JP4170285B2 - Usage-oriented P2P grid computing system and computer program - Google Patents

Description

  The present invention relates to a usage-oriented P2P grid (Grid) computing system and a computer program that dynamically combine a plurality of computing resources scattered on a network to configure a virtual machine.

P2P (Peer to Peer) is a network mechanism in which individual computers exchange with each other without going through a server, and is mainly used for searching for file sharing.
There are two types of file search methods in P2P. One of them is a hybrid system (also called a Napster (registered trademark) system) that uses a server that manages only information centrally, inquires of the server, and then downloads a file entity. The other is a pure type system (also referred to as Gnutella (registered trademark) system) that performs search to download without using a server (see Non-Patent Document 1).
“Nikkei Network” March 2003, p. 120-p. 132

Since P2P is mainly intended for file sharing, search optimization is realized by a method in which replicas of files to be searched are provided at various locations.
In a method called share cast that shares streaming data, each time a streaming data file is transferred, the machine responsible for the transfer holds the replica.
Such a method is not efficient for the purpose of collecting computing resources of grid computing. In addition, P2P software called Winny (registered trademark) distributes metadata called search keys to widely disclose their existence, but this method can only make the first computer search more efficient. Subsequent searches have not been streamlined.

  Therefore, an object of the present invention is to provide a usage-oriented P2P type grid computing system and a computer program that enable efficient second and subsequent searches.

The utilization form-oriented P2P type grid computing system according to claim 1 is a utilization form oriented P2P type grid computing system in which a plurality of computing resources dispersed on a network are dynamically combined to form a virtual machine. The transmission computer includes a transmission target computer list holding means for holding a transmission target computer list that lists computers with an outgoing link that is a unidirectional logical link, and transmits each transmission link based on the transmission target computer list. A search request means for making a search request created by itself to a linked computer, and a computer that is newly discovered and used as a result of the search by referring to the transmission target computer list is registered in the transmission target computer list. Outgoing link re-linking means for re-setting outgoing links, and the outgoing link re-linking means A first replacement request means for making a first transfer link replacement request including the transmission target computer list with respect to the computer that is the target of the outgoing link, and the computer that is the target of the outgoing link, A first transfer target computer list holding means for holding a first transfer target computer list that lists computers with a transfer link that is a logical link, and a search request transmitted from a search source computer and transferred by another computer receiving said first through each transfer link based on the transfer target computer list, a first search request transferring means for transferring a search request received to the computer, the first transfer link received from the search source computer The computer included in the transmission target computer list included in the reassignment request is registered in the first transfer target computer list, and the transfer link is reconfigured. 1 and transfer link replacement means, second reconnection request means for performing a second transfer link reconnection request that does not contain the originating subject computer list to the computer as a target for tensioning the transfer link by said first transfer link replacement means, The computer to which the transfer link is extended includes a second transfer target computer list holding unit that holds a second transfer target computer list that lists the computers having the transfer link that is a logical link, and a search source A search request transmitted from a computer or a search request transmitted from a search source computer and transferred by another computer is received, and is sent to the computer via each transfer link based on the second transfer target computer list. A second search request transfer means for transferring the received search request; and a computer that is the transmission source of the second transfer link switching request. And a second transfer link switching means for registering in the machine list and transferring the transfer link.

  The utilization form-oriented P2P grid computing system according to claim 2, wherein the search source computer is currently stretched from a predetermined allowable number of outgoing links when the outgoing links are changed by the outgoing link changing means. Outgoing link number judging means for judging whether the number of outgoing outgoing links is small, and when the outgoing link number judging means judges that the currently outgoing outgoing link number is not smaller than the allowable outgoing link number, And further comprising: outgoing link deleting means for deleting at least one of outgoing outgoing links.

The utilization form-oriented P2P type grid computing system according to claim 3 , wherein the computer to which the outgoing link is to be extended is a predetermined first when the transfer link is changed by the first transfer link changing means. First transfer link number determination means for determining whether the number of currently transferred transfer links is smaller than the allowable transfer link number, and the first transfer link number determination means for determining whether the current transfer link number is extended from the first allowable transfer link number. And a first transfer link deleting means for deleting at least one of the currently established transfer links when it is determined that the number of transfer links is not small.

The utilization form-oriented P2P type grid computing system according to claim 4 , wherein the computer to which the transfer link is to be extended has a predetermined second when the transfer link is changed by the second transfer link changing means. Second transfer link number determination means for determining whether or not the number of transfer links currently extended is smaller than the number of allowable transfer links, and the current extension of the number of transfer links from the second allowable transfer link number by the second transfer link number determination means. And a second transfer link deleting means for deleting at least one of the currently established transfer links when it is determined that the number of transfer links is not small.

The computer program according to claim 5 is a computer program used for a computer in a usage-oriented P2P type grid computing system that dynamically combines a plurality of calculation resources scattered on a network to constitute a virtual machine, A search request step for making a search request created by itself to a computer having an outgoing link via each outgoing link based on a list of outgoing computers that lists the computers having outgoing links that are unidirectional logical links; and A transmission link replacement step for registering a computer newly discovered and used as a result of the search with reference to the transmission target computer list in the transmission target computer list to perform replacement of the transmission link , and transmission in the transmission link replacement step Sending to the computer that is the target of the link A reconnection request step for transferring link reconnection request including elephant computer list, characterized by causing the computer to execute.

The computer program according to claim 6 determines whether or not the number of outgoing links currently extended is smaller than a predetermined allowable outgoing link number when the outgoing link is changed in the outgoing link changing step. And outgoing link deletion that deletes at least one outgoing link when it is determined that the outgoing outgoing link number is not smaller than the allowable outgoing link number in the outgoing link number judging step And causing the computer to execute the steps.

The computer program according to claim 7 , in the search request step, performs a search request using a search key indicating a requirement regarding a static state or a dynamic state of a computing resource, and uses the search key as a result of the search request. A result receiving step of receiving a result notification from another computer satisfying the indicated requirements;

A computer program according to claim 8 is a computer program used for a computer in a usage-oriented P2P type grid computing system that dynamically combines a plurality of computing resources scattered on a network to constitute a virtual machine, a search request received from another computer, via a respective transfer links based on the transfer target computer list enumerating computer pitched forward link is a bidirectional logical links, further search request transfer to be transferred to another computer A transfer link transfer request received from another computer, and the computers listed in the transmission target computer list included in the received transfer link replacement request are registered in the transfer target computer list and transfer link replacement is performed. Transfer link replacement step for performing the transfer link By changing step, characterized in that to execute a reconnection request step for transferring link reconnection request to the computer as a target does not include the originating object computer list tensioning a transfer link, to a computer.

10. The computer program according to claim 9 , wherein when the transfer link is replaced in the transfer link replacement step, it is determined whether or not the number of transfer links currently extended is smaller than a predetermined allowable transfer link number. And a transfer link deletion that deletes at least one of the currently established transfer links when it is determined that the currently established transfer link number is not smaller than the allowable transfer link number in the transfer link number determining step. And causing the computer to execute the steps.

The computer program according to claim 10 , a computing resource collection step for collecting information indicating a static state or a dynamic state of its own computing resource, and a static state or a dynamic state of the computing resource indicated by the collected information A result notification step for returning a result notification when the state satisfies the requirements regarding the static state or the dynamic state of the computing resource indicated by the search key included in the search request; and a processing request corresponding to the result notification is received. And a calculation processing allocation step for performing the requested processing.

The computer program according to claim 11 is a computer program used for a computer in a usage-oriented P2P type grid computing system that dynamically combines a plurality of computing resources dispersed on a network to constitute a virtual machine, a search request received from another computer, via a respective transfer links based on the transfer target computer list enumerating computer pitched forward link is a bidirectional logical links, further search request transfer to be transferred to another computer Causing the computer to execute a step and a transfer link switching step of receiving the transfer link switching request, registering the computer that has transmitted the received transfer link switching request in the transfer target computer list, and transferring the transfer link. It is characterized by.

13. The computer program according to claim 12 , wherein when the transfer link is replaced in the transfer link replacement step, it is determined whether or not the number of transfer links currently extended is smaller than a predetermined allowable transfer link number. And a transfer link deletion that deletes at least one of the currently established transfer links when it is determined that the currently established transfer link number is not smaller than the allowable transfer link number in the transfer link number determining step. And causing the computer to execute the steps.

The computer program according to claim 13 is a computing resource collection step for collecting information indicating a static state or a dynamic state of its own computing resource, and a static state or a dynamic state of the computing resource indicated by the collected information. A result notification step for returning a result notification when the state satisfies the requirements regarding the static state or the dynamic state of the computing resource indicated by the search key included in the search request; and a processing request corresponding to the result notification is received. And a calculation processing allocation step for performing the requested processing.

  According to the present invention, in order to establish an outgoing link with a computer that has been discovered and used as a result of a computer search as a search source, a search request created by itself after the outgoing link is established is discovered and used as a result of a previous search in one hop. It is possible to propagate to a computer that has been set up, and it is possible to efficiently perform a search after setting up an outgoing link. In the invention of establishing a transfer link, for example, it is possible to propagate to a computer having a similar attribute with a small number of hops, and it is possible to efficiently perform a search after the transfer link is established.

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

<Establishing links in grid computing systems>
The usage-oriented P2P grid computing system in the present embodiment is configured using a pure P2P system such as Gnutella (registered trademark). Note that the names of computers (peers) constituting the usage form-oriented P2P-type grid computing system are properly used according to their positions.

