JP2003152773A - Network repeater, network relaying method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To prevent an occurrence of a packet loss with an economical configuration in a network repeater. SOLUTION: A first processing means 31 and a second processing means 32 share relay processing that includes encapsulating processing. If a packet P (packet to be transmitted to the Internet 6) is stored in an input buffer 12-1 through an input-output port 11-1, the first processing means 31 applies a portion of processing in the relay processing to the packet P. Then, the first processing means 31 performs loopback of the packet P to the j-th input port through a loopback circuit 2 and stores the packet P in an input buffer 12-j for loopback. After that, the second processing means 32 applies the residual processing to the packet P and outputs the processed packet P to an input-output port 11-n for Internet connection.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a network relay technology applied to bridges, routers, multilayer switches, etc., and more particularly to a network relay technology capable of eliminating packet loss with an economical structure.

[0002]

2. Description of the Related Art In a network relay device such as a bridge, a router, and a multilayer switch, generally, a packet received through an input port is temporarily stored in an input buffer, and the stored packets are sequentially processed in the order of storage. I am trying to do it. Therefore, if the processing time for a packet becomes longer than the packet arrival interval,
Received packets gradually stay in the input buffer, and eventually overflow (packet loss) occurs. Further, even in a network relay device of a type that does not have an input buffer for each input port, if the processing time becomes longer than the packet arrival interval, packet loss will occur.

When a packet loss occurs, the packet is retransmitted in the upper layer of the network. When packet retransmission processing is performed, there may be a vicious cycle of increased traffic, increased load on the network relay device, packet loss, and retransmission processing. In addition, the processing of the client often stops until the retransmission processing of the upper layer is completed.

In order to prevent the occurrence of such a situation, conventionally, the operation clock of the network relay device has been increased so that the processing time for a packet is shorter than the arrival interval of the packet.

[0005]

However, the method of preventing the packet loss by increasing the operation clock of the network relay device requires the use of expensive hardware capable of high-speed operation, which increases the price. There is also a problem that power consumption increases.

[0006] In recent years, network expansion and LA
With the improvement of line speed of N, WAN, etc., bridge,
The amount of data flowing through network relay devices such as routers and multilayer switches is explosively increasing. Furthermore, in the network relay device, in addition to basic processing such as bridging processing and routing processing, encapsulation processing, address conversion processing, filtering processing, etc. have come to be performed. It tends to become more and more complicated. Therefore, in the future, it is sufficiently predicted that the packet loss cannot be dealt with only by increasing the operation clock of the network relay device.

An object of the present invention is to prevent packet loss with an economical structure.

[0008]

In order to achieve the above-mentioned object, a network relay device of the present invention comprises a plurality of input ports and a plurality of output ports, and performs a conversion process on a packet received via the input port. Is a network relay device that executes a relay process including a packet and outputs the packet for which the relay process has been completed to an output port corresponding to the destination, wherein the relay process is divided into a plurality of partial processes, and the received packet is On the other hand, when sequentially performing the plurality of partial processes, after the completion of one partial process, the processing result is looped back to the input port allocated for the next partial process among the plurality of input ports, It is provided with means for causing the next partial processing to perform processing using the looped back processing result.

According to this structure, the packets received through the input port are sequentially subjected to the partial processing. Therefore, even if the processing time of the entire relay processing is longer than the packet arrival interval, The processing time of the partial processing can be made shorter than the arrival time of the packet, and as a result, the occurrence of packet loss can be prevented. For example, when the processing time of the entire relay process is 2T and the packet arrival interval is 1T, the packet loss is prevented by dividing the relay process into two partial processes and setting the processing time of each divided process to 1T. be able to. In addition, the operation clock of the network relay device can be kept low compared to the case where the relay process is not divided into a plurality of partial processes, so that the network relay device can be configured using low-speed and inexpensive parts. Also, the power consumption can be kept low.

More specifically, the network relay device of the present invention comprises a plurality of input ports, an input buffer for each of the plurality of input ports, and a plurality of output ports, and the input buffer is connected to the input buffer via the input ports. When the output port corresponding to the destination of the accumulated packet is a specific output port of the plurality of output ports, a relay process including a conversion process is executed on the accumulated packet, and the relay process is completed. A network relay device for outputting the stored packet to the specific output port, and the output port corresponding to the destination of the packet stored in the input buffer is the specific output port, for the stored packet A part of the relay process is executed, and the packet for which the part of the process is completed is used as a route of the plurality of input ports and output ports. By performing a loopback using the output port for back and the input port for loopback, the packets are accumulated in the loopback input buffer corresponding to the loopback input port, and the packets accumulated in the loopback input buffer are stored. There is provided means for executing the remaining processing of the relay processing and outputting the packet for which the remaining processing is completed to the specific output port.

