WO2014101708A1

WO2014101708A1 - Data transmission method and network node in layer 2 network

Info

Publication number: WO2014101708A1
Application number: PCT/CN2013/089936
Authority: WO
Inventors: 喻敬海; 付振涛; 韩辉
Original assignee: 中兴通讯股份有限公司
Priority date: 2012-12-26
Filing date: 2013-12-19
Publication date: 2014-07-03
Also published as: CN103905325A; CN103905325B

Abstract

Embodiments of the present invention relate to a data transmission method and a network node in a layer 2 network. The method comprises: configuring, according to a network architecture, a balance group for a network node on the basis of a principle for avoiding a broadcast storm, one balance group comprising one or more interfaces; the network node receiving a packet from a receiving interface; and the network node forwarding the packet to an interface excluding the balance group the receiving interface is located.

Description

Layer 2 network data transmission method and network node

Technical field

The present invention relates to network communication technologies, and more particularly to a layer 2 network data transmission method and network node.

Background technique

With the increasing use of Internet applications, data center applications are becoming more widespread. In the relevant standards organizations, various technical standards related to data centers are also actively promoted. In order to enable more convenient virtual machine dynamic migration in the data center network, the data center network is required to become a basic requirement for building a data center.

In a Layer 2 network, in order to improve the reliability and robustness of the network connection, redundancy is usually present on the group network, so that when a failure occurs, traffic can be switched to the backup link. However, the existence of redundant links leads to natural loops in the network, which leads to broadcast storms in the network, causing traffic congestion and other problems. STP (Spanning Tree Protocol) and its subsequent improvement protocol can avoid loops by changing the port state of device nodes between network nodes. At the same time, when the link fails, data is changed by changing the state of the device port. Forwarding is forwarded through other reachable links to ensure the continuation of network data transmission. However, STP and its subsequent improved protocols have their Achilles heel in data center applications, that is, bandwidth utilization is seriously insufficient, and a large number of links cannot be used because the ports are blocked by the protocol. To this end, the industry has proposed several related technologies to implement a large Layer 2 network without STP. The current discussion is more about IRF (Intelligent Resilient Framework), VSS (Virtual Switching System), VPC (Virtual Port-Channel), TRILL (Transparent Interconnection of Lots of Links) technology, and SPB (Shortest Path Bridging) technology.

IRF technology, VSS and VPC technologies are all stacking technology implementations. IRF technology is a virtualization technology applied to low-end switch devices. It can virtualize multiple low-end switch devices (member devices) into a high-end switch device (virtual device). At the same time, the physical ports of each member device are bundled together, used as a logical port, used in configuration and networking. It is similar to a single physical device, which enables cross-device link aggregation, which also avoids the occurrence of loops and increases the robustness of the link. From the networking diagram of the data center, the network structure after IRF aggregation is equivalent to a tree structure, and the conditions for loop occurrence no longer exist. The IRF technology needs to enable the IRF control protocol on the virtual member devices and exchange protocol packets between the virtual member devices.

Both TRILL and SPB technologies are technologies that implement multipathing in data forwarding. TRILL technology is a "Ethernet frame multi-path forwarding" technical solution proposed by the IETF. The proposed technology subverts the traditional Ethernet frame forwarding mode. Because multipath technology has always been a technology that is only available in Layer 3 IP. TRILL applies this technology to Layer 2 switch devices. The switch that can implement this function is called the "Routing Bridge" (RBridge). Link state control protocol (TRILL (Transparent Interconnection of Lots of Links) IS) between RBridge and the IS-IS (Intermediate System to Intermediate System Routing Protocol) routing protocol -IS implements the calculation of the shortest path and equivalent multipath between each other. TRILL IS-IS only calculates the topology between RBridges, and does not care about the topology between the two hosts on the network. When forwarding the Ethernet frame, the Ingress RBridge adds the encapsulation source RBridge identifier and the destination RBridge identifier to the Ethernet frame, and encapsulates the outer VLAN identifier and the outer hop RBridge identifier, so that the hop is forwarded to the hop by hop. Egress RBridge (Egress RBridge) node, Egress RBridge strips the TRILL header, restores the traditional Ethernet frame, and performs traditional Ethernet frame forwarding. By constructing a data center network using a switch device having such technical characteristics, a large Layer 2 network without loops without STP is realized. However, implementing a large Layer 2 network through this technology requires that the switch equipment used must be able to support this technology, and the original switch cannot be supported by a simple software upgrade. Summary of the invention

The embodiments of the present invention provide a Layer 2 network data transmission method and a network node, so as to solve the problem that a broadcast storm is likely to occur in a Layer 2 network.