  This embodiment considers the following items (temporal locality, spatial locality) and improves search efficiency by localizing computing resources that hit each client with high probability on the logical link space. It is something to be made.

  When we use computers, their purpose of use is relatively limited within a certain time range. For example, it is considered that a user who performs a certain numerical fluid calculation is likely to perform a numerical fluid calculation the same day using the same calculation resource. The same can be considered for the usage pattern-oriented P2P grid computing system of the present embodiment. That is, if a peer (client peer) discovers and uses computational resources via several hops, the computational resources once discovered and used are reused by the same peer (client peer) within a short time. The possibility is high. This is called the temporal locality of the user's usage characteristics.

The purpose of the client using the computer is highly correlated with the client attributes such as hobbies and occupations. For example, many engineering students often use spreadsheet applications to create reports, or users with an interest in CG (Computer Graphics) have an environment that allows them to calculate CG. Needing resources frequently. That is, it is considered that the user does not necessarily need all the computing resources existing on the network, but only a certain local computing resource group.
Note that a space formed from this group of computing resources is called a user's use space, and that space is local is called spatial locality.

  Hereinafter, reconfiguration of a logical link using the temporal locality in the usage-oriented P2P type grid computing system of the present embodiment will be described with reference to FIG. FIG. 1 is a diagram for explaining an outline of dynamic link reconfiguration using temporal locality in a usage-oriented P2P grid computing system.

FIG. 1 shows 1a to 1e as peers. In the state shown in FIG. 1A, it is assumed that a search is performed by the one peer 1a, and the peer 1d is found and used. Then, the peer (client peer) 1a that has performed the search holds the IP (Internet Protocol) address of the peer 1d as a list, and uses a logical link (hereinafter referred to as an outgoing link) with the peer 1d as the outgoing peer of the peer 1a. Tighten. This state is shown in FIG. Thereby, thereafter, the search request created by the peer (client peer) 1a is propagated from the peer 1a to the peer 1d in one hop, and the search efficiency is improved. However, although the outgoing link in FIG. 1B connects to a peer that hits with high probability for the peer (client peer) 1a, the peer 1a is the peer 1d that is the outgoing peer of the peer (client peer) 1a. Since it is not guaranteed that it is a computational resource that hits with high probability, a unidirectional link from peer 1a to peer 1d is used.
Note that if a new outgoing link exceeds a predetermined maximum allowable outgoing link number, a new outgoing link is established after deleting a peer outgoing link that has not been used most recently.

  Hereinafter, restructuring of a logical link using the spatial locality in the usage-oriented P2P type grid computing system of the present embodiment will be described with reference to FIG. FIG. 2 is a diagram for explaining an outline of dynamic link reconfiguration using spatial locality in the usage-oriented P2P grid computing system.

FIG. 2 shows 2a to 2j as peers. In the state of FIG. 2, it is assumed that a search is performed by the one peer 2a and the peers 2c, 2f, and 2j are found and used. Then, the peers 2c, 2f, and 2j acquire each other's IP address (details will be described later), and establish a logical link (hereinafter referred to as a transfer link). This state is shown in FIG. This transfer link is a bidirectional link when the link is established.
Note that when a new transfer link is established, the predetermined maximum allowable transfer link number is exceeded, a new transfer link is established after deleting the oldest link.

  Further, the formation of a cluster (usage space) having a loose relationship based on a chain of spatial locality will be described with reference to FIG. FIG. 3 is a diagram for explaining the formation of a cluster having a gradual relationship by a spatial locality chain. The arrows connecting the peers in FIG. 3 indicate transfer links.

FIG. 3 shows clusters 1A, 1B, and 1C as clusters. The clusters 1A, 1B, and 1C have different search source peers (client peers), and use the spatial locality described in FIG. Formed by restructuring the logical link.
In the example of FIG. 3, the cluster 1A includes peers 3a to 3g, the cluster 1B includes peers 3f to 3l, and the cluster 1C includes peers 3l to 3p. Each of the peers 3f and 3g is included in both the clusters 1A and 1B, and the peer 3l is included in both the clusters 1B and 1C. Depending on the peers included in a plurality of clusters and the presence of the transfer link extended to the peer, for example, the search request is changed from the peer forming only cluster 1A to the peer forming only cluster 1B, and from the peer forming cluster 1A to cluster 1C. It is possible to propagate with a small number of hops to the forming peer.

  For example, because the space between the cluster 1A and the cluster 1B overlaps, the user of the peer (client peer) that originated the cluster 1A and the user of the peer (client peer) that originated the cluster 1B Are considered to be users having common attributes such as the same hobby or the same occupation. For this reason, it is considered that the user of the cluster 1A is more likely to use the calculation resource existing in the cluster 1B than the calculation resource existing in a cluster other than the clusters 1A and 1B. From this, it can be said that the system of the present embodiment in which the search request is propagated from the cluster 1A to the cluster 1B with a small number of hops has improved the search efficiency.

  In addition, although the space between the cluster 1A and the cluster 1C does not directly overlap, the cluster 1A and the cluster 1C overlap each other with the cluster 1B. Is considered to be more likely to be used than a calculation resource existing in a cluster other than the clusters 1A, 1B, and 1C. From this, it can be said that the system of the present embodiment in which the search request is propagated from the cluster 1A to the cluster 1C with a small number of hops has improved the search efficiency.

  In the following, the procedure of the reconfiguration process of the logical link (outgoing link, transfer link) performed in the usage pattern oriented P2P type grid computing system in the present embodiment will be described with reference to the drawings.

  First, a processing procedure performed in a peer (client peer) will be described with reference to FIG. FIG. 4 is a flowchart showing the operation of the client peer. In addition, the replacement of the outgoing link is based on the idea of LRU (Least Recently Used), which is well known as a block replacement algorithm in the cache mechanism, and the logical link (outgoing link) of the least recently used peer is deleted. In the initial stage, when the outgoing link is not established with other peers, manually set up the peer that establishes the outgoing link, or broadcast the search request to establish the outgoing link with the peer that was discovered and used. To do.

  First, a peer (client peer) seeking a computing resource determines a search key and a search range (the number of hops), and sends a search request based on the search key to a peer connected by the outgoing link via the outgoing link. The result notification wait state is entered (step S101). The search request is sequentially transferred via the transfer link. Thereafter, the client peer receives a result notification from the hit resource peer (step S102). Then, it is determined whether or not the search is performed again (step S103). When the search is performed again (S103: YES), the process returns to step S101, and the processes of steps S101 to S103 are repeated. On the other hand, when the search is not performed again (S103: NO), the process proceeds to step S104. In the client peer, the user selects a calculation resource to be used by using the result notification (step S104).

  The client peer determines whether the current outgoing link count Dcurrent is less than the preset allowable outgoing link count Dmax (step S105). If the current outgoing link count Dcurrent is not less than the allowable outgoing link count Dmax (S105: NO), the outgoing link of the least recently used peer is deleted (step S106), and the process proceeds to step S107. This is to prevent the network load from becoming excessively large by deleting outgoing links that are set to peers that are not frequently used. On the other hand, if the current outgoing link count Dcurrent is less than the allowable outgoing link count Dmax (S105: YES), the process proceeds to step S107.

  The client peer registers the IP address of the resource peer that is newly hit and used in the search in the outgoing peer ID list (sender target computer list), and establishes the outgoing link with the resource peer (step S107). Subsequently, the client peer makes a transfer link replacement request (first transfer list replacement request) including the outgoing peer ID list to the resource peer that is newly hit and used in the search (step S108). Thereafter, the client peer executes the job using the computing resource of the resource peer.

Next, a processing procedure performed in the resource peer will be described with reference to FIGS. 5 to 8 are flowcharts showing the operation of the resource peer.
As shown in FIG. 5, the resource peer is waiting for a connection request from another peer (step S201), and receives request data from the other peer (step S202). It is determined whether or not the received request data is a transfer link replacement request (step S203). If it is not a transfer link replacement request (S203: NO), a resource search process (see FIG. 6) is executed (step S204). On the other hand, if it is a transfer link replacement request (S204: YES), the process proceeds to step S205.

  The client peer determines whether or not the outgoing peer ID list is included in the transfer link switching request (step S205). If the calling peer ID list is included (S205: YES), the first transfer link reassignment process (see FIG. 7) is executed (step S206). On the other hand, if the calling peer ID list is not included (S205: NO), the second transfer link reassignment process (see FIG. 8) is executed (step S207).

In the resource search process (S204), as shown in FIG. 6, it is determined whether it is necessary to transfer the received search request (step S301). If transfer is necessary (S301: YES), the search request is transferred via the transmission link and the transfer link with reference to the transmission peer ID list and the transfer peer ID list (step S302), and the process proceeds to step S303. On the other hand, if it is not necessary to transfer (S301: NO), the process proceeds to step S303.
Based on the search key included in the search request, the client peer determines whether it hits the search (contents match) (step S303). If the contents do not match (S303: NO), the process returns to waiting for a connection request (step S201 in FIG. 5). On the other hand, if the contents match (S303: YES), the process proceeds to the process of step S304, the result is notified to the search source client peer (eg, that the search hits itself) (step S304), and a connection request is waited (FIG. 5). Return to step S201).

