JP3966319B2 - Packet relay apparatus having communication quality control function - Google Patents

Description

  The present invention relates to a relay device that interconnects a plurality of networks and relays packets.

  With the increase in Internet users, traffic (packets) flowing through the Internet has increased rapidly. In the packet-type communication method used on the Internet, packets from a large number of users can share the same line, so the cost per band can be kept low. Moreover, the fact that strict management such as quality control for each user was not performed is also a factor for realizing low cost.

  Due to the low cost of this packet-type communication method, there has been a movement to reduce the communication cost by integrating the telephone network and the corporate network that have been realized in the conventional network with the Internet. In order to integrate these, it is necessary to realize communication quality (QoS: Quality of Service) such as a low delay time and a low discard rate, which has been realized in the conventional telephone network and enterprise network.

  QoS control that realizes QoS must identify specific applications (telephone traffic, etc.) to be controlled and individual users (enterprises, etc.) while preferentially forwarding them with priority according to the contract. . As a priority transfer system, an ATM (Asynchronous Transfer Mode) exchange is known. The priority transfer function in this ATM switch is described in, for example, Japanese Patent Laid-Open No. 6-197128 (hereinafter referred to as “Prior Art 1”). Here, two output buffers for CBR and VBR are provided for each output line. By making the output priority of the cells stored in the CBR buffer higher than that of the cells stored in the VBR buffer, the communication delay time in the ATM switch can be reduced for CBR traffic cell groups with severe restrictions on communication delay. It can be suppressed within a certain value.

  However, the ATM switch sets the connection in advance, reads the priority information (cell transfer priority, etc.) in the connection information table set in the ATM switch based on the connection information of the input cell, and gives priority to the priority information. Apply the transfer function (connection type communication).

  On the other hand, since the router device does not set a connection in advance, it does not have a connection information table in the case of an ATM switch or priority information in the connection information table (packet type communication). For this reason, in order to perform QoS control in the router device, in addition to the priority transfer function similar to that of the ATM switch, a flow detection means for detecting priority information from information in the header for each input packet is required. A priority transfer function is applied to the priority information detected by the flow detection means. In this specification, a packet identification condition created by combining information such as information in the header is a flow condition, a series of traffic that matches the flow condition, and whether the input packet matches the flow condition. It is called flow detection to determine whether or not information necessary for QoS control such as priority information is determined.

  The QoS control in the router device is mentioned in, for example, Japanese Patent Laid-Open No. 6-232904 (hereinafter referred to as “Prior Art 2”). Prior art 2 uses a mapping table that holds priority information for all combinations of information for identifying priority in a packet and protocol (= higher application) information in order to execute QoS control in a router. Disclose that the degree information is determined. Based on the determined priority information, the priority transfer function can be applied to ensure QoS.

  However, the interior node 228, which is located in the backbone of the DS domain 225 (described later) in FIG. 2, has a large number of flows, and is connected to a high-speed line, cannot perform QoS control at high speed and may not realize QoS.

  As a prior art for solving this problem, there is, for example, Diffserv (Differentiated Service) (hereinafter referred to as “Prior Art 3”) described in RFC2475 of IETF (Internet Engineering Task Force). Prior art 3 realizes QoS of interior nodes by making boundary nodes of relatively light load located at the edge of the network highly functional and limiting high load interior nodes located at the core of the network to simple functions .

Prior Art 3 will be described with reference to FIG. FIG. 2 shows a network in which a corporate network A 221, a corporate network B 222, a corporate network C 223 and a corporate network D 224 are connected by a DS domain 225.
The DS domain 225 executes QoS control based on the same policy (for example, Telnet has priority), and realizes QoS that is contracted in advance between the corporate network and the Internet. The DS domain 225 includes a boundary node A 226 and a boundary node B 227 located at the edge of the DS domain 225, and an interior node 228 located at the core of the DS domain 225.

  Consider a case in which a packet is transmitted from the corporate network A 221 to the corporate network D224. When the boundary node A226 at the entrance of the DS domain 225 receives a packet from the corporate network A221, the source / destination IP address, source / destination in the TCP / IP header is detected by flow detection means (called a classifier in the conventional technique 3). Flow detection is performed using the port number, protocol, etc. as a flow condition, the priority in the DS domain 225 is determined, and the priority is written in the DS field in the packet header. The boundary node B 227 located at the exit of the DS domain 225 and the interior node 228 having a high load perform flow detection based on only the value of the DS field and execute QoS control at high speed.

