JP6822032B2 - Processing decision device, processing decision method, and processing decision program - Google Patents

Description

The present invention relates to, for example, a processing decision device that determines a process to be executed when an information processing device transmits data.

IP (Internet Protocol) is an example of a protocol that follows the case of communicating data on a communication network such as the Internet. Two types of IP addresses, an IPv4 address and an IPv6 address, have been developed as IP addresses assigned to the information processing device when the information processing device communicates. IPv4 represents Internet Protocol version 4. IPv6 represents Internet Protocol version 6. As a result of the shortage of IPv4 addresses due to the explosive increase in the number of information processing devices connected to the Internet, IPv6 addresses have been developed and the use of IPv6 addresses is expanding. Comparing IPv4 and IPv6, there are differences in the method of noting the address, the method of processing packets in the relay device, and the like. The difference between IPv4 and IPv6 will be specifically described in the embodiment with reference to FIG.

Here, IP will be described. In IP, communication processing is executed in units called packets. A packet is roughly classified into an IP header containing information on a destination device and the like, and IP data including data to be communicated.

When transmitting the target data to the destination device via the communication network, the source device creates a packet including an IP address indicating the destination device, and transmits the created packet to the relay device (for example, a router). .. The relay device transfers the received packet to the destination device or another relay device in the communication path to the destination device. In a series of processes from the process of transmitting a packet by the source device to the process of receiving the packet by the destination device, a plurality of relay devices may execute a transfer process related to the packet. Each relay device selects an appropriate transfer destination relay device based on the IP address representing the destination device included in the received packet, and transmits the packet to the selected relay device. The process of transferring a packet between a plurality of relay devices is executed until the packet arrives at the destination device.

Non-Patent Document 1 is a method of determining the maximum packet size that can be processed in a communication network in which a source device and a destination device are communicated with each other before the source device transmits a packet to the destination device. Is disclosed.

Patent Document 1 and Patent Document 2 disclose an information processing system that sets a maximum packet size when communicating via a communication network.

The information processing system disclosed in Patent Document 1 changes the maximum packet size used in communication processing via the communication network when the window size related to the communication network is larger than a predetermined value. Here, the window size represents the amount of data that can be continuously transmitted to the communication network without waiting for an acknowledgment.

The information processing system disclosed in Patent Document 2 determines the maximum packet size that does not cause a retransmission timeout according to a predetermined procedure based on the round-trip time required for the round-trip processing of data reciprocating between the source device and the destination device. Then, the communication process is executed based on the determined maximum packet size.

Patent Document 3 discloses a communication device that updates the maximum value (PMTU: Path Maximum Transfer Unit) of packets that can be transmitted to the shortest communication path in a communication network. The communication device has a packet length table in which the lengths of packets associated with a communication network to which the destination device can communicate can be stored. The communication device notifies the maximum packet size for the communication network when the length of the packet transmitted to the destination device is longer than the length of the packet for the communication network stored in the table. Further, the length of the packet related to the communication network is updated to the maximum packet size.

Japanese Unexamined Patent Publication No. 2012-039191 Japanese Unexamined Patent Publication No. 2011-166418 International Publication No. 2012/1204035

"Path MTU Discovery for IPv6", [online], August 1996, RFC 1981, [Search September 14, 2016], Internet (URL: https: //tools.ietf.org/html/rfc1981) "Internet Protocol, Version 6 (IPv6) Specialization", [online], December 1998, RFC2460, [Search September 14, 2016], Internet (https://tools.ietf.org/html/rfc2460)

However, in the method disclosed in Non-Patent Document 1, the acquisition process of acquiring the maximum packet size that can be processed by the relay device from each relay device that executes the transfer process on the communication path from the source device to the destination device. is necessary. A certain processing time is required for the acquisition processing. When a packet is transmitted from the source device to the destination device with as little delay as possible, the acquisition process contributes to a communication delay.

Further, even if the maximum packet size is acquired by using the techniques described in Patent Documents 1 to 3 and the communication process is executed according to the acquired maximum packet size, the acquisition to acquire the maximum packet size is not necessarily obtained. The time required from the process to the communication process is not always short. The reason for this is that the acquisition time required for the acquisition process may be long.

Therefore, one of the objects of the present invention is to provide a processing determination device or the like capable of realizing efficient communication regarding communication processing between a plurality of information processing devices.

As one aspect of the present invention, the processing determination device is
When the target data is transmitted from the source device to the destination device, it is possible to communicate on the communication path with respect to the processing procedure representing the content of the process executed on the communication path between the source device and the destination device. An acquisition time calculation means for calculating the acquisition time required for the acquisition process to acquire an appropriate packet size,
A communication time calculation means that obtains the throughput related to the communication path based on the packet size related to the communication processing, and calculates the communication time required for the communication processing based on the obtained throughput and the size of the target data.
The required time obtained by totaling the acquisition time calculated by the acquisition time calculating means and the communication time calculated by the communication time calculating means is calculated for a plurality of types of processing procedures, and the calculated required time is short. A process selection means for selecting a procedure is provided.

Further, as another aspect of the present invention, the processing determination method is
When the target data is transmitted from the source device to the destination device, it is possible to communicate on the communication path with respect to the processing procedure representing the content of the process executed on the communication path between the source device and the destination device. Calculate the acquisition time required for the acquisition process to acquire the appropriate packet size.
The throughput related to the communication path is obtained based on the packet size related to the communication processing, and the communication time required for the communication processing is calculated based on the obtained throughput and the size of the target data.
The total required time of the calculated acquisition time and the calculated communication time is calculated for a plurality of types of processing procedures, and the calculated processing procedure with the short required time is selected.

Further, as another aspect of the present invention, the processing decision program
When the target data is transmitted from the source device to the destination device, it is possible to communicate on the communication path with respect to the processing procedure representing the content of the process executed on the communication path between the source device and the destination device. The acquisition time calculation function that calculates the acquisition time required for the acquisition process to acquire the packet size,
A communication time calculation function that obtains the throughput related to the communication path based on the packet size related to the communication processing and calculates the communication time required for the communication processing based on the obtained throughput and the size of the target data.
The required time, which is the sum of the acquisition time calculated by the acquisition time calculation function and the communication time calculated by the communication time calculation function, is calculated for a plurality of types of processing procedures, and the calculated required time is calculated. The computer is provided with a process selection function that selects a short process procedure.

Further, the same purpose is realized by a computer-readable recording medium for recording the program.

According to the processing determination device and the like according to the present invention, efficient communication can be realized for communication processing between a plurality of information processing devices.

It is a block diagram which shows the structure which the processing decision apparatus which concerns on 1st Embodiment of this invention has. It is a flowchart which shows the flow | flow of the process in the process decision apparatus which concerns on 1st Embodiment. It is a figure which conceptually represents an example of the network information stored in the network information storage part. It is a figure which shows an example of the required time about the 2nd processing procedure, and an example of the required time about the 1st processing procedure. It is a block diagram which shows an example of the structure which an information processing system has. It is a block diagram which shows the structure which the processing decision system which concerns on 2nd Embodiment of this invention has. It is a flowchart which shows the flow of process in the process decision system which concerns on 2nd Embodiment. It is a block diagram which shows an example of the structure which an information processing system has. It is a figure which conceptually represents an example of network information. It is a block diagram which shows the structure which the processing decision apparatus which concerns on 3rd Embodiment of this invention has. It is a flowchart which shows the flow of the process in the process decision apparatus which concerns on 3rd Embodiment. It is a block diagram which shows schematic the hardware configuration example of the calculation processing apparatus which can realize the processing decision apparatus which concerns on each embodiment of this invention. It is a figure which conceptually represents the communication process according to IPv4, and the communication process according to IPv6.