  The first transfer link transfer process (S206) is a case where a transfer link transfer request is received from the client peer, and as shown in FIG. 7, the resource peer has an allowable transfer link number Fmax preset by the current transfer link number Current. It is judged whether it is less than (step S401). If the current transfer link number Current is not less than the allowable transfer link number Fmax (S401: NO), the oldest transfer link for transfer link construction is deleted (step S402), and the process proceeds to step S403. This is to prevent the load on the network from becoming too large by preventing the number of transfer links from increasing. On the other hand, when the current transfer link number Current is less than the allowable transfer link number Fmax (S401: YES), the process proceeds to step S403.

  The resource peer refers to the outgoing peer ID list included in the transfer link reassignment request and registers the IP addresses of peers included in the peer that do not have the transfer link in the transfer peer ID list (first transfer target computer list). Then, a transfer link is established with the peer (step S403). Subsequently, the resource peer makes a transfer link replacement request (second transfer link replacement request) to the peer that has newly constructed the transfer link (step S404), and returns to the connection request wait (step S201 in FIG. 5). However, unlike the transfer link switching request made by the client peer, this transfer link switching request does not include the outgoing peer ID list.

  The second transfer link transfer process (S207) is a case where a transfer link transfer request is received from a resource peer newly discovered and used by a client peer. As shown in FIG. It is determined whether the Current is less than the preset allowable transfer link number Fmax (step S501). If the current transfer link number Current is not less than the allowable transfer link number Fmax (S501: NO), the oldest transfer link of the transfer link construction is deleted (step S502), and the process proceeds to step S503. This is to prevent the load on the network from becoming too large by preventing the number of transfer links from increasing. On the other hand, when the current transfer link number Current is less than the allowable transfer link number Fmax (S501: YES), the process proceeds to step S503.

  The resource peer registers the IP address of the source peer of the received transfer link reconfiguration request in the transfer peer ID list (second transfer target computer list), and establishes the transfer link with the source peer of the transfer link reconfiguration request. Construction is performed (step S503), and the process returns to the connection request wait (step S201 in FIG. 5).

Hereinafter, the function of the peer necessary for realizing the above-described processing will be described with reference to FIG. FIG. 9 is a functional block diagram for explaining the function of the peer.
The peer includes each unit that functions as a client processing unit 10 that performs various processes when operating as a client peer and a resource processing unit 20 that performs various processes when operating as a resource peer.

The client processing unit 10 includes a transmission peer ID list holding unit 10a, a search request processing unit 10b, a transmission link number determination unit 10c, a transmission link deletion unit 10d, a transmission link reconfiguration unit 10e, and a transfer link reconfiguration request unit 10f. It has each part which functions as.
The calling peer ID list holding unit 10a holds a calling peer ID list in which IP addresses of peers to which each outgoing link is connected are listed.
The search request processing unit 10b creates a search request including the search key and the number of hops, and transmits the created search request to the peer with the outgoing link via the outgoing link with reference to the outgoing peer ID list. The result notification is received from the resource peer (steps S101, S102, S103). The search request processing unit 10b also determines whether to perform a search again (step S104).

The outgoing link number determination unit 10c determines whether the current outgoing link number Dcurrent is less than the allowable outgoing link number Dmax (step S105).
The outgoing link deleting unit 10d deletes one outgoing link when the current outgoing link number Dcurrent is not less than the allowable outgoing link number Dmax (step S106).
The outgoing link switching unit 10e registers the IP address of the peer that is newly discovered and used as a result of the search using the result notification or the like in the outgoing peer ID list and establishes the outgoing link with the peer (step S107). .

  The transfer link switching request unit 10f makes a transfer link switching request including the calling peer ID list to the peer newly setting the calling link (step S108).

The resource processing unit 20 includes a request data determination unit 21, a resource search processing unit 22 (step S204), a transfer peer ID list holding unit 23, a first transfer link reassignment processing unit 24 (step S206), and a second transfer. Each unit functions as the link replacement processing unit 25 (step S207).
The request data determination unit 21 receives request data from another peer, determines whether it is a search request or a transfer link reconfiguration request, and further determines whether the transfer link reconfiguration request includes an outgoing peer ID list ( Steps S202 and S203).
The resource search processing unit 22 functions as a transfer processing unit 22a that transfers a search request to a peer that needs to be transferred (steps S301 and S302) and a search processing unit 22b that performs a search process (steps S303 and S304). It has each part.
The transfer peer ID list holding unit 23 holds a transfer peer ID list (first and second transfer target computer list) in which IP addresses of peers connected to each transfer link are listed. The IP addresses are registered so that the order of registration is known.

The first transfer link replacement processing unit 24 includes units that function as a transfer link number determination unit 24a, a transfer link deletion unit 24b, a transfer link replacement unit 24c, and a transfer link replacement request unit 24d.
The transfer link number determination unit 24a determines whether or not the current transfer link number Current is less than the allowable transfer link number Fmax (step S401).
The transfer link deleting unit 24b deletes one of the transfer links when the current transfer link number Current is not less than the allowable transfer link number Fmax (step S402).
The transfer link switching unit 24c refers to the outgoing peer ID list included in the transfer link switching request, registers the IP address of the new transfer destination peer in the transfer peer ID list, and transfers the transfer link with the peer. (Step S403).
The transfer link switching request unit 24d makes a transfer link switching request to the peer that has newly set the transfer link (step S404).

The second transfer link replacement processing unit 25 includes units that function as a transfer link number determination unit 25a, a transfer link deletion unit 25b, and a transfer link replacement unit 25c.
The transfer link number determination unit 25a determines whether the current transfer link number Current is less than the allowable transfer link number Fmax (step S501).
The transfer link deleting unit 25b deletes one of the transfer links when the current transfer link number Current is not less than the allowable transfer link number Fmax (step S502).
The transfer link switching unit 25c registers the IP address of the source peer of the transfer link switching request in the transfer peer ID list, and sets up a transfer link with the peer (step S503).

Hereinafter, a flow of request data for a search request in a state where an outgoing link and a forward link are extended in consideration of temporal locality and spatial locality will be described with reference to FIG. FIG. 10 is a diagram for explaining the flow of request data for a search request. However, peers A to I are shown in FIG. 10, and the current outgoing link and transfer link states are shown. Note that a one-way arrow between peers indicates an outgoing link, and a two-way arrow indicates a transfer link.
The request data for the search request is created by the peer A, and the request data is sent out. Each of the peers B, C, and F receives the transmitted request data and registers the request data.
Peer B forwards the received request data to peers E and I, peer C forwards the received request data to peers D and F, and peer F forwards the received request data to peers C, E, H, and G. Since the peer F has already received the request data received from the peer C, the peer F discards the request data. Since peer C has already received the request data received from peer F, it discards the request data. Then, the peers D, E, G, H, and I that have received the request data for the first time register the received request data.
By repeating this, the request data is propagated one after another.

  As described above, according to the present embodiment, the outgoing link is set in consideration of the temporal locality described above, and the transfer link is extended in consideration of the spatial locality described above. After the link or the transfer link is established, there is an advantage that the search efficiency is improved.

Although the preferred embodiments of the present invention have been described above, the present invention is not limited to the above-described embodiments, and various design changes can be made within the scope described in the claims. is there.
For example, in the above-described embodiment, only the IP address of the peer to which request data is next sent is held. However, the present invention is not limited to this. The IP address of the next peer may be held. In this case, there is an advantage that fault tolerance can be improved.
A mechanism for realizing this will be described with reference to FIG. FIG. 11 is a diagram for explaining a mechanism for holding the IP addresses of two peers (candidates). However, FIG. 11 corresponds to the state of FIG. Only peer A shows candidates one after another.
Here, pay attention to peer A. Peer A transmits a search request to peers B, C, and F of the next candidate (one peer ahead). The peers B, C, and F that have received this transmit the next candidates to the peer A, respectively.
When peer A receives the next candidate from peer B, it registers it as a candidate for peer B one after another.
When Peer A receives the next candidate from Peer C, it excludes itself (Peer A) and Peer F in its next candidate among the peers included in the next candidate received from Peer C, and the remaining peers are related to Peer C. Register as candidates one after another.
When the peer A receives the next candidate from the peer F, the peer A registers the remaining peers as candidates for the peer F one after another, except for the peer C included in the next candidate received from the peer F.

  It should be noted that a program for realizing the functions of each processing unit described above is recorded on a computer-readable recording medium, the program recorded on the recording medium is read into a computer system, and executed to execute the above-described various processes. You may go. The “computer system” here includes an OS and hardware such as peripheral devices. The “computer system” includes a WWW system having a homepage providing environment (or display environment). The “computer-readable recording medium” refers to a portable medium such as a flexible disk, a magneto-optical disk, a ROM, and a CD-ROM, and a storage device such as a hard disk built in the computer system. Further, the “computer-readable recording medium” refers to a volatile memory (RAM) in a computer system that becomes a server or a client when a program is transmitted via a network such as the Internet or a communication line such as a telephone line. In addition, those holding programs for a certain period of time are also included.

  The program may be transmitted from a computer system storing the program in a storage device or the like to another computer system via a transmission medium or by a transmission wave in the transmission medium. Here, the “transmission medium” for transmitting the program refers to a medium having a function of transmitting information, such as a network (communication network) such as the Internet or a communication line (communication line) such as a telephone line. The program may be for realizing a part of the functions described above. Furthermore, what can implement | achieve the function mentioned above in combination with the program already recorded on the computer system, and what is called a difference file (difference program) may be sufficient.

