KR20020091203A - Programmable layer 3 address self-learning scheme in a network switch - Google Patents

Abstract

The packet identifier module is configured to determine whether a received data packet has occurred at the router. If the packet identifier module identifies that the received data packet was received at a network node other than the router, the switch module selectively stores the layer 2 address and associated layer 3 address of the data packet as an associated layer two-layer three address pair in the address table. do. Selective storage of an association layer two-layer three address is also referred to as learning the Internet Protocol (IP) -Media Access Control Association (MAC) of the data packet. By selectively learning the IP-MAC association of selected data packets from non-router ports, the possibility of overflow of the address table is reduced. In addition, by using the learned IP-MAC association, the network switch can switch layer 3 data packets to bypass the router and reduce latency.

Description

PROGRAMMABLE LAYER 3 ADDRESS SELF-LEARNING SCHEME IN A NETWORK SWITCH}

Local area networks use network cables or other media to link stations on the network. Each local area network architecture uses a medium access control (MAC) that allows the network interface devices of each network node to access the network medium.

The Ethernet protocol IEEE 802.3 has been developed to specify half-duplex and full-duplex media access mechanisms for data packet transmission. Bidirectional media access mechanisms provide two-way, point-to-point communication links between two network elements, for example, between network nodes and switch hubs.

In switch local area networks, there is an increasing demand for high speed connectivity, more flexible switching performance, and the ability to accommodate complex network architectures. For example, US Pat. No. 5,953,335 discloses a network switch configured to switch Layer 2 Type Ethernet (IEEE 802.3) data packets between different network nodes. The received data packet may comprise a VLAN (virtual LAN) tag frame in accordance with the IEEE 802.1q protocol specifying another subnetwork (via a router) or a defined group of stations. Since switching occurs at the layer 2 level, it is necessary for the router to transmit data packets between subnetworks.

Efforts to improve the switching performance of network switches, including layer 3 (eg, Internet protocol) processing, typically require CPU based control of the network address table for layer 3 address learning. For example, a router may perform layer two-layer three association based on a defined address resolution protocol. Currently, Layer 2 switches are configured to operate in non-blocking mode (data packets can be output from the network switch at the same rate as the receive rate) so that the router is a bottleneck for the LAN. Thus, the use of a switch with Layer 2-Layer 3 switching capability can offload the router and reduce latency. In addition, conventional learning techniques in layer 2 switches that learn the media access control (MAC) addresses of all received data packets are not practical in layer 3 switches because layer 3 learning quickly overwhelms the address table in the network switch.

The present invention is directed to learning the network address of a data packet in a nonblocking network switch configured to switch data packets between subnetworks and routers.

Reference is made to the accompanying drawings. Like reference numerals denote like elements throughout the drawings.

1 is a block diagram of a packet switch network including multiple network switches for switching data packets between sub-networks according to an embodiment of the invention.

2 is a block diagram illustrating a network switch of FIG. 1 according to an embodiment of the present invention.

3 is a flowchart illustrating learning in the network switch of FIG. 1 according to an embodiment of the present invention.

4 is another flow chart illustrating learning in the network switch of FIG. 1 in accordance with an embodiment of the present invention.

FIG. 5 is another flowchart illustrating learning in the network switch of FIG. 1 according to an embodiment of the present invention.

What is needed is a device that allows a network switch to provide auto-learning of network addresses for layer 2 and layer 3 switching for 100 Mbps and gigabit links without blocking of data packets.

There is also a need for an apparatus that allows non-blocking network switches to selectively learn the layer 2 addresses and associated layer 3 addresses of incoming data packets at wire speed without overwhelming the network switch address table.

These and other needs can be obtained by the present invention. In the present invention, a network switch for switching data packets includes a plurality of ports for transmitting and receiving a plurality of data packets. Incoming data packets are evaluated by the packet identifier module to determine whether received data packets are received from a router connected to the network switch. When a received data packet is received from a network node other than a router, the switch module selectively stores the layer 2 source address and associated layer 3 source address of the received data packet as an associated layer two-layer three address pair in the address table. Thus, the possibility of overflow in the address table is reduced because the address table contains very few entries.

