The communication system 300b executes communication of the data transmitted and received by the application 200a with another communication system 300 (for example, the communication system 300a) in accordance with, for example, MultiPath TCP (MPTCP)/IP using the multipath on the network 400. For example, in a case where data to be received is made redundant, the communication system 300b extracts necessary data from the redundant data and transfers the extracted data to the application 200b.

The application 200b receives the data from the application 200a via the communication system 300b, and executes a predetermined process such as a process of storing data in a predetermined storage.

In the computer system 1A, when the data is transmitted: 200a executed in the server 500a to the application 200b executed in the server 500b, the application 200a transmits the predicted bandwidth to the redundancy controller 100 and transfers the data to be transmitted to the communication system 300a. The redundancy controller 100 determines a redundancy to be used when the data of the application 200a is transmitted based on the predicted bandwidth, and sets the redundancy in the communication system 300a. The communication system 300a makes the data redundant in accordance with the redundancy set by the redundancy controller 100, and transmits the redundant data to the communication system 300b of the server 500b using the multipath of the network 400.

The communication system 300b of the server 500b receives the transmitted redundant data via the network, extracts necessary data from the redundant data, and transfers the extracted data to the application 200b. The application 200b executes a predetermined process using the data received from the communication system 300b.

According to the computer system 1A, the data to be transmitted by the application 200a can be dynamically transmitted with an appropriate redundancy between the server 500a and the server 500b.

Next, the redundancy controller 100 will be described in detail.

FIG. 6 is a functional configuration diagram of the redundancy controller according to the first embodiment.

The redundancy controller 100 includes a processing controller 101, a bandwidth-based redundancy limit calculator 1100, a recommended redundancy calculator 1200, a register 1010, a register 1020, a minimum operator 1030, and a maximum operator 1040.

The processing controller 101 integrally controls exchange of various kinds of information with the application 200 and the communication system 300, and exchange of processing and information by each unit provided in the redundancy controller 100. Here, the communication system 300 includes an MPTCP/IP driver 310 and a network: interface card (NIC) driver 320. The MPTCP/IP driver 310 executes communication in accordance with a MPTCP/IP. Specifically, the MPTCP/IP driver 310 duplicates communication target data N times in accordance with a set redundancy N, and transmits respective pieces of the duplicated communication target data to a transmission side through different paths. The NIC driver 320 executes communication corresponding to a NIC.

The bandwidth-based redundancy limit calculator 1100 calculates an upper limit of the redundancy (redundancy limit) for the application in a case where a bandwidth usable by the communication system 300 is taken into consideration, and outputs the upper limit. Details of the bandwidth-based redundancy limit calculator 1100 will be described later.

The recommended redundancy calculator 1200 calculates a recommended value of the redundancy (recommended redundancy) at the time of transmitting the data of the application 200, and outputs the recommended value. Details of the recommended redundancy calculator 1200 will be described later.

The register 1010 stores a minimum value of the redundancy (minimum redundancy) in the communication of the application 200. The register 1020 stores a setting value of a redundancy value (redundancy setting value: current redundancy) in the communication of the application 200.

The minimum operator 1030 outputs a smaller value of the redundancy limit output from the bandwidth-based redundancy limit calculator 1100 and the recommended redundancy output from the recommended redundancy calculator 1200. Accordingly, a value output from the minimum operator 1030 is always equal to or less than the redundancy limit.

The maximum operator 1040 outputs a larger value of an output value from the minimum operator 1030 and the minimum redundancy of the register 1010. The value output is stored as the redundancy setting value in the register 1020 by the processing controller 101, and the redundancy setting value is set in the MPTCP/IP driver 310 of the communication system 300 by the processing controller 101.

Next, a redundancy control process by the redundancy controller 100 will be described.

FIG. 7 is a flowchart of the redundancy control process according to the first embodiment.

The redundancy control process is executed, for example, in a case where the redundancy controller 100 receives the predicted bandwidth from the application 200. The redundancy control process is not limited thereto, and may be executed in a case where there is a change in a packet loss rate or in a case where an overall usage bandwidth changes by a certain amount or more.

First, the processing controller 101 acquires, from the NIC driver 320, a largest bandwidth (maximum bandwidth) usable in the network 400 by the communication system 300, the entire bandwidth (overall usage bandwidth) actually used by the communication system 300, and the packet loss rate (an example of a communication quality indicator) in the communication in the network 400 (10000).