The embodiment of the invention provides a method for data transmission of a layer 2 network, including:

Configuring an equalization group for the network node according to the network architecture to avoid broadcast storms, and one equalization group includes one or more interfaces; The network node receives the message from the receiving interface;

The network node forwards the packet to an interface other than the equalization group where the receiving interface is located.

An embodiment of the present invention provides a network node, where the network node includes:

Several interfaces;

a balancing group configuration unit configured to configure a balancing group for the network node according to a network architecture to avoid a broadcast storm, and one equalization group includes one or more interfaces;

The packet forwarding control module is configured to forward the packet to the interface other than the equalization group where the receiving interface is located when receiving the packet from the receiving interface.

The method and the network node in the embodiment of the present invention configure the equalization group for the network node according to the network architecture in advance to avoid the broadcast storm. When the packet is forwarded, all the other groups except the equalization group where the receiving interface is located according to the preset equalization group are performed. The interface can forward the packet to avoid broadcast storms. The solution of the embodiment of the present invention only needs to be set, and the requirements on the node device are low and easy to implement. In addition, when the MAC (Media Access Control) address learning and updating is required, the interface of the same equalization group implements the sharing of MAC address learning according to the equalization policy, thereby improving the performance of the system. BRIEF abstract

1 is a schematic diagram of Embodiment 1 of a Layer 2 network data transmission method according to the present invention;

2 is a schematic diagram of an equalization group configuration according to an embodiment of the present invention;

3 is a schematic diagram of Embodiment 2 of a Layer 2 network data transmission method according to the present invention;

4 is a schematic diagram of performing MAC processing according to an embodiment of the present invention;

FIG. 5 is a schematic diagram of a specific process for performing MAC learning;

6-8 are schematic structural diagrams of modules of an embodiment of a network node according to an embodiment of the present invention;

9-11 are schematic diagrams of an application example of the present invention; wherein FIG. 9 is a schematic diagram of forwarding and MAC learning in a standard fat tree structure according to an embodiment of the present invention; FIG. 10 is a forwarding and MAC of a non-standard fat tree structure according to an embodiment of the present invention; FIG. 11 is a schematic diagram of forwarding and MAC learning in a multicast case according to an embodiment of the present invention. Preferred embodiment of the invention

The technical solutions of the embodiments of the present invention are described in detail below with reference to the accompanying drawings and specific embodiments, so that those skilled in the art can understand the embodiments of the present invention and can be implemented, but the embodiments are not Limited. It should be noted that the embodiments in the present application and the features in the embodiments may be combined with each other without conflict.

Example 1

Embodiment 1 of the Layer 2 network data transmission method of the present invention, as shown in FIG. 1, the method includes: Step 101: Configure a balance group for a network node according to a network architecture to avoid a broadcast storm, and one equalization group includes one or more interfaces. ;

The network node in the embodiment of the present invention may be a network access device and an aggregation device or a network core device. To better describe the content of the embodiment of the present invention, the following concept definition is introduced:

Uplink interface: In the data center network structure, the interface that interacts with the upper-layer network node is the uplink interface of the layer network node.

Downlink interface: In the data center network structure, the interface that interacts with the lower layer network node is the downlink interface of the layer network node.

In the embodiment of the present invention, the interfaces in the equalization group are all uplink interfaces used for interaction with the upper layer network device or downlink interfaces used for interaction with the lower layer network node.

