WO2016031043A1 - Process distributing device, process distributing program, and data processing system - Google Patents

Abstract

This load balancing device (200) stores an association table file in which respective identifiers of server devices (300) each storing content data to be used in data processing are associated with processing commands each designating data processing. The load balancing device receives a processing request packet from a client device (110), and selects, from the association table file, the identifier of a server device associated with the same processing command as the processing command included in the processing request packet. Then, the load balancing device transmits a distribution packet including the processing command to the server device identified by the identifier selected from the association table file.

Description

Processing distribution device, processing distribution program, and data processing system

The present invention relates to a technique for distributing data processing to a plurality of server devices.

There is a three-level web server system including a client device, a web server device, and a database server device. In a three-tier web server system, the web server device is also called a front-end server. The database server device is also called a back-end server.

Patent Document 1 and Non-Patent Document 1 disclose a technique for distributing loads of a plurality of front-end servers by providing a load balancer in a web server system.
The load balancer distributes a plurality of data processes to a plurality of front-end servers so that the loads on the respective front-end servers are equalized.
However, the load balancer can distribute the load of a plurality of front-end servers, but cannot distribute the load of a plurality of back-end servers. Therefore, the load balancer cannot sufficiently distribute the load in the entire system.

Non-Patent Document 2 discloses a distributed storage technology that distributes loads of a plurality of storage devices.
In the distributed storage technology, a storage area for distributed storage is secured in each of a plurality of storage devices, and a virtual storage device is constructed by consolidating the storage areas for each distributed storage. The data is multiplexed and stored.
When the distributed storage technology is applied to the web server system, the data processing may be distributed to a back-end server that does not store the target data. In this case, the back-end server to which the data processing is distributed needs to communicate with the back-end server storing the target data in order to access the target data. And this communication processing becomes an overhead, data processing is delayed, and the throughput of a system falls.

JP 2003-196178 A

An object of the present invention is to enable data processing to be distributed to a server device that stores content data used in data processing.

The processing distribution apparatus of the present invention is
A correspondence table file storage unit that stores a correspondence table file in which a processing instruction designating data processing is associated with a server identifier of a server device that stores content data used in data processing;
A processing command receiving unit that receives a first processing command that specifies first data processing using the first content data;
A correspondence table management unit that selects from the correspondence table file a server identifier associated with the same processing instruction as the first processing instruction received by the processing instruction reception unit;
A processing distribution unit that requests the server device identified by the server identifier selected by the correspondence table management unit to execute the first data processing.

According to the present invention, data processing can be distributed to a server device that stores content data used in data processing.

1 is a schematic diagram of a load distribution system 100 according to Embodiment 1. FIG. 2 is a functional configuration diagram of a load distribution apparatus 200 according to Embodiment 1. FIG. 3 is a functional configuration diagram of a server device 300 according to Embodiment 1. FIG. 4 is a flowchart illustrating an operation of the load distribution apparatus 200 according to the first embodiment. 6 is a diagram illustrating an example of a correspondence table file 291 according to Embodiment 1. FIG. 6 is a diagram illustrating an example of a server list file 292 according to Embodiment 1. FIG. 4 is a flowchart illustrating an operation of the server apparatus 300 according to the first embodiment. 4 is a flowchart illustrating an operation of the server apparatus 300 according to the first embodiment. 6 is a diagram illustrating an example of a data arrangement file 391 according to Embodiment 1. FIG. 2 is a hardware configuration diagram of a load distribution apparatus 200 according to Embodiment 1. FIG. 6 is a configuration diagram of a client server system 101 according to Embodiment 2. FIG. 6 is a functional configuration diagram of a client device 110 according to Embodiment 2. FIG.

Embodiment 1 FIG.
A mode in which data processing is distributed to a server device that stores content data used in data processing will be described.

FIG. 1 is a schematic diagram of a load distribution system 100 according to the first embodiment.
An overview of the load distribution system 100 according to the first embodiment will be described with reference to FIG.
The load distribution system 100 (an example of a data processing system) is a system that distributes a plurality of processing requests generated from one or more client devices 110 to a plurality of server devices (300A to 300D).

The load distribution system 100 includes one or more client devices 110, a plurality of server devices (300A to 300D), and a load distribution device 200 (an example of a processing distribution device). These apparatuses communicate via the network 109.
When the server devices are not distinguished, each server device is referred to as a server device 300.