Next, the processing controller 101 transfers the predicted bandwidth, the maximum bandwidth, and the overall usage bandwidth to the bandwidth-based redundancy limit calculator 1100, acquires the redundancy setting value (current redundancy) from the register 1020, transfers the redundancy setting value to the bandwidth-based redundancy limit calculator 1100, and receives an output (redundancy limit) from the bandwidth-based redundancy limit calculator 1100 (10010).

Next, the processing controller 101 transfers the packet loss rate to the recommended redundancy calculator 1200, and receives an output (recommended redundancy) from the recommended redundancy calculator 1200 (10020).

Next, the processing controller 101 inputs the redundancy limit and the recommended redundancy to the minimum operator 1030. The minimum operator 1030 determines a smaller value of the redundancy limit and the recommended redundancy as a candidate redundancy and outputs the determined value to the processing controller 101 (10030).

Next, the processing controller 101 inputs the candidate redundancy to the maximum operator 1040, acquires the minimum redundancy from the register 1010, and inputs the minimum redundancy to the maximum operator 1040. The maximum operator 1040 determines a larger value of the candidate redundancy and the minimum redundancy as the redundancy setting value and outputs the determined value to the processing controller 101 (10040).

The processing controller 101 sets the redundancy setting value in the register 1020, sets the redundancy setting value as a redundancy to be used in the MPTCP/IP driver 310 of the communication system 300 (10050), and brings the redundancy controller 100 into a standby state. Accordingly, in the communication system 300, communication is executed after redundancy is executed in accordance with the redundancy setting value.

Next, the bandwidth-based redundancy limit calculator 1100 will be described in detail.

FIG. 8 is a functional configuration diagram of the bandwidth-based redundancy limit calculator according to the first embodiment.

The bandwidth-based redundancy limit calculator 1100 includes a processing controller 1101, a delay register 1110, a multiplier 1120, a subtracter 1130, a subtracter 1131, and an integer divider 1140.

The processing controller 1101 receives various kinds of information (maximum bandwidth, overall usage bandwidth, predicted bandwidth, and current redundancy) input from the processing controller 101, and integrally controls exchange of processing and information by each unit provided in the bandwidth-based redundancy limit calculator 1100.

The delay register 1110 holds and outputs a last predicted bandwidth (previous predicted bandwidth).

The multiplier 1120 multiplies the input current redundancy by the previous predicted bandwidth to calculate a usage bandwidth at the current (current usage bandwidth) of the application 200 (target application), and outputs the usage bandwidth.

The subtracter 1130 subtracts the current usage bandwidth from the input overall usage bandwidth to calculate a usage bandwidth (another usage bandwidth) used by an application other than the target application, and outputs the usage bandwidth.

The subtracter 1131 subtracts the another usage bandwidth from the input maximum bandwidth to calculate a bandwidth usable at the current (usable bandwidth), and outputs the bandwidth.

The integer divider 1140 divides the usable bandwidth by the predicted bandwidth, obtains an integer value by rounding down a fraction below a decimal point of a quotient thereof, and outputs the integer value as the redundancy limit.

Next, a redundancy limit calculation process executed by the bandwidth-based redundancy limit calculator 1100 will be described.

FIG. 9 is a flowchart of the redundancy limit calculation process according to the first embodiment.

The redundancy limit calculation process is executed, for example, in a case where the bandwidth-based redundancy limit calculator 1100 acquires a calculation instruction (maximum bandwidth, overall usage bandwidth, predicted bandwidth, current redundancy) from the processing controller 101.

First, the processing controller 1101 acquires the previous predicted bandwidth from the delay register 1110, and sets the input predicted bandwidth in the delay register 1110 (11000).

Next, the processing controller 1101 inputs the previous predicted bandwidth and the input current redundancy to the multiplier 1120. The multiplier 1120 multiplies the current redundancy by the previous predicted bandwidth to calculate a current usage bandwidth, and outputs the current usage bandwidth to the processing controller 1101 (11010).

Next, the processing controller 1101 inputs the current usage bandwidth and the input overall usage bandwidth to the subtracter 1130. The subtracter 1130 subtracts the current usage bandwidth from the overall usage bandwidth to calculate another usage bandwidth, and outputs the another usage bandwidth to the processing controller 1101 (11020).

Next, the processing controller 1101 inputs the input maximum bandwidth and the another usage bandwidth to the subtracter 1131. The subtracter 1131 subtracts the another usable bandwidth from the maximum bandwidth to calculate a usable bandwidth, and outputs the usable bandwidth to the processing controller 1101 (11030).

Next, the processing controller 1101 inputs the usable bandwidth and the input predicted bandwidth to the integer divider 1140. The integer divider 1140 divides the usable bandwidth by the predicted bandwidth, obtains an integer value by rounding down a fraction below a decimal point of a quotient thereof, and outputs the integer value as the redundancy limit to the processing controller 1101 (11040).