First, in order to facilitate understanding of the present invention, IPv4 and IPv6 will be described with reference to FIG. FIG. 13 is a diagram conceptually representing communication processing according to IPv4 and communication processing according to IPv6. FIG. 13A conceptually represents communication processing according to IPv4. FIG. 13B conceptually represents communication processing according to IPv6.

The relay device executes a transfer process of transferring the received data to an information processing device different from the own device in the communication path from the source device to the destination device. According to IPv4, the maximum value (that is, the maximum packet size) is set for the size of packets that can be processed at one time for each relay device. When each relay device receives a packet having a size larger than the maximum packet size, each relay device divides the received packet into a plurality of packets having a size equal to or less than the maximum packet size, and the packet obtained by the division. The transfer process related to is executed.

For convenience of explanation, in the case of the example shown in FIG. 13, the maximum packet size for the relay device is assumed to be, for example, 1500 bytes (bytes). Further, a packet having a size of X (where X represents a natural number) bytes is referred to as an "X-byte packet".

Referring to FIG. 13 (A), the source device transmits the 2000-byte packet 1001 to be transmitted toward the destination device (packet 1002 in FIG. 13 (A)).

The relay device in the communication path receives the packet 1002. When the relay device receives the 2000-byte packet 1002, the relay device divides the packet 1001 into a 1500-byte packet 1004 and a 500-byte packet 1003 according to the specifications related to IPv4, and executes a transfer process related to these two packets.

On the other hand, in IPv6, the function of the relay device to divide the packet is abolished. In IPv6, the source device is determined to divide the packet into packets having a size equal to or less than the maximum packet size of the relay device, and transmit the packet obtained by the division to the communication network.

Referring to FIG. 13B, for example, it is assumed that the source device transmits the 2000-byte packet 1101 toward the destination device. In this case, the relay device that has received the packet from the source device transmits information indicating that the size of the packet is larger than the maximum packet size (1500 bytes in this example) to the source device. The source device receives the information, divides the packet into a 1500-byte packet 1103 and a 500-byte packet 1102 according to the received information, and transmits these two packets to the destination device. The relay device receives the packet 1102 and the packet 1103, and executes a transfer process of transferring the received packet 1102 and the packet 1103 to the destination device (packet 1104 and packet 1105 in FIG. 13B). .. Therefore, in IPv6, the source device may execute the acquisition process in advance to acquire the maximum packet size regarding the communication path to the destination device.

Next, an embodiment of the present invention will be described in detail with reference to the drawings.

<First Embodiment>
The configuration of the processing determination device 101 according to the first embodiment of the present invention will be described in detail with reference to FIG. FIG. 1 is a block diagram showing a configuration of the processing determination device 101 according to the first embodiment of the present invention.

The processing determination device 101 according to the first embodiment includes an input unit 102, a first processing time calculation unit 103, a second processing time calculation unit 104, and a processing determination unit 105. The processing determination device 101 may further include a network information storage unit 106.

Network information (exemplified in FIG. 3) can be stored in the network information storage unit 106. The network information stored in the network information storage unit 106 will be described with reference to FIG. FIG. 3 is a diagram conceptually representing an example of network information stored in the network information storage unit 106.

In the network information, the destination identifier representing the destination device, the packet size in the communication processing executed in the communication path between the source device and the destination device, and the number of relay devices in the communication path are associated with each other. In the network information, the source identifier representing the source device, the packet loss rate indicating the degree of packet loss in which packets are lost in the communication path, and the packet size in the communication processing executed in the communication path. It may be associated with the minimum value of (hereinafter referred to as "minimum packet size"). Further, in the network information, the packet size may be the maximum packet size. The number of relay devices may be, for example, the number of hops in the communication path.

In the network information stored in the network information storage unit 106 illustrated in FIG. 3, the source identifier “AAAA”, the destination identifier “BBBB”, the packet size “1500”, the minimum packet size “100”, and the like, The packet loss rate "0.1" and the number of relay devices "4" are associated with each other. This is because the packet size is 1500 bytes, the minimum packet size is 100 bytes, and the number of relay devices in the communication path is four with respect to the communication path from the source device AAAA to the destination device BBBB. It means that the packet loss rate for the route is 0.1%. The network information may be information representing the history of communication executed via the communication network, or may be information created for the communication network.

The network information does not necessarily include all the items illustrated in FIG. For example, when the network information related to the communication processing in the source device is stored in the own device, the source identifier is an identifier representing the own device. In this case, the network information does not need to include the source identifier. In addition, the network information may include values related to items other than the items illustrated in FIG. 3 (for example, FIG. 9). The network information is not limited to the example shown in FIG.

The process determination device 101 performs a process in which the required time is short according to the process described later with reference to FIG. 2 from among a plurality of process procedures as exemplified in the first process procedure to the third process procedure described below. Select a procedure.

○ (1st processing procedure) A processing procedure for dividing the target data into packets with a predetermined packet size (for example, the minimum packet size indicated in a protocol such as IPv6) and executing a communication process for transmitting the packet.
○ (Second processing procedure) The acquisition process of acquiring the packet size that can be communicated in the communication path between the source device and the destination device is executed from the relay device, and the target data is converted into a packet according to the acquired packet size. A processing procedure for executing a communication process of dividing and transmitting the packet. For convenience of explanation, the packet size acquired from the relay device is referred to as the "first maximum packet size" according to the process described with reference to Patent Documents 1 to 3, and the like.
○ (Third processing procedure) The maximum packet size that can be communicated in the communication path is specified based on the storage device (for example, network information), the target data is divided into packets according to the specified maximum packet size, and the packet is divided into packets. Processing procedure to send.

In the following description, for convenience of explanation, the target data to be transmitted from the source device to the destination device can be created based on one or more packets including the divided data of the target data. And. Further, it is assumed that the target data size is the total value of the sizes of each packet. Further, it is assumed that the network information is stored in the source device and does not include the source identifier.

Next, the processing in the processing determination device 101 according to the first embodiment of the present invention will be described in detail with reference to FIG. FIG. 2 is a flowchart showing a processing flow in the processing determination device 101 according to the first embodiment.

The input unit 102 is, for example, the data size of the target data to be transmitted from the external device or the like to the destination device (hereinafter referred to as “target data size”), and the destination identifier representing the destination device. Enter information about etc. The input unit 102 outputs the target data size and the destination identifier of the input information to the first processing time calculation unit 103 and the second processing time calculation unit 104.

The first processing time calculation unit 103 inputs the target data size output by the input unit 102 and the destination identifier.

The first processing time calculation unit 103 specifies the number of units associated with the destination identifier (that is, the number of relay devices in the communication path) based on the network information (exemplified in FIG. 3). That is, the first processing time calculation unit 103 specifies the number of relay devices in the communication path from the source device to the destination device based on the network information (exemplified in FIG. 3). The first processing time calculation unit 103 acquires the first maximum packet size related to the communication path based on the specified number and the round-trip time required for the round-trip processing in which data reciprocates between the two information processing devices. The acquisition time required for the above is calculated (step S101). For example, the first processing time calculation unit 103 calculates the round-trip time for the specified number of units as the acquisition time.

Next, the first processing time calculation unit 103 specifies the packet size associated with the destination identifier and the packet loss rate associated with the destination identifier based on the network information (exemplified in FIG. 3). The first processing time calculation unit 103 calculates the specified maximum value of the packet size (referred to as "second maximum packet size" for convenience of explanation). The first processing time calculation unit 103 transmits the target data to the calculated second maximum packet size and the specified packet loss rate according to a processing procedure as described later with reference to Equation 1. The communication time required for the communication process of transmitting from to the destination device is calculated (step S102).

The first processing time calculation unit 103 calculates the total value of the calculated acquisition time and the calculated communication time as the required time required for the acquisition processing and the completion of the communication processing (step S103). ). That is, the first processing time calculation unit 103 calculates the time required for processing according to the second processing procedure described above.