The present invention provides a method of switching data packets at a network switch port. The method includes receiving a data packet by one port of a network switch and determining whether the port has received the data packet from a router. The method also based on the determination that the port received the data packet from a network node other than the router, the layer 2 address and layer 3 address from the data packet as an associated layer two-layer three address pair as an address table. And optionally storing at. Thus, the address table contains few entries, thus reducing the possibility of overflow in the address table.

The present invention provides a network switch for switching data packets received at a network switch port. The network switch includes a plurality of ports for transmitting and receiving a plurality of data packets (one port of the plurality of ports is connected to a router), a packet identifier module, and a switch module.

The packet identifier module is configured to determine whether a received data packet is received from a router. The switch module is configured to selectively store layer 2 addresses and layer 3 addresses from the data packets as associated layer two-layer three address pairs in an address table based on received data packets being received from network nodes other than the router. It is composed.

Additional advantages and novel features of the invention will be set forth in the description which follows, and will be apparent to those skilled in the art from the following review and may be learned from the practice of the invention. The advantages of the present invention can be obtained by means and combinations particularly pointed out in the claims.

1 is a block diagram illustrating a packet switch network 10, such as an Ethernet (IEEE 802.3) network. The packet switch network includes an integrated (ie, single chip) multiport switch 12 that enables data packet communication between the network stations 14. Each network station 14, for example a client workstation, is configured to transmit and receive data packets at 10 Mbps or 100 Mbps according to the IEEE 802.3 protocol. Each of the integrated multiport switches 12 are interconnected by a gigabit Ethernet link 16 to enable data packet transmission between subnetwork (subnet) 18a, 18b, 18c. Thus, each subnetwork includes a switch 12 and network stations 14.

Each switch 12 includes a switch port 20. The switch port 20 includes a media access control (MAC) module 22 and a port filter 24 (also called a packet identifier module). The MAC module 22 sends and receives data packets to and from associated network stations 14 via a 10/100 Mbps Physical Layer (PHY) transceiver (not shown) in accordance with the IEEE 802.3u protocol. Each switch 12 also includes a switch module 25 configured to determine frame delivery for received data packets. In particular, the switch module 25 is configured to make layer 2 switching decisions based on source MAC address, destination MAC address, VLAN information in the Ethernet (IEEE 802.3) header. The switch module 25 is also configured to make selective layer 3 switching decisions based on the evaluation of the IP data portion in the Ethernet packet.

As shown in FIG. 1, each switch 12 has an associated host CPU 26 and buffer memory 28 (eg, SSRAM). The host CPU 26 controls the overall operation of the switch 12 including programming of the switch module 25. The buffer memory 28 is used by the switch to store the data frame while the switch module 25 processes the forwarding decision for the received data packet.

Each switch 12 also includes a memory 30, which is configured to restrictively store an Internet Protocol (IP) -Media Access Control (MAC) association of data packets as an address table.

As noted above, the switch module 25 is configured to perform layer 2 switch determination and selective layer 3 switching determination. The use of a layer 3 switching decision is particularly effective if the station 14 of the subnetwork 18a wants to send an email to selected network stations of the subnetwork 18b, 18c. Since the subnetwork 18b 18c is on a different subnet, the host of the subnetwork 18a does not know the layer 2 address for the host on the subnetwork 18b, 18c. The switch module 25 of the switch 12a needs to send an e-mail message to the router 19, which incurs an additional delay. The use of layer 3 switching decisions by the switch module 25 allows the switch module 25 to manage the packets, including improved forwarding decisions, and route them to higher priority packets for latency sensitive applications such as video or voice. You can decide whether it should be considered. Since the router is typically a bottleneck for the LAN, the switch module 25 offloads the router and also improves round trip delay.