Next, the processing controller 1101 outputs the redundancy limit to the processing controller 101 (11050), and brings the bandwidth-based redundancy limit calculator 1100 into a standby state. According to the redundancy limit calculation process, in a communication state at that time, it is possible to appropriately calculate the redundancy limit which is the upper limit of the redundancy possible at the time of transmitting data of the predicted bandwidth.

Next, the recommended redundancy calculator 1200 will be described in detail.

FIG. 10 is a functional configuration diagram of the recommended redundancy calculator according to the first embodiment.

The recommended redundancy calculator 1200 includes a processing controller 1201, an additional redundancy setting table processing unit 1210, a register 1220, a register 1230, an adder 1240, and a minimum operator 1250.

The processing controller 1201 receives the packet loss rate input from the processing controller 101, and integrally controls exchange of processing and information by each unit provided in the recommended redundancy calculator 1200.

The additional redundancy setting table processing unit 1210 executes a process of receiving a packet loss rate and outputting a corresponding additional redundancy, including an additional redundancy setting table 1211 indicating a correspondence relation between the packet loss rate and a redundancy to be added (additional redundancy: an example of redundancy specifying information). Details of the additional redundancy setting table processing unit 1210 will be described later.

The register 1220 stores a base value of the redundancy (base redundancy) in the communication of the application 200. The register 1230 stores a maximum value of the redundancy value (maximum redundancy) in the communication of the application 200.

The adder 1240 adds the base redundancy and the additional redundancy to calculate a candidate recommended redundancy, and outputs the candidate recommended redundancy.

The minimum operator 1250 outputs a smaller value of maximum the redundancy and the candidate recommended redundancy as the recommended redundancy.

Next, a recommended redundancy calculation process by the recommended redundancy calculator 1200 will be described.

FIG. 11 is a flowchart of the recommended redundancy calculation process according to the first embodiment.

The recommended redundancy calculation process is executed, for example, in a case where the recommended redundancy calculator 1200 acquires a calculation instruction (packet loss rate) from the processing controller 101.

First, the processing controller 1201 sends the acquired packet loss rate to the additional redundancy setting table processing unit 1210, and acquires an additional redundancy value from the additional redundancy setting table processing unit 1210 (12000).

Next, the processing controller 1201 inputs the additional redundancy value to the adder 1240, acquires the base redundancy from the register 1220, and inputs the base redundancy to the adder 1240. The adder 1240 adds the base redundancy and the additional redundancy value to calculate a candidate recommended redundancy, and outputs the candidate recommended redundancy to the processing controller 1201 (12010).

Next, the processing controller 1201 inputs the candidate recommended redundancy to the minimum operator 1250, acquires a maximum redundancy from the register 1230, and inputs the maximum redundancy to the minimum operator 1250. The minimum operator 1250 outputs a smaller value of the maximum redundancy and the candidate recommended redundancy to the processing controller 1201 as the recommended redundancy (12020).

Next, the processing controller 1201 outputs the recommended redundancy to the processing controller 101 (12030), and brings the recommended redundancy calculator 1200 into a standby state. According to the recommended redundancy calculation process, it is possible to appropriately calculate a recommended redundancy which is an appropriate redundancy in consideration of the packet loss rate, and it is possible to reduce a network load and power consumption.

Next, the additional redundancy setting table processing unit 1210 will be described in detail.

FIG. 12 is a functional configuration diagram of the additional redundancy setting table processing unit according to the first embodiment.

The additional redundancy setting table processing unit 1210 executes a process of managing the additional redundancy setting table 1211.

The additional redundancy setting table 1211 is a table storing a correspondence relation between the packet loss rate and an appropriate additional redundancy value, and stores an entry for each threshold value of the packet loss rate. The entry in the additional redundancy setting table 1211 includes items of a packet loss rate threshold value 1211a and an additional redundancy value 1211b. For the packet loss rate threshold value 1211a, a threshold value (packet loss rate threshold value) of the packet loss rate corresponding to the entry is stored. For the additional redundancy value 1211b, an additional redundancy value in a case of exceeding the packet loss rate threshold value corresponding to the entry (in a case of being equal to or less than a next larger packet loss rate threshold value of another entry) is stored. Accordingly, the example of FIG. 12 indicates that the additional redundancy value is 0 in a case where the packet loss rate is equal to or less than 0.01, the additional redundancy value is 1 in a case where the packet loss rate is larger than 0.01 and equal to or less than 0.1, and the additional redundancy value is 2 in a case where the packet loss rate is larger than 0.1 and equal to or less than 0.5. In the present embodiment, information indicating the relation between the packet loss rate and the additional redundancy value is used, but the present invention is not limited thereto, and information indicating a relation between the packet loss rate and the redundancy may be used.