The client device 110 is a computer that requests execution of data processing. Hereinafter, data used in data processing is referred to as content data.

The plurality of server devices (300A to 300D) are computers that execute data processing.
A storage device (server storage unit 390 in FIG. 3 to be described later) included in each server device constitutes a distributed storage (distributed storage area 399 in FIG. 3 to be described later) in which a plurality of content data is distributed and stored.
A plurality of pieces of content data are distributed and stored in a plurality of server devices. Each content data is multiplexed and stored in two or more server devices.
In FIG. 1, content data A 381 and content data B 382 are multiplexed and stored in server apparatus 300A and server apparatus 300C. Further, the content data C383 and the content data D384 are multiplexed and stored in the server device 300B and the server device 300D.

The load distribution apparatus 200 is a computer that distributes a plurality of processing requests for requesting execution of data processing to a plurality of server apparatuses. The load balancer 200 is also called a load balancer.
The load distribution apparatus 200 receives a processing request from the client apparatus 110, distributes the processing request to one of the server apparatuses 300, receives a processing result from the server apparatus 300, and responds to the client apparatus 110 with the processing result.

An example of the operation of the load distribution system 100 will be described based on (1) to (5) in FIG.
(1) The client device 110 requests execution of data processing C using the content data C383.
(2) The load distribution apparatus 200 distributes the processing request for requesting the execution of the data processing C to one of the server apparatuses. At this time, since the content data C383 used in the data processing C is stored in the server device 300B and the server device 300D, a server device appropriate as a processing request distribution destination is the server device 300B or the server device 300D.
When the appropriate server device is known, the load distribution device 200 distributes the processing request for the data processing C to the server device 300B or the server device 300D.
When an appropriate server device is not known, the load distribution device 200 distributes a processing request for data processing C to a server device with a light load. A server device with a light load can be identified by a conventional load balancing technique.
Here, it is assumed that the load distribution apparatus 200 does not know an appropriate server apparatus and distributes a processing request for data processing C to the server apparatus 300A.
(3) The server device 300A selects the server device 300B (or server device 300D) that stores the content data C383 based on a data arrangement file 391 (see FIG. 3) described later. Then, the server device 300A accesses the content data C383 by communicating with the server device 300B (or the server device 300D), and executes data processing C.
(4) The server device 300A returns the execution result of the data processing C and the access information to the load distribution device 200. This access information is information indicating that the server apparatus 300B (or server apparatus 300D) is an appropriate server apparatus as a distribution destination of processing requests for data processing C.
(5) The load distribution apparatus 200 stores the access information of the data processing C, and responds to the client apparatus 110 with the execution result of the data processing C.

In the above (5), the access information of the data processing C is stored in the load balancer 200. Therefore, the load distribution apparatus 200 can distribute processing requests for data processing C that occur thereafter to the server apparatus 300B (or server apparatus 300D).
When the processing request for the data processing C is distributed to the server apparatus 300B, the server apparatus 300A does not need to communicate with the server apparatus 300B as in (3) above. Therefore, a processing delay associated with communication between server devices does not occur, and the system throughput is improved.

FIG. 2 is a functional configuration diagram of the load distribution apparatus 200 according to the first embodiment.
A functional configuration of the load distribution apparatus 200 according to Embodiment 1 will be described with reference to FIG. However, the functional configuration of the load distribution apparatus 200 may not be the same as the functional configuration illustrated in FIG.

The load distribution apparatus 200 includes a request reception unit 210 (an example of a processing instruction reception unit), a correspondence table management unit 220, a request distribution unit 230 (an example of a processing distribution unit), and a load distribution storage unit 290 (a correspondence table file storage). Part of an example).

The load distribution storage unit 290 stores data used, generated, or input / output by the load distribution apparatus 200. For example, the load distribution storage unit 290 stores a correspondence table file 291 and a server list file 292.
The correspondence table file 291 associates an identifier of the server device 300 that stores content data used in data processing with a processing instruction that specifies data processing. An example of the correspondence table file 291 will be described later (see FIG. 5).
The server list file 292 associates information such as an IP address with the identifier of the server device 300. An example of the server list file 292 will be described later (see FIG. 6).