[0011]

DESCRIPTION OF THE PREFERRED EMBODIMENTS Next, embodiments of the present invention will be described in detail with reference to the drawings.

Referring to FIG. 1, there is shown a configuration example of a multilayer switch as an embodiment of the present invention. The multi-layer switch of this embodiment includes a LAN line processing unit 1
A loopback circuit 2, a packet conversion processing unit 3,
It is composed of a packet buffer management unit 4 and a buffer memory 5.

The LAN line processing unit 1 includes a plurality of input / output ports 11-1 to 11-1 each consisting of a pair of an input port and an output port.
1-n and input buffers 12-1 to 12-n for the respective input / output ports 11-1 to 11-n. Of the input / output ports 11-1 to 11-n, the j-th input / output port 11-j (loopback input / output port 11-j) is
The n-th input / output port 11-n (specific input / output port 11-n) is connected to the loopback circuit 2 and is connected to the Internet 6. The input / output ports other than the loopback input / output port 11-j and the specific input / output port 11-n are connected to different LANs (not shown). The LAN line processing unit 1 is, for example, M
It is configured using an LSI called an AC chip.

The loopback circuit 2 connects the output port (referred to as a loopback output port) that constitutes the loopback input / output port 11-j and the input port (loopback input port) to make a loopback. The packet output from the output port is looped back to the input port for loopback.

The packet conversion processing section 3 is composed of, for example, a network processing processor, and comprises a first processing means 31, a second processing means 33, a forward table 33, and a recording medium K1. ing.

The packet conversion processing unit 3 executes a relay process including an encapsulation process, and the first and second processing means 31 and 32 divide the relay process and perform it.

The first processing means 31 is the input buffer 12
Loopback input buffer 1 of -1 to 12-n
Input buffers other than 2-j are sequentially processed, and the following processes A to C are performed.

A. When the packet is stored in the input buffer to be processed, the output port of the output destination of the packet is determined based on the destination address of the packet and the content of the forward table 33. B. If the output port determined in A is a specific output port for Internet connection, the packet is passed to the packet buffer management unit 4, and the port number of the loopback output port is passed as information indicating the output destination of the packet. . C. If the output port determined in A is not a specific output port for Internet connection, the packet is passed to the packet buffer management unit 4, and the port number of the output port determined in A is set as the information indicating the output destination of the packet. hand over.

The second processing means 32 processes the loopback input buffer 12-j as a processing target and performs the following processes D and E.

D. Loopback input buffer 12-j
The packet stored in is extracted and encapsulation processing is performed. E. The packet that has undergone the encapsulation process is passed to the packet buffer management unit 4, and the port number of the specific output port for internet connection is passed as information indicating the output port of the packet.

The recording medium K1 provided in the packet conversion processing unit 3 is a disk, a semiconductor memory, or another recording medium, and a program for causing the network processor to function as the packet conversion processing unit 3 is recorded therein. This program is read by the network processing processor, and its operation is controlled, so that the first and second processing means 3 are executed on the network processing processor.
1 and 32 are realized.

The buffer memory 5 is divided into a plurality of partial areas, and each partial area stores a packet and the port number of the output port of its output destination. The packet buffer management unit 4 stores the pair of the packet and the port number passed from the packet conversion processing unit 3 in the partial area next to the partial area in which the previous pair is stored, and the storage order is oldest first. Then, the pair of packet and port number is read out, and the packet is output to the output port of the port number via the packet conversion processing unit 3 → LAN line processing unit 1. That is, the packet buffer management unit 4 and the buffer memory 5 operate as a queue.

[0023]

[Description of Operation of the Embodiment] Next, the operation of the present embodiment will be described in detail.

Now, for example, as shown in FIG. 2, it is assumed that the received packet 7 is input to the input / output port 11-2 and accumulated in the input buffer 12-2. In FIG. 2, the same symbols as those in FIG. 1 represent the same parts. In addition, the received packet 7 has a destination address (D
A), source address (SA), type (TYPE), I
P header (IP Header), information (Infoma)
section) is included. In addition, the IP header includes the existence time (TTL) and the checksum (CS).