FIG. 13 is a flowchart of a process of the additional redundancy setting table according to the first embodiment.

The process of the additional redundancy setting table is executed in a case where the packet loss rate is received.

The additional redundancy setting table processing unit 1210 compares the received packet loss rate with the packet loss rate threshold value of the additional redundancy setting table 1211, and searches for an entry having a threshold value smaller than the received packet loss rate (13000). In a case where there are a plurality of entries each having a threshold value smaller than the received packet loss rate, an entry having a maximum threshold value is selected from those entries.

Next, the additional redundancy setting table processing unit 1210 determines whether an entry has been found in the search (13010).

As a result, in a case where an entry is found in the search (Yes in 13010), the additional redundancy setting table processing unit 1210 outputs an additional redundancy value of the found entry to the processing controller 1201 (13020), and returns to the standby state.

On the other hand, in a case where no entry is found in the search (No in 13010), the additional redundancy setting table processing unit 1210 outputs a default additional redundancy value (for example, 0) (13100), and returns to the standby state.

Next, a setting screen for setting the additional redundancy setting table 1211 and the like will be described.

FIG. 14 is a diagram illustrating the setting screen according to the first embodiment.

A setting screen 5000 includes an additional redundancy setting table setting interface 5010, a maximum redundancy setting interface 5020, a base redundancy setting interface 5030, a minimum redundancy setting interface 5040, a Save button 5050, and a Close button 5060.

The additional redundancy setting table setting interface 5010 includes an input area for inputting a value corresponding to each item (packet loss rate threshold value 1211a and additional redundancy value 1211b) of the additional redundancy setting table 1211. The maximum redundancy setting interface 5020 includes an area for inputting a maximum redundancy to be set in the register 1230. The base redundancy setting interface 5030 includes an area for inputting a base redundancy to be set in the register 1220. The minimum redundancy setting interface 5040 includes an area for inputting a minimum redundancy to be set in the register 1010.

The Save button 5050 is a button for receiving an instruction to set each value set on the setting screen 5000 to each setting destination (storage destination). When the Save button 5050 is pressed, the additional redundancy setting table processing unit 1210 stores a value of each item input to the additional redundancy setting table setting interface 5010 in the additional redundancy setting table 1211. The Close button 5060 is a button for receiving an instruction to close the setting screen 5000, and when the Close button 5060 is pressed, the setting screen 5000 is closed.

In the present embodiment, values to the additional redundancy setting table 1211 and the like are set using the setting screen 5000 similar to a graphical user interface (GUI), but a method of setting the values to the additional redundancy setting table 1211 and the like is not limited thereto, and the values may be set using, for example, a command line interface (CLI).

Second Embodiment

Next, a computer system according to a second embodiment will be described. The second embodiment is an example of a computer system that can cope with a case where there are a plurality of applications (target applications) for which the redundancy is dynamically adjusted.

In the case where there are a plurality of target applications for which the redundancy is dynamically adjusted, the plurality of applications share a same communication system 300, so that it is necessary to arbitrate an increase in redundancy among the plurality of applications so as not to exceed a maximum bandwidth usable in the communication system 300. Therefore, a computer system 1B according to the second embodiment has a function of arbitrating an increase in redundancy among a plurality of applications with respect to the computer system 1A according to the first embodiment.

FIG. 15 is a configuration diagram of the computer system according to the second embodiment. Functional portions similar to those of the computer system 1A according to the first embodiment are denoted by the same reference numerals.

The computer system 1B includes a plurality of servers 501 (501a and 501b), and the server 501a and the server 501b are connected via the network 400. A hardware configuration of the server 501 is the same as that of the server 500 illustrated in FIG. 1, and in the following description, the same reference numerals as those of the server 500 are used for the hardware configuration.

The server 501a executes a plurality of applications 200 (200a, 200c, and 200e) for which the redundancy is dynamically adjusted. The server 501a includes a redundancy controller 110 instead of the redundancy controller 100 in the server 500a. The server 501a may execute one or more applications (non-target applications) for which the redundancy is not dynamically adjusted, and the communication system 300a may execute communication processing of the non-target applications. The redundancy controller 110 is mainly implemented by the CPU 510 executing a program. The server 501b includes a plurality of applications 200 (200b, 200d, and 200f) and a communication system 300b.