However, the second maximum packet size and the first maximum packet size do not always match. The first maximum packet size may be, for example, a value calculated by the apparatus described in Non-Patent Document 1 and the like. The second maximum packet size may be an estimated value of the first maximum packet size. The acquisition process does not necessarily have to be the process shown in Patent Documents 1 to 3, and may be, for example, a process of reading the maximum packet size stored in an external storage device. That is, the acquisition process is not limited to the above-mentioned example.

Further, when calculating the acquisition time for the third processing procedure (for example, when the network information (exemplified in FIG. 3) includes the destination identifier), the first processing time calculation unit 103 may calculate the acquisition time, for example. Set a predetermined acquisition time for the time. If the processing time required for the first processing time calculation unit 103 to read the network information stored in the network information storage unit 106 is short enough to be negligible as compared with the communication time, the predetermined acquisition time is, for example, 0. Is. That is, in this case, the first processing time calculation unit 103 sets 0 for the acquisition time.

Further, even when the network information (exemplified in FIG. 3) includes the destination identifier, when the communication path may be changed (for example, the communication process is executed via the communication path). When a predetermined determination time has elapsed from the timing), it is necessary to execute a process of acquiring the first maximum packet size from the relay device or the like. Alternatively, when the network information (exemplified in FIG. 3) does not include the destination identifier, it is necessary to execute a process of acquiring the first maximum packet size from the relay device or the like. That is, in these cases, the source device executes the process according to the second processing procedure. Therefore, the first processing time calculation unit 103 calculates the acquisition time by executing the same processing as the processing shown in step S101.

Next, the first processing time calculation unit 103 determines the throughput related to the communication path when the target data is communicated between the source device and the destination device according to the packet having the second maximum packet size. calculate. For example, when communication processing according to TCP (Transmission Control Protocol) is executed in a communication network, the first processing time calculation unit 103 uses, for example, a calculation model as exemplified in Equation 1 to perform the communication processing. The throughput related to the communication path for communicating the target data according to the packet having the second maximum packet size is calculated.

However, Packet Size represents the size (amount, size) of the packet. RTT (round-trip time) represents a communication time required for a process of reciprocating by communication between a plurality of information processing devices in the communication path. RTO (transmission timeout) represents a timeout period for TCP. p represents the packet loss rate for the communication path. The RTO may be, for example, four times the value of the RTT.

Equation 1 is called a TCP Friendly calculation equation and is proposed by RFC (Request for Comments) 5348. The first processing time calculation unit 103 calculates the communication time required for the communication processing for communicating the target data according to the second maximum packet size based on the throughput and the target data size (step S103). That is, the first processing time calculation unit 103 calculates the communication time required for the communication processing according to the second maximum packet size.

The first processing time calculation unit 103 totals the calculated acquisition time and the calculated communication time, and calculates the totaled result as the required time (step S103).

The second processing time calculation unit 104 inputs the target data size output by the input unit 102 and the destination identifier. The second processing time calculation unit 104 calculates the acquisition time required for the processing for acquiring the minimum packet size related to the communication path. The minimum packet size may be a packet size guaranteed by the specifications related to IPv6 and the like. When the minimum packet size is the minimum packet size guaranteed by the specifications related to IPv6, the second processing time calculation unit 104 calculates, for example, 0 as the acquisition time.

The second processing time calculation unit 104 performs the same processing as the processing described with reference to step S102 based on the input target data size and the destination identifier, thereby performing the minimum packet size. Calculate the communication time related to the packet size. The second processing time calculation unit 104 calculates the required time for the minimum packet size by executing the same processing as the processing described with reference to step S103 (step S104). However, as described above, when the minimum packet size is the minimum packet size guaranteed by the specifications related to IPv6, the second processing time calculation unit 104 calculates, for example, 0 as the acquisition time. In step S104, the second processing time calculation unit 104 calculates the time required for the processing to be executed in the case of the minimum packet size. Therefore, the second processing time calculation unit 104 calculates the time required for the processing in which the processing is executed according to the first processing procedure.

Next, the processing determination unit 105 compares the time required for the processing according to the second processing procedure with the time required for the processing according to the first processing procedure, and performs the processing with the shorter required time. Select (step S105). That is, the processing determination unit 105 selects a shorter required time from the required time calculated by the first processing time calculation unit 103 and the required time calculated by the second processing time calculation unit 104, thereby performing a plurality of processing procedures. The processing procedure having a short required time is selected from the above.

The source device may execute the communication process for communicating the target data according to the processing procedure determined by the processing determination device 101. The source device may further update the network information based on the amount (eg, first maximum packet size, etc.) acquired in the communication process.

Next, the processing in the processing determination device 101 according to the first embodiment will be described with reference to the example shown in FIG. FIG. 5 is a block diagram showing an example of the configuration of the information processing system 151.

The information processing system 151 communicates with a data transmission terminal 152 representing a source device, a server terminal 154 representing a destination device, and a communication network 153 controlled by communication according to IPv6 that connects the source device and the destination device. And have. The data transmission terminal 152 includes a processing determination device 101 according to the first embodiment of the present invention.

For convenience of explanation, in the example shown in FIG. 5, it is assumed that the communication network 153 is controlled according to TCP. It is assumed that the data transmission terminal 152 transmits 1 megabyte (MB) of target data to the server terminal. Further, it is assumed that the network information (exemplified in FIG. 3) does not include the destination identifier representing the server terminal 154.

In the data transmission terminal 152, the processing determination device 101 determines whether or not the network information (exemplified in FIG. 3) includes a destination identifier representing the server terminal 154. In this case, according to the above assumption, the network information (exemplified in FIG. 3) does not include the destination identifier representing the server terminal 154. In this case, the processing determination device 101 sets the processing time based on the communication history measured for, for example, a terminal different from the server terminal 154 or a communication network different from the communication network segment with which the server terminal 154 communicates. calculate.

The processing determination device 101 calculates, for example, the average value of the packet sizes included in the network information (exemplified in FIG. 3) as the second maximum packet size for the communication path, and is further included in the network information. The average value of the packet loss rates is calculated as the packet loss rate for the communication path. The mean value may be, for example, a statistic such as a mode value or a median value. The processing determination device 101 calculates the throughput related to the communication path with respect to the calculated second maximum packet size and the calculated packet loss rate according to the processing shown in Equation 1.

For convenience of explanation, it is assumed that the processing determination device 101 calculates that the number of relay devices is 5, the packet loss rate is 0.2%, and the maximum packet size is 3000 bytes for the communication path. Also, the RTT is assumed to be 100 milliseconds.

The processing determination device 101 calculates the throughput related to the communication path between the data transmission terminal 152 and the server terminal 154 (in this case, about 6.5 megabits per second, about 6.5 Mbps) according to Equation 1. In other words, the processing determination device 101 calculates a predicted value of throughput for the communication path according to Equation 1. The processing determination device 101 calculates the communication time by dividing the target data size by the throughput. For example, the processing determination device 101 calculates about 1.2 seconds as the communication time for the communication path.

For example, the first maximum that can communicate between the source device and the destination device according to the process disclosed in Non-Patent Document 1 (called Path MTU Discovery, hereinafter referred to as "PMTU method"). You can get the packet size. The process of acquiring the first maximum packet size is performed for each relay device in the communication path between the source device and the destination device, for example. In this case, the first processing time calculation unit 103 executes the same processing as the processing described with reference to FIG. For example, the first processing time calculation unit 103 sets the acquisition time required for the acquisition process of acquiring the maximum packet size from each relay device as the communication time (RTT) required for the process of reciprocating between the source device and the destination device by communication. ), And the communication time for the number of relay devices in the communication path is calculated. For example, the first processing time calculation unit 103 calculates the acquisition time by multiplying the number of the relay devices and the communication time. When the number of relay devices is five and the communication time is 0.1 seconds, the first processing time calculation unit 103 calculates 0.5 seconds as the acquisition time.