The first processing means 31 in the packet conversion processing section 3 sequentially processes input buffers other than the loopback input buffer 12-j. Now, for example, assuming that the input buffer 12-2 is the processing target, since the received packet 7 is accumulated in the input buffer 12-2, the processing shown in the flowchart of FIG. 4 is performed.

First, the first processing means 31 extracts the destination address (DA) from the received packet 7 (step A1). Next, the output port of the output destination of the received packet 7 is determined based on the destination address (DA) and the contents of the forward table 33 (step A2).

After that, the existence time (TTL) is decremented by 1, and the checksum (CS) is recalculated (step A).
3, A4). Next, it is determined whether or not the output port obtained in step A2 is a specific output port for internet connection (nth output port) (step A).
5).

If it is determined that the received packet 7 is the specific output port, that is, if the received packet 7 is to be sent to the Internet 6 (YES in step A5), the packet buffer management unit 4 loops the received packet 7 and the loop. A pair with the port number (denoted as #j) of the back output port is passed (step A6). As a result, the packet buffer management unit 4 stores the pair of the received packet 7 and the port number #j in the storage target area of the buffer memory 5. After that, the packet buffer management unit 4 sets the buffer memory 5
The pair of the received packet 7 and the port number #j is read from and the received packet 7 is transferred to the packet conversion processing unit 3 →
The data is output to the loopback output port with the port number #j via the LAN line processing unit 1. The received packet 7 output from the loopback output port is stored in the loopback input buffer 12-j via the loopback circuit 2 → loopback input port.

On the other hand, when it is determined that the received packet is not the specific output port, that is, when the received packet 7 is to be sent to another LAN (NO in step A5), the packet buffer management unit 4 receives the received packet. 7 and step A2
The pair with the port number (denoted as #x) of the output port determined in step S7 is passed (step A7). As a result, the packet buffer management unit 4 stores the pair of the received packet 7 and the port number #x in the storage target area of the buffer memory 5. After that, the packet buffer management unit 4 reads the pair of the received packet 7 and the port number #x from the buffer memory 5, and transfers the received packet 7 to the port via the packet conversion processing unit 3 → LAN line processing unit 1. Output to the output port of number #x.

On the other hand, the second processing means 32 processes only the loopback input buffer 12-j,
Received packet 7 in loopback input buffer 12-j
When is stored, the processing shown in the flowchart of FIG. 5 is performed.

First, an additional IP header is created (step B1). Then, as shown in FIG.
A transmission packet 8 is created by adding an additional IP header to (step B2). After that, a pair of the transmission packet 8 and the port number (defined as #n) of the specific output port is passed to the packet buffer management unit 4 (step B).
3). As a result, the packet buffer management unit 4 stores the pair of the transmission packet 8 and the port number #n in the storage target area of the buffer memory 5. After that, the packet buffer management unit 4 reads the pair of the transmission packet 8 and the port number #n from the buffer memory 5, and sends the transmission packet 8 to the port via the packet conversion processing unit 3 → LAN line processing unit 1. Output to the specific output port of number #n.

In the above-described embodiment, the relay process performed by the network relay device is divided into two partial processes, but it may be divided into three or more partial processes. In that case, it is necessary to provide a processing means and a loopback circuit according to the number of divisions. For example, if the relay process is divided into m first to m-th partial processes,
~ M processing means for executing the mth partial processing, (m-1) loopback circuits for looping back the processing results of the first to (m-1) processing means, and the first to the first (M-
It is necessary to provide (m-1) input buffers corresponding to the loopback circuit of 1).

[0033]

Another Embodiment of the Invention FIG. 6 is a block diagram of another embodiment of the present invention, which is different from the embodiment shown in FIG. The part 3a is provided, and the loopback circuit 2k is connected to the input / output port 11-k (loopback input / output port 11-k).

The packet conversion processing unit 3a executes relay processing including encapsulation processing and filter processing, and is realized by, for example, a network processing processor.

The difference between the packet conversion processing unit 3a and the packet conversion processing unit 3 shown in FIG.
The second processing means 32a is provided instead of the above, the recording medium K1a is provided instead of the recording medium K1, and the third processing means 34 is added.

The second processing means 32a has substantially the same function as the second processing means 32 shown in FIG. 1, but outputs the packet which has undergone the encapsulation processing to a specific output port for internet connection. Instead, the difference is that the data is output to the loopback output port to which the loopback circuit 2k is connected.