For example, the application 200a (200c and 200e) receives an I/O request for data with respect to the server 501b from a terminal (not illustrated), and executes data exchange of target data with the application 200b (200d and 200f) of the server 501b. FIG. 15 illustrates an example in which the application 200a transmits data to the application 200b, the application 200c transmits data to the application 200d, and the application 200e transmits data to the application 200f.

The redundancy controller 110 dynamically adjusts redundancy in communication for each application.

Next, the redundancy controller 110 will be described in detail.

FIG. 16 is a functional configuration diagram of the redundancy controller according to the second embodiment. In FIG. 16, the same components as those of the redundancy controller 100 according to the first embodiment are denoted by the same reference numerals.

The redundancy controller 110 does not include the registers 1010 and 1020 in the redundancy controller 100, newly includes an application-specific setting table processing unit 2000, includes a processing controller 111 instead of the processing controller 101, includes a bandwidth-based redundancy limit calculator 2100 instead of the bandwidth-based redundancy limit calculator 1100, and includes a recommended redundancy calculator 2200 instead of the recommended redundancy calculator 1200.

In the present embodiment, the application 200 is implemented to output an application identifier (application ID) in addition to the predicted bandwidth, and the redundancy controller 110 receives the application identifier and the predicted bandwidth from the application 200.

The bandwidth-based redundancy limit calculator 2100 calculates a redundancy limit in a bandwidth usable by the communication system 300, and outputs the redundancy limit. Details of the bandwidth-based redundancy limit calculator 2100 will be described later.

The recommended redundancy calculator 2200 calculates a recommended redundancy at the time of transmitting data of the application 200, and outputs the recommended redundancy. Details of the recommended redundancy calculator 2200 will be described later.

The application-specific setting table processing unit 2000 executes a management of an application-specific setting table 2001 that stores setting information specific to each application 200. Details f the application-specific setting table processing unit 2000 will be described later.

Next, a redundancy control process by the redundancy controller 110 will be described.

FIG. 17 is a flowchart of the redundancy control process according to the second embodiment.

The redundancy control process is executed, for example, in a case where the redundancy controller 110 receives the application identifier and the predicted bandwidth from the application 200. The redundancy control process is not limited thereto, and may be executed in a case where there is a change in a packet loss rate or in a case where an overall usage bandwidth changes by a certain amount or more.

First, the processing controller 111 acquires the maximum bandwidth, the overall usage bandwidth, and the packet loss rate from the NIC driver 320 (10000).

Next, the processing controller 111 transfers the acquired application identifier and predicted bandwidth to the application-specific setting table processing unit 2000, and receives an output (previous predicted bandwidth, priority coefficient, current redundancy, base redundancy, and maximum redundancy) from the application-specific setting table processing unit 2000 (20010).

Next, the processing controller 111 transfers the acquired predicted bandwidth, maximum bandwidth, overall usage bandwidth, current redundancy, priority coefficient, and previous predicted bandwidth to the bandwidth-based redundancy limit calculator 2100, and receives an output (redundancy limit) from the bandwidth-based redundancy limit calculator 2100 (20015).

Next, the processing controller 111 transfers the packet loss rate, the base redundancy, and the maximum redundancy to the recommended redundancy calculator 2200, and receives an output (recommended redundancy) from the recommended redundancy calculator 2200 (20020).

Next, the processing controller 111 inputs the redundancy limit and the recommended redundancy to the minimum operator 1030. The minimum operator 1030 determines a smaller value of the redundancy limit and the recommended redundancy as a candidate redundancy and outputs the determined value to the processing controller 111 (20030).

Next, the processing controller 111 inputs the candidate redundancy and the minimum redundancy to the maximum operator 1040. The maximum operator 1040 determines a larger value of the candidate redundancy and the minimum redundancy as the redundancy setting value and outputs the determined value to the processing controller 111 (20040).

Next, the processing controller 111 sets the redundancy setting value as the redundancy to be used in the MPTCP/IP driver 310 of the communication system 300, transfers the redundancy setting value to the application-specific setting table processing unit 2000, updates the current redundancy (20050), and brings the redundancy controller 110 into a standby state. Accordingly, in the communication system 300, communication is executed after redundancy is executed in accordance with the setting value.

Next, the bandwidth-based redundancy limit calculator 2100 will be described in detail.

FIG. 18 is a functional configuration diagram of the bandwidth-based redundancy limit calculator according to the second embodiment. The same components as those of the bandwidth-based redundancy limit calculator 1100 according to the first embodiment are denoted by the same reference numerals.

