can communicate with each other via a network. An acquisition means for acquiring a storage destination candidate list including node apparatus identification information for identifying a node apparatus that is a candidate for a storage destination of content data, and content data to be stored; and the content data acquired by the acquisition means And a first storage destination candidate list used for selecting another node device that stores the content data stored in the content storage unit, the content storage unit storing the content data, and the storage destination candidate list acquired by the acquisition unit And a second storage destination candidate list to be transmitted to the other node device. Means, from among the divided first storage destination candidate list by the dividing means, and selecting means for selecting the node device identification information indicating the node device which stores the contents data stored in said content storage means A storage instruction for instructing the node device identified by the node device identification information selected from the first storage destination candidate list by the selection unit to store the content data stored in the content storage unit Save instruction means for transmitting the save instruction information including the second save destination candidate list divided by the dividing means and the content data saved in the content saving means, and the selecting means , selected the node device identification information of the previous SL first destination candidate list from the first storage destination candidate list And deleting means for deleting from a node apparatus, characterized in that it comprises a.
In order to solve the above problem, an invention according to claim 7 is provided in a computer included in the node device in a distributed content storage system that stores a plurality of content data in a plurality of node devices that can communicate with each other via a network. Obtaining a storage destination candidate list including node device identification information for identifying a node device that is a candidate for the storage destination of the content data, and content data to be stored, and storing the acquired content data as content Storing in the means, and transmitting the acquired storage destination candidate list to the other node device and the first storage destination candidate list used for selecting another node device that stores the stored content data. dividing the second storage destination candidate list, the first storage location which is the divided From the auxiliary list, the content and selecting the node device identification information indicating the node device which stores the content data stored in the storage means, the node device selected from among the first storage destination candidate list Storage instruction information that instructs the node device identified by the identification information to store the content data stored in the content storage unit and includes the divided second storage destination candidate list; and and transmitting said content data stored in the content storage unit, a step of deleting the node device identification information selected from among the first storage destination candidate list before Symbol first destination candidate list, the a feature and to Help program to be executed.
In order to solve the above-mentioned problem, the invention according to claim 8 is a storage executed in the node device in a distributed content storage system in which a plurality of content data is stored in a plurality of node devices that can communicate with each other via a network. An acquisition method for acquiring a storage destination candidate list including node device identification information for identifying a node device that is a candidate for a storage destination of the content data, and content data to be stored, and the acquisition step A content storage step of storing the content data acquired in step S2 in a content storage unit, and another node for storing the content data stored in the content storage unit in the storage destination candidate list acquired in the acquisition step A first save destination candidate list used for selecting a device and the other node A second storage destination candidate list to be sent to de device, a dividing step of dividing the, from among the divided first storage destination candidate list in the dividing step, the content data stored in the content storage unit In the selection step of selecting the node device identification information indicating the node device to be stored, and in the selection step, the node device identified by the node device identification information selected from the first storage destination candidate list , Storage instruction information for instructing storage of the content data stored in the content storage means, including storage instruction information including the second storage destination candidate list divided in the dividing step, and stored in the content storage means a storage instruction step of transmitting said content data, in said selection step, said first storage destination candidate list A deletion step of deleting from the previous SL first destination candidate list said node device identification information selected from a storage instruction method which comprises a.

According to these inventions, it becomes possible to instruct the node device to store based on the first storage destination candidate list. For example, each node device or a management device that manages the storage status of content data is instructed every time. The content data can be efficiently distributed and stored in the content distributed storage system without making an inquiry. In addition, since the node device identification information for identifying the node device instructed to store the content data is deleted from the divided first storage destination candidate list, the same node device is instructed to store the content data redundantly. The content data can be stored while preventing the content data from being stored , and the content data storage instruction process can be shared among the node devices.

Further , the storage destination candidate list is divided into a first storage destination candidate list used for selection of other node devices and a second storage destination candidate list transmitted to other node devices, and is stored in other node devices. Since the second storage destination candidate list is transmitted to other node devices when the instruction is given, the other node devices that have received the storage instruction information also instruct content data storage based on the second storage destination candidate list. it is possible.

In order to solve the above problems, the invention according to claim 2, in the node device according to claim 1, wherein the selecting means includes a first from among said first storage destination candidate list divided by the dividing means 1 The predetermined number of the node device identification information is selected, and the storage instruction unit stores the content data stored in the content storage unit in the node device identified by the node device identification information selected by the selection unit. The node device is characterized in that the storage instruction information for instructing storage of the storage instruction information including the second storage destination candidate list and the content data stored in the content storage unit are transmitted. .

According to the present invention, a first predetermined number of node device identification information is selected from the first storage destination candidate list, and storage instruction information and content are stored for the node device identified by the selected node device identification information. Since the data is transmitted, it is possible to instruct the first predetermined number of node devices to store the content data.

In order to solve the above-mentioned problem, the invention according to claim 3 is a determination means for determining whether or not the first predetermined number of node device identification information can be selected in the node device according to claim 2. And the selection means selects the first predetermined number of the node device identification information, and the determination means determines that the selection is not possible. In some cases, the information processing device includes identification information generating means for generating the first predetermined number of node device identification information, and the storage instruction means is generated by the identification information generating means when the determination means determines that selection is impossible. to the node device node apparatus identified by the identification information, a said store instruction information for instructing the storage of the content data stored in the content storage unit A storage instruction information including the serial second destination candidate list, a node apparatus and transmits and said content data stored in the content storage means.

According to the present invention, even if that can not be selected at the first predetermined number of node devices, it is possible to instruct a reliable storage of content data to another node device.

In order to solve the above problem, the invention according to claim 4 is the node device according to any one of claims 1 to 3 , wherein the selection unit is stored in the content storage unit. The node device identification information is repeatedly selected until the disclosure date and time when content data can be used among a plurality of the node devices, and the storage instruction unit stores the storage instruction information and the content storage unit until the disclosure date and time. The node device repeatedly transmits the stored content data.

According to the present invention, the selection of the node device identification information to the public time and date of the content data, a repeating row Ukoto the transmission of the content data stored in the storage instruction information and content storage means, the pre-distribution of the content data its Can be done until the date of publication.

In order to solve the above-mentioned problem, the invention according to claim 5 is the node device according to any one of claims 1 to 4 , wherein the storage instruction transmitted from the storage instruction means of another node device. A storage instruction information receiving means for receiving information, and when the storage instruction information is received by the storage instruction information receiving means, the acquisition means acquires the second storage destination candidate list and the content data; When the storage instruction information is received by the storage instruction information receiving unit, the content storage unit stores the content data acquired by the acquisition unit, and the storage instruction information receiving unit receives the storage instruction information. When received, the dividing unit stores the second storage destination candidate list acquired by the acquiring unit in the content storing unit. The divided third storage destination candidate list to be used for selection of another node device for storing contents data, a fourth storage destination candidate list to be transmitted to another node apparatus to store the content data, to the store instruction When the storage instruction information is received by the information receiving unit, the selection unit selects the node device identification information from the third storage destination candidate list divided by the dividing unit, and the storage instruction information When the storage instruction information is received by the reception unit, the storage instruction unit is configured to divide the node device identified by the node device identification information selected by the selection unit into the node device divided by the dividing unit. 4 transmits the content data stored in the storage instruction information and the contents holding means includes a storage destination candidate list, prior to When the storage instruction information is received by the storage instruction information receiving unit, the deletion unit uses the third storage destination to store the node device identification information selected from the third storage destination candidate list by the selection unit. The node device is characterized in that it is deleted from the candidate list .