The request reception unit 210 receives a processing request packet including a processing instruction designating data processing from the client device 110 and transmits a processing response packet including execution result data indicating the execution result of the data processing to the client device 110.
The processing request packet is a packet that requests execution of data processing, and the processing response packet is a packet that responds to the execution result of data processing.

The correspondence table management unit 220 includes a correspondence table reference unit 221 (an example of a correspondence server selection unit) and a correspondence table editing unit 222 (an example of a correspondence server registration unit), and manages the correspondence table file 291.
The correspondence table reference unit 221 selects from the correspondence table file 291 the identifier of the server apparatus 300 associated with the same processing instruction as the processing instruction included in the processing request packet.
The correspondence table editing unit 222 associates access information data, which will be described later, with processing instructions included in the processing request packet and registers them in the correspondence table file 291.

The request distribution unit 230 transmits a distribution packet including a processing command to the server device 300 identified by the identifier selected by the correspondence table reference unit 221. Then, the request distribution unit 230 receives the execution result packet including the execution result of the data processing from the server device 300.
The distribution packet is a packet that requests execution of data processing, and the execution result packet is a packet that responds to the execution result of data processing.

FIG. 3 is a functional configuration diagram of the server apparatus 300 according to the first embodiment.
A functional configuration of the server apparatus 300 according to the first embodiment will be described with reference to FIG. However, the functional configuration of the server apparatus 300 may not be the same as the functional configuration illustrated in FIG.

The server apparatus 300 includes a WEB server unit 301, a DB server unit 320, a distributed storage management unit 330 (an example of an access request unit), an access information generation unit 340, and a server storage unit 390 (content data storage unit, data arrangement). An example of a file storage unit). The WEB server unit 301 includes a WEB application unit 310.

The server storage unit 390 stores data used, generated or input / output by the server device 300.
For example, the server storage unit 390 stores a data arrangement file 391, a server list file 392, a content data group 380, and the like.
The data arrangement file 391 associates the identifier of the server apparatus 300 in which the content data is stored with the identifier of the content data. An example of the data arrangement file 391 will be described later (see FIG. 9).
The server list file 392 associates information such as an IP address with the identifier of the server device 300. The server list file 392 is the same file as the server list file 292 of the load balancer 200 (see FIG. 2).
The content data group 380 is one or more content data. The content data group 380 is stored in a storage area reserved for distributed storage. Hereinafter, the storage area reserved for the distributed storage is referred to as a distributed storage area 399.

The WEB server unit 301 executes a WEB server program for causing the server device 300 to function as a WEB server.
The WEB application unit 310 includes an execution request reception unit 311, a process execution unit 312, and an execution result response unit 313.
The execution request reception unit 311 receives the distribution packet from the load distribution apparatus 200.
The process execution unit 312 executes data processing specified by the process instruction included in the distribution packet.
The execution result response unit 313 transmits an execution result packet including execution result data indicating the execution result of the data processing and the access information data generated by the access information generation unit 340 to the load distribution apparatus 200.

The DB server unit 320 executes a DB server program for causing the server device 300 to function as a database server (DB server).
The distributed storage management unit 330 accesses content data stored in the distributed storage area 399.
When the content data to be accessed is not stored in the distributed storage area 399, the distributed storage management unit 330 selects the identifier of the server apparatus 300 associated with the identifier of the content data from the data arrangement file 391. Then, the distributed storage management unit 330 requests the server apparatus 300 identified by the selected identifier to access content data.
When access to content data is requested from another server apparatus 300, the distributed storage management unit 330 accesses content data stored in the distributed storage area 399.

The access information generation unit 340 generates access information data including the identifier of the server device 300 that stores the content data used in the data processing.

FIG. 4 is a flowchart illustrating the operation of the load distribution apparatus 200 according to the first embodiment.
The operation of the load distribution apparatus 200 in the first embodiment will be described with reference to FIG. However, the operation of the load distribution apparatus 200 may not be the same as the operation described based on FIG.

In S <b> 110, the client apparatus 110 transmits a processing request packet for requesting execution of data processing to the load distribution apparatus 200.
Then, the request reception unit 210 of the load distribution apparatus 200 receives the processing request packet. The processing request packet includes a processing instruction that specifies data processing.