<Exchange of state information of computing resources in grid computing system: Application usage example when using semantic information network SIONet (Semantic Information Oriented Network)>
Next, an example of a method for searching for information on computing resources in a grid computing system using a semantic information network as a P2P network will be described. In this semantic information network, transmission of the information is controlled based on the meaning of the information, and for this purpose, a search using the semantic information is performed. As a specific example, a semantic information network called SIONet is used. SIONet is the name of an existing P2P system, and SIONet itself will be described later in the section “Supplemental explanation about SIONet”.

  In this way, a plurality of computing resources exchange their own state information using the semantic information network as a communication means, and based on this, the computing resources having a desired state are searched and obtained as a result of the search (several). A virtual computer (grid computing) is realized by distributing and coordinating work (processing) to computing resources. For this reason, the following functions are expanded or added in order to retrieve information on the status of computing resources through the semantic information network.

First, the computational resource search method is expanded from simple file name mapping to a computational resource search method “based on semantic information”. By using this method, it is possible to search not only the CPU load status but also the status of other calculation resources such as the network load and the types of applications that can be executed in the collection parameter search range of the calculation resource search.
Second, using a community concept in a P2P (Peer to Peer) system, a group of computing resources is statically constructed as a community, and is divided based on policies such as available applications and security levels. By using a P2P system that can control information search across communities, unnecessary traffic can be reduced and efficient search can be performed as compared with conventional search by broadcast.

Thirdly, by managing the participation and withdrawal of computing resources using the community participation authentication function in the P2P system, it becomes possible to widely recruit computing resources from general users' PCs and the like.
Fourthly, by constructing a portal site based on HTTP (HyperText Transfer Protocol) and using it as a reception window for grid calculation processing from the user, it is possible to easily implement grid computing for general users.

Hereinafter, an example in which a system is constructed using SIONet having a function of easily realizing community management and construction among P2P technologies will be described with reference to the drawings.
FIG. 12 is a diagram for explaining the exchange of state information of computing resources in a grid computing system using a semantic information network, and FIG. 13 is provided in each component of the grid computing system shown in FIG. It is a figure for demonstrating a function. As shown in FIG. 12, the grid computing system includes computing resources 101 to 113, a portal site 120, and a request source computer (user terminal) 130.

  SIONet software and grid middleware software are installed in the computational resources 101 to 113 which are SIONet entities, and these software are started. In SIONet, a terminal (calculation resource) that starts SIONet software is referred to as a SIONet entity (also simply referred to as “entity”).

The computing resource activated as an entity constitutes a community for grid calculation (corresponding to the above-described cluster) using the SIONet community creation and participation function (herein, in SIONet, a general community is referred to as an event place). ). The event place is semantic information that is a function of SIONet by dynamically or statically “semantic information” of the state of the computational resource and network characteristics (described later) by grid middleware installed in each computational resource. Register regularly with filters (also called simply “filters”).
The contents registered in the semantic information filter of each computing resource include, for the computing resource status, IP address / system administrator name / OS version / CPU load / applicable application / architecture type / memory capacity, etc. . As for network characteristics, there are bandwidth / latency / protocol and the like.

  The computing resource activated as an entity responds (fires) to an inquiry (stimulation) from the portal site when the condition is satisfied.

  FIG. 14 is a diagram showing a software structure in the above-described calculation resource. The calculation resource (entity) 200 functions as a SIONet entity, and the software structure of the calculation resource 200 includes various OSs 201 (Windows). (Registered trademark) and UNIX (registered trademark)), communication middleware 202 (SOAP (Simple Object Access Protocol), etc.), P2P-PF (platform) 203, SIONet API (Application Program Interface) 204, P2P It has a hierarchical structure composed of middleware 211.

  Further, the P2P middleware 211 is equipped with a discovery engine controller 212 for executing a network service based on semantic information, and includes a calculation processing resource collection function 213, a calculation processing allocation function 214, and a PF (platform) linkage function. 215 and the like are provided. The calculation resource collection function 213 has a function of registering state information as a calculation resource of the own terminal and network state information in a semantic information filter. Examples of the calculation resource state information include an IP address, system management, and the like. Name, OS / version, CPU load, application, architecture type, memory, etc. are registered, and bandwidth, latency, protocol, etc. are registered as network status information. The PF (platform) cooperation function 215 includes an authentication PF, a copyright protection PF, a charging PF, and the like.

The portal site 120 is a portal site for grid computing, and has a function of accepting a grid computing processing request from the requesting computer (user terminal) 130 and constructing a virtual machine.
The portal site 120 installs SIONet software and grid middleware software, and operates as a SIONet entity. In addition, a Web service function and a virtual machine function are constructed in the upper layer.
The virtual machine management function of the portal site 120 is performed by a VMM (Virtual Machine Manager). The Web service function is a function that accepts grid computing processing from the user (requesting computer), and provides parameters for configuring various virtual machines as menus in response to requests from the user.
The virtual machine function is a function that divides a process given in response to a calculation request from a user into a plurality of parts and manages the progress and result of the process allocated to each calculation resource. The configuration of the virtual machine is determined individually according to the content of the processing request from the user.

  In addition, the portal site 120 extracts the calculation processing request from the user as “semantic information” in order to efficiently search for the calculation resource that actually configures the virtual machine according to the request from the user, and the meaning of SIONet. Search (stimulate) using the information search function. Multiple portal sites will be installed to improve reliability. A user accesses a portal site by a specified URL (Uniform Resource Locator), but by the DNS function, one portal site address is selected from a plurality of portal site addresses by round robin, and the portal site having the address is accessed. A connection is made. As a result, load distribution of the portal site is realized.

  FIG. 15 is a diagram showing the software structure in the portal site described above. The calculation resource (grid calculation processing resource) 300 functions as a SIONet entity. The software structure of the portal site 300 is as follows. Based on various OS 301 (Windows (registered trademark), UNIX (registered trademark), etc.), communication middleware 302 (SOAP, etc.), P2P-PF (platform) 303, SIONet API (Application Program Interface) 304, P2P middleware 311 and P2POPen API 316 have a hierarchical structure.

  The P2P middleware 311 is equipped with a discovery engine controller 312 for executing a network service based on semantic information, and includes a calculation processing resource collection function 313, a calculation processing allocation function 314, and a PF (platform) linkage function. 315 and the like are provided, which have functions of converting user requests into semantic information and searching (stimulating), selecting discovered calculation resources, and requesting calculation processing. In addition, when a Web service function 317, a grid VM manager 318, a grid VM synthesizer 319, a compiler 320, and the like are provided, and a calculation request from a user can be received by HTTP and the processing contents can be divided, Divide and aggregate results if divided. The PF (platform) cooperation function 315 includes an authentication PF, a copyright protection PF, a charging PF, and the like.

  The request source computer (user terminal) 130 is a user terminal that requests the grid computing system to perform calculation processing. Connect to the portal site 120 via HTTP through a browser and make a grid computing calculation processing request. Since the calculation process itself is performed in the grid (in the network), it is only a requirement that the browser is installed regardless of the terminal specifications. A calculation processing request by the request source computer (user terminal) 130 is implemented by selecting parameters (for example, application, calculation processing, processing fee, etc.) using a menu provided by the portal site 120.

The configuration and characteristics of the grid computing system using SIONet described above will be summarized below.
In the grid computing system, middleware for a grid computing resource collection function is constructed on the P2P (SIONEt) API of an entity that is a component of the system. By using the “semantic information search function” realized by the middleware on SIONet, it is possible to construct an optimal virtual machine in response to a calculation processing request from a requesting computer requesting a calculation processing request. Computation resources can be discovered immediately and efficiently.

  The computing resource and the portal site are both SIENet entities, and the computing resource registers the state of its own terminal as semantic information in a filter statically and dynamically. The contents registered as semantic information in the middleware for the grid resource collection function are calculation resource information and network characteristic information. The contents converted into semantic information as the computing resource information include IP address, system administrator name, OS and version, CPU load, executable application, architecture type, memory capacity (total capacity and free capacity), hard disk capacity ( Total capacity and free capacity). Further, the contents converted into semantic information as network characteristics include network load / bandwidth / latency / protocol and the like.

With the above-mentioned mechanism, it has more search parameters than the previous system, and the contents indicate the latest and optimal information of the calculation resources, so the optimal calculation resources can be collected efficiently. Can do.
In addition, since the computing resource that becomes the entity of SIONet is used as a grid computing resource, it is necessary to create a community (event place) that is a static aggregate in advance and be a member of the community. . The calculation resource is statically included in the event place, and the state of the terminal is stored in the semantic information filter, so the portal site performs a search based on the semantic information and allocates the optimal calculation resource to the extra traffic. It is possible to collect effectively without increasing the directory and without the need for a directory.
Furthermore, by using an input / output management function for an event place using an authentication function, management of registration / deletion of computing resources can be performed. Accordingly, the computing resource can be used not only for specially prepared resources but also for an unspecified number of terminals used by general users.

In addition, the event place has a function of automatically connecting the two adjacent entities and continuing the connection even when the entity constituting the event place goes down for some reason. Therefore, by using this event place, even if the computational resource goes down for some reason, only that terminal (computational resource) will leave the event place and will not affect the entire system.
Furthermore, by using an event place, it is possible to construct a community (event place) according to the application and the security level, and it is possible to give diversity to the system.