The second maximum packet size does not always match the maximum packet size acquired in the communication process. Therefore, the first processing time calculation unit 103 may obtain, for example, the probability when transmission cannot be performed with the maximum packet size, and calculate the expected value of the acquisition time based on the probability.

After that, the first processing time calculation unit 103 sets the acquisition time (for example, 1.2 seconds) calculated according to the processing shown in step S104 (FIG. 2) and the communication time (for example, 0.5 seconds). By summing up, the time required for the processing to be executed in the case of the maximum packet size (for example, 1.7 (= 1.2 + 0.5) seconds) is calculated.

The second processing time calculation unit 104 executes the same processing as the processing executed by the first processing time calculation unit 103 with respect to the minimum packet size, so that the time required for the processing executed in the case of the minimum packet size can be determined. calculate. The second processing time calculation unit 104 sets, for example, 1280 bytes specified in the specification regarding IPv6 (for example, RFC 2460) as the minimum packet size. In this case, the second processing time calculation unit 104 sets 0 for the acquisition time required for the acquisition process for acquiring the minimum packet size. However, the minimum packet size is specified by the IPv6 specification (eg, RFC 2460) and is therefore varied accordingly. In the case of the above example, the second processing time calculation unit 104 calculates, for example, about 2.8 seconds as the communication time.

The processing determination unit 105 calculates the required time (for example, 1.7 seconds) calculated by the first processing time calculation unit 103 for the maximum packet size and the required time (for example, 1.7 seconds) calculated by the second processing time calculation unit 104 for the minimum packet size. 2.8 seconds) and compare the size. In the case of this example, the processing determination unit 105 follows the maximum packet size of the plurality of processing procedures because the 1.7 seconds calculated for the maximum packet size is shorter than the 2.8 seconds calculated for the maximum packet size. Select the processing procedure to be transmitted (that is, the second processing procedure).

The data transmission terminal 152 acquires the first maximum packet size according to the processing procedure selected by the processing determination device 101 (in this case, the processing procedure executed with respect to the maximum packet size) (for example, processing according to the PMTU method). Is executed, and the target data is transmitted to the server terminal 154 according to the first maximum packet size.

The data transmission terminal 152 does not necessarily have to execute an acquisition process for acquiring the first maximum packet size (for example, a process according to the PMTU method). An example of the processing executed in this case will be described. The data transmission terminal 152 transmits the target data to the server terminal 154 according to the maximum packet size (for example, 3000 bytes). As described above with reference to FIG. 13, when the maximum packet size is larger than the packet size that can be processed by the relay device, the relay device is larger than the packet size that can be processed by the data transmitting terminal 152. Send information that represents. When the data transmission terminal 152 receives the information from the relay device, the data transmission terminal 152 may specify the first packet packet size based on the received information.

In the above example, since the required time for the second processing procedure is shorter than the required time for the first processing procedure, the processing determination device 101 has selected the second processing procedure. However, the required time for the second processing procedure and the required time for the first processing procedure vary depending on the target data size, as illustrated in FIG. FIG. 4 is a diagram showing an example of the required time for the second processing procedure and an example of the required time for the first processing procedure. The horizontal axis of FIG. 4 represents the required time, and the right side indicates that the required time is longer. The vertical axis of FIG. 4 represents the target data size, and the upper side represents the larger size.

As illustrated in FIG. 4, the processing procedure with a short required time differs depending on the target data size. Therefore, the processing determination device 101 selects a processing procedure having a short required time according to the target data size.

For example, when the target data size is 200 kilobytes (KB), the time required for the first processing procedure is about 0.58 seconds, whereas the time required for the second processing procedure is about 0.74 seconds. Is. Therefore, when the target data size is 200 kilobytes, the processing determination device 101 selects the first processing procedure having a short required time.

On the other hand, when the target data size is 400 kilobytes (KB), the required time for the first processing procedure is about 1200 milliseconds, whereas the required time for the second processing procedure is about 900 milliseconds. Seconds. Therefore, the processing determination device 101 selects the second processing procedure having a short required time when the target data size is 400 kilobytes.

When the target data is processed in the second processing procedure, the period from 0 ms to 650 ms represents the acquisition time required for the acquisition process for acquiring the first maximum packet size. For example, the acquisition process represents a process executed according to the PMTU method described above.

The data transmission terminal 152 transmits the target data to the server terminal 154 according to the processing procedure selected by the processing determination device 101. For example, when the processing procedure selected by the processing determination device 101 is the second processing procedure, the data transmission terminal 152 obtains the first maximum packet size for the server terminal 154 according to the PMTU method, and obtains the first maximum packet size. According to this, the target data is transmitted to the server terminal 154. In this case, the data transmission terminal 152 has, for example, network information in which the source identifier representing the own terminal, the destination identifier representing the server terminal 154, and the obtained first maximum packet size are associated with each other (example in FIG. 3). Is created, and the created network information is stored in the network information storage unit 106. That is, the data transmission terminal 152 updates the network information. The data transmission terminal 152 may further create network information including the time required for the process of actually obtaining the first maximum packet size.

Further, when the processing determination unit 105 requests information such as the maximum packet size for a certain terminal based on network information (exemplified in FIG. 3), the processing determination unit 105 is a terminal that is communication-connected to the communication network segment to which the certain terminal communicates. Network information about may be used. For example, the processing determination unit 105 determines whether or not a plurality of terminals communicate with each other in one communication network segment, such as an identifier representing each terminal (described later with reference to FIG. 9) or an AS (Autonomous System) number. Judgment is made based on the similarity (or consistency) regarding information such as.

In the above-described embodiment, when the source device transmits the target data to the destination device, the process determination device 101 specifies a certain packet size (for example, the maximum packet size), and further, the target data according to the certain packet size. Calculate the communication time required for the process of transmitting. However, the processing determination device 101 may store a certain packet size and the communication time calculated for the certain packet size in a storage device (not shown). In this case, the processing determination device 101 stores the size of the second target data and the packet size when transmitting the second target data in the communication processing regarding the second target data different from the target data. Of the data stored in the device, the communication time calculated for matching (or similar) data may be read. In this case, the processing determination device 101 may set the read communication time as the communication time for the second target data. According to this process, the process of calculating the communication time is short because the process of calculating the communication time according to Equation 1 is not required.

Further, in the communication network, when the communication process is executed according to the protocol in which the packet size can be set in the layer higher than the IP layer, the target data is transmitted according to the process procedure determined by the process determination device 101. The source device may specify the packet size related to the target data in the upper layer. For example, the source device can set the packet size using MSS (Maximum Segment Size) in the TCP layer.

Next, the effect of the processing determination device 101 according to the first embodiment of the present invention will be described.

According to the processing determination device 101 according to the first embodiment, efficient communication can be realized with respect to communication processing between a plurality of information processing devices. The reason for this is that the process determination device 101 selects a process having a short required time according to the target data size representing the data to be communicated between the source device and the destination device. The reason for this will be described in detail.

When the source device transmits the target data to the destination device, there is one or more relay devices relaying the target data in the communication path between the source device and the destination device. ing. When the target data is transmitted via the communication network, the relay device divides the target data into data in units called packets, and executes a process of transferring each packet obtained by the division. Since the communication time required for the process of transmitting the target data from the source device to the destination device changes according to the size of the packet, the acquisition process for acquiring the packet size when the time is short is executed. There is also.