For example, the GET method of an HTTP request is an example of a processing instruction, and an IP packet including this HTTP request is an example of a processing request packet. HTTP is an abbreviation for HyperText Transfer Protocol. IP is an abbreviation for Internet Protocol.
After S110, the process proceeds to S120.

In S <b> 120, the correspondence table reference unit 221 determines whether a server identifier associated with the same processing instruction as the processing instruction included in the processing request packet is registered in the correspondence table file 291.
The corresponding server identifier is called a corresponding server identifier, and the server device 300 identified by the corresponding server identifier is called a corresponding server.

For example, it is assumed that the processing instruction included in the processing request packet is an HTTP request “GET / aaa HTTP / 1.1”. In this case, two correspondence server identifiers (server A and server C) are registered in the correspondence table file 291 (see FIG. 5).
Further, it is assumed that the processing command included in the processing request packet is an HTTP request “GET / ccc HTTP / 1.1”. In this case, the corresponding server identifier is not registered in the correspondence table file 291 (see FIG. 5).
If the corresponding server identifier is registered in the correspondence table file 291 (YES), the process proceeds to S121.
If the corresponding server identifier is not registered in the correspondence table file 291 (NO), the process proceeds to S122.

FIG. 5 is a diagram illustrating an example of the correspondence table file 291 according to the first embodiment.
An example of the correspondence table file 291 in the first embodiment will be described with reference to FIG.
The correspondence table file 291 associates an access data column, an access server column, and a corresponding server column with a request column.
The request column indicates a processing instruction.
The access data column indicates the identifier of the content accessed in the data processing specified by the processing instruction.
The access server column indicates the identifier of the corresponding server that has accessed the access data in the previous data processing among one or more corresponding servers.
The corresponding server column indicates an identifier of each of one or more corresponding servers.

In S121 (see FIG. 4), the request distribution unit 230 selects one corresponding server identifier from one or more corresponding server identifiers. At this time, the request distribution unit 230 may select an identifier of the server device 300 with a light load from one or more corresponding server identifiers. The server device 300 with a light load can be identified by a conventional load distribution technique.
The selected corresponding server identifier is called a distribution destination identifier, and the server device 300 identified by the distribution destination identifier is called a distribution destination server.
After S121, the process proceeds to S130.

In S122, the request distribution unit 230 selects one of the server identifiers from the plurality of server identifiers registered in the server list file 292 (see FIG. 6). At this time, the request distribution unit 230 may select an identifier of the server device 300 with a light load from a plurality of server identifiers. The server device 300 with a light load can be identified by a conventional load distribution technique.
The selected server identifier is called a distribution destination identifier, and the server device 300 identified by the distribution destination identifier is called a distribution destination server.
After S122, the process proceeds to S130.

FIG. 6 is a diagram illustrating an example of the server list file 292 according to the first embodiment.
An example of the server list file 292 according to the first embodiment will be described with reference to FIG.
The server list file 292 associates an information column such as an IP address with a server column.
The server column indicates an identifier of the server device 300 provided in the load distribution system 100.
The IP address column indicates the IP address of the server device 300.

In S130 (see FIG. 4), the request distribution unit 230 selects an IP address associated with the same server identifier as the distribution destination identifier selected in S121 or S122 from the server list file 292 (see FIG. 6).
The request distribution unit 230 generates a packet addressed to the distribution destination server using the selected IP address as a transmission destination address. This packet is called a distribution packet.
The distribution packet is a packet that requests the distribution destination server to execute data processing. The distribution packet includes a processing instruction included in the processing request packet.

The request distribution unit 230 transmits the distribution packet to the distribution destination server.
After S130, the process proceeds to S131.

In S131, the request distribution unit 230 receives an execution result packet including execution result data and access information data from the distribution destination server.
The execution result data indicates the execution result of the data processing.
The access information data includes an access data identifier, an access server identifier, and a corresponding server identifier group.
The access data identifier indicates an identifier for identifying accessed content data.
The access server identifier indicates the identifier of the server device 300 that has accessed the content data.
The corresponding server identifier group is one or more corresponding server identifiers. The corresponding server identifier is an identifier of each of the one or more server devices 300 that stores the same content data as the accessed content data.
After S131, the process proceeds to S140.