According to the disclosed embodiment, the network switch 12 is configured to learn the IP-MAC association of the selected data packet. Each packet identifier module 24 of the network switch is configured to determine whether a received data packet is received from the router 19. If the packet identifier module 24 identifies the received data packet as being received from a network node other than the router 19, the switch module 25 of the network switch 12 optionally selects the layer 2 source address and associated layer of the data packet. The three source addresses are stored in the address table as associative layer two-layer three address pairs. Selective storage of associative layer two-layer three addresses is also referred to as IP-MAC association learning of data packets. By selectively learning the IP-MAC association of selected data packets from non-router ports, the possibility of overflow of the address table is reduced. In addition, using the learned IP-MAC association, the network switch performs layer 3 switching to enable bypass of routers between connected subnetworks and reduce latency.

FIG. 2 shows a detailed block diagram of the port filter 24 shown in FIG. Port filter 24 includes receive first in, first out (FIFO) buffer 51, MAC queuing logic 52, memory 53, MAC dequeuing logic 54, transmit FIFP buffer 55 and processor interface module 57. It includes.

Receive FIFO 51 is a buffer configured to temporarily store the incoming data packet in response to receiving the incoming data packet from the receive portion of port 20.

MAC queuing logic 52 provides various functions to port filter 24. MAC queuing logic 52 is provided for writing received data packets to SSRAM 28 via data bus 59 from receive FIFO 51 to external memory interface 56. The MAC queuing logic 52 also provides a plurality of status signals 58 to the switch module 25 in response to the MAC queuing logic that processes the received data packets. The status signal 58 provides the switch module 25 with an indication that the received data packet has been transmitted to the external memory interface 56 without error or that the transmission of the received data packet is complete. The status signal 58 also includes a subnetwork routing signal RNETS_ENABLE and a learning signal L3IRC_LEARN.

When the MAC queuing logic 52 sets the RNETS_ENABLE signal, the switch module 25 is informed that the received data packet is part of mutual network traffic between subnetworks directly connected to the network switch 12a.

When the MAC queuing logic 52 sets up the L3IRC_LEARN signal, the switch module 25 learns the IP-MAC address association for the received data packet.

Memory 53 provides register space 53a for MAC queuing logic 52 parameters to perform learning and subnetwork routing functions. Register space 53a provides at least one SUBNET_ID and SUBNET_MASK register for MAC queuing logic. The CPU 26 programs the registers through the processor interface (pi_mod) 57. The SUBNET_ID register is provided to store the IP address to which each port belongs. Each port on switch 12a has one SUBNET_ID register. SUBNET_MASK is provided to store the 32-bit IP address mask of each port. Each port on switch 12a has one SUBNET_MASK mask register.

MAC dequeuing logic 54 is provided to retrieve the received data packet from SSRAM 28 and forward the data packet to the appropriate port in response to processing by the switch module 25.

Transmit FIFO 55 provides a buffer for outgoing data packets before transmission by port 20.

Incoming data packets are received at port 20 and buffered at receive FIFO 51. MAC queuing logic 52 delivers the data packet to external memory interface 56 for storage in SSRAM 28 over data bus 59. Using layer 3 information. The MAC queuing logic 52 determines whether the received data packet is part of mutual subnetwork traffic by comparing the destination IP address in the IP header with the value stored in the register of the memory 53.

In particular, if a received data packet is received from a non-router port, the IP destination address is masked for SUBNET_MASK of all other ports. The result of the next mask operation is compared against the SUBNET_ID register on all other ports. If the result of the compare operation is successful, the MAC queuing logic 52 sets the RNENTS_ENABLE signal to the switch module 25.

The MAC queuing logic 52 also allows the switch module 25 to learn the source IP-MAC address association of the received data packet to the IP address of the subnetwork that is directly connected to the network switch 12a if the packet arrived from the non-router port. It may be configured to determine whether there is a need to do. The host CPU 26 programs the registers of the memory 53 so that the switch module 25 knows which port is connected to the router.