JP-A-6-197128

It is not realistic for the current network operator to replace all existing routers at the same time in order to shift to a network (hereinafter referred to as a Diffserv network) to which Diffserv described in Prior Art 3 is applied. The process of smoothly migrating to a Diffserv network while minimizing the costs and risks associated with migration consists of the following two stages.
[Migration stage]
The point where packet discard or delay time increases in the network is called a “hot spot”. This hot spot router is selectively replaced with a router with strong QoS control. The communication quality is greatly improved by eliminating this hot spot.

Necessary functions of the router to realize this transition stage are to detect the priority information by performing flow detection using the source / destination IP address, source / destination port number, protocol, etc. in the TCP / IP header. Function (referred to as Diffserv function 1).
[Operation stage]
As the transition to routers with QoS control progresses at the transition stage, QoS improves. When most routers are replaced, the network administrator of the DS domain starts operating the Diffserv network. A necessary function of the router used as the interior node is a function (referred to as Diffserv function 2) for determining priority information from the DS field. On the other hand, the necessary functions of the router used as the boundary node are the Diffserv function 2 required at the DS domain exit, and the source / destination IP address, source / destination in the TCP / IP header required at the DS domain entrance. This is a function (referred to as Diffserv function 3) that performs flow detection using the destination port number, protocol, etc. as a flow condition and determines the value to be written in the DS field.

  Therefore, in order to smoothly transition to the Diffserv network, the router used as the interior node possesses Diffserv functions 1 and 2, and the DS domain administrator and network management depending on the stage (transition stage or operation stage) It is necessary that the device can easily switch between the Diffserv function 1 and the Diffserv function 2.

  However, in the prior art 3, such a viewpoint is not examined. A first object of the present invention is to provide a router having the functions of the Diffserv function 1 and the Diffserv function 2 and capable of switching the Diffserv function.

  In order to make a smooth transition to the Diffserv network, the router used as a boundary node has Diffserv functions 1, 2 and 3, and DS domain administrators and network management devices can easily perform the functions according to the stage. It is necessary to be able to switch.

However, in the prior art 3, such a viewpoint is not examined. A second object of the present invention is to provide a router having the functions of the Diffserv function 1, the Diffserv function 2 and the Diffserv function 3, and capable of switching the Diffserv function.
In the operation stage, a router used as a boundary node must have Diffserv functions 2 and 3 so that a DS domain administrator and a network management apparatus can easily switch the functions.
However, in the prior art 3, such a viewpoint is not examined. A third object of the present invention is to provide a router having the functions of the Diffserv function 2 and the Diffserv function 3 and capable of switching the Diffserv function.

  In the operation stage, the router needs to have a function of flexibly switching the Diffserv function according to the position (edge or core) in the DS domain and the DS domain configuration. For example, the boundary node A226 in FIG. 2 needs to apply the Diffserv function 3 to the packet from the corporate network A221 and apply the Diffserv function 2 to the packet from the interior node 228. Diffserv function 3 must be applied to all packets

  However, in the prior art 3, such a viewpoint is not examined. A fourth object of the present invention is to provide a router capable of flexibly switching the Diffserv function according to the position in the DS domain and the configuration of the DS domain.

  The interior node 228 to which the high-speed line is connected must execute the Diffserv function 2 at high speed.

  However, in the conventional technique 3, a method for executing the Diffserv function 2 at a high speed while having the functions of the Diffserv function 1, the Diffserv function 2, and the Diffserv function 3 has not been studied. A fifth object of the present invention is to provide a router having the functions of the Diffserv function 1, Diffserv function 2 and Diffserv function 3, and capable of executing the Diffserv function 2 at high speed.

  In order to achieve the above object, in the packet relay device of the present invention, communication quality control of the packet in the packet relay device is performed from at least one of the address information of the input packet of the packet relay device and the information for identifying the application. A determination unit 1 for determining information, a determination unit 2 for determining communication quality control information of the packet relay device of the packet from information for identifying the priority of the input packet, and address information and application of the input packet are identified. Among the information, at least two determination means among the determination means 3 for determining information for identifying the priority of a packet input from at least one information, the determination means 1, the determination means 2, and the determination means 3 are selected. It has a mode table that holds mode information indicating whether to apply.

    In another packet relay apparatus, the mode information is possessed for each input line.

  The other problems to be solved by the present application and the means for solving the problems will be clarified in the “Embodiments of the Invention” section of the present application and the drawings.