According to this invention, when the node device receives the storage instruction information and receives the storage instruction, the node device selects the node device based on the third storage destination candidate list obtained by dividing the acquired second storage destination candidate list. Since the storage instruction information including the fourth storage destination candidate list and the content data are transmitted to the selected node device, the storage instruction information can be transmitted to the selected node device.

In order to solve the above-mentioned problem, the invention according to claim 6 is the node device according to claim 5 , wherein the storage instruction information received by the storage instruction information receiving unit is transmitted from the other node device. A node device comprising: disclosure date / time information acquisition means for acquiring disclosure date / time information indicating a disclosure date / time at which the content data stored in the content storage unit can be used among a plurality of the node devices. .

  According to the present invention, a node device that has received an instruction to save content data can easily acquire and grasp the disclosure date and time of the content data.

According to the present invention, it becomes possible to instruct a node device to store based on the first storage destination candidate list, and for example, inquires of another node device or a management device that manages the storage status of content data every time. Therefore, the content data can be efficiently distributed and stored in the content distributed storage system. In addition, since the node device identification information for identifying the node device instructed to store the content data is deleted from the divided first storage destination candidate list, the same node device is instructed to store the content data redundantly. The content data can be stored while preventing the content data from being stored , and the content data storage instruction process can be shared among the node devices.
Further, the storage destination candidate list is divided into a first storage destination candidate list used for selection of other node devices and a second storage destination candidate list transmitted to other node devices, and is stored in other node devices. Since the second storage destination candidate list is transmitted to other node devices when the instruction is given, the other node devices that have received the storage instruction information also instruct content data storage based on the second storage destination candidate list. be able to.

  DESCRIPTION OF EXEMPLARY EMBODIMENTS Hereinafter, the best embodiment of the invention will be described with reference to the drawings.

[1. Configuration of distributed content storage system]
First, with reference to FIG. 1 and the like, a schematic configuration and the like of the content distributed storage system according to the present embodiment will be described.

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

  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 (Fiber To A network (real-world communication network) 8 such as the Internet is constructed by a line provider (device) 6 and a communication line (for example, a telephone line or an optical cable) 7. Note that a router for transferring data (packets) is appropriately inserted into the network 8 in the example of FIG.

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

  A network 9 shown in the upper frame 100 of FIG. 1 is a P2P network (overlay network, logical network) 9 constituting a virtual link formed using the existing network 8. Such a P2P network 9 is realized by a specific algorithm, for example, an algorithm using DHT.

  Each node Nn participating in the distributed content storage system S (in other words, the P2P network 9) is assigned a node ID that is unique identification information having a predetermined number of digits. The node ID is, for example, a value (for example, the bit length is 160 bits) obtained by hashing an IP address or a manufacturing number individually assigned to each node Nn with a common hash function (for example, SHA-1). Yes, it will be distributed in one ID space without any bias.

  Further, the content distributed storage system S is a content input server CS as an example of the storage instruction device of the present invention that inputs new content into the content distributed storage system S, and content data (content copy data) of each node Nn. In the following description, the free storage capacity of the storage unit composed of HD (Hard Disk) or the like, which is a content recording means for recording and storing (storing), is collected and stored in each node Nn. A log collection server LS is provided as an example of a log management apparatus that manages and saves node information in association with an IP address and a node ID of each node Nn.

  Note that the participation in the distributed content storage system S is such that a non-participating node Nn (for example, the node N25) self-identifies to an authentication server (not shown) via the network 8 in order to receive permission to participate in the system S. System usage registration is requested together with the IP address information and node ID (registration request), and the authentication server performs authentication processing for registration in the content distribution storage system S.

  Then, the new participation node Nn permitted to participate participates in the system S with respect to any node Nn that has already participated in the system S (for example, a contact node that always participates in the system S). Participating in the content distributed storage system S by transmitting a participation message indicating that it has been done.

  Each node Nn participating in the distributed content storage system S holds a routing table using DHT. Therefore, the node Nn (contact node or the like) that has received the participation message from the new participation node Nn copies the routing table held by itself and sends it to the new participation node Nn.

  This routing table defines the transfer destinations of various messages on the content distributed storage system S, and specifically includes the node ID, IP address, port number, etc. of the node Nn that is moderately separated in the ID space. Multiple node information items are registered. The IP address and port number are examples of network address information.

  One node Nn participating in the content distributed storage system S registers the minimum necessary node information of the nodes Nn among all the nodes Nn participating in the system S in the routing table, With respect to the node Nn that does not know (store) the node information, various messages are transferred between the nodes Nn to be delivered.

  Such a routing table using DHT is well known in Japanese Patent Application Laid-Open No. 2006-197400 and the like, and will not be described in detail.

  Next, content used in each node Nn will be described.

  In the content distributed storage system S, replicas of various contents with different contents (for example, movies, music, etc.) are distributed and stored in a storage unit of a plurality of nodes Nn in a predetermined file format. The replica can be used. For example, a replica of movie content with the title XXX is stored in the storage unit of the node N5, while a replica of movie content with the title YYY is stored in the storage unit of the node N3. Are distributed and stored in a plurality of nodes Nn (hereinafter referred to as “content holding nodes”).

  In addition, information such as a content name (title) and a content ID (identification information unique to each content) is added to each of these content replicas. This content ID is generated, for example, by hashing the content name + arbitrary numerical value (or may be the first few bytes of the content data) with a hash function common to obtaining the node ID (node ID and Placed in the same ID space). Alternatively, the system administrator may give a unique ID value (same bit length as the node ID) for each content. In this case, the catalog in which the correspondence between the content name and the content ID is written is distributed to all the nodes Nn participating in the distributed content storage system S by the system administrator.

  When a new content is input to the content distribution storage system S by the content input server CS, a replica of the new content is stored in the node Nn that is estimated to have a larger free storage capacity in the storage unit. Instructed.

  As shown in FIG. 2, each node Nn participating in the distributed content storage system S (P2P network 9) has information (free space) for identifying the free recording capacity of its own storage unit with respect to the log collection server LS. (Recording capacity specifying information) is transmitted periodically (for example, once a day, for every predetermined period).

  If the free recording capacity specifying information is information that can specify the free recording capacity of the storage unit of the node Nn, in addition to the free recording capacity of the storage unit itself, for example, information indicating the total operating time of the device of the node Nn. Or information indicating the number of times the node Nn has acquired a replica in the past (number of downloads), information indicating the number of times the replica acquired by the node Nn has been played (number of times of viewing), or a node Nn in the past as another node Information indicating the number of storage instructions received from Nn or the content input server CS (the number of pre-distribution), or information indicating the number of times that the node Nn has made the replica available to other nodes Nn (the number of times of disclosure) Etc. It can be specified that the smaller the total operating time mentioned above, the larger the free recording capacity of the storage unit, and the smaller the number of downloads, viewing times, etc., the larger the free recording capacity of the storage unit. it can.

  The log collection server LS receives the free recording capacity specifying information from each node Nn and stores it as node information in association with the node ID and IP address of each node Nn.