Equilibrium group: It can also be called an interface group or a port group to avoid the broadcast storm. The same type of interface (the uplink interface or the downlink interface or a part of the uplink interface or the downlink interface) is bundled together to prevent the intra-group interface from being received. The traffic is forwarded to other interfaces in the group. At the same time, MAC address learning is shared or traffic is shared, and traffic protection is performed. Similar to link bundling, but no protocol negotiation is required, and it exists locally and does not need to have the same equalization group as the peer.

Traffic balancing is performed by learning the peer MAC evenly on the ports of the equalization group. When the packets are forwarded from the equalization group to the outside, the traffic is naturally checked and the service MAC is basically balanced.

For a network node in a certain Ethernet multi-link environment, its interface is either an uplink interface or a downlink interface, the uplink interface is represented by UP, and the downlink interface is represented by DP; On the uplink or downlink interface, you can configure an equalization group as required. As shown in FIG. 2, the equalization group includes all the uplink interfaces or all the downlink interfaces. In the actual networking, the equalization group may include only a part of the uplink interfaces or only a part of the downlink interfaces. If the network node is a network access device and an aggregation device, the uplink interface can be configured as an equalization group. If the network node is a network core device, the interface is balanced according to the topology of the aggregation device connected to the network core device. group.

Step 102: The network node receives the packet from the receiving interface.

The packet in the embodiment of the present invention is mainly a packet that needs to be flooded, such as a broadcast packet, a protocol packet, or an unknown broadcast packet. For unicast packets, you need to look up the forwarding table and forward it to the corresponding port. It will not forward to all ports.

Step 103: The network node forwards the packet to an interface other than the equalization group where the receiving interface is located.

In the first embodiment, the packets received by the interface of the same equalization group are not forwarded to other interfaces in the equalization group where the receiving interface is located. If an equalization group includes all the uplink interfaces, the broadcast received from the uplink interface is Multicast or unknown unicast packets are no longer forwarded to another upstream interface. The network node is configured with an equalization group based on the network architecture to prevent the broadcast storm. In the case of packet forwarding, packets are forwarded according to the preset equalization group to all interfaces except the equalization group where the receiving interface is located. The solution is generated, that is, the broadcast storm is avoided. The solution of the embodiment of the present invention only needs to be set, and the requirements for the node device are low, and are easy to implement.

Example 2

Embodiment 2 of the Layer 2 network data transmission method of the present invention, as shown in FIG. 3, the method includes: Step 301: Configure a balance group for a network node according to a network architecture to avoid a broadcast storm, and one equalization group includes one or more interfaces. ;

The interfaces in the equalization group are all uplink interfaces for interacting with upper network nodes or downlink interfaces for interacting with lower layer network nodes.

Step 302: The network node receives the packet from the receiving interface.

Step 303: The network node according to the MAC in the message (Media Access Control, media access) Ask control) information for MAC processing;

Specifically, as shown in FIG. 4, the MAC processing includes:

Step 401: The network node queries a local MAC address table according to the MAC information carried in the packet.

Step 402: If no matching address entry is found, the network node performs MAC address learning;

The step of learning the MAC address includes: determining whether the equalization group in which the receiving interface is located has other interfaces;

If there is no other interface, the receiving interface performs MAC address learning;

If there are other interfaces, the interface in the equalization group in which the receiving interface is located is selected according to the load balancing policy to perform the MAC address learning.

Step 403: If a matching address entry is found, the network node determines whether the MAC address update condition is met.

The conditions for the MAC address update include:

Condition A: The interface in the matched address entry is in the same equalization group as the receiving interface; Condition B: the interface in the matched address entry is in a different equalization group than the receiving interface and is not the same type of interface; Or

Condition C: The interface in the matched address entry is in a different equalization group than the receiving interface, but belongs to the same type of interface, and the network node supports virtual machine migration.

Step 404: When it is determined that the MAC address update condition is met, the network node performs MAC address update.