The portal site accepts a processing request from a requesting computer (user terminal), converts a computing resource for configuring a virtual machine that satisfies the request as semantic information, and uses the SIONet function based on the semantic information. (The portal site needs to participate in the same event place as the calculation resource in advance in order to perform semantic information search by SIONet).
In computing resource search from the portal site, the processing status of computing resources (for example, CPU usage rate, processing acceptance status based on statistical information based on network (NW) usage rate, memory capacity, free hard disk capacity), etc. Given that parameter, search for the optimal computational resource (stimulus).

  A plurality of portal sites that accept calculation processing requests from a requesting computer (user terminal) are deployed in order to continue the service even in the event of a failure (improvement of reliability). The DNS function is used to determine which portal site the user selects. That is, the user accesses the portal site using the URL, but a plurality of registered IP addresses are responded by round robin, thereby distributing the load and improving the fault tolerance.

  The portal site realizes processing acceptance by HTTP in order to reduce the requesting computer (user terminal) that requests grid computing calculation processing, and realizes versatility accessible from a browser.

  The configuration and characteristics of the grid computing system that exchanges the status information of the computing resources using the semantic information network has been described above. A more specific example will be described below.

  FIG. 16 is a diagram for explaining a configuration example of the SIONet network, and shows an example in which the event place is divided into a plurality according to the application and the degree of security. In the example shown in FIG. 16, four event places A to D are included in the network.

  The portal sites 401 to 403 exist across all existing event places A to D. The portal site that has received a request for grid computing processing from the requester computer (user terminal) 410 divides the processing as necessary, determines necessary computing resources, and searches them based on semantic information. Here, since the semantic information search does not spread to the event place having information not related to the calculation resource requested by the portal site, the search traffic can be deleted.

  The detailed processing image of each entity will be described with reference to FIGS. 17 and 18. Here, in order to simplify the explanation, an example of processing in one event place is shown. The example shown in FIGS. 17 and 18 is a system in a case where an event place is formed by one portal site 501 and six computing resources R1 to R6, and a request source computer (user terminal) 510 on the left end has a system. The example is based on the premise that processing is requested to this grid system.

  FIG. 17 is a diagram illustrating an example of a sequence representing a processing image. FIG. 18 is a diagram showing an example of semantic information. The portal site 501 that has received a processing request from the requesting computer 510 searches for the computing resources R1 to R6 in order to construct a virtual machine, and each of the conditions at that time. The states of the computational resources R1 to R6 are shown. These states of the calculation resources R1 to R6 are registered in the filters F1 to F6 as semantic information.

First, preprocessing in the calculation resources R1 to R6 and the portal site will be described.
First, the individual calculation resources R1 to R6 are activated as SIONet entities, and the middleware for grid resource search / collection is activated at the upper level. This middleware dynamically or statically registers the load status of computing resources, the name of an application that can be executed, and the like as semantic information in the filters S1 to F6 of SIONet. The individual computing resources R1 to R6 that have become SIONet entities statically configure one event place (grid event place). Here, it is assumed that the event place is formed with the configuration shown in FIGS. 17 and 18.
The portal site 501 is also a SIONet entity and is a member of the same grid event place as the computing resource group. The portal site 501 here is assumed to be located at the place shown in the figure on the event place.

Hereinafter, with reference to FIG. 17, a processing image is described in order. The calculation resources R1, R4 and R6 satisfy the condition (requirement information), and the other calculation resources R2, R3 and R5 do not satisfy the condition.
First, the requesting computer 510, which is a grid user requesting calculation processing, finds the nearest portal site by using the DNS function (URL → IP address conversion function), and executes the request for grid calculation processing using a Web browser. . At this time, the parameters for configuring the virtual machine, such as the application to be executed, the security level, and the turnaround time, are specified. The parameter is specified using a pull-down menu set in advance in the portal site 501 (step S1).

The portal site 501 that has received the calculation process divides the tasks that can be processed in parallel according to the calculation process request content. Further, calculation resources necessary for constructing a virtual machine for performing calculation processing are calculated based on parameters received from the request source computer (user terminal) 510. These functions are implemented by a VMM (Virtual Machine Manager). Furthermore, semantic information as a search key for collecting these necessary calculation resources is determined (process A: step S2).
In the portal site 501, in order to find the optimal calculation resource, the search by the SIONet function is started using the semantic information determined in the process A, and a “search message by semantic information” is transmitted to the calculation resource R 1 (stimulus (Step S3).

The calculation resource R1 transfers the “search message based on semantic information” received from the portal site 501 to the next calculation resource R2 connected at the event place (transfers the stimulus) (step S4).
Further, the calculation resource R1 stimulated by the portal site 501 is “ignited” by the SIONet function (ignition A) because the content of the filter F1 satisfies the conditions for the stimulation of the portal site. The information that the fire has occurred is returned to the portal site 501 together with the firing condition by the calculation resource R1. The ignition conditions are as follows. CPU = Pent * u * 1.5 GHz, CPU usage rate = 20%, OS = W * n200 *, application = P * v-Ra *, memory = 128 MB, HD = 20 GB, NW = 100 Mbps, NW usage rate = 30 % (Step S5).

  The calculation resource R2 transfers the received “search message based on semantic information” as it is to the next calculation resource R3 and the calculation resource R4 connected at the event place (stimulus is transferred) (step S6). Note that since the calculation resource R2 has two connection destinations in the event place, the stimulus is transferred to the two calculation resources R3 and R4. The computation resource R2 itself does not ignite and therefore does nothing because the content of the filter F2 does not satisfy the requirements for the received stimulus. The calculation resource R3 that has received the stimulus from the calculation resource R2 does not transfer the stimulus because there is no calculation resource connected to the event place, and the information of the filter F3 does not satisfy the requirement for the stimulus. There is no fire and nothing is done.

The calculation resource R4 that receives the stimulus from the calculation resource R2 transfers the received “search message based on semantic information” to the next calculation resource R5 and the calculation resource R6 connected at the event place as they are (transfers the stimulus). (Step S7). Since the calculation resource R4 has two connection destinations in the event place, the calculation resource R4 transfers the stimulus to two places.
In addition, the calculation resource R5 and the calculation resource R6 that have received the stimulus from the calculation resource R4 do not transfer the stimulus because there is no calculation resource connected to the event place ahead of the calculation resource R4. Since some information of F5 does not satisfy the requirement for stimulation, it does not ignite and does nothing.
Further, since the content of the filter F4 satisfies the condition for the received stimulus, the calculation resource R4 “fires” by the SIONet function. The ignition conditions are as follows. CPU = Pent * u * 850 MHz, CPU usage rate = 30%, OS = W * n200 *, application = P * v-Ra *, memory = 64 MB, HD = 8 GB, NW = 10 Mbps, NW usage rate = 25% Yes (ignition B). Information that it has ignited is returned to the portal site 501 by P2P together with the igniting condition by the computing resource R4 (step S8).
Further, since the content of the filter F6 satisfies the condition for the received stimulus, the calculation resource R6 is “fired” by the SIONet function. The ignition conditions are as follows. CPU = Pent * u * 1.7 GHz, CPU usage rate = 20%, OS = W * n200 *, application = P * v-Ra *, memory = 256 MB, HD = 100 GB, NW = 10 Mbps, NW usage rate = 15 % (Ignition C). Information that it has ignited is returned to the portal site 501 by P2P together with the igniting condition by the calculation resource R6.

The portal site 501 receives and confirms the firing response from the computing resource (this time, three responses from the computing resources R1, R4, and R6 (there are steps S5, S8, and S9)), and based on the response firing conditions. Determine the optimal computing resource. Here, since it is determined that the number of calculation resources that require the VMM is “two”, the optimal calculation resources are narrowed down to the top two from the firing conditions, and are determined as the calculation resources R1 and R6. Since the response time is set as the priority content this time, the CPU specifications, usage rate, and memory capacity are the criteria for selecting the calculation resources R1 and R6 (Process B: Step S10).
The portal site 501 allocates the calculation process to the calculation resource R1 and the calculation resource R6 based on the determination result of the process B (step S11). This allocation is performed directly by P2P in “between portal site = computation resource R1” and “between portal site = computation resource R6”.

Then, the calculation resource R1 executes the calculation process assigned to the calculation resource R1 in the process B (process C), and the process result is returned (returned) to the portal site (step S12).
This response is performed by P2P directly between the portal site = the computing resource R1.
In addition, the calculation process assigned to the calculation resource R6 in the process B is executed by the calculation resource R6 (process D), and the process result is returned (returned) to the portal site 501 (step S13). This response is performed by P2P directly between the portal site = the computing resource R6.
Thereafter, in the portal site 501, the entire processing results are integrated based on the processing results of the processing resource R1 and the processing resource R6 (processing E: step S14). Further, the portal site reports the processing result of processing D to the requesting computer 510 (step S15).

  The calculation resource R4 ignites and responds, but since there is no calculation processing request from the portal site 501, a transition is made to the initial state due to timeout (process F: step S16).

The grid computing system that exchanges the status information of the computing resources using the semantic information network has been described above. However, by constructing the semantic information network and collecting the optimal computing resources based on the semantic information, a directoryless merit is achieved. This makes it possible to diversify the search conditions for collecting computing resources of the grid computing system.
In addition, it is possible to update the status information (not only the CPU load, but also various information) of computing resources on demand, so that optimal computing resources can be found in real time and the performance of the grid computing system can be improved. it can.