The bandwidth-based redundancy limit calculator 2100 does not include the delay register 1110, further includes a multiplier 2110, includes a processing controller 2101 instead of the processing controller 1101, and includes an integer divider 2130 instead of the integer divider 1140.

The processing controller 2101 receives various kinds of information (maximum bandwidth, overall usage bandwidth, current redundancy, predicted bandwidth, priority coefficient, and previous predicted bandwidth) input from the processing controller 111, and integrally controls exchange of processing and information by each unit provided in the bandwidth-based redundancy limit calculator 2100.

The multiplier 2110 multiplies the input predicted bandwidth and priority coefficient to calculate a priority-considered bandwidth which is a bandwidth for the application 200 (target application) in consideration of the priority of the application, and outputs the priority-considered bandwidth.

The integer divider 2130 divides a usable bandwidth by the priority-considered bandwidth, obtains an integer value by rounding down a fraction below a decimal point of a quotient thereof, and outputs the integer value as the redundancy limit.

Next, a redundancy limit calculation process executed by the bandwidth-based redundancy limit calculator 2100 will be described.

FIG. 19 is a flowchart of the redundancy limit calculation process according to the second embodiment.

In FIG. 19, processing similar to those of the redundancy limit calculation process according to the first embodiment are denoted by the same reference numerals.

The redundancy limit calculation process is executed, for example, in a case where the bandwidth-based redundancy limit calculator 2100 acquires a calculation instruction (maximum bandwidth, overall usage bandwidth, current redundancy, predicted bandwidth, priority coefficient, and previous predicted bandwidth) from the processing controller 111.

First, the processing controller 2101 executes steps 11010, 11020, and 11030 in the same manner as the processing controller 1101.

Next, the processing controller 2101 inputs the predicted bandwidth and the priority coefficient to the multiplier 2110. The multiplier 2110 multiplies the predicted bandwidth by the priority coefficient to calculate a priority-considered bandwidth, and outputs the priority-considered bandwidth to the processing controller 2101 (21030).

Next, the processing controller 2101 inputs the usable bandwidth and the priority-considered bandwidth to the integer divider 2130. The integer divider 2130 divides the usable bandwidth by the priority-considered bandwidth, obtains an integer value by rounding down a fraction below a decimal point of a quotient thereof, and outputs the integer value as the redundancy limit to the processing controller 2101 (21040).

Next, the processing controller 2101 outputs the redundancy limit to the processing controller 111 (21050), and brings the bandwidth-based redundancy limit calculator 2100 into a standby state. According to the redundancy limit calculation process, it is possible to appropriately calculate the redundancy limit, which is the upper limit of the redundancy possible at the time of transmitting the data of the predicted bandwidth, in a communication state at that time in consideration of the priority of the application.

Next, the recommended redundancy calculator 2200 will be described in detail.

FIG. 20 is a functional configuration diagram of the recommended redundancy calculator according to the second embodiment. The same components as those of the recommended redundancy calculator 1200 according to the first embodiment are denoted by the same reference numerals.

The recommended redundancy calculator 2200 does not include the registers 1220 and 1230, and includes a processing controller 2201 instead of the processing controller 1201.

The processing controller 2201 receives various kinds of information (packet loss rate, maximum redundancy, and base redundancy) input from the processing controller 111, and integrally controls exchange of processing and information by each unit provided in the recommended redundancy calculator 2200.

Next, a recommended redundancy calculation process by the recommended redundancy calculator 2200 will be described.

FIG. 21 is a flowchart of the recommended redundancy calculation process according to the second embodiment. In FIG. 21, processing steps similar to those of the recommended redundancy calculation process according to the first embodiment are denoted by the same reference numerals.

The recommended redundancy calculation process is executed, for example, in a case where the recommended redundancy calculator 2200 acquires a calculation instruction (packet loss rate, base redundancy, and maximum redundancy) from the processing controller 111.

First, the processing controller 2201 executes step 12000 in the same manner as the processing controller 1201.

Next, the processing controller 2201 inputs the base redundancy and the additional redundancy value to the adder 1240. The adder 1240 adds the base redundancy and the additional redundancy value to calculate a candidate recommended redundancy, and outputs the candidate recommended redundancy to the processing controller 2201 (22010).

Next, the processing controller 2201 inputs the maximum redundancy and the candidate recommended redundancy to the minimum operator 1250. The minimum operator 1250 outputs a smaller value of the maximum redundancy and the candidate recommended redundancy to the processing controller 2201 as the recommended redundancy (22020).