When the MAC address update condition A is satisfied, the network node selects an interface in the equalization group in which the receiving interface is located to perform MAC address update according to the load balancing policy; and when the MAC address update condition B and C is satisfied, the receiving interface of the network node The MAC address is updated (that is, the MAC address learned after the interface that receives the packet takes effect, and the MAC address learned by the original interface is deleted).

Step 304: The network node forwards the packet to other interfaces except the equalization group where the receiving interface is located. In the above Embodiment 2, the interface of the network node and the configured equalization group comply with the following rules:

A. The packets received by the same interface are not forwarded to other interfaces in the equalization group. If an equalization group includes all uplink interfaces, the broadcast/multicast or unknown received from the uplink interface. A unicast packet is no longer forwarded to another upstream interface.

B. If the MAC address learned by the interface of the same type as the interface that receives the packet is available, and the network node does not support VM migration, the interface of the interface packet does not learn MAC address.

C. If the MAC address learned by the same balanced group interface as the interface that receives the packet is already available, you can learn the appropriate interface (such as the interface with less load) according to the balancing policy.

E. The MAC address learned by the interface of different types is valid. The MAC address learned after the interface that receives the packet takes effect, and the MAC address learned by the original interface is deleted.

The network node is configured with an equalization group based on the network architecture to prevent the broadcast storm. In the case of packet forwarding, packets are forwarded according to the preset equalization group to all interfaces except the equalization group where the receiving interface is located. The solution is generated, that is, the broadcast storm is avoided. The solution of the embodiment of the present invention only needs to be set, and the requirements for the node device are low, and are easy to implement. In addition, when MAC address learning and update are required, the interface of the same equalization group implements the sharing of MAC address learning according to the equalization policy, which improves the performance of the system.

In the above embodiments 1 and 2, if an interface fails (for example, a broken link), the MAC table of the interface can be transferred to another interface of the same equalization group as the faulty interface.

According to the solution of the embodiment of the present invention, when a network node receives an Ethernet packet, performs MAC lookup and MAC learning according to MAC (Media Access Control) information carried in the packet;

The node first searches whether the local MAC table has the MAC information according to the MAC information of the packet, and finds whether there is another interface in the equalization group, and finds whether the interface has learned the MAC information in the equalization group;

If there is no other interface in the EQ group, the interface that receives the packet performs MAC learning or update according to the MAC learning rule. If there are other interfaces in the EQ group, MAC learning or processing is performed according to the EQ group configuration policy. In addition, the MAC learned by different types of interfaces takes effect after the MAC learned, and the learned MAC of the original interface is deleted.

The specific process of MAC learning in the network node is shown in Figure 5. This process is a concrete embodiment of the above rules. The steps are as follows:

Step 501: The network node receives the Ethernet packet.

Step 502: The node analyzes the received packet, obtains its MAC address, and receives interface information of the packet.

Step 503: The node queries the MAC table information of the local node.

Step 504: Determine, according to the result of the queried MAC table information, whether there is an address entry of the MAC in the corresponding packet; if not, continue processing; otherwise, go to step 508;

Step 505: The MAC address table of the node does not have an address entry corresponding to the MAC, and analyzes whether the interface that receives the packet has another interface. If not, step 506 is performed; otherwise, go to step 507;

Step 506: The MAC address carried in the interface learning packet of the received packet of the node is added to the MAC address entry, and the process ends.

Step 507: Select, according to the load balancing policy, the MAC address carried in the learning packet of the interface in the equalization group where the receiving interface is located; the learning completion process ends;

Step 508: Analyze whether the interface information of the existing MAC address entry and the interface of the received message are in the same equalization group; if they are the same, go to step 509; otherwise, go to step 511; Step 509: Determine whether the two interfaces are The interface of the same type, if it is not the same type of interface, go to step 511, otherwise, go to step 510;

Step 510: Determine whether the network node supports the virtual machine migration technology. If yes, go to step 511. Otherwise, the new interface does not learn because the MAC address already exists on the original interface, and the process ends.