The third processing means 34 filters the packets accumulated in the loopback input buffer 12-k as a processing target.

The recording medium k1a is a disk, a semiconductor memory, or another recording medium, and stores a program for causing the network processing processor to function as the packet conversion processing unit 3a. This program is read by the network processing processor, and by controlling its operation,
The first, second, and third processing means 31, 32a, 34 are realized.

Next, the operation of this embodiment will be described.

When the packet P input from the input / output port 11-1 is accumulated in the input buffer 12-1, the first processing means 31 carries out the processing shown in the flow chart of FIG. Now, for example, if the output port corresponding to the destination of the packet P is a specific output port for Internet connection (YES in step A5), the packet P
Are stored in the loopback input buffer 12-j via the loopback circuit 2.

After that, the second processing means 32a sets the packet P stored in the loopback input buffer 12-j as the processing target, and then the step B1 in the flowchart of FIG.
The processing shown in B2 is performed. After that, the second processing means 32a
Instead of performing the processing of step B3, performs processing for outputting the packet P that has undergone the encapsulation processing to the loopback output port to which the loopback circuit 2k is connected. As a result, the packet P is stored in the loopback input buffer 12-k.

After that, the third processing means 34 performs the processing shown in the flowchart of FIG. 7 with the packet P stored in the loopback input buffer 12-k as the processing target.

At the first step C1, the source address (SA) is extracted from the packet P. Next step C2
Then, based on the source address (SA) and the address designated by the administrator, it is determined whether or not the source of the packet P is permitted to use the Internet 6.

When it is determined that the use of the Internet 6 is prohibited, the packet P is discarded (YES in step C2, step C3). On the contrary,
When it is determined that the use of the Internet is permitted, the pair of the packet P and the port number #n of the specific output port for Internet connection is passed to the packet buffer management unit 4 (NO in step C2, step C4). . As a result, the packet buffer management unit 4 stores the pair of the packet P and the port number #n in the storage target area of the buffer memory 5. After that, the packet buffer management unit 4
Is the packet P and the port number #n from the buffer memory 5.
And a packet number of the packet P via the packet conversion processing unit 3a → LAN line processing unit 1
It outputs to the specific output port of n.

[0045]

As described above, according to the present invention, since the partial processing is sequentially performed on the packet received through the input port, the processing time of the entire relay processing is longer than the packet arrival interval. Even if it is long, the processing time of each partial processing can be made shorter than the packet arrival interval,
As a result, packet loss can be prevented. In addition, the operation clock of the network relay device can be kept low compared to the case where the relay process is not divided into a plurality of partial processes, so that the network relay device can be configured using low-speed and inexpensive parts, Power can be kept low.

[Brief description of drawings]

FIG. 1 is a block diagram of an embodiment of the present invention.

FIG. 2 is a diagram for explaining the operation of the embodiment of the present invention.

FIG. 3 is a diagram showing a configuration example of a reception packet 7 and a transmission packet 8.

FIG. 4 is a flow chart showing a processing example of a first processing means 31.

FIG. 5 is a flowchart showing a processing example of a second processing means 32.

FIG. 6 is a block diagram of another embodiment of the present invention.

7 is a flowchart showing a processing example of a third processing means 34. FIG.

[Explanation of symbols]

1 ... LAN line processing unit 11-1 to 11-n ... I / O port 12-1 to 12-n ... Input buffer 2, 2k ... Loopback circuit 3, 3a ... Packet conversion processing unit 31 ... First processing means 32 ... Second processing means 33 ... Forward table 34 ... Third processing means K1, K1a ... recording medium 4 ... Packet buffer management unit 5 ... Buffer memory 6 ... Internet 7 ... Received packet 8 ... Transmission packet DA ... destination address SA ... Source address TYPE ... kind IP Header ... IP header Information ... Information TTL ... Presence time CS ... Checksum

Claims (13)