Next, the processing controller 2201 outputs the recommended redundancy to the processing controller 111 (22030), and brings the recommended redundancy calculator 2200 into a standby state. According to the recommended redundancy calculation process, it is possible to calculate a recommended redundancy which is an appropriate redundancy in a case where the packet loss rate is taken into consideration, and it is possible to reduce a network load and power consumption.

Next, the application-specific setting table processing unit 2000 will be described in detail.

FIG. 22 is a functional configuration diagram of the application-specific setting table processing unit according to the second embodiment.

The application-specific setting table processing unit 2000 executes a process of managing the application-specific setting table 2001.

The application-specific setting table 2001 is a table for managing various kinds of information for each application, and stores an entry for each application. The entry of the application-specific setting table 2001 includes items of an application ID 2001a, a priority coefficient 2001b, a maximum redundancy 2001c, a base redundancy 2001d, a minimum redundancy 2001e, a current redundancy 2001f, and a predicted bandwidth (previous) 2001g.

The application ID 2001a stores application identification information of an application corresponding to the entry. The priority coefficient 2001b stores a coefficient of priority (priority coefficient: communication priority) for a bandwidth used by the application corresponding to the entry. The priority coefficient is, for example, 1.0 for an application having a highest priority (bandwidth can be preferentially used), and the priority coefficient increases as the priority decreases. The maximum redundancy 2001c stores a maximum value of a redundancy (maximum redundancy) for the application corresponding to the entry. The base redundancy 2001d stores a base value of the redundancy (base redundancy) in the application corresponding to the entry. The minimum redundancy 2001e stores a minimum value of the redundancy (minimum redundancy) of the application corresponding to the entry. The current redundancy 2001f stores a redundancy at the current (current redundancy) set for the application corresponding to the entry. The predicted bandwidth (previous) 2001g stores a previous predicted bandwidth of the application corresponding to the entry.

FIG. 23 is a flowchart of a process of the application-specific setting table according to the second embodiment.

The process of the application-specific setting table is executed by the application-specific setting table processing unit 2000 in a case where the application identifier and the predicted bandwidth are received or in a case where the application identifier and the current redundancy are received. The application-specific setting table processing unit 2000 executes steps 23000 to 23120 in the case where the application identifier and the predicted bandwidth are received, and executes steps 23200 to 23220 in the case where the application identifier and the current redundancy are received.

In the case where the application identifier and the predicted bandwidth are received, the application-specific setting table processing unit 2000 searches the application-specific setting table 2001 for an entry matching the application identifier (23000), and determines whether the entry matching the application identifier is found (23010).

As a result, in a case where the entry matching the application identifier is found (Yes in 23010), the application-specific setting table processing unit 2000 outputs a priority coefficient, a maximum redundancy, a base redundancy, a minimum redundancy, a current bandwidth, and a predicted bandwidth of the found entry to the processing controller 111 (23020), updates the predicted bandwidth of the predicted bandwidth (previous) 2001g of this entry to a received predicted bandwidth (23030), and enters a standby state.

On the other hand, in a case where no entry matching the application identifier is found (No in 23010), the application-specific setting table processing unit 2000 outputs a default priority coefficient (for example, 1.0), a default maximum redundancy (for example, 1), a default base redundancy (for example, 1), a default minimum redundancy (for example, 1), and a default predicted bandwidth (for example, 0) to the processing controller 111 (23120), and enters a standby state.

On the other hand, in the case where the application identifier and the current redundancy are received, the application-specific setting table processing unit 2000 searches the application-specific setting table 2001 for an entry matching the application identifier (23200), and determines whether the entry matching the application identifier is found (23210).

As a result, in a case where the entry matching the application identifier is found (Yes in 23210), the application-specific setting table processing unit 2000 updates the current redundancy of the current redundancy 2001f of the found entry to a received current redundancy width (23220), and enters a standby state. On the other hand, in a case where no entry matching the application identifier is found (No in 23210), the application-specific setting table processing unit 2000 enters a standby state.

Next, a setting screen for setting the application-specific setting table 2001 will be described.

FIG. 24 is a diagram illustrating the setting screen according to the second embodiment.

A setting screen 5100 includes an application-specific setting table setting interface 5110, a Save button 5120, and a Close button 5130.

The application-specific setting table setting interface 5110 includes an input area for inputting values corresponding to a plurality of items (application ID 2001a, priority coefficient 2001b, maximum redundancy 2001c, base redundancy 2001d, and minimum redundancy 2001e) set by a user of the application-specific setting table 2001. The Save button 5120 is a button for receiving an instruction to set each value set in the application-specific setting table setting interface 5110 in the application-specific setting table 2001. When the Save button 5120 is pressed, the application-specific setting table processing unit 2000 stores a value of each item input to the application-specific setting table setting interface 5110 in the application-specific setting table 2001. The Close button 5130 is a button for receiving an instruction to close the setting screen 5100, and when the Close button 5130 is pressed, the setting screen 5100 is closed.