  In addition, the directory-less system reduces dynamic information exchange and lookup procedures between computing resources and directories, leading to a reduction in extra traffic. In addition, by using a transfer function based on semantic information and an event place, broadcast search can be improved and traffic volume can be further reduced.

  In addition, it becomes possible to divide event places according to applications for processing computing resources and the degree of security, so that the system can be diversified and service variations can be increased. In addition, even in the event of an individual failure of a computing resource, the service can be continued without affecting the entire system. Furthermore, in addition to dedicated computing resources, terminals used by general users can be used as computing resources, contributing to the globalization of grid computing systems.

Next, an example in which the status information of the computing resource is exchanged between the requesting computer as the client peer and the computing resource as the resource peer will be described.
Here, a grid computing system as shown in FIG. 19 is assumed. In the figure, a request source computer 610 is connected to a calculation resource 600a, and the calculation resource 600a is further connected to calculation resources 600b, 600c, and 600d. The computing resource 600b is connected to the computing resource 600e, the computing resource 600d is connected to the computing resource 600f, and the computing resource 600f is connected to the computing resource 600g. Hereinafter, the calculation resources 600a to 600g are collectively referred to as the calculation resource 600. The computing resource 600a may be a computing resource having the same function as the portal server, and the request source computer 610 may be the same as the portal server. Further, any of the calculation resources may be a request source computer.

FIG. 20 shows a resource search processing flow of the request source computer 610 in FIG.
The request source computer 610 receives input of requirement information indicating a system condition of a calculation resource to be used as a search key (step S21). As the system condition, a CPU usage rate, a remaining memory capacity, an executable application, and the like can be used. For example, “CPU usage rate x% or less” or the like is input.

  When the request source computer 610 receives the input of the requirement information, the request source computer 610 transmits a search message (corresponding to the search request sent by the client peer described above) to the computing resource 600a adjacent to the request source computer 610 (step S22). The search message as a stimulus includes at least a search key indicating the input requirement information and an identifier capable of identifying itself on the network. As an identifier that can identify the requesting computer 610 itself on the network, for example, the IP address of the requesting computer 610 is used. The request source computer 610 activates a reception wait timer after transmitting the search message, and enters a response reception wait state as a result of the search message (step S23). When the request source computer 610 receives the result response data (result notification transmitted by the resource peer described above) as a notification of firing from the calculation resource 600 that satisfies the search key (step S24), the request source computer 610 stores the result response data therein. (Step S25). Then, the reception of the result response data from the computing resource 600 that satisfies the search key and the storage of the result response data are repeated until the reception waiting timer reaches 0. When the reception waiting timer reaches 0, the request source computer 610 ends the result response reception waiting state (step S26), and displays the reception result list stored therein in step S25 on a display or the like (step S27).

FIG. 21 shows a search message reception waiting process flow of the computing resource 600.
The computing resource 600 collects static information of its own computing resources by a computing resource information acquisition process (FIG. 22), which will be described later, when the power is turned on or when it participates in a semantic information network and registers it in the filter ( Step S41). Static information is information that does not change over time or does not change in a short time. For example, CPU specifications, IP address, OS type, executable application name, memory capacity (total capacity), HD Capacity (total capacity), etc. Note that the static information collection may be executed periodically or when the static information is changed.

  After registering the static information in the filter, the computing resource 600 receives a search message from the requesting computer 610 or another computing resource 600 (step S42). The search message includes a search key and an identifier of the request source computer 610. The computing resource 600 determines whether there is another computing resource 600 to which the received search message is to be transferred (step S43). If there is a computing resource 600 to which the search message is to be transferred (step S43: Yes), the received search message is transferred (step S44).

Subsequently, the computing resource 600 matches the search key included in the received search message with the static information registered in the filter (step S45). Specifically, it is determined whether or not the static information included in the search key matches the static information registered in its own filter. If it is determined that the static information included in the search key and the static information registered in its own filter do not match, it waits for reception of the next search message.
On the other hand, when it is determined that the static information included in the search key matches the static information registered in its own filter, the calculation resource 600 performs its own calculation resource information acquisition process (FIG. 22) to be described later. The dynamic information of the computing resource provided is acquired (step S46). This dynamic information is information that changes sequentially, such as its current CPU usage rate, remaining memory capacity, and network status. The computing resource 600 matches the search key included in the received search message with the acquired dynamic information (step S47). Specifically, it is determined whether or not the dynamic information included in the search key matches its own dynamic information. If it is determined that the dynamic information included in the search key and its own dynamic information do not match (step S47: No), it waits for reception of the next search message. On the other hand, when it is determined that they match (step S47: Yes), the computing resource 600 transmits a result response including its own identifier and information about its own computing resource to the requesting computer 610 (step S48).

FIG. 22 shows a calculation resource information acquisition process flow of the calculation resource 600.
The computing resource 600 collects its own static information and stores it in the temporary area (step S61). Thereafter, the computing resource 600 creates a thread by multithreading and executes dynamic information acquisition processing.
When the dynamic information acquisition loop in the dynamic information acquisition process is started (step S62), the computing resource 600 acquires dynamic information such as its current CPU usage rate, remaining memory capacity, and network status (step S62). S63). Then, the acquired dynamic information data is held in the temporary area (step S64). If the dynamic resource acquisition loop termination condition is not satisfied, the computing resource 600 periodically repeats the processing of steps S63 to S64 for acquiring and storing dynamic information at intervals of 10 seconds, for example. If the dynamic information acquisition loop termination condition is satisfied, the dynamic information acquisition loop is terminated (step S65). The dynamic information acquisition loop end condition is, for example, leaving from the P2P network.

  On the other hand, after collecting the static information in step S61, the computing resource 600 starts a query request waiting loop, and enters a waiting state for receiving a query from the search message reception waiting process shown in FIG. 21 (step S71). When receiving a query from the search message reception waiting process, the computational resource 600 branches according to the type of query (step S72). If the inquiry is for static information transmitted from step S41 in FIG. 21, the static information held in the temporary area in step S61 is returned (step S73). If the inquiry is for dynamic information transmitted from step S46 in FIG. 21, the dynamic information held in the temporary area in step S64 is returned (step S74). When the query request wait loop termination condition is not satisfied, the computing resource 600 enters a query request reception wait state, receives the query request, and repeats the processing of steps S72 to S74 for returning information. If the query request wait loop termination condition is satisfied, the query request wait loop is terminated (step S75). The query request wait loop end condition is, for example, a departure from the P2P network.

  20 to 22, after the request source computer 610 displays a list of the calculation resources 600 that satisfy the search key, the request source computer 610 performs the same process as in step S10 and subsequent steps in FIG. The calculation process is assigned to an appropriate calculation resource 600, and the calculation resource 600 performs the assigned calculation process and returns the processing result to the requesting computer 610.

[Supplementary explanation about SIONet]
Here, “SIONEt” will be supplementarily described.
As shown in FIG. 23, SIONet is a metanetwork that distributes events based on semantic information (metadata), and dynamically searches for a specific entity from a large number of unspecified entities that are super-distributed on the network.・ Can be discovered. In other words, SIONet is a network that delivers an event based on semantic information (sending to whom) instead of the destination address (sending to whom) used in the conventional network.

  In SIONet, as a definition of SIONet entity, all computers such as personal computers, workstations, portable information terminals, and mobile phones are collectively referred to as hosts. Furthermore, a host on which SIONet software is installed is referred to as “SIONE entity” or simply “entity”. An entity is a virtualization of a host on which SIONet software is installed as a unit of autonomous distributed cooperation in SIONet.

Entities are classified into three types: SE (service entity), NE (network entity), and SNE (service network entity).
The SE (service entity) is an entity that behaves as a service, and is a virtualized P2P application as an internal entity within the entity.
The NE (network entity) is an entity that behaves as a network component, is an internal entity for constructing and operating SIONets, and a plurality of NEs (network entities) are distributed and coordinated to self-organize the network. .
An SNE (service network entity) is an entity that behaves from the viewpoint of both a service and a network component, and is used when constructing a pure P2P network, and self-organizes the network by autonomously distributing them.

  As shown in FIG. 23, the event is composed of semantic information and data. As the semantic information, for example, “resident in the suburbs of Tokyo”, “person who enjoys classical music”, “Meiji-dori There are “people walking now”, “travel content holders” and so on. The event structure will be described later.

  FIG. 24 is a diagram for explaining the SIONet mechanism. The SIONet includes a plurality of event places, and the event place includes a plurality of entities. Further, SIONet is an autonomous distributed cooperative network (autonomous distributed computer) in which the network is self-organized when all entities including the components of SIONet perform autonomous distributed cooperation. Network entities that are SIONet network components include "semantic information switch (SI-SW)", "semantic information router (SI-R)", and "semantic information gateway (SI-GW)". Elements include “session”, “shared link (SL)”, and the like, and by self-organizing as necessary, a secure and scalable P2P network can be constructed by a bottom-up approach.

  The semantic information switch (SI-SW) is a network entity (NE) that provides a switching mechanism for switching events based on semantic information, and the semantic information router (SI-R) is based on semantic information. The network entity (NE) that performs event routing (event transfer) between SI and SW, and the semantic information gateway (SI-GW) is a network entity (NE) for realizing event sharing between event places. .

  The “session” is a connection between the semantic information switch (SI-SW) and the service entity (SE), and the service entity (SE) can transmit and receive events only through the session. There are three types of sessions: an event transmission session, a reception session, and a transmission / reception session. The “shared link” is a concept for performing bidirectional event sharing between a plurality of different entities. For example, an entity group (event place) is formed when a certain entity requests establishment of a shared link (SL) to another entity.