However, since the acquisition process requires a processing time, even when the acquisition process is executed, the acquisition time required for the process of acquiring an appropriate packet size and the packet having the packet size are not necessarily included. The required time, which is the total value of the communication time required for the process of communicating the target data, is not always short. The processing determination device 101 according to the present embodiment selects the packet size when the required time is short among the plurality of packet sizes. That is, the process determination device 101 selects a process having a short required time from a plurality of processes having different packet sizes by selecting a packet size when the required time is short. As a result, according to the processing determination device 101 according to the present embodiment, it is possible to realize efficient communication with respect to the required time including the acquisition process for the communication processing between the plurality of information processing devices.

Further, according to the processing determination device 101 according to the first embodiment, the communication processing for communicating the target data can be realized by the processing procedure having a short required time. The reason for this is that the processing determination device 101 has a plurality of processing determination devices 101 based on the required time including the acquisition time for determining an appropriate packet size and the communication time for the communication processing for communicating the target data according to the determined packet size. This is because the processing procedure having the shortest required time is determined among the processing procedures. That is, the processing determination device 101 has a plurality of processing procedures based on not only the communication time when communication is executed according to a certain processing procedure but also the required time including the acquisition time required for the processing for specifying the certain processing procedure. Among them, the processing procedure with the short processing time is determined. As a result, according to the processing determination device 101 according to the first embodiment, real-time performance can be ensured in the communication processing.

Further, the first processing time calculation unit 103 can realize more efficient communication by specifying the second maximum packet size based on the network information. The reason for this is that it is unlikely that the packet size that can be transmitted in the communication path between the two information processing devices will be changed in a short time, so it is included in the history of the communication processing executed in the communication path. This is because there is a possibility that the first maximum packet size related to the communication path at the time of executing the communication process can be specified by referring to the packet size.

According to the process determination device 101 according to the present embodiment, the process that realizes efficient communication can be specified in a short period of time. The reason for this is that the packet size when the required time is short is likely to be the minimum packet size or the maximum packet size. That is, the processing determination device 101 selects either a processing procedure executed according to the maximum packet size (that is, the second processing procedure) or a processing procedure executed according to the minimum packet size (that is, the first processing procedure). By doing so, a processing procedure with a short overall time required is selected.

According to the source device (information processing device, communication device) according to the present embodiment, the communication process between the source device and the destination device can be executed in a short period of time. The reason for this is that the communication device executes the communication process according to the process selected by the process determination device 101 as the process having a short required time.

According to the source device (information processing device, communication device) according to the present embodiment, efficient communication processing can be realized in a short period of time. The reason for this is that by updating the network information for each process of acquiring the packet size, it is possible to reduce the time elapsed from the timing when the communication process is executed. In this case, since the network information is likely to include the maximum packet size when the communication process is executed, the process determination device 101 can accurately calculate the required time for the second process procedure.

<Second embodiment>
Next, a second embodiment of the present invention based on the above-mentioned first embodiment will be described.

In the following description, the characteristic parts relating to the present embodiment will be mainly described, and the same reference number will be assigned to the same configuration as that of the first embodiment described above to omit duplicate description. To do.

The configuration of the processing decision system 201 according to the second embodiment of the present invention will be described in detail with reference to FIG. FIG. 6 is a block diagram showing a configuration of the processing decision system 201 according to the second embodiment of the present invention.

The processing decision system 201 according to the second embodiment includes a processing decision device 202 and a network information providing device 203. The processing determination device 202 includes an input unit 102, a first processing time calculation unit 103, a second processing time calculation unit 104, a processing determination unit 105, a network information communication unit 204, and a network information storage unit 207. .. The network information providing device 203 includes a network information acquisition unit 205 and a network information storage unit 206.

The network information storage unit 206 and the network information storage unit 207 store information similar to the network information described with reference to FIG.

In the network information providing device 203, the network information acquisition unit 205 reads, for example, specific information requested by the processing decision device 202 from the network information (exemplified in FIG. 3) stored in the network information storage unit 206. The read specific information is transmitted (provided) to the processing decision device 202. The specific information is, for example, a transferable packet size such as a maximum packet size, or the number of relay devices (for example, the number of hops) in the communication path between the source device and the destination device.

Next, the process in the process decision system 201 according to the second embodiment of the present invention will be described in detail with reference to FIG. 7. FIG. 7 is a flowchart showing a processing flow in the processing decision system 201 according to the second embodiment.

The input unit 102 inputs information regarding the target data size, a destination identifier representing the destination device related to the target data size, and the like from, for example, an external device, and outputs the input information to the network information communication unit 204. ..

The network information communication unit 204 inputs the information output by the input unit 102. When the network information about the destination device is not stored in the network information storage unit 207, the network information communication unit 204 transmits the request information for requesting the network information about the destination device to the network information providing device 203 (step S201). ). For example, the network information communication unit 204 transmits the request information including the input destination identifier to the network information providing device 203.

When the network information providing device 203 receives the request information, the network information providing device 203 reads the network information related to the destination device represented by the destination identifier included in the request information from the network information storage unit 206, and reads the read network information. It is transmitted to the processing determination device 202.

In the processing determination device 202, the network information communication unit 204 receives the network information transmitted by the network information providing device 203 in response to the request information (step S202). The network information includes, for example, the packet size that can be transmitted in the communication path to the destination device.

The first processing time calculation unit 103 is the same as the processing described with reference to FIG. 2 based on the network information received by the network information communication unit 204 and the network information stored in the network information storage unit 207. Processing is executed (steps S101 to S103).

In the following, when the network information stored in the network information storage unit 206 and the network information stored in the network information storage unit 207 do not include the network information related to the destination device, the first process is performed. An example of the processing executed by the time calculation unit 103 will be specifically described.

The first processing time calculation unit 103 may create network information about the destination device based on the network information about the information processing device that is communication-connected to the communication network segment with which the destination device is connected. For example, the first processing time calculation unit 103 calculates an average value of packet sizes included in network information related to the information processing device, and sets the calculated average value as the second maximum packet size related to the destination device. .. When the information regarding the acquisition time is included in the network information, the first processing time calculation unit 103 calculates, for example, the average value of the acquisition time required for the acquisition process for acquiring the maximum packet size for the information processing device. The calculated average value may be set to the acquisition time for the destination device.

The first processing time calculation unit 103 includes network information related to all information processing devices stored in the network information storage unit 207 or network information related to all information processing devices stored in the network information storage unit 206. , At least, network information about the destination device may be created based on one of the network information. For example, the first processing time calculation unit 103 calculates the average value of the packet sizes included in the network information related to all the information processing devices, and uses the calculated average value as the second maximum packet size related to the destination device. Set. When the information about the acquisition time is included in the network information, the first processing time calculation unit 103 calculates the average value of the acquisition time required for the acquisition process to acquire the maximum packet size for all the information processing devices. The calculated average value may be set to the acquisition time for the destination device.

The second processing time calculation unit 104 performs processing as described with reference to FIG. 2 based on the network information acquired by the network information communication unit 204 and the network information stored in the network information storage unit 206. The same process is executed (step S104). After that, the process determination unit 105 executes the same process as the process described with reference to FIG. 2 (step S105).

The source device may execute a communication process for transmitting the target data to the destination device according to the processing procedure determined by the processing decision device 202.

When the network information communication unit 204 inputs the maximum packet size acquired in the communication process executed by the source device, the network information communication unit 204 creates network information including the maximum packet size as the packet size for the destination device, and creates the network information. The network information is stored in the network information storage unit 206. The network information communication unit 204 further transmits the created network information to the network information providing device 203.

In the network information providing device 203, the network information acquisition unit 205 receives the network information transmitted by the network information communication unit 204, and stores the received network information in the network information storage unit 206. That is, if the network information storage unit 206 stores network information related to the destination device before the source device executes the communication process, the network information acquisition unit 205 is acquired in the communication process. The network information stored in the network information storage unit 206 is updated based on the information received. If the network information storage unit 206 does not store the network information related to the destination device before the source device executes the communication process, the network information acquisition unit 205 is acquired in the communication process. Based on the information, the network information stored in the network information storage unit 206 is created.