  As shown in FIG. 3, when the content input server CS inputs a new content replica to the content distributed storage system S, that is, when distributed and stored in the nodes Nn participating in the content distributed storage system S. Includes a storage destination candidate list in which a second predetermined number (for example, 10 or 100) of node information (node information Nx_n) having a larger free storage capacity in the storage unit than the log collection server LS is posted. A request is made (see FIG. 3 [1]), and a storage destination candidate list is obtained from the log collection server LS (acquisition means) (see FIG. 3 [2]). Then, the acquired storage destination candidate list is stored in the storage unit of the content input server CS (node information storage means), and one of the node information posted in the storage destination candidate list is randomly selected (first predetermined number). Node information (selection means) and instruct the node Nn corresponding to the node information to store a replica of the new content (see FIG. 3 [3]). For example, when the node information Nx_1 is selected from the node information posted on the storage destination candidate list, the node N1 indicated by the node information Nx_1 is instructed to store a replica of the new content (save instruction unit). . The node Nn that receives the content storage instruction from the content input server CS receives the content replica and the storage destination candidate list from the content input server CS and stores (records) them in its own storage unit. 2 and 3, only the nodes N5, N8, N10, etc. are shown as the nodes Nn participating in the content distributed storage system S (P2P network 9), and the diagrams are simplified.

  The new content stored in the node Nn that has received the storage instruction is posted on the catalog list distributed by the system operator when the release date arrives, and a replica of the content can be downloaded (content distribution) Can be shared among a plurality of nodes Nn participating in the storage system S). Each node Nn that desires to view the content (i) searches for the content (ii) downloads the content from the node Nn that stores the content, and views and views the content.

  In addition, the location of the replica stored in this manner, that is, a set of node information (node ID, IP address, etc.) of the node Nn storing the replica and a content ID corresponding to the replica of the content is included. Index information is stored (stored in the index cache) and managed by a node Nn (hereinafter referred to as “root node” or “root node of content data (content ID)”) that manages the location of the replica of the content. It has come to be.

  That is, the node information of the content holding node storing the content replica is managed by the root node so as to be provided in response to an inquiry from another node Nn.

  For example, the index information about the replica of the movie content with the title XXX is managed by the node N4 which is the root node of the content (content ID), and the index information about the replica of the movie content with the title YYY is Managed by the node N7 which is the root node of the content (content ID). Further, such a root node is determined to be, for example, a node Nn having a node ID closest to the content ID (for example, the higher-order digits match more).

  When a user of a certain node Nn wants to acquire a replica of the desired content, the node Nn that desires to acquire the replica (hereinafter referred to as “user node”) determines the content ID and the self of the content selected by the user. A content location inquiry (search) message (query) including the IP address of the client is generated and sent to another node Nn according to a routing table using its own DHT. That is, the user node sends a content location inquiry (search) message toward the root node (to the root node) (that is, inquires the location of the content replica to the root node). As a result, the content location inquiry (search) message finally arrives at the root node by DHT routing using the content ID as a key.

  Note that attribute information such as the content name and content ID of the content to be selected by the user at each node Nn is described in the content catalog list. The content ID included in the content location inquiry (search) message may be generated by the user node by hashing the content name with the common hash function. The DHT routing is known in Japanese Patent Application Laid-Open No. 2006-197400 and the like, and thus detailed description thereof is omitted.

  The root node that receives the content location inquiry (search) message acquires index information corresponding to the content ID included in the content node from the index cache, and uses the index information as a user who is the transmission source of the content location inquiry message. Reply to the node. The user node that has acquired the index information in this way connects to the content holding node based on the IP address of the content holding node included in the index information, transmits a content transmission request message, and then creates a replica of the content from there. It becomes possible to acquire. Note that the index information may include, for example, node information of a plurality of content holding nodes (when replicas of the same content are stored in a plurality of content holding nodes). In such a case, the user node can select one content holding node from among the plurality of content holding nodes and connect to the selected content holding node to obtain a content replica.

  The root node transmits a content transmission request message to the content holding node indicated by the IP address or the like included in the index information, whereby the user node acquires the replica from the content holding node. You can also The user node can also acquire the index information from a cache node that caches the same index information as the root node until the content location inquiry message reaches the root node.

  The node Nn that has received a storage instruction from the content input server or another node Nn and newly stored a replica of the content notifies the root node that manages the content that the replica has been stored (in other words, the system S A publish message including the content ID of the replica and its own node information (node ID, IP address, etc.) and generating the publish message Send to the root node (to the root node).

  As a result, the publish message arrives at the root node by DHT routing using the content ID as a key, like the content location inquiry (search) message. Then, the root node registers (stores in the index cache area) index information including a set of node information and content ID included in the received publish message. In this way, the node Nn that has received the save instruction newly becomes a content pre-holding node that holds a replica of the content.

  Note that the index information including the set of node information and content ID included in the publish message is also registered (cached) in the cache node in the transfer path to the root node.

  In addition, the user node that acquired and stored the desired replica from the content holding node also sends the above-described publish message to the root node to notify the root node that the replica has been stored (to the root node). ) Send out and newly become a content holding node that holds a replica of the content.

  In the content distributed storage system S described above, before a newly entered content replica becomes available in the system S (before publication), any content from the content input server CS as an example of a storage instruction device Is distributed to some nodes Nn (content pre-retention nodes) by further transmitting the replica to other nodes Nn and instructing the storage to be transmitted. To be saved. This is to avoid concentration of access to the replica of the content after the newly input content is disclosed.

  At this time, the content input server CS stores from the log collection server LS that regularly collects and manages the free recording capacity specifying information of the storage unit from all the nodes Nn participating in the content distributed storage system S. A storage destination candidate list on which a second predetermined number of node information having a larger free recording capacity indicated by the free recording capacity specifying information is obtained, and based on this, a first predetermined number (first predetermined number) is acquired. A <second predetermined number) of nodes Nn are selected at random, and the selected node Nn is instructed to store a replica of the new content. Further, the node Nn that is instructed to store is also a node that has a larger free recording capacity in the storage unit for storing (recording) the replica based on the storage destination candidate list received from the content input server CS as the node Nn itself Nn is selected to instruct the storage of a replica of newly input content.

  Thereby, the node Nn having a large free recording capacity of the storage unit for storing (recording) the replica can be set as the content pre-holding node.

[2. Configuration and function of each device]
[2-1. Configuration and function of node Nn]
Next, the configuration and function of the node Nn will be described with reference to FIG.

  FIG. 4 is a diagram illustrating a schematic configuration example of the node Nn.

  As shown in FIG. 4, each node Nn includes a control unit 11 as a computer including a CPU having a calculation function, a working RAM, a ROM for storing various data and programs, and various data (for example, content data). Storage unit 12 as node information storage means and content recording means composed of a hard disk or the like for storing and storing (storing) various programs, etc. A buffer memory 13 for temporarily storing a replica of the content data and the like, and decoding (data expansion, decoding, etc.) of the encoded video data (video information) and audio data (audio information) included in the content data replica A decoder unit 14 and the decoded video data; A video processing unit 15 that performs a predetermined drawing process on the data and outputs the video signal; a display unit 16 such as a CRT or a liquid crystal display that displays video based on the video signal output from the video processing unit 15; The decoded audio data is converted into an analog audio signal by D (Digital) / A (Analog) conversion, then amplified by an amplifier and output, and the audio signal output from the audio processing unit 17 is converted into a sound wave. And a communication unit 20 for controlling communication of information among other nodes Nn, the content input server CS, the log collection server LS, etc. through the network 8, and accepts an instruction from the user and responds to the instruction An input unit (for example, a keyboard, a mouse, or an operation panel) that provides the control signal to the control unit 11 ) And 21, is configured to include a control unit 11, storage unit 12, a buffer memory 13, decoder unit 14, a communication unit 20, and the input unit 21 are connected to each other via a bus 22. As the node Nn, a personal computer, an STB (Set Top Box), a TV receiver, or the like can be applied.