In S140, the correspondence table editing unit 222 uses the processing instruction included in the processing request packet and the access information data (access data identifier, access server identifier, correspondence server identifier group) included in the execution result packet, and uses the correspondence table. The file 291 is edited as follows.
In the correspondence table file 291 (see FIG. 5), when a corresponding record including the same processing instruction as the processing instruction included in the processing request packet is registered in the request column, the correspondence table editing unit 222 includes the access information data. Based on this, the corresponding record is updated. That is, the correspondence table editing unit 222 updates the access data column of the corresponding record with the access data identifier, updates the access server column of the corresponding record with the access server identifier, and sets the corresponding server column of the corresponding record to the corresponding server identifier. Update with groups.
In the correspondence table file 291 (see FIG. 5), when the corresponding record including the same processing instruction as the processing instruction included in the processing request packet is not registered, the correspondence table editing unit 222 accesses the processing instruction and access. A new record is generated using information data. That is, the correspondence table editing unit 222 includes a processing instruction in the request column, an access data identifier in the access data column, an access server identifier in the access server column, and a corresponding server identifier group in the corresponding server column. Generate a new record that contains it. Then, the correspondence table editing unit 222 registers the new record in the correspondence table file 291.
After S140, the process proceeds to S150.

In S150, the request reception unit 210 generates a processing response packet that responds to the execution result of the data processing, and transmits the processing response packet to the client device 110 that is the transmission source of the processing request packet. The processing response packet includes execution result data included in the execution result packet.
After S150, the operation of the load distribution apparatus 200 for one processing request packet ends.

7 and 8 are flowcharts showing the operation of the server apparatus 300 in the first embodiment.
The operation of server apparatus 300 in the first embodiment will be described based on FIG. 7 and FIG. However, the operation of the server apparatus 300 may not be the same as the operation described based on FIGS. 7 and 8.

In S210, the execution request receiving unit 311 receives a distribution packet including a processing instruction.
After S210, the process proceeds to S220.

In S220, the process execution unit 312 starts executing the process logic based on the process instruction included in the distribution packet.
The processing logic is a program called a module, a routine, or a function, and indicates a data processing procedure. For example, the processing logic includes a procedure for generating a query for accessing content data.

For example, when the processing instruction is “GET / aaa HTTP / 1.1”, the processing execution unit 312 selects a processing logic for the GET method from among a plurality of processing logics, and uses “aaa” as a parameter. Start processing logic execution.
After S220, the process proceeds to S230.

In S230, the process execution unit 312 generates a query for accessing the content data according to the processing logic, and passes the query to the DB server unit 320.
After S230, the process proceeds to S231.

In S231, the DB server unit 320 receives the query, generates an access command for accessing the content data specified in the query, and passes the access command to the distributed storage management unit 330.
After S231, the process proceeds to S232.

In S232, the distributed storage management unit 330 receives the access command, and determines whether the content data specified in the access command is stored in the distributed storage area 399. Content data specified in the access command is referred to as corresponding content.
If the content is stored in the distributed storage area 399 (YES), the process proceeds to S233.
If the corresponding content is not stored in the distributed storage area 399 (NO), the process proceeds to S235 (see FIG. 8).

In S233, the distributed storage management unit 330 accesses the corresponding content stored in the distributed storage area 399 according to the access command.
For example, the distributed storage management unit 330 reads the corresponding content from the distributed storage area 399.

The distributed storage management unit 330 delivers the execution result of the access command to the DB server unit 320. For example, the execution result of the access command includes the corresponding content read from the distributed storage area 399.

The DB server unit 320 receives the execution result of the access instruction, generates a query execution result using the access command execution result, and passes the query execution result to the process execution unit 312. For example, the query execution result includes the corresponding content read from the distributed storage area 399.
After S233, the process proceeds to S234.

In S234, the distributed storage management unit 330 selects a server identifier group associated with the same content data identifier as the corresponding content from the data arrangement file 391 (see FIG. 9). For example, when the corresponding content is content A, the distributed storage management unit 330 selects two server identifiers (server A and server C) from the data arrangement file 391 (see FIG. 9).
Then, the distributed storage management unit 330 passes the server identifier group and the identifier of the corresponding content to the access information generation unit 340.

The access information generation unit 340 receives the server identifier group and the identifier of the corresponding content, generates access information data, and passes the access information data to the execution result response unit 313.
The access information data includes the identifier of the corresponding content as the access data identifier, the identifier of the distribution destination server as the access server identifier, and the received server identifier group as the corresponding server identifier group.
After S234, the process proceeds to S240.