  It is possible to provide a router that can smoothly transition from the current network to the Diffserv network that can ensure communication quality.

  Examples of the present invention will be described below. First, the general operation of the router of the present invention will be described with reference to FIGS. 1 and 3 to 5. FIG.

FIG. 1 shows a configuration example of a router. The router 100 includes a header processing unit 110 that performs routing processing, flow detection, and ARP (Address Resolution Protocol) processing, a packet input / output unit 120 that transfers packets, and a processor 130. The header processing unit 110 includes a routing processing unit 111, a flow detection unit 112, and an ARP processing unit 113. The packet input / output unit 120 includes an output FIFO (First In First Out) buffer distribution circuit 121, a line corresponding unit 122-i (i = 1 to N) and line i 123-i. In addition, a management terminal 140 and a network management device 150 outside the router 100 are connected to the processor 130.
FIG. 3 shows an example of a packet format in the network. The packet format in the network is composed of a header part 310 and a data part 320. The header section 310 includes a source MAC address (Source Address Media Access Control: hereinafter referred to as “SAMAC”) 300 that is a physical address (hardware address) of a router that has transmitted the packet immediately before, and a router that receives the packet next. A destination MAC address (Destination Address Media Access Control: hereinafter referred to as “DAMAC”) 301 which is a physical address and a source IP address (Source IP Address: hereinafter referred to as “SIP”) which is a source address (address of a transmission terminal). ) 302, a destination IP address (Destination IP Address: hereinafter referred to as “DIP”) 303 that is a destination address (address of the receiving terminal), and a source port (Source Port: hereinafter referred to as “SPORT”) indicating a protocol (= higher application) ”304, a destination port (hereinafter referred to as“ DPORT ”) 305, and a DS 306 representing the priority in the DS domain. The data unit 320 includes user data 321 that is user data. In addition to the above information, information such as an upper protocol of the IP protocol is stored in the header section 310, but it can be processed in the same manner as the above information. The format of FIG. 3 shows the case where the transport layer protocol is a TCP (Transmission Control Protocol) or UDP (User Datagram Protocol) and the network layer protocol is an IP (Internet Protocol) packet. The network layer protocol may be IPX).

  FIG. 4 shows an example of a packet format inside the router 100 of the present invention. The packet format inside the router is provided with an internal header section 330 in the network packet format. This internal header section 330 includes an input line number 307 that is a line number to which a packet is input, an output line number 308 that is a line number that outputs a packet, and a priority that is priority information used in the priority transfer function. It consists of information 309.

  When a packet is input from the line i 123-i, the receiving circuit 124-i adds the line number i to which the packet is input as the input line number 307. Then, after converting into the packet format inside the router, it is transmitted to the input FIFO buffer 126-i. The output line number 308 and the priority information 309 at this time are meaningless information. The input FIFO buffer 126-i accumulates packets and transmits the packets to the output FIFO buffer distribution circuit 121 in the order in which the packets are accumulated. Then, the output FIFO buffer distribution circuit 121 stores the packet in the temporary storage buffer 128 and outputs the header information 11 to the header processing unit 110. The header information 11 includes information on the internal header portion 330 and the header portion 310.

  The routing processing unit 111 searches the routing table from the DIP in the header information 11, and outputs the line number for transfer to the subnet to which the DIP belongs, and the IP address (NIP) of the router that next receives the packet sent by the router 100 : Next Hop IP Address). The processor 130 of the router 100 creates and manages this routing table. This routing table search is described in, for example, Japanese Patent Laid-Open No. 10-222535. Further, the routing processing unit 111 outputs the output line information 12 composed of the output line number to the output FIFO buffer distribution circuit 121 of the packet input / output unit 120 and the NIP information 14 composed of NIP to the ARP processing unit 113. . When receiving the output line information 12, the output FIFO buffer distribution circuit 121 writes the output line information 12 to the output line number 308 of the packet stored in the temporary storage buffer 128.

  When receiving the NIP information 14, the ARP processing unit 113 determines a MAC address corresponding to the NIP. Further, DAMAC information 15 composed of the MAC address is output to the output FIFO buffer distribution circuit 121 of the packet input / output unit 120. When receiving the DAMAC information 15, the output FIFO buffer distribution circuit 121 writes the DAMAC information 15 into the DAMAC 301 of the packet stored in the temporary storage buffer 128.