  When the content distributed storage system S includes a contact node that is an access destination when participating in the system S, the storage unit 12 stores the IP address and port number of the contact node. Yes. Further, the storage unit 12 stores a stored content management table for registering information (title, content ID, etc.) regarding the replica of the stored (recorded) content.

  In such a configuration, the control unit 11 performs overall control by reading and executing a program (including the storage instruction processing program and the node processing program of the present invention) stored in the storage unit 12 or the like by the CPU. By participating in the content distributed storage system S, processing as at least one of the user node, relay node, root node, cache node, content holding node, and content pre-holding node described above is performed. .

  In addition, the control unit 11 that performs processing as the storage instruction device is an acquisition unit, a node information storage unit, a selection unit, a storage instruction unit, an identification information generation unit, a determination unit, a split node information generation unit, a storage instruction information in the present invention. It functions as a receiving means, an updating means, and a disclosure date / time information obtaining means. The storage instruction processing program and 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 stored in the recording medium. You may make it read via a drive.

  The control unit 11 periodically acquires the free recording capacity of the storage unit 12. For example, the total capacity of the cache area of the hard disk in which the replica of the storage unit 12 is recorded and the recording capacity (usage capacity) that is already used may be obtained and subtracted from the total capacity (free recording capacity) = Total capacity-used capacity). Then, based on the acquired free recording capacity, free recording capacity specifying information is generated and transmitted to the log collection server LS.

  In addition, when receiving an instruction to store a replica of a content to be newly input to the content distribution storage system S from the content input server CS or another node Nn, the control unit 11 stores the replica in the storage unit 12. The storage destination candidate list received together with the storage instruction is also temporarily stored in the storage unit 12. Then, the list is divided for transmission and storage, a first predetermined number of nodes Nn are selected from the storage destination candidate list for storage, and a replica and a storage destination candidate list for transmission are selected for the selected node Nn. Send and instruct to save replica. The division of the storage destination candidate list will be described in detail later.

[2-2. Configuration and function of log collection server LS]
Next, a schematic configuration of the log collection server LS will be described with reference to FIG. FIG. 5 is a block diagram illustrating a schematic configuration of the log collection server LS according to the embodiment.

  As shown in FIG. 5, the log collection server LS included in the distributed content storage system S according to the embodiment includes a CPU having a calculation function, a working RAM (Random Access Memory), and a ROM (Read that reads various data and programs). A log database 202a in which node information including the free recording capacity, node ID, and IP address of the storage unit of each node Nn collected from each node Nn is stored and stored (stored). And communication of information between the storage unit 202 composed of an HD or the like for storing and storing various data and programs, and other devices such as the nodes Nn and the content input server CS through the network It receives instructions from the communication unit 203 for performing control and an operator who operates the log collection server LS and receives the instructions And an input unit (for example, a keyboard, a mouse, or an operation panel) 204 that outputs an instruction signal corresponding to the control unit 201, and includes a control unit 201, a storage unit 202, a communication unit 203, and an input unit 204. Are connected to each other via a bus 205 so that data can be exchanged between them.

  Then, when the CPU in the control unit 201 executes various programs recorded in the storage unit 202 or the like, the control unit 201 performs overall control of the overall operation as the log collection server LS according to the embodiment.

  FIG. 6 shows an example of node information stored and saved in the log database 202 a provided in the storage unit 202.

  When the control unit 201 periodically receives the free recording capacity specifying information from each node Nn, the control unit 201 stores it in the log database 202a in association with the node ID and IP address of each node Nn. This node ID and IP address may be periodically received from each node Nn together with the free recording capacity specifying information, or after each node Nn participates in the content distribution storage system S, it is the first time (first time) to the log collection server LS. Only when transmitting the free recording capacity specifying information, each node Nn transmits the node ID and the IP address together with the free recording capacity specifying information to the log collection server LS, and the log collection server LS associates this with the log database 202a. Each node Nn transmits only the node ID and free recording capacity specifying information from the second time onward, and the log collection server LS logs the free recording capacity specifying information received together with the received node ID as a key. What is necessary is just to comprise so that it may match | combine and preserve | save with the database 202a.

  In accordance with the above procedure, the log database 202a is associated with the free recording capacity (Nx_n), node ID (Nx_n), and IP address (Nx_n) of the storage unit of all nodes Nn participating in the content distributed storage system S. Are registered (stored) as node information Nx_1, node information Nx_2, node information Nx_3, and node information Nx_n.

  Then, in response to a request from the content input server CS, the control unit 201 extracts from the log database 202a the requested node information having a large free recording capacity (second predetermined number) and extracts a storage destination candidate list. It is generated and transmitted to the content input server CS.

[2-3. Configuration and function of content input server CS]
Next, a schematic configuration of the content input server CS will be described with reference to FIG. FIG. 7 is a block diagram showing a schematic configuration of the content input server CS according to the embodiment.

  As shown in FIG. 7, the content input server CS included in the content distributed storage system S according to the embodiment includes a CPU having a calculation function, a working RAM (Random Access Memory), and a ROM (Read Read) that records various data and programs. In order to record and store (store) content data to be input, content data that has been input, a storage destination candidate list acquired from the log collection server LS, and other necessary programs, etc. A storage unit 302 configured as a node information storage unit configured by HD, and the like, and a communication unit 303 for controlling communication of information with each device such as each node Nn and log collection server LS through the network 8 An instruction signal is received in response to an instruction from an operator who operates the content input server CS An input unit (for example, a keyboard, a mouse, or an operation panel) 304 that outputs to the control unit 301. The control unit 301, the storage unit 302, the communication unit 303, and the input unit 304 are connected via a bus 305. Connected to each other so that data can be exchanged between them.

  Then, the CPU in the control unit 301 reads out and executes the program (including the storage instruction processing program of the present invention) recorded in the storage unit 302 and the like so as to control the overall operation and cooperate with the above-described components. Then, the content input server CS is caused to function as a storage instruction device in the present invention. And the control part 301 which performs a process as a preservation | save instruction | indication apparatus functions as an acquisition means in this invention, a node information storage means, a selection means, a preservation | save instruction means, a determination means, and an identification information generation means. The storage instruction 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 via a drive of the recording medium. It may be read.

  The control unit 301 selects a first predetermined number of nodes Nn from the storage destination candidate list stored in the storage unit 302 as a replica of the content to be newly input to the content distributed storage system S, and replicas the selected node Nn. And send the save destination candidate list to instruct to save the replica.

  In the present embodiment, when the control unit 301 of the content input server CS instructs the storage of the content replica, the content replica is transmitted to the storage destination node Nn together with the instruction, so-called “push type”. Is stored. Then, the node Nn instructed to store the content replica records the replica in the cache area of its own storage unit 12 to become a content pre-holding node and to notify the root node that the replica has been stored. (In other words, for publishing to other nodes Nn participating in the system S), a publish message including the content ID of the replica and its own node information is directed to the root node ( Send to the root node). As a result, the publish message arrives at the root node by DHT routing using the content ID as a key, like the content location inquiry (search) message described above.