FIG. 9 is a diagram illustrating an example of the data arrangement file 391 according to the first embodiment.
An example of the data arrangement file 391 in the first embodiment will be described with reference to FIG.
The data arrangement file 391 associates an information field such as content with a server field.
The server indicates an identifier of each of the one or more server apparatuses 300.
The content indicates an identifier of each of one or more pieces of content data stored in the server device 300.

In S240 (see FIG. 7), the process execution unit 312 receives a query execution result from the DB server unit 320.
The process execution unit 312 executes data processing based on the execution result of the query. For example, the process execution unit 312 generates a WEB page using the corresponding content included in the query execution result.
Then, the process execution unit 312 ends the execution of the data process, and generates execution result data indicating the execution result of the data process. For example, the process execution unit 312 generates execution result data including a WEB page generated by data processing.
After S240, the process proceeds to S250.

In S250, the execution result response unit 313 receives the access information data from the access information generation unit 340.
Then, the execution result response unit 313 generates an execution result packet including execution result data and access information data, and transmits the execution result packet to the load distribution apparatus 200.
After S250, the operation of the server apparatus 300 with respect to one distribution packet ends.

In S235 (see FIG. 8), the distributed storage management unit 330 selects, from the data arrangement file 391 (see FIG. 9), a server identifier group associated with the same content data identifier as the corresponding content specified in the access command. To do.
Then, the distributed storage management unit 330 selects one of the server identifiers from the server identifier group. At this time, the distributed storage management unit 330 may select an identifier of the server device 300 with a light load from the server identifier group. The server device 300 with a light load can be identified by a conventional load distribution technique.
The selected server identifier is referred to as a corresponding server identifier, and the server device 300 identified by the corresponding server identifier is referred to as a corresponding server.
After S235, the process proceeds to S236.

In S236, the distributed storage management unit 330 selects an IP address associated with the same server identifier as the corresponding server identifier from the server list file 392. The server list file 392 is a file similar to the server list file 292 described with reference to FIG.
The distributed storage management unit 330 generates a packet addressed to the corresponding server by using the selected IP address as the transmission destination address. This packet is called an access request packet.
The access request packet is a packet for requesting the corresponding server to execute an access command. The access request packet includes an access command.

The distributed storage management unit 330 transmits an access request packet to the corresponding server.
After S236, the process proceeds to S237.

In S237, the distributed storage management unit 330 of the corresponding server receives the access request packet.
The distributed storage management unit 330 of the corresponding server accesses the corresponding content stored in the distributed storage area 399 of the corresponding server according to the access command included in the access request packet.
Then, the distributed storage management unit 330 of the corresponding server generates an access response packet including the execution result of the access command, and transmits the access response packet to the server apparatus 300 that is the transmission source of the access request packet.
After S237, the process proceeds to S238.

In S238, the distributed storage management unit 330 of the distribution destination server receives the access response packet.
In the distribution destination server, the distributed storage management unit 330 delivers the execution result of the access command included in the access response packet to the DB server unit 320.
The DB server unit 320 receives the execution result of the access command, generates a query execution result using the access command execution result, and passes the query execution result to the process execution unit 312 (similar to S233).
After S238, the process proceeds to S239.

In S239, the distributed storage management unit 330 of the distribution destination server receives the identifier of the corresponding content, the server identifier group selected from the data arrangement file 391, and the corresponding server identifier selected from the server identifier group in the access information generation unit 340. hand over.
The access information generation unit 340 receives the identifier of the corresponding content, the server identifier group, and the corresponding server identifier, generates access information data, and transfers the access information data to the execution result response unit 313 (similar to S234).
The access information data includes an identifier of the corresponding content as an access data identifier, includes a server identifier group as a corresponding server identifier group, and includes a corresponding server identifier as an access server identifier.
After S239, the process proceeds to S240 (see FIG. 7). The processing after S240 is as described based on FIG.

FIG. 10 is a hardware configuration diagram of the load distribution apparatus 200 according to the first embodiment.
A hardware configuration of the load distribution apparatus 200 according to Embodiment 1 will be described with reference to FIG. However, the hardware configuration of the load distribution apparatus 200 may not be the same as the configuration shown in FIG.