  On the other hand, the flow detection unit 112 searches the entry table 850 in FIG. 6 (details will be described later) based on the header information 11, and performs priority information used in the priority transfer function, execution / non-execution of DS rewriting, DS Rewrite DS information that is a value to be written to is determined. Further, packet priority information 13 consisting of priority information, DS rewriting valid information 16 indicating execution / non-execution of DS rewriting, and packet rewriting DS information 17 consisting of rewriting DS information are output FIFO of the packet input / output unit 120. The data is output to the buffer distribution circuit 121.

When receiving the packet priority information 13, the output FIFO buffer distribution circuit 121 writes the packet priority information 13 into the packet priority information 309 stored in the temporary storage buffer 128. In addition, when the DS rewrite valid information 16 and the packet rewrite valid DS information 17 are received, the DS rewrite valid information 16 is “executed” and the packet DS306 is rewritten to the packet rewrite DS information 17. The value of DS306 is left as it is without rewriting. When the above processing ends, the output FIFO buffer distribution circuit 121 outputs the output FIFO buffer 127-ij (j = 1 or 2) indicated by the priority information 309 of the line corresponding unit 122-i indicated by the output line number 308. Send a packet to The line corresponding unit 122-i stores the packet in the output FIFO buffer 127-ij. The transmission circuit 125-i in the line corresponding unit 122-i controls reading of the output FIFO buffer 127-ij. As read-out control, “complete priority control”, “weighted cyclic control”, and the like are known. In “complete priority control”, when packets are accumulated in the output FIFO buffer 127-i1 having a high priority, the packets are read in the order in which they are accumulated from the output FIFO buffer 127-i1. Only when no packet is accumulated in the output FIFO buffer 127-i1, the packets are read out in the order of accumulation from the output FIFO buffer 127-i2 having a low priority. On the other hand, in the “weighted cyclic control”, packets are read from the output FIFO buffer 127-i1 and the output FIFO buffer 127-i2 based on a preset ratio. Note that the read control in the transmission circuit 125-i is set from the network management device 150 or from the management terminal 140. Further, the transmission circuit 125-i deletes the internal header portion 330 of the read packet.
Then, the MAC address assigned to the line i 123-i is written into the SAMAC 301, and the packet is transmitted to the line i 123-i.

  The detailed operation of the flow detection unit 112 will be described below. FIG. 8 shows a block diagram of the flow detection unit 112. The flow detection unit 112 includes a result determination unit 810, a condition match determination unit 820, an entry reading unit 830, a control unit 840, and an entry table 850. The control unit 840 includes a Diffserv mode table 841 that sets modes 1 to 3 for each input line, and a Diffserv mode determination unit 842 that determines the Diffserv mode from the input line number.

  A table format of the Diffserv mode table 841 is shown in FIG. Mode 1 is a mode for realizing the transition stage. In mode 1, the flow detection unit 112 applies the Diffserv function 1. That is, the flow detection unit 112 performs flow detection using the transmission source / destination IP address, transmission source / destination port number, and the like in the TCP / IP header as flow conditions to determine priority information. Mode 2 and mode 3 are modes for realizing the operation stage. In mode 2, the flow detection unit 112 applies the Diffserv function 2. That is, the flow detection unit 112 determines priority information from the DS field. In mode 3, the flow detection unit 112 applies the Diffserv function 3. That is, the flow detection unit 112 performs flow detection using the transmission source / destination IP address, transmission source / destination port number, and the like in the TCP / IP header as flow conditions, and determines rewrite DS information. In this specification, the modes 1 to 3 are referred to as Diffserv modes. The administrator of the DS domain can easily set the Diffserv mode table 841 from the management terminal 140 via the processor 130. Similarly, the network management device 150 can be easily set via the processor 130 as well.

  FIG. 6 shows the format of the entry table 850. The entry table 850 in FIG. 6 includes H entries 630. The entry 630 includes a flow condition part 631 and a QoS control information part 632. The QoS control information unit 632 includes priority information 611 used for priority transfer and rewrite DS information 612 that is rewrite DS information. The flow condition unit 631 includes a flow condition for identifying a transmission source or a destination user and a flow condition for identifying a protocol.