  In addition, the content input server CS obtains from the log collection server LS the storage destination candidate list in which 10 pieces of node information from the node information Nx_1 to the node information Nx_10 are posted. Is stored in the system according to the popularity of the content, etc., and the number of node information requested to the log collection server LS (second predetermined number) is appropriately determined according to the stored number. For example, if a large number of replica distribution requests are predicted after the release due to high popularity, a large number of storages should be determined, and at least a number greater than the determined number of storages should be requested. What is necessary is just to comprise. Note that the popularity of content refers to, for example, when the content is a movie and has already been released to the theater, or is determined according to the number of spectators, or based on the award history of contests, etc. If the content is music, it may be determined in consideration of the sales of the artist's past works.

  Then, information (publication date / time information) indicating the publication date / time, which is the date / time when the content replica can be shared between other nodes Nn, is included in the storage instruction information or the content replica and transmitted to the selected node Nn. Configure to The node Nn that receives the save instruction information and receives the replica save instruction stores the replica in the cache area of its own storage unit 12 in association with the content ID, and performs registration processing (transmission of a publish message). .

  After that, when the release date and time indicated by the save time information or the release time information acquired in the content replica is reached, the content information (content ID, title, etc.) is posted on the catalog list distributed by the system operator, and the content The other nodes Nn participating in the distributed storage system S generate a content location inquiry message (query) that inquires about the location of a desired replica based on the content ID of the content listed in the catalog list and send it to the root node. Then, it becomes possible to know the node Nn holding the replica and download the replica from the node Nn holding the replica.

  The number of node information requested by the content input server CS to the log collection server LS (second predetermined number) is larger than the number of nodes Nn (first predetermined number) selected by the node Nn that has received the save instruction. And

  Further, the node Nn that receives the replica storage instruction from the content input server CS instructs the other nodes Nn participating in the content distributed storage system S to store the content replica. That is, the node Nn that has received a replica storage instruction from the content input server CS functions as a storage instruction device. Then, the other node Nn that has received this storage instruction similarly instructs other nodes Nn participating in the content distributed storage system S to store the content replica. As described above, the content input server CS functioning as a storage instruction device or the node Nn participating in the system S repeats the replica storage instruction to the node Nn participating in the system S until the release date and time. Content replicas can be distributed and stored in advance in the system S before publication.

[3. Save destination candidate list]
Next, division of a storage destination candidate list that is transmitted and received between each node Nn when a replica storage instruction is issued will be described.

  The node Nn that has received the storage instruction information from the content input server CS (storage instruction information receiving means) determines the storage destination candidate list acquired from the content input server CS as the storage destination candidate list for storage and the storage destination candidate list for transmission. Divide into FIG. 8 is an example in which the storage destination candidate list received from the content input server CS is divided into two so that the node information is halved.

  For example, a storage destination candidate list (node information Nx_1 to Nx_10) in which, for example, ten (second predetermined number) node information is posted from the content input server CS (node information Nx_1 to Nx_10) is acquired and stored in its own storage unit 12 (node Information storage means). After that, five pieces of node information (an example of the third predetermined number) are extracted from the saved destination candidate list (node information Nx_1 to Nx_10) and divided, and the destination candidate list (node information Nx_6) as divided node information is divided. ˜Nx — 10) (divided node information generating means).

  Then, the storage destination candidate list (node information Nx_1) that is obtained by removing the node information Nx_6 to Nx_10 obtained by dividing (extracting) the storage destination candidate list (node information Nx_1 to Nx_10) stored in the storage unit 12 of itself. To Nx_5) (update means), and from the save destination candidate list (node information Nx_1 to Nx_5) stored in the storage unit 12, the node Nn to be instructed to save is selected (selection means), and the selected node Nn The node information extracted with respect to the transmission destination candidate list for transmission (node information Nx_6 to Nx_10) is transmitted together with the replica, and the storage is instructed (storage instruction means).

  Hereinafter, the storage destination candidate list transmitted from the log collection server LS to each node Nn through the content input server CS will be described with reference to FIGS.

  FIG. 9 is a diagram illustrating a state of the storage destination candidate list exchanged between the log collection server LS, the content input server CS, and the nodes N5 and N1, and FIG. 10 is exchanged between the nodes N1, N7, and N8. It is a figure which shows the mode of the preservation | save destination candidate list.

  The log collection server LS extracts, from the log database 202a, node information corresponding to the second predetermined number (the number requested from the content input server CS) from the node information having the largest available recording capacity, and the node information is posted. The storage destination candidate list (node information Nx_1 to Nx_10) is generated and transmitted to the content input server CS.

  The content input server CS stores the received storage destination candidate list (node information Nx_1 to Nx_10) in its own storage unit 302, and a node that instructs to store a replica from the stored storage destination candidate list (node information Nx_1 to Nx_10) One Nn is selected at random. In the figure, the node N5 is selected, and the selected node N5 is instructed to store the replica together with the storage destination candidate list (node information Nx_1 to Nx_10).

  When the node N5 receives the storage destination candidate list (node information Nx_1 to Nx_10) from the content input server CS and receives an instruction to save the replica, the node N5 receives a third predetermined number from the storage destination candidate list (node information Nx_1 to Nx_10). The node information is extracted (divided), and the storage destination candidate list (node information Nx_1 to Nx_5) for storage excluding the extracted node information is stored in its own storage unit 12. One node for instructing to store the replica is randomly selected from the storage destination candidate list (node information Nx_1 to Nx_5) stored in the storage unit 12 of the device itself. In the figure, the node N1 is selected, and the selected node N1 is instructed to store the replica together with the transmission destination candidate list (node information Nx_6 to Nx_10) including the extracted node information.

  Next, when the node N1 receives the storage destination candidate list on which five (second predetermined number) node information (Nx_6 to Nx_10) is received from the node N5 and receives an instruction to store the replica, the storage destination candidate list A third predetermined number of node information is extracted (divided) from (node information Nx_6 to Nx_10), and a storage destination candidate list (node information Nx_6 to Nx_7) for storage excluding the extracted node information is stored in its own storage unit 12. To remember. From the storage destination candidate list (node information Nx_6 to Nx_7) stored in the storage unit 12 of the self, one node (first predetermined number) instructing the storage of the replica is randomly selected. In the figure, the node N7 is selected, and the selected node N7 is instructed to store the replica together with the transmission destination candidate list (node information Nx_8 to Nx_10) including the extracted node information.

  Further, after instructing the node N1 to store the replica, the node N5 deletes the information of the node N1 instructed to store from the storage destination candidate list stored in its own storage unit 12, as shown in FIG. The third predetermined number of node information is further extracted (divided) from the updated storage destination candidate list (node information Nx_2 to Nx_5), and the storage destination candidate list for storage excluding the extracted node information ( Node information Nx_2 to Nx_3) is stored in its own storage unit 12. Then, one node instructing to save the replica is randomly selected from the save destination candidate list (node information Nx_2 to Nx_3) stored in the storage unit 12 of the self. In the figure, the node N3 is selected, and the selected node N3 is instructed to store the replica together with the transmission destination candidate list (node information Nx_4 to Nx_5) for transmission composed of the extracted node information.

  Similarly, the node N3 also divides the storage destination candidate list (node information Nx_4 to Nx_5) received from the node N1 for storage and transmission, and replicas the node N4 selected from the storage destination candidate list for storage. Instruct to save.

  In the example illustrated in FIG. 11, the node N4 receives the storage destination candidate list on which only the node information of the node N5 is posted, and the node N4 instructs the node N5 to store. However, as described above, since the node N5 has already stored the replica according to the storage instruction from the content input server CS, the storage instruction is duplicated for the node N5 as it is. In preparation for such a case, when the content input server CS sends the storage destination candidate list to the node N5, the node information of the node N5 may be deleted from the storage destination candidate list and transmitted. Good.