The load balancer 200 is a computer including an arithmetic device 901, an auxiliary storage device 902, a main storage device 903, a communication device 904, and an input / output device 905.
The arithmetic device 901, auxiliary storage device 902, main storage device 903, communication device 904, and input / output device 905 are connected to the bus 909.

The arithmetic device 901 is a CPU (Central Processing Unit) that executes a program.
The auxiliary storage device 902 is, for example, a ROM (Read Only Memory), a flash memory, or a hard disk device.
The main storage device 903 is, for example, a RAM (Random Access Memory).
The communication device 904 performs communication via the Internet, a LAN (local area network), a telephone line network, or other networks in a wired or wireless manner.
The input / output device 905 is, for example, a mouse, a keyboard, or a display device.

The program is stored in the auxiliary storage device 902.
For example, an operating system (OS) is stored in the auxiliary storage device 902. Further, a program for realizing the function described as “˜unit” is stored in the auxiliary storage device 902.
The program is stored in the auxiliary storage device 902, loaded into the main storage device 903, and executed by the arithmetic device 901.

“Determining”, “Determining”, “Extracting”, “Detecting”, “Settings”, “Registering”, “Selecting”, “Generating”, “To” Information, data, files, signal values or variable values indicating the results of processing such as “input”, “output of”, etc. are stored in the main storage device 903 or the auxiliary storage device 902.

The client device 110 and the server device 300 have the same hardware configuration as that of the load distribution device 200.

According to the first embodiment, for example, the following effects can be obtained.
By providing the correspondence table file 291, the load balancer 200 can distribute processing requests for data processing to an appropriate server device 300. That is, the load distribution apparatus 200 can distribute processing requests for data processing to the server apparatus 300 that stores content data (corresponding content) used in data processing.
If the processing request distribution destination server apparatus 300 stores the corresponding content, the processing request distribution destination server apparatus 300 does not need to communicate with another server apparatus 300 in order to access the corresponding content. Therefore, a processing delay associated with communication between server devices does not occur, and the system throughput is improved.

The first embodiment is an example of a form of the load distribution system 100.
That is, the load distribution system 100 may not include some of the components described in the first embodiment. Further, the load distribution system 100 may include components that are not described in the first embodiment.

Embodiment 2. FIG.
A form of a client server system that does not include the load distribution apparatus 200 will be described.
Hereinafter, items different from the first embodiment will be mainly described. Matters whose description is omitted are the same as those in the first embodiment.

FIG. 11 is a configuration diagram of the client server system 101 according to the second embodiment.
In FIG. 11, a client server system 101 (an example of a data processing system) includes one or more client devices 110 and a plurality of server devices 300.

FIG. 12 is a functional configuration diagram of the client device 110 according to the second embodiment.
In FIG. 12, the client device 110 includes a request accepting unit 210, a correspondence table management unit 220, and a request distribution unit 230, similarly to the load distribution device 200 (see FIG. 2).
In addition, the client device 110 includes a client storage unit 119 (an example of a correspondence table file storage unit) that stores a correspondence table file 291 and a server list file 292.

The operation of the client device 110 in the second embodiment is the same as the operation of the load distribution device 200 in the first embodiment (see FIG. 4).
However, in S110, the request reception unit 210 receives a processing command that the user inputs to the client device 110 instead of receiving a processing request packet.
In S150, the request reception unit 210 displays the execution result data on the screen instead of transmitting the processing response packet.

In the second embodiment, the client device 110 can achieve the same effects as the load distribution device 200 in the first embodiment. In other words, the client device 110 can distribute processing requests for data processing to the server device 300 that stores content data used in data processing.

The second embodiment is an example of a form of the client server system 101.
In other words, the client server system 101 may not include some of the components described in the second embodiment. Further, the client server system 101 may include components that are not described in the second embodiment.

The processing procedure described with reference to the flowcharts in each embodiment is an example of the processing procedure of the method and program according to each embodiment. The method and program according to each embodiment may be realized by a processing procedure partially different from the processing procedure described in each embodiment.

In each embodiment, “to part” can be read as “to process”, “to process”, “to program”, “to apparatus”, and the like.