Next, the processing in the information processing system 156 according to the second embodiment of the present invention will be described with reference to the specific example shown in FIG. FIG. 8 is a block diagram showing an example of the configuration of the information processing system 156.

The information processing system 156 includes a data transmission terminal 152, a data transmission terminal 155, a server terminal 154, and a communication network 153 according to IPv6. The data transmission terminal 152 has a processing determination device 202. The data transmission terminal 155 has a processing determination device 212. The communication network 153 has a communication connection between the data transmission terminal 152, the data transmission terminal 155, and the server terminal 154, and includes the network information providing device 203 as described above for communication connection. The processing determination device 212 has the same function as the processing determination device 202 as described with reference to FIGS. 6 and 7.

For convenience of explanation, it is assumed that the network information storage unit 206 of the network information providing device 203 does not store network information related to the information processing device that communicates with the communication network to which the server terminal 154 communicates. Further, the data transmission terminal 152 transmits data (hereinafter referred to as "first data") to the server terminal 154, and then the data transmission terminal 155 transmits data (hereinafter, "second data") to the server terminal 154. ") Is transmitted.

The communication process in which the data transmission terminal 152 transmits the first data to the server terminal 154 is the same process as the example described in the first embodiment. Therefore, the description of the communication process will be omitted.

After transmitting the first data to the server terminal 154, the data transmission terminal 152 transmits communication information such as the first maximum packet size acquired in the communication process regarding the first data to the network information providing device 203. .. The first maximum packet size is, for example, 3000 bytes in the example shown in the first embodiment. Further, the communication information includes, for example, the IP address of the data transmission terminal 152, the IP address of the server terminal 154, the communication network segment to which the server terminal 154 communicates, and the relay device in the communication path from the data transmission terminal 155 to the server terminal 154. It contains information such as the number of units (for example, the number of hops).

The network information providing device 203 receives the communication information transmitted by the data transmitting terminal 152, and updates the network information (exemplified in FIG. 9) stored in the network information storage unit 206 based on the received communication information. FIG. 9 is a diagram conceptually representing an example of network information. The network information illustrated in FIG. 9 has the same configuration as the network information illustrated in FIG. In the example shown in FIG. 9, the source identifier and the communication network segment are described in hexadecimal.

For example, the communication information includes the source identifier "2001: 1234: packet: 1234: 0: 0: 0: 1", the communication network segment "2001: 1234: packet: 1234: 0: 0: 0: 0/64", It is assumed that the maximum packet size "3000" and the number of hops "5" are included. In "2001: 1234: prefix: 1234: 0: 0: 0: 0/64", "2001: 1234: prefix: 1234: 0: 0: 0: 0" is the IP address described according to IPv6. Represented, "/ 64" represents the prefix length. That is, in this, among the IP addresses "2001: 1234: base: 1234: 0: 0: 0: 0", the 64 bits shown in "0: 0: 0: 0" are the addresses inside the communication network segment. It is a numerical value to be represented, and indicates that the address shown in "2001: 1234: base: 1234" is network segment information for mutually identifying communication network segments.

When the network information providing device 203 receives the communication information transmitted by the data transmission terminal 152, each information included in the communication information and the date and time when the communication information is created (example shown in FIG. 9). In, the information associated with "2016/10/10 11: 11: 11") is created, and the network information is updated based on the created information) (the last line of the network information shown in FIG. 9).

Next, the data transmission terminal 155 transmits the request information requesting the network information regarding the server terminal 154 to the network information providing device 203 before transmitting the second data to the server terminal 154. In this case, the data transmission terminal 155 requests network information about the server terminal 154 by, for example, transmitting an identifier such as a URL (Uniform Resource Locator) representing the server terminal 154 and an IP address to the network information providing device 203. Send request information.

In the network information providing device 203, when the network information acquisition unit 205 receives the request information transmitted by the data transmission terminal 155, the network information providing device 203 reads and reads an identifier such as an IP address included in the received request information. It is determined whether or not the network information about the information processing device represented by the identifier (in this example, the server terminal 154) is stored in the network information storage unit 206. For example, the network information acquisition unit 205 determines whether or not the information processing device can make a communication connection to a communication network segment included in the network information stored in the network information storage unit 206 (that is, the request information). Whether or not there is network segment information that matches the identifier included in) is determined.

When the network information storage unit 206 stores the network information related to the information processing device, the network information acquisition unit 205 reads the network information related to the information processing device and transmits the read network information to the data transmission terminal 155. To do. When the network information storage unit 206 does not store the network information related to the information processing device, the network information acquisition unit 205 is included in the request information based on the network information stored in the network information storage unit 206. Network information about the identifier may be created. In this case, the network information acquisition unit 205 has, for example, the average value (or mode, median, etc.) of the packet size (or the number of hops, etc.) for each network information stored in the network information storage unit 206. ) Is calculated. The network information acquisition unit 205 creates network information including the calculated value as network information related to the identifier, and transmits the created network information to the data transmission terminal 155.

The network information exemplified in FIG. 9 includes a communication network segment capable of communicating with the information processing device represented by the identifier included in the request information. In this case, the network information providing device 203 specifies the network information (including the maximum packet size, the number of hops, the date and time, etc.) related to the identifier from the network information storage unit 206, and transmits the specified network information as data. Send to terminal 155.

Next, in the data transmission terminal 155, the processing determination device 212 receives the network information transmitted by the network information providing device 203, and then calculates the acquisition time required for the acquisition process to acquire the maximum packet size. In the case of the example shown in FIG. 9, since the data transmission terminal 155 can acquire the maximum packet size from, for example, the network information providing device 203, the processing determination device 212 sets the predetermined acquisition time to the maximum packet. Set as the acquisition time required for the acquisition process to acquire the size. In this case, the predetermined acquisition time may be, for example, 0 or RTT.

Further, the processing determination device 212 may determine that there is a high possibility that the network information has been changed when a predetermined elapsed time has elapsed from the date and time included in the received network information. The predetermined elapsed time is, for example, 6 hours, 12 hours, 24 hours, and the like. When there is a high possibility that the network information has been changed (for example, 24 hours have passed from the date and time), the processing determination device 212 performs the same processing as the processing shown in the first embodiment. By executing this, the acquisition time required for the acquisition process for acquiring the first maximum packet size is calculated.

After that, the processing determination device 212 calculates and calculates the communication time required for the communication processing for transmitting the second data according to the second maximum packet size by executing the same processing as the processing shown in Equation 1. The required time, which is the total value of the communication time and the acquisition time, is calculated. In addition, the processing determination device 202 calculates the time required for processing to transmit the second data according to the minimum packet size guaranteed by the specifications related to IPv6. Next, the processing determination device 202 performs the time required for the process of transmitting the second data according to the maximum packet size (that is, the second processing procedure) and the process of transmitting the second data according to the minimum packet size (that is,). Of the required time required for the first processing procedure), a processing procedure having a shorter required time is selected.

The data transmission terminal 155 transmits the second data to the server terminal 154 according to the process selected by the process determination device 202.

Next, the effect of the processing decision system 201 according to the second embodiment of the present invention will be described.

According to the processing decision system 201 according to the second embodiment, the communication processing for communicating the target data can be realized by the processing procedure having a short processing time. The reason for this is that the configuration of the processing decision system 201 according to the second embodiment includes the configuration of the processing decision device 101 according to the first embodiment.