  As described above, the node Nn that has received the storage instruction from the content input server CS functions as a storage instruction device, and the node Nn that has a relatively large free recording capacity in the storage unit that is listed in the storage destination candidate list. The node Nn that received the storage instruction instructs to store the replica, and the node Nn that has received the storage instruction further instructs other nodes Nn to store the replica based on the storage destination candidate list. . The content replica storage instruction and the storage based on the instruction are indicated by the storage instruction information received from the content input server CS or other node Nn that is the storage instruction source or the disclosure date / time information received in the content replica. It will be repeated until the content release date.

  By the way, since the storage destination candidate list is divided and updated every time a storage instruction is given at each node Nn, it is assumed that the node information posted in the storage destination candidate list before the release date is lost. In addition, when the content input server CS cannot acquire the storage destination candidate list from the log collection server LS, or the node Nn receiving the storage instruction from the content input server CS cannot receive the storage destination candidate list from the content input server CS. Cases are also envisaged. In such a case, for example, when the content input server CS cannot acquire the storage destination candidate list from the log collection server LS, the control unit 301 of the content input server CS functions as an identification information generating unit, and the content input server The server CS is configured to generate a first predetermined number of node IDs and send a save instruction message toward the generated node ID. Further, even when the node Nn that has received the storage instruction from the content input server CS cannot receive the storage destination candidate list from the content input server CS, the control unit 11 sets the first predetermined number of node IDs in each node Nn. Generate and send a save instruction message toward the generated node ID.

  Then, the sent save instruction message reaches the node Nn having the same node ID as the generated node ID or the node Nn having a node ID close to the generated node ID, and the final destination of the save instruction message That is, the node Nn stores the replica. In this case, in addition to the configuration in which the storage instruction message and the replica are transmitted together and the replica is transmitted by the “push type”, only the storage instruction message is transmitted, and the node Nn that is the final destination of the storage instruction message is the message The storage instruction source (content input server or node Nn) is requested based on the node information (node ID, IP address, etc.) of the storage instruction source included in the request to obtain a replica to be acquired. May be.

[4. Processing of each device]
In the above operation, processing in the log collection server LS, the content input server CS, and each node Nn will be described in detail with reference to the drawings.

[4-1. Node Nn free recording capacity specifying information transmission process]
FIG. 12 is a flowchart showing processing of the control unit 11 when an arbitrary node device Nn participating in the content distributed storage system S transmits free recording capacity specifying information to the log collection server 12. The processing is periodically started every predetermined period such as times.

  First, the control unit 11 acquires a free recording capacity of the storage unit 12 (step S21).

  Next, free recording capacity specifying information is generated based on the acquired free recording capacity (step S22), the free recording capacity specifying information is transmitted to the log collection server LS together with the node ID (step S23), and the process is terminated. In the case of the first transmission of the free recording capacity specifying information, the self IP address is also transmitted to the log collection server LS.

[4-2. Processing of log collection server LS]
FIG. 13 is a flowchart showing the processing of the control unit 201 in the log collection server LS. For example, when the system administrator or the like operates the input unit 204 to instruct execution of the processing (or the communication unit 203 And when the system manager receives information to instruct execution of processing from another apparatus operated by the system administrator).

  First, the control unit 201 determines whether or not the power of the log collection server LS is turned off (step S30). If the power is not turned off (step S30: No), the node participating in the content distributed storage system S It is determined whether or not the free recording capacity specifying information is received from Nn (step S31).

  As a result of the determination, when the free recording capacity specifying information is received (step S31: Yes), the free recording capacity indicated by the received free recording capacity specifying information is associated with the node ID using the received node ID as a key. And stored in the log database 202a (step S32). If this is the first reception from the node Nn, the received IP address is also stored in association with it, and if it is the second or later reception, the stored free recording capacity is newly received. Update based on.

  On the other hand, when the free recording capacity specifying information is not received (step S31: No), the process proceeds to step S33.

  Next, it is determined whether or not transmission of the storage destination candidate list is requested from the content input server CS (step S33).

  As a result of the determination, when transmission of the storage destination candidate list is not requested (step S33: No), the process proceeds to step S30, and when transmission of the storage destination candidate list is requested (step S33: Yes). Then, among the node information registered in the log database 202a, node information having a larger free recording capacity is listed for the requested number to generate a storage destination candidate list (step S34). That is, when ten requests are made, a storage destination candidate list is generated that includes ten pieces of node information from node information having the largest available recording capacity to node information having the tenth largest available recording capacity. Then, the generated storage destination candidate list is transmitted to the content input server CS (step S35), the process proceeds to step S30, and the processes from step S30 to step S35 are repeated until the power is turned off.

  Then, when the power is turned off (step S30: Yes), the process is terminated.

[4-3. Processing of content input server CS]
FIG. 14 is a flowchart showing the processing of the control unit 301 in the content input server CS. For example, when a system administrator or the like operates the input unit 304 to instruct execution of the processing (or the communication unit 303 is changed). The storage instruction processing program of the present invention is read out and the processing is started (when information indicating that the processing is instructed is received from another device operated by the system administrator).

  First, the control unit 301 determines whether or not the power of the content input server CS has been turned off (step S40). If the power has not been turned off (step S40: No), a new content distribution storage system S is input. It is determined whether there is content to be processed (step S41).

  As a result of the determination, if there is no content to be input (step S41: No), the process proceeds to step S40. If there is content to be input (step S41: Yes), a node is determined based on the degree of popularity of the content. A storage destination candidate list is requested from the log collection server LS by designating the number of information (second predetermined number) (step S42).

  Subsequently, it is determined whether or not the storage destination candidate list has been acquired from the log collection server LS (step S43). If the storage destination candidate list has been acquired (step S43: Yes), a first predetermined number is obtained from the acquired storage destination candidate list. A node Nn (for example, one) is selected (step S44), and a storage destination candidate list is transmitted to the selected node Nn to instruct to store a replica of the content (save instruction information is transmitted) (step S45). .

  On the other hand, when the storage destination candidate list cannot be obtained from the log collection server LS (step S43: No), the control unit 303 generates a first predetermined number of node IDs (step S46), and the generated node IDs. A storage instruction message (storage instruction information) for instructing storage of a replica of the content is sent to the node Nn (step S47).

  Thereafter, after instructing storage in step S45 or step S47, the process proceeds to step S40, and the processes from step S40 to step S47 are repeated until the power is turned off.

  Then, when the power is turned off (step S40: Yes), the process is terminated.

[4-4. Main processing of node Nn]
FIG. 15 is a flowchart showing the main processing of the control unit 11 in an arbitrary node Nn participating in the content distributed storage system S, and after participation in the content distributed storage system S (for example, after access to a contact node). ), The storage instruction processing program and the node processing program of the present invention are read and the processing starts. In addition, when the above-described “4-1. Free recording capacity specifying information transmission process” is being executed, it is performed in parallel with the free recording capacity specifying information transmission process.

  First, the control unit 11 determines whether or not the power of the node Nn itself is turned off (step S60). If the power is not turned off (step S60: No), from the content input server CS or another node Nn. It is determined whether or not an instruction to store a content replica has been issued (step S61).

  As a result of the determination, if saving of the replica is instructed, it is determined whether or not the replica of the instructed content can be saved in its own storage unit 12 (step S62). Specifically, based on the free recording capacity of the storage unit 12 and the data capacity of the replica instructed to store, it can be determined whether or not the replica instructed to store can be stored. Compare the importance of the replica that has already been stored with the importance of the replica that has been instructed to save (for example, the higher popularity is given priority for storage). The existing replica may be deleted from the storage unit 12 to secure a free recording capacity.