FIG. 25 is a diagram illustrating an example of the structure of an SIONet event. The SIONet event includes a control information part (CIPart (Control Information Part)), a semantic information part (SIPart (Semantic Information Part)), and a data part ( DATATAP).
The control information part (CIPart) is a control field for effective control of SIONet and is not open to the service entity (SE). The semantic information part (SIPart) stores semantic information (vocabulary and its value) of transmission data and a lexical concept (event type) of semantic information. The data part (DATATAPart) stores transmission data (various data and programs such as text data and binary data).
In addition, a stimulus is transmitting an event. A response is that the filter matches the event. Firing means starting an entity that has registered a matched filter and notifying an event.

  FIG. 26 is a diagram for explaining the semantic information switch and the filter. The semantic information switch (SI-SW) provides a switching mechanism for switching events based on the semantic information. The service entity (SE) transmits and receives events via a session (connection between SI-SW and SE).

  The filter is a content that the service entity (SE) registers the event acquisition condition in the semantic information switch (SI-SW) through the session. Set the event type (event vocabulary concept) of the event you want to acquire and the matching condition with the semantic information.

FIG. 27 is a diagram for explaining the event place and the semantic information gateway, and the event place is an aggregate of semantic information switches (SI-SW).
The event place is a concept of glue pink, which is a concept used as a security guarantee unit, a unit of load distribution, grouping of groups, etc., and achieves the following objectives.
First, the event transfer range is limited. That is, it limits the spread of chain reactions based on stimulation and ignition.
Second, the target range of event routing is limited. It is a set of semantic information switches (SI-SW) connected by a shared link, and a link topology or event routing method can be selected as an event place.
Third, it is a space that guarantees the uniqueness of the semantic information system, and suppresses the explosive increase in the event types handled.

  The semantic information gateway (SI-GW) is a network entity (NE) for realizing event sharing between event places. As a result, it is possible to link event places having different uses and purposes.

<Primary Computing Resource Collection Method in Grid Computing System: Example of Application of P2P System for File Exchange>
Next, a calculation resource collection method in the grid computing system will be described. In the grid computing system, as described above, the state information of the computing resources is mutually exchanged by P2P (Peer to Peer) type communication. Each computing resource has a file with a predetermined file name corresponding to its own state (CPU usage rate, etc.). Further, by searching for a file name using software for exchanging files with P2P (for example, Gnutella (registered trademark)), the requesting computer searches for a computing resource in a predetermined state, and the corresponding state Request work (processing) for the computing resource.

  FIG. 28 is a diagram showing a configuration of a grid computing system for explaining a calculation resource collecting method, and shows an example configured using a pure P2P system such as Gnutella (registered trademark). The file name search in Gnutella (registered trademark) has a mechanism in which file name searches are performed in a chained manner. In the grid computing system of the present invention, this function is used for status information (for example, CPU) of computing resources. (Use rate) is extended so that it can be searched by chaining by file name.

  In FIG. 28, the computing resources 1001 to 1013 participate in Gnutella Net (registered trademark) in advance, measure the CPU usage rate in the background, and assign the file name corresponding to the value to the pure P2P system (Gnutella (registered trademark)). Trademark) etc.) is stored in a predetermined directory.

  The requesting computer 1020 for requesting calculation processing first participates in the Gnutella Net (registered trademark), and then allocates a calculation resource having an empty CPU necessary for assigning a process (for example, a task) to the Gnutella Net (registered trademark). Search by broadcasting to). The computing resources 1001 to 1013 satisfying the request respond to the requesting computer 1020, and the requesting computer 1020 assigns the computing process to the most suitable computing resource.

  Further, in the grid computing system of the present invention, the file search function of the pure P2P system is applied to the search of the CPU usage rate, etc., so how to reflect the CPU usage rate in the file name is a point.

  For this reason, the computing resources 1001 to 1013 regularly measure the CPU load (usage rate) of the terminal itself in the background. Further, a file having a file name based on Table 1 shown in FIG. 29A is created from the obtained value, and stored in a directory designated by a pure P2P system (Gnutella (registered trademark) or the like).

  In the example shown in FIG. 29, the file name of the file to be created and the search key have the following relationship. For example, when the CPU usage rate is 90% to 100%, the CPU is almost free, so that it is possible to search only with the search key “J” used when searching for a calculation resource of “almost free” or more. Thus, the file name to be created includes a search key “J” and a file name “J” that does not include other search keys. Further, when the CPU usage rate is 80% or more and less than 90%, the CPU is at least 10% free. Therefore, the search keys “J” and “ The file name to be created includes the search keys “J” and “I” so that the search can be made only with the search key “I” used when searching for a calculation resource of “10% or more free”. The file name does not include the search key “IJ”. Further, when the CPU usage rate is 70% or more and less than 80%, the CPU is at least 20% free. Therefore, the search keys “J”, “ Search is possible only with the search key “I” used when searching for a calculation resource of “10% or more free” and the search key “H” used when searching for a calculation resource of “20% or more free”. Thus, the file name to be created is the file name “HIJ” that includes the search keys “J”, “I”, and “H” and does not include other search keys.

  A script that performs the processing described above is created and executed on each of the computing resources 1001 to 1013. With this function, the CPU load state is periodically saved as a file name. By searching for the file using a pure P2P system such as Gnutella (registered trademark), the calculation considering the free state of the CPU is performed. Search for resources becomes possible.

  Further, when searching for the computing resources 1001 to 1013 from the request source computer 1020, a search key based on Table 2 shown in FIG. 29B is used. For example, in a computational resource in which the CPU is at least 80% idle, the file name to be created always includes “B”. Therefore, if “B” is searched from the request source computer 20 as a search key. A computing resource whose CPU state is in an idle state of 80% or more is discovered. Then, the request source computer 1020 assigns a calculation processing process to the found calculation resource.

  In the grid computing system, the computing resource collection function in the grid computing system is realized using a pure P2P system. Compared with the directory-type computing resource collection function that uses a management server that is generally used in conventional grid computing systems, an information retrieval method based on a brokerless concept in which there is no uniform information provider is used. In the present embodiment, it is possible to construct a grid computing system that can cope with dynamic fluctuations in computing resources and has excellent fault tolerance. In addition, since this method eliminates the need for a directory, there is a merit that management becomes easy.

  In the above embodiment, an example in which the CPU usage rate is used as the status information of the calculation resource is shown. However, the present invention is not limited to this, and various other status information such as a memory capacity, a calculation speed, and a communication speed. Can also be used, and state information combining these can also be used.

  The name and form of the computing resource and the requesting computer are not limited as long as they are hardware having a computing function and a network connection function such as a personal computer, a PDA, and a mobile phone. The network includes both wired and wireless connection methods. The computing resource and the requesting computer can be replaced by a job.

  The calculation resources 101 to 113, 200, 600, 1001 to 1013, the request source computers 130, 410, 510, 610, and 1020 and the portal sites 120, 300, 401 to 403, and 501 described above are provided inside. Has a computer system. Then, the functions of the computing resources 101 to 113, 200, 600, 1001 to 1013 and the request source computers 130, 410, 510, 610, and 1020 and the portal sites 120, 300, 401 to 403, and 501 are realized. The above-described various processes may be performed by recording a program for recording on a computer-readable recording medium, reading the program recorded on the recording medium into a computer system, and executing the program. The “computer system” here includes an OS and hardware such as peripheral devices. The “computer system” includes a WWW system having a homepage providing environment (or display environment). The “computer-readable recording medium” refers to a portable medium such as a flexible disk, a magneto-optical disk, a ROM, and a CD-ROM, and a storage device such as a hard disk built in the computer system. Further, the “computer-readable recording medium” refers to a volatile memory (RAM) in a computer system that becomes a server or a client when a program is transmitted via a network such as the Internet or a communication line such as a telephone line. In addition, those holding programs for a certain period of time are also included.

  The program may be transmitted from a computer system storing the program in a storage device or the like to another computer system via a transmission medium or by a transmission wave in the transmission medium. Here, the “transmission medium” for transmitting the program refers to a medium having a function of transmitting information, such as a network (communication network) such as the Internet or a communication line (communication line) such as a telephone line. The program may be for realizing a part of the functions described above. Furthermore, what can implement | achieve the function mentioned above in combination with the program already recorded on the computer system, and what is called a difference file (difference program) may be sufficient.