  The flow conditions for identifying the source or destination user are the SIP upper limit value and SIP lower limit value SIP upper limit value 601, SIP lower limit value 602, DIP upper limit value 603, DIP lower limit value 604, and SIP and DIP upper limit values. An IP valid bit 621 indicating that the lower limit value is valid, an input line number 607 which is an input line number, and an input line number valid bit 623 indicating that the input line number 607 is valid. The boundary node A226 or boundary node B227 in FIG. 2 can identify the enterprise network (enterprise network A221 or enterprise network B222, enterprise network C223 or enterprise network D224) that has transmitted the packet by the input line number. . The reason why the upper limit value and the lower limit value are set by SIP and DIP is to allow the network (= subnet) to be designated by one entry 630. FIG. 5 shows the format of the IP address 540. The IP address 540 includes a network address 541 and a host address 542. A network (= subnet) is identified by the network address 541, and a terminal in the network is identified by the host address 542. Since the upper bits of the IP address 540 are network addresses, terminals in the same network have continuous IP addresses. Therefore, all terminals in the network can be designated by the IP address range (upper limit value and lower limit value).

  The flow conditions for identifying the protocol are a SPORT 605 that is a source port, a DPORT 606 that is a destination port, and a port valid bit 622 indicating that the SPORT 605 and the DPORT 606 are valid. The IP valid bit 621, port valid bit 622, and input line number valid bit 623 are “valid” when identifying a packet by IP address, port number, and input line number, respectively. "Is set.

  A flowchart of the flow detection unit 112 is shown in FIG. The process of the flow detection unit 112 is divided into four processes: a detection start process 700, an entry read process 730, a condition match determination process 720, and a result determination process 710. The following three processes are executed by the entry reading unit 830, the condition match determination unit 820, and the result determination unit 810, respectively.

  Hereinafter, processing at the time of flow detection will be described in order. In the detection start processing 700, when the header information 11 of the packet is transmitted to the header processing unit 110, the flow detection unit 112 detects the input line number 307, SIP 302, DIP 303, SPORT 304, DPORT 305, DS 306 in the header information 11. Intra-packet line number storage means 826-2, intra-packet SIP storage means 822-2, intra-packet DIP storage means 822-2, intra-packet SPORT storage means 824-2, intra-packet The data is stored in the DPORT storage means 825-2 and the DS storage means 815 of the result determination unit 810 (step 701). The Diffserv mode determination unit 842 of the control unit 840 determines that the value of the Diffserv mode table 841 corresponding to the input line number in the intra-packet line number storage unit 826-2 is the Diffserv mode (Step 704). In the case of mode 1 or mode 3, the Diffserv mode determination means 842 transmits an activation signal to the entry reading unit 830 (step 703).

  First, the case where the Diffserv mode is mode 1 or mode 3 will be described. In the case of mode 1 or mode 3, after the detection start process 700, an entry reading process 730 is performed. In the entry reading process 730, when the activation signal is received from the control unit 840, the entry reading unit 830 resets the value M of the entry number counter 831 to 1 so that the first entry 630-1 of the entry table 850 is read. (Step 731). Next, the entry table address generation circuit 832 generates the address of the entry table 850 from the value M (1 in this case) of the entry number counter 831, reads the entry 630-1, SIP upper limit value 601-1 and SIP lower limit value Information of the value 602-1 is stored in the SIP storage means 822-3 in the entry in the condition matching determination unit 820, information of the DIP upper limit value 603-1 and the DIP lower limit value 604-1 is stored in the DIP storage means 823-3 in the entry, The information of SPORT 605-1 and DPORT 606-1 is stored in the in-entry SPORT storage means 824-3 and the in-entry DPORT storage means 825-3, respectively, and the IP valid bit 621-1, port valid bit 622-1 and input line number valid. Bit 623-1 is stored in effective bit storage means 827, and priority information 611-1 and rewrite DS information 612-1 are stored in priority information storage means 813 and rewrite DS information storage means 816 of result determination unit 810, respectively (step 732). Further, the value M of the entry number counter 831 is incremented by 1 so that the entry 630-2 is read when the next entry reading process 730 is executed (step 733). By repeating the entry reading process 730, the entry reading unit 830 reads the entries 630 in order from the smallest entry table address to the largest entry table address.