  As a result of the determination, if it is possible to store the replica of the content instructed to be stored in its own storage unit 12 (step S62: Yes), the content replica and the storage are stored from the storage instruction source (the content input server CS or another node Nn). The destination candidate list is received (step S63), and a replica of the content is stored in its own storage unit 12 (step S64). The storage destination candidate list is stored in the storage unit 12.

  On the other hand, when it is not instructed to store the replica (step S61: No), and when it is not possible to store the instructed replica (step S62: No), the process proceeds to step S60.

  Then, after storing the replica (step S64), it functions as a storage instruction device (step S65), and instructs other nodes Nn to store the replica based on the node information of the storage destination candidate list.

  First, it is determined whether or not there is a storage destination candidate list in the storage unit 12 (step S66). If there is a storage destination candidate list (step S66: Yes), the storage destination candidate list is transmitted to the storage destination candidate for transmission. The list is divided into a list and a storage destination candidate list for storage (step S67). Specifically, a third predetermined number of node information is extracted from the storage destination candidate list stored in the storage unit 12 to generate a storage destination candidate list for transmission, and the storage destination candidate list stored in the storage unit 12 is Update to the save destination candidate list excluding the extracted node information.

  Next, a first predetermined number of nodes Nn are randomly selected from the storage destination candidate list (for storage) stored in the storage unit 12 (step S68), and the generated storage destination candidate list and contents are selected in the selected node Nn. The replica is transmitted, the replica is instructed (storing instruction information is transmitted), and the node Nn is deleted from the storage destination candidate list in the storage unit 12 (step S69).

  On the other hand, when there is no storage destination candidate list in the storage unit 12 (step S66: No), the control unit 11 generates a first predetermined number of node IDs (step S70), toward the node Nn of the generated node ID. Then, a storage instruction message (storage instruction information) for instructing storage of the content replica is transmitted (step S71).

  Then, the loop processing from step S66 to S69 is performed until the content replica publication date and time, and when the publication date and time is reached, the loop processing is terminated (step S72).

  Thereafter, the process proceeds to step S60, and when the power is turned off (step S60: Yes), the process is terminated.

  As described above, when a new content replica is inserted into the content distributed storage system S, the content input server CS (or the node Nn) includes the node Nn in which the recording unit 12 has a relatively large free recording capacity. Since the first predetermined number of nodes Nn are selected from the storage destination candidate list and the storage is instructed to the selected node Nn, the recording capacity of the recording unit 12 of each node Nn can be used effectively in a balanced manner. Can be realized.

  In addition, since the first predetermined number of nodes Nn are randomly selected in step S68, it is possible to prevent the storage instructions from being concentrated on the node Nn having the largest available recording capacity.

  In the above-described embodiment, the first predetermined number is “1” and one node Nn is selected from the storage destination candidate list. However, the present invention is not limited to this, and a plurality of nodes Nn are selected. May be. When a plurality of nodes Nn are selected (the first predetermined number is 2 or more), the storage destination candidate list is stored by itself (the first predetermined number) for transmission to each node Nn selected as the storage instruction destination. What is necessary is just to divide | segment into "the 1st predetermined number +1" which is the part (1) to do. For example, a storage destination candidate list in which 10,000 (second predetermined number) node information is posted is acquired, and 100 nodes Nn are selected as the first predetermined number from this storage destination candidate list to store replicas. It may be configured to indicate. The first predetermined number depends on the second predetermined number or the period until the release date and time (for example, if there is no time until the release date and time, the first predetermined number is increased and the number of replicas is transferred to a large number of nodes Nn as soon as possible. It may be changed as appropriate in consideration of, for example, completing pre-distribution.

  Further, when the content input server CS cannot select the first predetermined number of nodes Nn to be instructed to store, the first predetermined number of node IDs are generated as in steps S46 and S47, and the generated nodes Since the storage instruction message for instructing the storage of the replica is sent to the node Nn of the ID, even if the storage destination candidate list cannot be obtained from the log collection server LS, the node Nn in the content distributed storage system S The replica storage instruction can be reliably performed.

  Further, even when the node Nn cannot select the first predetermined number of nodes Nn to be instructed to store, the first predetermined number of node IDs are generated as in steps S70 and S71. Since the storage instruction message for instructing the storage of the replica is transmitted to the node Nn, the storage destination candidate list is displayed before the publication date and time by repeatedly dividing the storage destination candidate list in the storage instruction and the storage instruction. Even when the node information is lost and the first predetermined number of nodes Nn cannot be selected, it is possible to smoothly execute the replica storage instruction for other nodes Nn until the release date. Further, as another modification example in which each node Nn (and the content input server CS) cannot select the first predetermined number of nodes Nn to be instructed to save, the log collection server LS is accessed and the save destination candidate list is displayed. It may be configured to require. In this case, the log collection server LS may be requested and acquired for a storage destination candidate list on which at least the first predetermined number of node information is posted. According to this, each node Nn can acquire a storage destination candidate list including the latest node information.

  Further, when the node Nn that has received the save instruction issues a save instruction to another node Nn, the save destination candidate list generated by dividing its own save destination candidate list is stored as the save instruction destination node. Since it is configured to transmit to Nn, the node Nn that has received the storage instruction can also transmit a replica storage instruction based on the storage destination candidate list.

  In addition, the node Nn that has instructed the storage updates its own storage destination candidate list except for the node information of the generated transmission destination candidate list for transmission, and selects the node Nn based on the updated storage destination candidate list In addition, since the replica storage instruction is issued to the selected node Nn, the replica storage instruction process can be shared among the nodes Nn.

  Furthermore, since the node information of the node Nn instructed to store the replica is deleted from the storage destination candidate list stored in the storage unit 12, it is possible to prevent the replica instruction to store the replica to the same node Nn. Can do.

  Note that the node Nn may be configured to delete the node information of the node Nn from the storage destination candidate list after confirming that the replica can be reliably stored in the node Nn instructed to store the replica. In this case, the node Nn (storage instruction destination) that has received the storage instruction may be configured to notify the node Nn that is the storage instruction source of a storage completion report or the like after storing the replica. If the storage instruction source node Nn is not notified of the storage completion report from the storage instruction destination node Nn, the storage instruction source node Nn deletes the storage instruction destination node Nn from the storage destination candidate list and also stores the storage instruction destination node Nn. What is necessary is just to comprise so that the preservation | save instruction | indication message which instruct | indicates preservation | save of a replica may be sent toward node ID published in the node information of the node Nn. This message reaches a node Nn having a node ID close to the node ID, and the reached node Nn receives a replica storage instruction and stores the replica.

  Furthermore, when it is determined in step S62 that the replica of the content instructed to be stored cannot be stored, a storage instruction disabled report may be notified to the storage instruction source node Nn. Then, the storage instruction source node Nn that has received this may be configured to instruct the storage of the replica toward the node ID of the storage instruction source node Nn that has sent the notification, as described above.

  In addition, although the content distributed storage system S in the said embodiment was demonstrated on the assumption that it was formed by the algorithm using DHT, this invention is not limited to this.