The figure for demonstrating the outline of the reconstruction of the dynamic link using the time locality in a utilization form orientation P2P type | mold grid computing system. The figure for demonstrating the outline of the reconstruction of the dynamic link using the spatial locality in a utilization form orientation P2P type | mold grid computing system. The figure for demonstrating formation of the cluster which has a loose relationship by the chain of spatial locality. The flowchart which shows operation | movement of a client peer. The flowchart which shows operation | movement of a resource peer. The flowchart which shows operation | movement of a resource peer. The flowchart which shows operation | movement of a resource peer. The flowchart which shows operation | movement of a resource peer. The functional block diagram for demonstrating the function of a peer. The figure for demonstrating the flow of the request data of a search request. The figure for demonstrating the structure which hold | maintains the IP address of two peers ahead. The figure for demonstrating the grid computing system which exchanges the status information of a computational resource using a semantic information network. The figure for demonstrating the function of the component of the grid computing system of FIG. The figure which shows the software structure in the calculation resource (entity) of FIG. The figure which shows the software structure in the portal site of FIG. The figure for demonstrating the structural example of the network of the grid computing system which exchanges the status information of a computing resource. The figure which shows the example of the sequence showing the process image of FIG. The figure which shows the example of semantic information. The figure which shows the structural example of the grid computing system which exchanges the status information of a computing resource. The flowchart which shows operation | movement of the request origin computer of FIG. The flowchart which shows the operation | movement of the calculation resource of FIG. The flowchart which shows the operation | movement of the calculation resource of FIG. The figure which shows the outline | summary of SIONet. The figure for demonstrating the mechanism of SIONet. The figure which shows the example of the structure of an event. The figure for demonstrating a semantic information switch and a filter. The figure for demonstrating an event place and a semantic information gateway. The figure for demonstrating the grid computing system for demonstrating the calculation resource collection method. The figure which shows the example of the file name and search key which the calculation resource of FIG. 28 produces.

Explanation of symbols

10 client processing unit, 10a outgoing peer ID list holding unit, 10b search request processing unit, 10c outgoing link number judgment unit, 10d outgoing link deletion unit, 10e outgoing link reassignment unit, 10f transfer link renewal request unit, 20 resource processing unit, 21 request data determination unit, 22 resource search processing unit, 22a transfer processing unit, 22b search processing unit, 23 transfer peer ID list holding unit, 24 first transfer link reassignment processing unit, 24a transfer link number determination unit, 24b transfer link deletion , 24c transfer link switching unit, 24d transfer link switching request unit, 25 second transfer link switching processing unit, 25a transfer link number determination unit, 25b transfer link deletion unit, 25c transfer link switching unit, 101-113 computing resources, 120 Portal site, 130 Requester computer, 2 0 computational resources, 300 portals, 401-403 portal site 410 requesting computer 501 portal site 510 requesting computer, 600A～600g computing resources, 610 requesting computer, 1001-1013 computational resources, 1020 requesting computer

Claims (13)

In a usage-oriented P2P-type grid computing system that dynamically combines a plurality of computing resources scattered on a network to form a virtual machine,
The search source calculator is
A transmission target computer list holding means for holding a transmission target computer list that lists computers with outgoing links that are unidirectional logical links;
Search request means for making a search request created by itself for a computer that has established an outgoing link via each outgoing link based on the outgoing computer list;
Outgoing link reassigning means for registering newly used computers as a result of search with reference to the outgoing computer list and registering outgoing computers in the outgoing computer list, and for changing outgoing links,
First reassignment requesting means for performing a first transfer link reassignment request including the outgoing call target computer list to a computer to which an outgoing link is to be extended by the outgoing link replacement means;
With
The computer targeted for the outgoing link is
First transfer target computer list holding means for holding a first transfer target computer list listing computers with transfer links that are logical links;
A first search request received from a search source computer and transferred by another computer is received, and the received search request is transferred to the computer via each transfer link based on the first transfer target computer list. Search request forwarding means;
First transfer link replacement means for registering a computer included in the transmission target computer list included in the first transfer link replacement request received from the search source computer in the first transfer target computer list and performing transfer link replacement; ,
Second reassignment requesting means for making a second transfer link reassignment request that does not include a transmission target computer list for a computer to which a transfer link is established by the first transfer link reassigning means;
With
The computer for which the transfer link is established is
Second transfer target computer list holding means for holding a second transfer target computer list listing computers with transfer links that are logical links;
Search request transmission from the search source computer, or transmitted from the search source computer receives a search request transferred by the other computers, via a respective transfer links based on said second transfer target computer list, Second search request transfer means for transferring the search request received to the computer;
Second transfer link switching means for registering the computer that is the transmission source of the second transfer link switching request in the second transfer target computer list and switching the transfer link;
A utilization form-oriented P2P type grid computing system comprising: The search source computer is:
Outgoing link number judgment means for judging whether or not the outgoing link number currently stretched is smaller than the predetermined allowable outgoing link number when the outgoing link is replaced by the outgoing link replacement means;
Outgoing link deletion means for deleting at least one of outgoing outgoing links when it is determined by the outgoing link number judging means that the number of outgoing outgoing links is not smaller than the allowable outgoing link number;
The usage-oriented P2P type grid computing system according to claim 1, further comprising: The computer targeted for the outgoing link is
First transfer link number determination means for determining whether the number of transfer links currently extended is smaller than a predetermined first allowable transfer link number when the transfer link is changed by the first transfer link change means;
If the first transfer link number determination means determines that the currently established transfer link number is not smaller than the first allowable transfer link number, the first transfer link number deletion means deletes at least one of the currently established transfer links. A transfer link deletion means;
The usage-oriented P2P type grid computing system according to claim 1 or 2 , further comprising: The computer for which the transfer link is established is
Second transfer link number determination means for determining whether the number of transfer links currently extended is smaller than a predetermined second allowable transfer link number when transferring the transfer link by the second transfer link replacement means;
When the second transfer link number determination means determines that the currently established transfer link number is not smaller than the second allowable transfer link number, the second transfer link number determining unit deletes at least one of the currently established transfer links. A transfer link deletion means;
The utilization form-oriented P2P type grid computing system according to any one of claims 1 to 3 , further comprising: A computer program used for a computer in a usage-oriented P2P type grid computing system that dynamically combines a plurality of computing resources scattered on a network to form a virtual machine,
A search request step for making a search request created by itself to a computer having an outgoing link via each outgoing link based on a list of outgoing computers that lists the computers having outgoing links that are unidirectional logical links; and ,
An outgoing link renewal step of registering a computer to be newly discovered and used as a result of a search with reference to the outgoing computer list and renewing the outgoing link by registering in the outgoing computer list;
A reassignment request step for performing a transfer link reassignment request including the outgoing call target computer list for the computer that is the target of the outgoing link renewal step in the outgoing link renewal step;
A computer program for causing a computer to execute. An outgoing link number determination step for determining whether the outgoing link number currently extended is smaller than the predetermined allowable outgoing link number when the outgoing link is changed in the outgoing link replacement step;
An outgoing link deletion step of deleting at least one of outgoing outgoing links when it is determined that the outgoing outgoing link number is not smaller than the allowable outgoing link number in the outgoing outgoing link number judging step;
The computer program according to claim 5 , wherein the computer is executed. In the search request step, a search request is made with a search key indicating a requirement regarding a static state or a dynamic state of a computing resource,
As a result of the search request, a result receiving step of receiving a result notification from another computer that satisfies the requirements indicated by the search key;
Computer program according to claim 5 or claim 6, characterized in that to execute the computer. A computer program used for a computer in a usage-oriented P2P type grid computing system that dynamically combines a plurality of computing resources scattered on a network to form a virtual machine,
A search request received from another computer, via a respective transfer links based on the transfer target computer list enumerating computer pitched forward link is a bidirectional logical links, further search request transfer to be transferred to another computer Steps,
Transfer that receives a transfer link replacement request from another computer, registers the computers listed in the transmission target computer list included in the received transfer link replacement request in the transfer target computer list, and performs transfer link replacement Link re-linking step,
A reassignment request step for making a transfer link reassignment request that does not include the outgoing computer list for the computer that is the target of the transfer link reassignment step,
A computer program for causing a computer to execute. A transfer link number determining step for determining whether the number of transfer links currently extended is smaller than a predetermined allowable transfer link number when transferring the transfer link in the transfer link replacement step;
A transfer link deletion step of deleting at least one of the currently established transfer links when it is determined that the currently established transfer link number is not smaller than the allowable transfer link number in the transfer link number determining step;
The computer program according to claim 8 , wherein the computer is executed. A computing resource collection step for collecting information indicating a static state or a dynamic state of the own computing resource;
Result notification that returns a result notification when the static state or dynamic state of the computational resource indicated by the collected information satisfies the requirements regarding the static state or dynamic state of the computational resource indicated by the search key included in the search request Steps,
A calculation processing assignment step for receiving a request for processing in response to the result notification and performing the requested processing;
Computer program according to claim 8 or claim 9, characterized in that to execute the computer. A computer program used for a computer in a usage-oriented P2P type grid computing system that dynamically combines a plurality of computing resources scattered on a network to form a virtual machine,
A search request received from another computer, via a respective transfer links based on the transfer target computer list enumerating computer pitched forward link is a bidirectional logical links, further search request transfer to be transferred to another computer Steps,
A transfer link switching step for receiving a transfer link switching request, registering the computer that has transmitted the received transfer link switching request in the transfer target computer list and transferring the transfer link; and
A computer program for causing a computer to execute. A transfer link number determining step for determining whether the number of transfer links currently extended is smaller than a predetermined allowable transfer link number when transferring the transfer link in the transfer link replacement step;
A transfer link deletion step of deleting at least one of the currently established transfer links when it is determined that the currently established transfer link number is not smaller than the allowable transfer link number in the transfer link number determining step;
The computer program according to claim 11 , wherein the computer is executed. A computing resource collection step for collecting information indicating a static state or a dynamic state of the own computing resource;
Result notification that returns a result notification when the static state or dynamic state of the computational resource indicated by the collected information satisfies the requirements regarding the static state or dynamic state of the computational resource indicated by the search key included in the search request Steps,
A calculation processing assignment step for receiving a request for processing in response to the result notification and performing the requested processing;
And characterized by causing a computer to execute the claim 11 or a computer program according to claim 12.

Images