The MAC queuing logic 52 may also be configured to learn the IP-MAC association if the MAC queuing logic 52 of the port identifier module 24 determines that the received data packet is for a router and is part of a mutual subnetwork traffic.

The MAC queuing logic 52 of the packet identifier module 24 may also be configured to learn the IP-MAC association of the received data packet if the received data packet is for a router and is part of a mutual subnetwork traffic.

In particular, MAC queuing logic 52 compares the MAC destination address of the received data packet with the MAC address of the router stored in memory 53. If the result of the compare operation is successful, the received data packet is for a router. The MAC queuing logic 52 of the port identifier module 24 then optionally stores the layer 2 source address and associated layer 3 address in the address table 30 as an associated layer two-layer three address pair in the switch module 25. Tell them to.

The MAC queuing logic 52 of the packet identifier module 24 may be configured to perform any of these functions depending on the traffic flow at the network switch 12 or the user's preference. MAC queuing logic 52 may be configured to execute various other functions required by the user.

FIG. 3 is a flowchart of the learning executed by the packet identifier module 24 shown in FIG. In step 310, a data packet is received at the port identifier module 24 from any of the ports 20.

The port identifier module 24 is configured at step 320 to determine whether a received data packet is being received from a non-router port. The host CPU programs which port is connected to the router.

If the received data packet is being received on the non-router port in step 320, then in step 330, the MAC queuing logic 52 of the port identifier module 24 asserts the learning signal to layer 2 address. Or inform the switch module 25 to store the MAC address and associated layer 3 address or IP address as an associated layer two-layer 3 address in an address table of memory 30.

If a received data packet is being received from the router port in step 320, then in step 340, the MAC queuing logic 52 of the port identifier module 24 deasserts the learning signal to the switch module 25. )do. The IP-MAC association of the received data packet is not learned.

4 is another flowchart of the learning executed by the packet identifier module 24 shown in FIG. Here, the IP-MAC association is learned when the received data packet is received from the non-router port and has the destination MAC address of the router. At step 410, a data packet is received at the port identifier module 24 from any of the ports 20.

The port identifier module 24 is configured at step 410 to determine whether a received data packet is being received from a non-router port and whether the MAC destination address of the data packet is a router. The host CPU programs which port is to be connected to the router, and the MAC queuing logic 52 compares the router's MAC address with the destination MAC address of the received data packet.

If the comparison from step 420 is successful, then in step 430 the received data packet is being received on the non-router port and the destination MAC address is a router. In step 430, the MAC queuing logic 52 of the port identifier module 24 stores the layer 2 source address or MAC source address and the associated layer 3 source address or IP source address as the associated layer two-layer three address. Is notified to the switch module 25 to store in the address table.

If the comparison fails in step 420, the port identifier module 24 may not notify the switch module 25 in step 440. The IP-MAC association of the received data packet is not learned.

FIG. 5 is another flowchart of the learning executed by the packet identifier module 24 shown in FIG. Here, the IP-MAC association is learned when the received data packet is part of the mutual subnetwork traffic and the destination MAC address is a router. At step 510, a data packet is received at the port identifier module 24 from any of the ports 20.

The port identifier module 24 is configured at step 510 to determine if a received data packet is being received from the non-router port. MAC queuing logic 52 masks the destination IP address with every other SUBNET_MASK in switch module 25. The masked result is then compared with all other SUBNET_IDs at switch 12a. The MAC queuing logic 52 also compares the destination MAC address of the received data packet with the router's MAC address.

If all comparisons are successful at step 520, then at step 530 the MAC queuing logic 52 of the port identifier module 24 associates the layer 2 source address or MAC source address and the associated layer 3 source address or IP source address. The switch module 25 is informed to store in the address table of the memory 30 as the layer two-layer three address.

If the comparison fails in step 520, the MAC queuing logic 52 of the port identifier module 24 may not notify the switch module 25 in step 540. The IP-MAC association of the received data packet is not learned.