In the present embodiment, values to the application-specific setting table 2001 are set using the setting screen 5100 similar to a graphical user interface (GUI), but a method of setting the values to the application-specific setting table 2001 limited thereto, and the values may be set using, for example, a command line interface (CLI).

Third Embodiment

Next, a computer system according to a third embodiment will be described. The third embodiment is an example of a computer system in which there are a plurality of applications for which the redundancy is dynamically adjusted, and the redundancy can be adjusted in consideration of a restriction (for example, a restriction on a communication cost, the communication cost being a metered rate system) other than a bandwidth usable by the application.

The computer system according to the third embodiment includes a redundancy controller 120 (see FIG. 25) instead of the redundancy controller 110 in the computer system 1B according to the second embodiment.

Next, the redundancy controller 120 will be described in detail.

FIG. 25 is a functional configuration diagram of the redundancy controller according to the third embodiment. In FIG. 25, the same components as those of the redundancy controller 110 according to the second embodiment are denoted by the same reference numerals.

The redundancy controller 120 newly includes a redundancy arbiter 3300 in the redundancy controller 110, includes a processing controller 121 instead of the processing controller 111, and includes an application-specific setting table processing unit 3000 instead of the application-specific setting table processing unit 2000.

The redundancy arbiter 3300 executes a process of adjusting the maximum redundancy based on another constraint condition different from a constraint condition of the bandwidth. Details of the redundancy arbiter 3300 will be described later.

The application-specific setting table processing unit 3000 executes a management of the application-specific setting table 2001 that stores setting information specific to each application 200.

Details of the application-specific setting table processing unit 3000 will be described later.

Next, a redundancy control process by the redundancy controller 120 will be described.

FIG. 26 is a flowchart of the redundancy control process according to the third embodiment. Processing steps similar to those of the redundancy control process according to the second embodiment (see FIG. 17) are denoted by the same reference numerals.

The redundancy control process is executed, for example, in a case where the redundancy controller 120 receives the application identifier and the predicted bandwidth from the application 200. The redundancy control process is not limited thereto, and may be executed in a case where there is a change in a packet loss rate or in a case where an overall usage bandwidth changes by a certain amount or more.

First, the processing controller 121 executes a process of step 20000 in the same manner as the processing controller 111.

Next, the processing controller 121 transfers the acquired application identifier and predicted bandwidth to the application-specific setting table processing unit 3000, and receives an output (previous predicted bandwidth, priority coefficient, current redundancy, and base redundancy) from the application-specific setting table processing unit 3000 (30010).

Next, the processing controller 121 executes a process of step 20015 in the same manner as the processing controller 111.

Next, the processing controller 121 sends the application identifier to the redundancy arbiter 3300, and receives an output (post-arbitration maximum redundancy) from the redundancy arbiter 3300 (30020).

Next, the processing controller 121 transfers the packet loss rate, the base redundancy, and the post-arbitration maximum redundancy to the recommended redundancy calculator 2200, and receives an output (recommended redundancy) from the recommended redundancy calculator 2200 (30025).

Next, the processing controller 121 executes processes of steps 20030 and 20040 in the same manner as the processing controller 111.

Next, the processing controller 121 sets the redundancy setting value as the redundancy to be used in the MPTCP/IP driver 310 of the communication system 300, transfers the redundancy setting value to the application-specific setting table processing unit 3000, updates the current redundancy (30050), and brings the redundancy controller 120 into a standby state. Accordingly, in the communication system 300, communication is executed after redundancy is executed in accordance with the setting value.

Next, the redundancy arbiter 3300 will be described in detail.

FIG. 27 is a functional configuration diagram of the redundancy arbiter according to the third embodiment.

The redundancy arbiter 3300 includes a processing controller 3301, a parameter requester 3310, a parameter requester 3320, a product sum operator 3330, a multiplier 3340, a comparator 3350, a selector 3360, a register 3370, and a register 3380.

The processing controller 3301 receives the application identifier input from the processing controller 101, and integrally controls processing by each unit provided in the redundancy arbiter 3300.

The register 3370 stores an arbiter coefficient for calculating a value (arbiter evaluation value) corresponding to a constraint condition (additional constraint condition) used for arbitration based on the bandwidth. In the present embodiment, for example, when the constraint condition is set as a communication charge, the arbiter coefficient is a coefficient for converting the bandwidth into a communication charge per unit time. The register