[Claims] 1. A plurality of input ports and a plurality of output ports are provided, wherein a relay process including a conversion process is executed on a packet received through the input port, and the packet for which the relay process is completed is sent to its destination. A network relay device for outputting to a corresponding output port, wherein when the relay process is divided into a plurality of partial processes and the plurality of partial processes are sequentially performed on the received packet, 1
After the end of one partial processing, the processing result is looped back to the input port assigned to the next partial processing of the plurality of input ports, and the processing result looped back to the next partial processing. A network relay device comprising means for performing processing using. 2. An output port comprising a plurality of input ports, an input buffer for each of the plurality of input ports, and a plurality of output ports, the output port corresponding to a destination of a packet accumulated in the input buffer via the input port. Is a specific output port of the plurality of output ports, a network relay that executes a relay process including a conversion process on the accumulated packet and outputs the packet for which the relay process is completed to the specific output port In the device, when the output port corresponding to the destination of the packet stored in the input buffer is the specific output port, a part of the relay process is performed on the stored packet Then, the packet that has been partially processed is treated as a loopback output port and a loopback input port among the plurality of input ports and output ports. Is stored in the loopback input buffer corresponding to the loopback input port by performing loopback using, and the remaining processing of the relay processing is performed on the packet stored in the loopback input buffer. A network relay device comprising means for executing and executing a packet for which the remaining processing is completed, to output to the specific output port. 3. The network relay device according to claim 2, wherein the loopback input port is connected to a loopback output port of the plurality of output ports, and the input buffer is provided. When the output port corresponding to the destination of the packet extracted from is the specific output port, a part of the relay process is performed on the extracted packet, and the part of the process is completed. Is stored in the loopback input buffer by outputting to the loopback output port, and the remaining processing of the relay processing is executed on the packet stored in the loopback input buffer, A network comprising: a packet conversion processing unit for outputting the packet for which the remaining processing is completed to the specific output port. Splicing device. 4. The network relay device according to claim 3, wherein the specific output port is an output port connected to the Internet, and the loopback output port is an output port connected to the loopback circuit. And a remaining output port is an output port connected to a different LAN, respectively. 5. The network relay device according to claim 4, wherein the conversion process is an encapsulation process. 6. A plurality of input ports and a plurality of output ports are provided, relay processing including conversion processing is executed on a packet received via the input port, and the packet for which the relay processing is completed is sent to its destination. A network relay method for outputting to a corresponding output port in a network relay device, wherein the relay process is divided into a plurality of partial processes, and the plurality of partial processes are sequentially performed on the received packet. After the end of the two partial processing,
A loopback is performed to an input port of the plurality of input ports allocated for the next partial process, and the next partial process is performed using the looped-back processing result. Network relay method. 7. A network relay method in a network relay device comprising a plurality of input ports, an input buffer for each of the plurality of input ports, and a plurality of output ports, wherein the network relay method comprises: When the output port corresponding to the destination of the packet accumulated in the input buffer is a specific output port of the plurality of output ports, a part of the relay process including the conversion process for the accumulated packet Is performed and the packet for which a part of the processing is completed is looped back by using the loopback output port and the loopback input port of the plurality of input ports and output ports. The data is accumulated in the loopback input buffer corresponding to the input port, and the packet is accumulated in the loopback input buffer. A network relay method, characterized in that the remaining processing of the relay processing is executed and the packet for which the remaining processing is completed is output to the specific output port. 8. The network relay method according to claim 7, wherein the specific output port is an output port connected to the Internet, and the specific output port and the output port other than the loopback output port are different from each other. A network relay method, which is an output port connected to a LAN. 9. The network relay method according to claim 8, wherein the conversion process is an encapsulation process. 10. A program for causing a computer having a plurality of input ports and a plurality of output ports to function as a network relay device, wherein the computer divides the relay process into a plurality of partial processes. When the plurality of partial processes are sequentially performed on the received packet, 1
After the end of one partial processing, the processing result is looped back to the input port assigned to the next partial processing of the plurality of input ports, and the processing result looped back to the next partial processing. A program that functions as a means for performing processing using. 11. A program for causing a computer having a plurality of input ports, an input buffer for each of the plurality of input ports, and a plurality of output ports to function as a network relay device, the computer comprising: If the output port corresponding to the destination of the packet accumulated in the input buffer via the input port is a specific output port of the plurality of output ports, the relay including conversion processing for the accumulated packet Part of the processing is executed, and the packet for which the part of the processing is completed is looped back using the loopback output port and the loopback input port of the plurality of input ports and output ports. By accumulating in the loopback input buffer corresponding to the loopback input port,
A program for causing a packet stored in the loopback input buffer to perform the remaining processing of the relay processing and outputting the packet for which the remaining processing is completed to the specific output port. . 12. The program according to claim 11, wherein the specific output port is an output port connected to the Internet, and the specific output port and the output port other than the loopback output port are different LANs. A program that is an output port to be connected. 13. The program according to claim 12, wherein the conversion process is an encapsulation process.