In the condition match determination processing 720, the condition match determination unit 820 includes an intra-entry SIP storage unit 822-3, an intra-entry DIP storage unit 823-3, an intra-entry SPORT storage unit 824-3, an intra-entry DPORT storage unit 825-3, an entry It is determined whether or not the input packet matches the flow conditions stored in the internal line number storage means 826-3.
The SIP comparison circuit 822-1 has the SIP upper limit value and lower limit value stored in the in-packet SIP storage means 82-2 and the SIP stored in the in-entry SIP storage means 822-3 are "SIP lower limit value≤SIP≤SIP If the condition “upper limit value” is satisfied or the IP valid bit in the valid bit storage means 827 is “invalid”, it is determined as “match” (step 721-1). The DIP comparison circuit 823-1 performs the same processing as that for SIP on DIP (step 721-2). The SPORT comparison circuit 824-1 is used when the SPORT stored in the intra-packet SPORT storage means 824-2 is equal to the SPORT stored in the intra-entry SPORT storage means 824-3, or the port valid bit is "invalid". It is determined as “match” (step 721-3). The DPORT comparison circuit 825-1 executes the same processing as SPORT for DPORT (step 721-4). The line number comparison circuit 826-1 stores the input line number stored in the intra-packet line number storage means 826-2 and the input line number stored in the intra-entry line number storage means 826-2, or stores effective bits. If the input line number valid bit stored in the means 827 is “invalid”, it is determined as “match” (step 721-5).
The condition match determination circuit 821 determines that the condition match result in the result determination unit 810 is “Yes” in Step 721-1, Step 721-2, Step 721-3, Step 721-4, and Step 721-5. Information indicating “match” is stored in the storage unit 812 (step 722-1). Otherwise, information indicating “mismatch” is stored (step 722-2). When the information indicating “match” is stored in the condition match result accumulating unit 812, the result determination unit 810 executes the result determination processing 710, and when the information indicating “mismatch” is stored, the process returns to step 732, and the flow The detection unit 112 executes the entry reading process 730 and the condition match determination process 720 again. When the number of flow conditions to be set increases, the flow detection unit 112 repeats the entry reading process 730 and the condition match determination process 720 many times, and thus cannot detect a flow at high speed.

  In the result determination process 710, the result determination circuit 811 operates according to the Diffserv mode determined in step 704. When the Diffserv mode determined by the Diffserv mode determination unit 842 is mode 1, the result determination circuit 811 determines the value of the priority information storage unit 813 as priority information, packet priority information 13 including the priority information, and The DS rewrite valid information 16 in which the DS rewrite is “invalid” is transmitted to the output FIFO buffer distribution circuit 121, and the flow detection is finished (step 713). On the other hand, when the Diffserv mode is mode 3, the result determination circuit 811 determines the value of the priority information storage unit 813 as the priority information and the value of the rewrite DS information storage unit 816 as the rewrite DS information. Packet priority information 13, DS rewrite valid information 16 for which DS rewrite is “valid”, and packet rewrite DS value information 17 composed of the rewrite DS information are transmitted to the output FIFO buffer distribution circuit 121 for flow detection. End (step 714).

  Next, the case where the Diffserv mode is mode 2 will be described. Since the Diffserv function 2 applied in the mode 2 is used in the interior node 228 with a high load, it must be executed at high speed. The flow detection unit 112 of the present invention skips the entry reading process 730 and the condition matching determination process 720, which become a bottleneck in speeding up the flow detection when the flow condition increases, and executes the flow detection at high speed.

  When the Diffserv mode determined by the Diffserv mode determination unit 842 in Step 704 is mode 2, the result determination circuit 811 reads information corresponding to the DS of the DS storage unit 815 from the priority information table 814 shown in FIG. 9 (Step 712). . Further, the read information is determined as the priority information of the input packet, and the packet priority information 13 including the priority information and the DS rewrite valid information 16 in which the DS rewrite is “invalid” are output FIFO buffer distribution circuits Then, the flow detection is finished (step 715). Since the DS is 6-bit information, the priority information table 814 only needs to have at most 64 pieces of priority information.

  According to the embodiment of the present invention described above, the Diffserv mode 1 is provided in the Diffserv mode table 841, thereby realizing the functions of the Diffserv function 1 and the Diffserv function 2, and the administrator of the DS domain and the network management apparatus. 150 can easily switch the Diffserv function.

  Furthermore, by having the Diffserv mode in the Diffserv mode table 841, the Diffserv function 1, the Diffserv function 2 and the Diffserv function 3 are possessed, and the administrator of the DS domain and the network management device can easily switch the Diffserv function. I can do it.

  Furthermore, by possessing the Diffserv mode in the Diffserv mode table 841, the Diffserv function 2 and the Diffserv function 3 can be possessed, and the administrator of the DS domain and the network management apparatus can easily switch the Diffserv function.

  Furthermore, by having the Diffserv mode in the Diffserv mode table 841 for each input line, the DS domain administrator and the network management device can flexibly switch the Diffserv function according to the position in the DS domain and the configuration of the DS domain. Can do.