According to the processing decision system 201 according to the second embodiment, the source device can transmit the target data to the destination device in a short period of time. The reason for this is that a plurality of source devices can mutually acquire network information in which the maximum packet size and the like are stored. In other words, the plurality of source devices can share the network information by mutually acquiring the network information in which the maximum packet size and the like are stored. For example, a source device that has never sent data to a destination device has a maximum packet size based on network information held by the source device that has sent data to a communication network to which the destination device can communicate. Can be obtained. In this case, if the source device sharing the network information is included in the same communication network segment, the maximum packet size can be acquired more accurately. As a result, the processing determination device 202 calculates the required time more accurately, so that the source device can complete the process of transmitting the target data in a shorter period of time.

According to the processing decision system 201 according to the present embodiment, efficient communication can be realized even when the source device and the destination device have never communicated with each other. The reason for this is the information processing device that communicates with the communication network segment to which the destination device communicates, the communication path between the source devices, and the communication path between the destination device and the source device. However, there is a high possibility that they match. In other words, the processing decision system 201 is likely to be able to accurately identify the packet size for the destination device based on the packet size for the information processing device. Therefore, since the required time required by the processing decision system 201 based on the packet size is accurate, efficient communication can be realized according to the processing decision system 201.

According to the processing decision system 201 according to the present embodiment, efficient communication can be realized even when the source device and the destination device have never communicated with each other. The reason for this is that even if the network information does not include the packet size for the destination device, the average value (or median, frequent value) of the packet size for multiple information processing devices is the packet size for the destination device. This is because there is a high possibility that it is.

According to the processing decision system 201 according to the present embodiment, communication between the source device and the destination device can be executed in a shorter period of time. The reason for this is that it is determined whether or not the packet size included in the network information is correct according to the elapsed time elapsed from the timing when the communication is executed, and the acquisition time is calculated based on the determined result. is there. The reason for this will be explained in more detail. When the elapsed time is short, it is unlikely that the communication path has been changed. Therefore, in the communication process, the acquisition process for acquiring an appropriate packet size is likely to be an extra process. Further, if the elapsed time is long, there is a high possibility that the communication route has been changed. Therefore, in the communication process, communication with a short communication time is realized by executing an acquisition process for acquiring an appropriate packet size. It is likely that you can. Therefore, when the first processing time calculation unit 103 determines the presence or absence of the acquisition processing, the processing that realizes the communication processing in a short period of time can be calculated more accurately.

<Third embodiment>
Next, a third embodiment of the present invention will be described.

In the following description, the characteristic parts of the present embodiment will be mainly described, and the same reference numbers will be assigned to the same configurations as those of the above-described embodiments, thereby omitting duplicate explanations.

The configuration of the processing determination device 301 according to the third embodiment of the present invention will be described in detail with reference to FIG. FIG. 10 is a block diagram showing a configuration of the processing determination device 301 according to the third embodiment of the present invention.

The processing determination device 301 includes an acquisition time calculation unit 302, a communication time calculation unit 303, and a processing selection unit 304.

The process determination device 301 is among a plurality of process procedures (for example, a first process procedure and a second process procedure) according to the process shown in FIG. 11 before the source device and the destination device communicate the target data. To determine the processing procedure for the target data.

Next, with reference to FIG. 11, the processing in the processing determination device 301 according to the third embodiment of the present invention will be described in detail. FIG. 11 is a flowchart showing a processing flow in the processing determination device 301 according to the third embodiment.

First, the acquisition time calculation unit 302 calculates the acquisition time required for the acquisition process for acquiring the packet size that can be communicated in the communication path for each processing procedure (step S301). The acquisition time is based on, for example, the number of relay devices in the communication path between the source device and the destination device, and the round-trip time required for the round-trip processing in which data reciprocates between the two devices. This is the time required for reciprocating processing. The acquisition time calculation unit 302 identifies the number of relay devices in the communication path between the source device and the destination device based on the network information (exemplified in FIG. 3), and determines the predetermined round-trip time and the number of the relay devices. The acquisition time is calculated by multiplying. For example, in the first processing procedure, the process of acquiring the packet size is not executed. Therefore, in the case of the first processing procedure, the acquisition time calculation unit 302 may calculate 0 as the acquisition time.

Next, the communication time calculation unit 303 calculates the communication time required for the communication processing from the timing when the source device transmits the target data to the timing when the destination device receives the target data for each processing procedure (step S302). ). The communication time calculation unit 303 specifies, for example, a packet loss rate indicating the degree of packet loss in the communication path based on network information (exemplified in FIG. 3), and further, between the source device and the destination device. Calculates the maximum packet size for the communication executed. Next, the communication time calculation unit 303 calculates the throughput related to the communication path by executing the process shown in Equation 1 with respect to the specified degree and the calculated maximum value. Next, the communication time calculation unit 303 calculates the communication time related to the communication process in the second processing procedure based on the calculated throughput and the target data size. Similarly, the communication time calculation unit 303 executes the process shown in Equation 1 with respect to the predetermined packet size (for example, the minimum packet size guaranteed by the specifications relating to IPv6) and the packet loss rate. By doing so, the communication time related to the communication process in the first processing procedure is calculated.

For each processing procedure, the processing selection unit 304 calculates the required time in which the acquisition time calculated by the acquisition time calculation unit 302 and the communication time calculated by the communication time calculation unit 303 are totaled (step S303). The process selection unit 304 selects a process procedure having a shorter required time from the plurality of process procedures (step S304).

After that, the source device may execute the process according to the process procedure selected by the process decision device 301.

The acquisition time calculation unit 302 shall be realized by the same function as that of the first processing time calculation unit 103 (FIGS. 1 and 6), the second processing time calculation unit 104 (FIGS. 1 and 6), and the like. Can be done. The communication time calculation unit 303 is realized by a function similar to the function of the first processing time calculation unit 103 (FIGS. 1 and 6) or the second processing time calculation unit 104 (FIGS. 1 and 6). Can be done. The process selection unit 304 can be realized by a function similar to the function of the process determination unit 105 (FIGS. 1 and 6) and the like. That is, the processing decision device 301 can be realized by the same functions as those of the processing decision device 101 (FIG. 1), the processing decision system 201 (FIG. 6), and the like.

Next, the effect of the processing determination device 301 according to the third embodiment of the present invention will be described.

According to the processing determination device 301 according to the third embodiment, efficient communication can be realized with respect to communication processing between a plurality of information processing devices. The reason for this is that the process determination device 301 selects a process having a short required time according to the target data size representing the data to be communicated between the source device and the destination device. The reason for this will be described in detail.

When the source device transmits the target data to the destination device, there is one or more relay devices relaying the target data in the communication path between the source device and the destination device. ing. When the target data is transmitted via the communication network, the relay device divides the target data into data in units called packets, and executes a process of transferring each packet obtained by the division. Since the communication time required for the process of transmitting the target data from the source device to the destination device changes according to the size of the packet, the acquisition process for acquiring an appropriate size when the time is short is applied to the communication network. May be executed.

However, since the acquisition process requires a processing time, even when the acquisition process is executed, the acquisition time required for the process of acquiring an appropriate size and the packet having the size are not necessarily the targets. The required time, which is the total value of the communication time required for the process of communicating data, is not always optimized. The processing determination device 301 according to the present embodiment selects the packet size when the required time is short among the plurality of packet sizes. That is, the processing determination device 301 selects a process having a short required time from a plurality of processes having different packet sizes by selecting a packet size when the required time is short. As a result, according to the processing determination device 301 according to the present embodiment, it is possible to realize efficient communication with respect to the required time including the acquisition processing for the communication processing between the plurality of information processing devices.

(Hardware configuration example)
An example of a configuration of hardware resources for realizing the processing determination device according to each embodiment of the present invention described above by using one calculation processing device (information processing device, computer) will be described. However, such a processing determination device may be physically or functionally realized by using at least two calculation processing devices. Further, the processing determination device may be realized as a dedicated device.