According to the disclosed embodiment, the packet identifier module is configured to determine whether a received data packet originated from a router. If the packet identifier module identifies that the received data packet was received from a network node other than the router, the switch module optionally stores the layer 2 address and associated layer 3 address of the data packet as an associated layer two-layer three address pair in an address table. do. By storing the IP-MAC association of the selected data packet, the network switch can reduce the search time in the address table when the switch references the address table when switching. Thus, the packet identifier module allows the network switch to provide Layer 3 and Layer 2 switching capabilities for 100 Mbps or Gigabit links without blocking of data packets.

The present invention has been described in terms of the most preferred embodiments, but is not limited thereto and includes various modifications and equivalents included within the spirit and scope of the claims.

Claims (14)

Receiving a data packet by one port of the network switch, Determining whether the port has received the data packet from a router; Selectively storing layer 2 addresses and layer 3 addresses from the data packets as associated layer two-layer three address pairs in an address table based on a determination that the port has received the data packet from a network node other than the router. And at the network switch. 2. The method of claim 1, wherein the selectively storing step is based on a determination that the port has received the data packet from a network node other than a router and in response to determining that a destination layer 2 address in the data packet specifies a router. Storing a layer 2 address and an associated layer 3 address as an associative layer two-layer three address pair. 3. The method of claim 2, wherein the layer 2 address and associated layer 3 address are source addresses. The method of claim 1, wherein the network switch comprises a second port and a third port connected to each of the first subnetwork and the second subnetwork. 5. The method of claim 4, further comprising determining whether the data packet includes address information specifying data packet transmission between the second port and the third port. 6. The method of claim 5, wherein the selectively storing step is based on a determination that the port has received the data packet from a network node other than a router and the data packet is configured to transfer data packets between the second port and the third port. Storing a layer 2 address and an associated layer 3 address as said associative layer two-layer three address pair in response to including address information specifying. 3. The method of claim 2, further comprising determining, by the port identifier module of the network switch, that the data packet includes address information specifying a data packet transmission between a second port and a third port. And a third port connected to the first and second sub-networks, respectively. A plurality of ports for transmitting and receiving a plurality of data packets, one port of the plurality of ports being connected to a router; A packet identifier module configured to determine whether a received data packet is received from a router; A switch module configured to selectively store layer 2 addresses and layer 3 addresses from the data packets as associated layer two-layer three address pairs in an address table based on received data packets being received from a network node other than the router. Network switch comprising a. 9. The apparatus of claim 8, wherein the packet identifier module is configured to determine whether the received data packet includes address information specifying a destination address of the router, and wherein the switch module is configured to receive data packet being received from a network node. And selectively store layer 2 addresses and layer 3 addresses from the data packet as associative layer two-layer three address pairs in response to address information based on the address information including the destination address of the router. 9. The network switch of claim 8, wherein the layer 2 address and the associated layer 3 address are source addresses. 9. The method of claim 8, wherein the second port of the plurality of ports is connected to a first subnetwork, the third port of the plurality of ports is connected to a second subnetwork, and the packet identifier module is configured to receive the received data packet. And determine whether the address information specifying the transmission of the received data packet between the first sub-network and the second sub-network is included. 12. The apparatus of claim 11, wherein the switch module is configured to receive the data packet in response to address information that is based on a received data packet being received from a network node and specifies the transmission of the received data packet between the first and second sub-networks. Selectively store layer 2 and layer 3 addresses of the network as associated layer two-layer three address pairs. 9. The apparatus of claim 8, further comprising a second port of the plurality of ports connected to a first subnetwork, and a third port of the plurality of ports connected to a second subnetwork, wherein the packet identifier module further comprises the received data packet. And determining whether or not to include address information specifying the transmission of the received data packet between the first and second sub-networks. 9. The network switch of claim 8, wherein each port of the plurality of ports is configured to include the packet identifier module.