  Furthermore, when the flow detection unit 112 is in mode 2, the router 100 skips the entry reading process 730 and the condition matching determination process 720, which are the bottlenecks in performing flow detection at high speed, from the priority information table 814. High-speed execution of Diffserv function 2 is realized by reading information at high speed.

So far, the embodiment in which the Diffserv mode is possessed for each input line has been described. If the Diffserv mode can be set for each entry (= each flow), the Diffserv function can be switched more flexibly. Hereinafter, differences from the embodiment having the Diffserv mode for each input line will be described.

  The format of the entry table 1150 is shown in FIG. 11, the block diagram of the control unit 1240 is shown in FIG. 12, and the flowchart is shown in FIG. In the entry 1130 of FIG. 11, the Diffserv mode 1100 is increased compared to the entry 630. The administrator of the DS domain can easily set the Diffserv mode 1100 from the management terminal 140 via the processor 130. Similarly, the network management apparatus 150 can easily set the Diffserv mode 1100 via the processor 130. Further, the control unit 1240 has Diffserv mode storage means 1241 instead of the Diffserv mode table 841.

  Compared to step 732, step 1332 of entry reading processing 1330 adds processing for storing the Diffserv mode 1100 in the entry 1130 in the Diffserv mode storage means 1241. Further, Step 704 for determining the Diffserv mode is changed to Step 1335 in which the Diffserv mode determination unit 1242 determines that the value of the Diffserv mode storage unit 1241 is the Diffserv mode. Since this step 1335 needs to be performed after the Diffserv mode 1100 accumulation processing in step 1332, it is executed in the entry read processing 1330. Further, in the result determination process 1310, the Diffserv function is switched based on the Diffserv mode determined by the Diffserv mode determination means 1242 (step 1311).

  According to the embodiment of the present invention described above, by having a Diffserv mode for each entry, a DS domain administrator or a network management device can perform the above operation according to the location in the DS domain or the configuration of the DS domain. Diffserv function can be switched flexibly.

The block diagram which shows the structure of the router of this invention. Diagram of Diffserv network. The figure which shows the format of the packet in a network. The figure which shows the format of the packet in the router to which this invention is applied. The figure which shows the format of an IP address. Entry table format when Diffserv mode is possessed for each input line. The flowchart of a flow detection part at the time of possessing Diffserv mode for every input line. The block diagram of the flow detection part at the time of possessing Diffserv mode for every input line. Priority information table format. Diffserv mode table format. The format of the entry table when each entry has Diffserv mode. The block diagram of a control part at the time of having Diffserv mode for every entry. The flowchart of a flow detection part at the time of possessing Diffserv mode for every entry.

Explanation of symbols

  11 ... Header information, 12 ... Output line information, 13 ... Packet priority information, 14 ... NIP information, 15 ... DAMAC information, 16 ... DS rewrite valid information, 17 ... Packet rewrite DS information.

Claims (14)