FIG. 12 is a block diagram schematically showing a hardware configuration example of a calculation processing device capable of realizing the processing determination device according to each embodiment of the present invention. The calculation processing device 20 includes a central processing unit (Central_Processing_Unit, hereinafter referred to as “CPU”) 21, a memory 22, a disk 23, a non-volatile recording medium 24, and a communication interface (hereinafter referred to as “communication IF”) 27. Have. The calculation processing device 20 may be connectable to the input device 25 and the output device 26. The calculation processing device 20 can transmit / receive information to / from other calculation processing devices and the communication device via the communication IF 27.

The non-volatile recording medium 24 is, for example, a computer-readable compact disc (Compact_Disc) or a digital versatile disc (Digital_Versail_Disc). Further, the non-volatile recording medium 24 may be a universal serial bus memory (USB memory), a solid state drive (Solid_State_Drive), or the like. The non-volatile recording medium 24 holds the program and makes it portable without supplying power. The non-volatile recording medium 24 is not limited to the above-mentioned medium. Further, instead of the non-volatile recording medium 24, the relevant program may be carried via the communication IF27 and the communication network.

That is, the CPU 21 copies the software program (computer program: hereinafter, simply referred to as "program") stored in the disk 23 to the memory 22 when executing the software program, and executes the arithmetic processing. The CPU 21 reads the data required for program execution from the memory 22. When the output to the outside is required, the CPU 21 outputs the output result to the output device 26. When inputting a program from the outside, the CPU 21 reads the program from the input device 25. The CPU 21 interprets a processing determination program (FIG. 2, FIG. 7, or FIG. 11) in the memory 22 corresponding to the function (processing) represented by each part shown in FIG. 1, FIG. 6, or FIG. 10 described above. And execute. The CPU 21 sequentially executes the processes described in the above-described embodiments of the present invention.

That is, in such a case, it can be considered that the present invention can also be achieved by the processing decision program. Further, it can be considered that the present invention can be achieved by using a non-volatile recording medium in which the processing decision program is recorded and which can be read by a computer.

The present invention has been described above using the above-described embodiment as a model example. However, the present invention is not limited to the above-described embodiments. That is, the present invention can apply various aspects that can be understood by those skilled in the art within the scope of the present invention.

101 Processing decision device 102 Input section 103 1st processing time calculation section 104 2nd processing time calculation section 105 Processing decision section 106 Network information storage section 151 Information processing system 152 Data transmission terminal 153 Communication network 154 Server terminal 201 Processing decision system 202 Processing Determining device 203 Network information providing device 204 Network information communication unit 205 Network information acquisition unit 206 Network information storage unit 207 Network information storage unit 155 Data transmission terminal 156 Information processing system 212 Processing decision device 301 Processing decision device 302 Acquisition time calculation unit 303 Communication Time calculation unit 304 Processing selection unit 20 Calculation processing device 21 CPU
22 Memory 23 Disk 24 Non-volatile recording medium 25 Input device 26 Output device 27 Communication IF
1001 packet 1002 packet 1003 packet 1004 packet 1101 packet 1102 packet 1103 packet 1104 packet 1105 packet

Claims (10)

When the target data is transmitted from the source device to the destination device, it is possible to communicate on the communication path with respect to the processing procedure representing the content of the process executed on the communication path between the source device and the destination device. An acquisition time calculation means for calculating the acquisition time required for the acquisition process to acquire an appropriate packet size,
The throughput related to the communication path is obtained based on the packet size related to the communication process of dividing the target data into packets and transmitted from the source device to the destination device, and the communication is based on the obtained throughput and the size of the target data. Communication time calculation means for calculating the communication time required for processing,
The required time obtained by totaling the acquisition time calculated by the acquisition time calculating means and the communication time calculated by the communication time calculating means is calculated for a plurality of types of processing procedures, and the calculated required time is short. A processing decision device comprising a processing selection means for selecting a procedure. In the communication time calculation means, the network information associated with the device identifier representing the information processing device on which the communication process is executed and the packet size acquired in the acquisition process is the source identifier representing the source device. The process according to claim 1, wherein the packet size related to the first information is specified as the packet size related to the communication process when the first information associated with the destination identifier representing the destination device is included. Decision device. In the communication time calculation means, the network information in which the segment information representing the network segment to which the information processing apparatus in which the communication process is executed is connected by communication and the packet size acquired in the acquisition process are associated with each other is described. The first aspect of claim 1, wherein it is determined whether or not the segment information related to the destination device is included, and if it is included, the packet size associated with the segment information related to the destination device is specified as the packet size related to the communication processing. Processing decision device. The processing determination device according to claim 2, wherein when the network information does not include the first information, the average value of the packet sizes included in the network information is calculated as the packet size related to the communication processing. The plurality of types of processing procedures are the first processing procedure executed according to the minimum packet size specified by the communication protocol according to the communication processing that divides the target data into packets and transmits the target data from the source device to the destination device. Then, the relay device included in the processing procedure is executed at the maximum value of the packet size that can be transmitted by the relay device that passes through in the execution of the communication process that divides the target data into packets and transmits the data from the source device to the destination device. This is the second processing procedure.
The processing determination device according to any one of claims 1 to 4, wherein the acquisition time calculation means calculates the acquisition time of the first processing procedure as 0. 2. The processing determination device according to claim 2 or 4.
A communication device including a data transmission means for transmitting the target data to the destination device according to the processing procedure selected by the processing determination device. The self-communication device further includes a network information storage means in which the network information, which is the source device, is stored.
The network information is further associated with the timing at which the information processing apparatus executes the communication process.
The data transmitting means creates the network information in which the timing of transmitting the target data and the destination identifier are associated with each other, and stores the created network information in the network information storage means.
In the network information, the acquisition time calculation means calculates the acquisition time of the destination identifier as 0 when the time elapsed from the timing associated with the destination identifier is within a predetermined determination time, and elapses. The communication device according to claim 6, wherein the acquisition time is calculated based on the number of relay devices in the communication path when the time is longer than the predetermined determination time. The self-communication device further includes a network information storage means in which the network information, which is the source device, is stored.
The communication device according to claim 6, wherein the data transmission means updates the network information based on the acquired packet size when the acquisition process for acquiring the packet size is executed in the processing procedure . The computer
When the target data is transmitted from the source device to the destination device, it is possible to communicate on the communication path with respect to the processing procedure representing the content of the process executed on the communication path between the source device and the destination device. Calculate the acquisition time required for the acquisition process to acquire the appropriate packet size.
The throughput related to the communication path is obtained based on the packet size related to the communication process of dividing the target data into packets and transmitted from the source device to the destination device, and the communication is based on the obtained throughput and the size of the target data. Calculate the communication time required for processing,
A processing determination method in which the calculated required time obtained by totaling the acquired acquisition time and the calculated communication time is calculated for a plurality of types of processing procedures, and the calculated processing procedure with the shorter required time is selected. When the target data is transmitted from the source device to the destination device, it is possible to communicate on the communication path with respect to the processing procedure representing the content of the process executed on the communication path between the source device and the destination device. The acquisition time calculation function that calculates the acquisition time required for the acquisition process to acquire the packet size,
The throughput related to the communication path is obtained based on the packet size related to the communication process of dividing the target data into packets and transmitted from the source device to the destination device, and the communication is based on the obtained throughput and the size of the target data. Communication time calculation function that calculates the communication time required for processing,
The required time, which is the sum of the acquisition time calculated by the acquisition time calculation function and the communication time calculated by the communication time calculation function, is calculated for a plurality of types of processing procedures, and the calculated required time is calculated. A processing decision program that enables a computer to realize a processing selection function that selects a short processing procedure.

Images