100 load distribution system, 101 client server system, 109 network, 110 client device, 119 client storage unit, 200 load distribution device, 210 request reception unit, 220 correspondence table management unit, 221 correspondence table reference unit, 222 correspondence table editing unit, 230 request distribution unit, 290 load distribution storage unit, 291 correspondence table file, 292 server list file, 300 server device, 301 WEB server unit, 310 WEB application unit, 311 execution request reception unit, 312 process execution unit, 313 execution result response Part, 320 DB server part, 330 distributed storage management part, 340 access information generation part, 380 content data group, 381 content data A, 382 content data B, 383 Content data C, 384 content data D, 390 server storage unit, 391 data allocation file, 392 server list file, 399 distributed storage area, 901 arithmetic unit, 902 auxiliary storage unit, 903 main storage unit, 904 communication unit, 905 input / output Device, 909 bus.

Claims (7)

1. A correspondence table file storage unit that stores a correspondence table file in which a processing instruction designating data processing is associated with a server identifier of a server device that stores content data used in data processing;
   A processing command receiving unit that receives a first processing command that specifies first data processing using the first content data;
   A correspondence table management unit that selects from the correspondence table file a server identifier associated with the same processing instruction as the first processing instruction received by the processing instruction reception unit;
   A processing distribution device, comprising: a processing distribution unit that requests the server device identified by the server identifier selected by the correspondence table management unit to execute the first data processing.
2. When the server identifier is not selected by the correspondence table management unit because the server identifier associated with the same processing instruction as the first processing instruction is not included in the correspondence table file, the processing distribution unit includes a plurality of servers. The processing distribution apparatus according to claim 1, wherein one of the apparatuses is requested to execute the first data processing.
3. The process distribution unit receives an execution result of the first data process and a server identifier of a server apparatus that stores the first content data from a server apparatus that is a request destination of the first data process,
   The said correspondence table management part matches the server identifier received by the said process distribution part with the said 1st process command, and registers it in the said correspondence table file, The Claim 1 or Claim 2 characterized by the above-mentioned. The processing distribution device described.
4. The correspondence table managing unit registers the plurality of server identifiers in the correspondence table file in association with the first processing instruction when a plurality of server identifiers are received by the processing distribution unit. The processing distribution device according to claim 3.
5. When the plurality of server identifiers are selected by the correspondence table management unit because there are a plurality of server identifiers associated with the same processing instruction as the first processing instruction, the processing distribution unit includes the plurality of server identifiers. 5. The processing distribution device according to claim 1, wherein the server device identified by any one of the server identifiers is requested to execute the first data processing. 6.
6. A processing distribution program that uses a correspondence table file,
   The correspondence table file is a file in which a server identifier of a server device that stores content data used in data processing is associated with a processing instruction that specifies data processing,
   A processing command receiving process for receiving a first processing command for specifying a first data processing using the first content data;
   A corresponding server selection process for selecting, from the correspondence table file, a server identifier associated with the same processing instruction as the first processing instruction received by the processing instruction reception process;
   A process distribution program for causing a computer to execute a process distribution process for requesting a server device identified by a server identifier selected by the corresponding server selection process to execute the first data process.
7. A processing distribution device and a plurality of server devices;
   The processing distribution device stores a correspondence table file storing a correspondence table file in which a processing instruction designating data processing is associated with a server identifier of a server device that stores content data used in data processing;
   A processing command receiving unit that receives a first processing command that specifies first data processing using the first content data;
   When the server identifier associated with the same processing instruction as the first processing instruction received by the processing instruction reception unit is not included in the correspondence table file, the first identifier is included in any of the plurality of server devices. A processing distribution unit that requests execution of the data processing, and receives a result of the execution of the first data processing and a server identifier of the server device that stores the first content data from the requested server device;
   A correspondence server registration unit that registers the first processing instruction in the correspondence table file in association with the server identifier received by the processing distribution unit;
   Each of the plurality of server devices is
   A content data storage unit for storing content data;
   A data arrangement file storage unit for storing a data arrangement file in which a data identifier for identifying content data is associated with a server identifier of a server device that stores the content data;
   A process execution unit for executing the first data process requested from the process distribution device;
   If the first content data is not stored in the content data storage unit, a server identifier associated with the data identifier of the first content data is selected from the data arrangement file and identified by the selected server identifier An access request unit for requesting the server device to access the first content data;
   An execution result response unit that responds to the process distribution device with an execution result of the first data processing executed by the process execution unit and a server identifier selected by the access request unit. Data processing system.

Images