Connected to another packet relay device, comprising a plurality of input lines, a plurality of output lines, and a control unit, wherein an input packet input from one input line of the plurality of input lines is output to the plurality of outputs A packet relay device that outputs to any output line of the line,
The packet relay device can perform the first and second operations among the first to third operations .
Wherein the control unit before Symbol first operation, the address information of the input packet, which applies the communication quality control for the packet based on at least one information among the information for identifying the application,
In the second operation, the control unit applies communication quality control to the packet based on information identifying the priority in the header of the input packet,
In the third operation, the other packet relay device identifies information in the header of the input packet based on at least one of the address information of the input packet and information for identifying the application. And applying communication quality control to the packet based on at least one of the address information, the information for identifying the application, or the information for identifying the priority,
Furthermore the control unit, in the second operation, on the basis of the information identifying the priority is Oite granted to another packet relay apparatus for performing the third operation, the communication quality control with respect to the packet Apply
The control unit determines which of the first operation and the second operation is to be applied to an input packet. The first operation, and the operation information indicating whether to apply any of the operation of the second operation, has an operating table for holding the input line corresponding,
2. The packet relay device according to claim 1, wherein the control unit determines which operation is applied to the packet according to which input line the input packet is input from. .   The control unit includes at least one of address information of an input packet and information for identifying an application, and at least two of the first operation, the second operation, and the third operation. 2. The packet relay device according to claim 1, further comprising an entry table having operation information indicating which operation is applied as an entry. The address information is
[1] Identification number of the input line,
[2] Identification number of the output line,
[3] Source physical address,
[4] Destination physical address,
[5] Source subnet identification information,
and,
[6] Destination subnet identification information,
The packet relay device according to claim 1, wherein the packet relay device is at least one of the above.   5. The packet relay device according to claim 1, wherein the information for identifying the application is a TCP port number.   6. The packet relay device according to claim 1, wherein the information for identifying the priority in the packet header is a value of a DS field. Connected to another packet relay device, comprising a plurality of input lines, a plurality of output lines, and a control unit, wherein an input packet input from one input line of the plurality of input lines is output to the plurality of outputs A packet relay device that outputs to any output line of the line,
The packet relay device can operate in the first mode and the second mode among the first to third modes ,
Wherein the control unit before Symbol first mode, without giving information identifying the priority in the header of the input packet, the address information of the input packet, at least one information among the information for identifying the application Applying communication quality control to the packet based on
In the second mode, the control unit applies communication quality control to the packet based on information for identifying priority in a header of the input packet.
In the third mode, the other packet relay device identifies information in the header of the input packet based on at least one of the address information of the input packet and information for identifying the application. Is given,
Furthermore the control unit, the in the second mode, based on the information identifying the priority that is Oite granted to another packet relay device operating in the third mode, the communication quality for the packet Apply the control,
The packet relay device, wherein the control unit determines which mode of the first mode or the second mode is applied to an input packet. Connected to another packet relay device and a management device, and includes a plurality of input lines, a plurality of output lines, and a control unit, and receives an input packet input from one input line of the plurality of input lines. A packet relay device for outputting to any one of the plurality of output lines,
The packet relay device can perform the first and second operations among the first to third operations ,
Wherein the control unit before Symbol first operation, the address information of the input packet, which applies the communication quality control for the packet based on at least one information among the information for identifying the application,
In the second operation, the control unit applies communication quality control to the packet based on information identifying the priority in the header of the input packet,
In the third operation, the other packet relay device identifies information in the header of the input packet based on at least one of the address information of the input packet and information for identifying the application. And applying communication quality control to the packet based on at least one of the address information, the information for identifying the application, or the information for identifying the priority,
Furthermore the control unit, in the second operation, on the basis of the information identifying the priority is Oite granted to another packet relay apparatus for performing the third operation, the communication quality control with respect to the packet Apply
The packet relay device, wherein the control unit applies either the first operation or the second operation to an input packet in accordance with an input from the management device. The first operation, and the operation information indicating whether to apply any of the operation of the second operation, has an operating table for holding the input line corresponding,
9. The packet relay device according to claim 8, wherein the control unit determines which operation is applied to the packet according to which input line the input packet is input from. .   The control unit includes at least one of address information of an input packet and information for identifying an application, and at least two of the first operation, the second operation, and the third operation. 9. The packet relay apparatus according to claim 8, further comprising an entry table having operation information indicating which operation is applied as an entry. The address information is
[1] Identification number of the input line,
[2] Identification number of the output line,
[3] Source physical address,
[4] Destination physical address,
[5] Source subnet identification information,
and,
[6] Destination subnet identification information,
The packet relay apparatus according to claim 8, wherein the packet relay apparatus is at least one of the above.   12. The packet relay device according to claim 8, wherein the information for identifying the application is a TCP port number.   13. The packet relay device according to claim 8, wherein the information for identifying priority in the packet header is a value of a DS field. A plurality of input lines, a plurality of output lines, and a control unit, connected to another packet relay apparatus and a management apparatus, and receiving an input packet input from one input line of the plurality of input lines; A packet relay device for outputting to any one of a plurality of output lines,
The packet relay device can operate in the first mode and the second mode among the first to third modes ,
Wherein the control unit before Symbol first mode, without giving information identifying the priority in the header of the input packet, the address information of the input packet, at least one information among the information for identifying the application Applying communication quality control to the packet based on
In the second mode, the control unit applies communication quality control to the packet based on information for identifying priority in a header of the input packet.
In the third mode, the other packet relay device identifies information in the header of the input packet based on at least one of the address information of the input packet and information for identifying the application. Is given,
Furthermore the control unit, in the second operation, on the basis of the information identifying the priority is Oite granted to another packet relay apparatus for performing the third operation, the communication quality control with respect to the packet Apply
The packet relay device, wherein the control unit applies either the first mode or the second mode to an input packet in accordance with an input from the management device.

Images