It is a figure which shows an example of the connection aspect of each node apparatus in the content distributed storage system which concerns on this embodiment. It is a conceptual diagram which shows a mode that each node Nn transmits empty recording capacity specific information to the log collection server LS. It is a conceptual diagram which shows a mode that the content input server CS instruct | indicates the preservation | save of a replica to the node Nn. It is a block diagram which shows the example of a schematic structure of the node Nn. It is a block diagram which shows the example of an outline structure of the log collection server LS. It is an example of node information stored and saved in the log database 202a. It is a block diagram which shows the example of an outline structure of the content input server CS. It is explanatory drawing which concerns on the division | segmentation of a storage destination candidate list. It is a figure which shows the mode of the storage destination candidate list exchanged between the log collection server LS, the content input server CS, and the nodes N5 and N1. It is a figure which shows the mode of the preservation | save destination candidate list exchanged between node N1, N7, and N8. It is a figure which shows the mode of the preservation | save destination candidate list exchanged between node N5, N3, and N4. It is a flowchart which shows the free recording capacity specific information transmission process of the control part 11 in the node Nn. It is a flowchart which shows the process of the control part 201 in the log collection server LS. It is a flowchart which shows the process of the control part 301 in the content input server CS. It is a flowchart which shows the main process of the control part 11 in the node Nn.

Explanation of symbols

8 Network 9 P2P network (overlay network)
11, 201, 301 Control unit 12, 202, 302 Storage unit 13 Buffer memory 14 Decoder unit 15 Video processing unit 16 Display unit 17 Audio processing unit 18 Speaker 20, 203, 303 Communication unit 21, 204, 304 Input unit 22, 205 305 Bus S Content distributed storage system Nn Node LS Log collection server CS Content input server

Claims (8)

The node device in a content distributed storage system that stores a plurality of content data in a plurality of node devices that can communicate with each other via a network,
An acquisition means for acquiring a storage destination candidate list including node device identification information for identifying a node device that is a candidate for a storage destination of the content data, and content data to be stored;
Content storage means for storing the content data acquired by the acquisition means;
The storage destination candidate list acquired by the acquisition unit is used to select a first storage destination candidate list used to select another node device that stores the content data stored in the content storage unit, and to the other node device. A second storage destination candidate list to be transmitted, and a dividing means for dividing the list into two,
A selection unit that selects the node device identification information indicating a node device that stores the content data stored in the content storage unit from the first storage destination candidate list divided by the division unit;
Storage instruction information that instructs the node device identified by the node device identification information selected from the first storage destination candidate list by the selection unit to store the content data stored in the content storage unit Storage instruction means for transmitting the storage instruction information including the second storage destination candidate list divided by the dividing means, and the content data stored in the content storage means,
By the selection unit, a deleting means for deleting the node device identification information selected from among the first storage destination candidate list before Symbol first destination candidate list,
A node device comprising: The selecting means selects a first predetermined number of the node device identification information from the first storage destination candidate list divided by the dividing means,
The storage instruction unit is the storage instruction information that instructs the node device identified by the node device identification information selected by the selection unit to store the content data stored in the content storage unit. The node apparatus according to claim 1 , wherein storage instruction information including a second storage destination candidate list and the content data stored in the content storage unit are transmitted . Determining means for determining whether the first predetermined number of node device identification information can be selected;
When it is determined by the determination means that the selection is possible, the selection means selects the first predetermined number of the node device identification information,
Identification information generating means for generating the first predetermined number of node device identification information when the determination means determines that selection is impossible,
When the determination unit determines that the selection is impossible, the storage instruction unit is stored in the content storage unit in the node device identified by the node device identification information generated by the identification information generation unit. The storage instruction information for instructing the storage of the content data, the storage instruction information including the second storage destination candidate list, and the content data stored in the content storage unit are transmitted. The node device according to claim 2 . The selection unit repeatedly selects the node device identification information until the date and time when the content data stored in the content storage unit becomes available between the plurality of node devices,
The storage instructing means until said public time, in any one of claims 1 to 3, characterized in that repeated transmission of the content data stored in the storage instruction information and the content storage means The described node equipment. A storage instruction information receiving means for receiving storage instruction information transmitted from a storage instruction means of another node device;
When the storage instruction information is received by the storage instruction information receiving unit, the acquisition unit acquires the second storage destination candidate list and the content data;
When the storage instruction information is received by the storage instruction information receiving means, the content storage means stores the content data acquired by the acquisition means,
When the storage instruction information is received by the storage instruction information receiving unit, the dividing unit uses the content data stored in the content storage unit to store the second storage destination candidate list acquired by the acquisition unit. Is divided into a third storage destination candidate list used for selection of other node devices that store the content data, and a fourth storage destination candidate list that is transmitted to another node device that stores the content data,
When the storage instruction information is received by the storage instruction information receiving unit, the selection unit selects the node device identification information from the third storage destination candidate list divided by the division unit,
When the storage instruction information is received by the storage instruction information receiving unit, the storage instruction unit is divided by the dividing unit into the node device identified by the node device identification information selected by the selection unit. Transmitting the storage instruction information including the fourth storage destination candidate list and the content data stored in the content holding unit,
When the storage instruction information is received by the storage instruction information receiving unit, the deletion unit stores the node device identification information selected from the third storage destination candidate list by the selection unit. 5. The node device according to claim 1, wherein the node device is deleted from the candidate list . From the other node device that has transmitted the storage instruction information received by the storage instruction information receiving unit, a disclosure date and time when the content data stored in the content storage unit can be used among a plurality of the node devices. 6. The node device according to claim 5, further comprising a disclosure date / time information acquisition unit that acquires the disclosure date / time information to be indicated . A computer included in the node device in a distributed content storage system that stores a plurality of content data in a plurality of node devices that can communicate with each other via a network,
Obtaining a storage destination candidate list including node device identification information for identifying a node device as a storage destination candidate for the content data, and content data to be stored;
Storing the acquired content data in a content storage means;
A first storage destination candidate list used for selecting the other node device that stores the stored content data, and a second storage destination candidate list that is transmitted to the other node device. Dividing into, and
Selecting the node device identification information indicating a node device that stores the content data stored in the content storage unit from the divided first storage destination candidate list;
Storage instruction information that instructs the node device identified by the node device identification information selected from the first storage destination candidate list to store the content data stored in the content storage unit, and is divided. Transmitting the storage instruction information including the second storage destination candidate list and the content data stored in the content storage unit;
Deleting node device identification information selected from the first storage destination candidate list from the first storage destination candidate list;
A program characterized by having executed . A storage instruction method executed in the node device in a distributed content storage system that stores a plurality of content data in a plurality of node devices that can communicate with each other via a network ,
An acquisition step of acquiring a storage destination candidate list including node device identification information for identifying a node device as a storage destination candidate of the content data, and content data to be stored;
A content storage step of storing the content data acquired in the acquisition step in a content storage unit;
The storage destination candidate list acquired in the acquisition step is used to select a first storage destination candidate list used to select another node device that stores the content data stored in the content storage unit, and to the other node device. A second saving destination candidate list to be transmitted;
A selection step of selecting the node device identification information indicating a node device that stores the content data stored in the content storage unit from the first storage destination candidate list divided in the division step ;
Storage instruction information for instructing the node device identified by the node device identification information selected from the first storage destination candidate list to store the content data stored in the content storage means in the selection step. A storage instruction step of transmitting the storage instruction information including the second storage destination candidate list divided in the division step, and the content data stored in the content storage unit;
In the selection step, a deletion step of deleting the node device identification information selected from among the first storage destination candidate list before Symbol first destination candidate list,
Storage instruction method which comprises a.

Images