Step 511: Select an interface in the equalization group in which the receiving interface is located to update related information in the MAC address table according to the load balancing policy. In order to implement the foregoing method, the embodiment of the present invention further provides a network node. As shown in FIG. 6, the network node includes:

Several interfaces;

The equalization group configuration unit 11 is configured to configure an equalization group for the network node according to the network architecture to avoid the broadcast storm, and one equalization group includes one or more interfaces;

The interfaces in the equalization group are both uplink interfaces for interacting with upper layer network devices or downlink interfaces for interacting with lower layer network devices.

The packet forwarding control module 12 is configured to forward the packet to the interface other than the equalization group of the receiving interface when receiving the packet from the receiving interface.

Corresponding to Embodiment 2, as shown in FIG. 7, the network node further includes:

The MAC address query unit 13 is configured to query the local MAC address table according to the MAC information carried in the packet.

The MAC address management unit 14 is configured to control the corresponding interface to perform MAC address learning when the matching address entry is not found, and control the corresponding interface to perform MAC address update when determining that the MAC address update condition is met;

The MAC address update determining unit 15 is configured to determine whether the MAC address update condition is met when the matching address entry is found.

Optionally, as shown in FIG. 8, the network node further includes an equalization group policy control unit 16 configured to control, according to the load balancing policy, an interface in the equalization group according to the equalization group configured by the equalization group configuration unit 11 The MAC address management unit 14 determines whether the equalization group in which the receiving interface is located has other interfaces, and if there is no other interface, controls the receiving interface to perform MAC address learning; otherwise, controls the equalization group policy control unit 16 to select The interface performs MAC address learning, so that MAC address learning is performed on different interfaces to implement traffic sharing, and the traffic of each interface is relatively balanced.

As described above, the conditions for the MAC address update include:

Condition A: The interface in the matched address entry is in the same equalization group as the receiving interface; Condition B: the interface in the matched address entry is in a different equalization group than the receiving interface and is not the same type of interface; Or Condition c, the interface in the matched address entry is in a different equalization group from the receiving interface, but belongs to the same type of interface, and the network node is migrated by the virtual machine.

Specifically, when the MAC address update condition A is satisfied, the MAC address management management unit controls the interface in the equalization group where the receiving interface selected by the equalization group policy control unit 16 to perform MAC address update; and satisfies the MAC address update condition. B and C, the MAC address management management unit 14 controls the receiving interface to perform MAC address update.

As shown in FIG. 8, the network node further includes an equalization group fault processing unit 17 configured to detect an interface in the equalization group according to the equalization group configured by the equalization group configuration unit 11, and when the interface in the equalization group fails. The MAC address management unit 14 is notified to transfer the MAC address table of the faulty interface to other interfaces of the equalization group in which the receiving interface is located. If the traffic in the equalization group shows a significant difference in traffic, it is processed by the equalization group policy control unit 16.

Compared with the related art, the embodiment of the present invention introduces an uplink interface, a downlink interface, and an equalization group, so that the network node completes the optimization learning of the MAC and the forwarding of the packet, thereby ensuring high-speed and efficient packet processing. On the other hand, the embodiment of the present invention does not need to uniformly run the control protocol and the interaction control packet on the network switching device, retains the Layer 2 feature, reduces the complexity of the configuration, improves the robustness of the system, and improves the system design. flexibility. The method of the embodiment of the present invention will be described below in conjunction with an application example. Application example 1

FIG. 9 shows an application example 1 , which mainly illustrates a detailed process of packet forwarding and MAC learning in a standard fat tree structure according to an embodiment of the present invention;

As shown in FIG. 9, this is a process diagram of forwarding and MAC learning in a standard fat tree (Fat-Tree) structure according to an embodiment of the present invention. The MAC learning process is as follows:

Step 901: The acl node receives the ARP request packet sent by the directly connected server, and the interface that receives the packet is D-P1 (the first interface in the downlink interface, the following is the same type);

Step 902: The acl node analyzes the source MAC address and the destination MAC address carried in the received packet, and the interface number D-P1 of the received packet. Step 903: The acl node learns the source MAC information and the information of the interface D-P1, and writes the MAC table. In the application example, the D-P1 interface learns the MAC address.

Step 904: The acl node has no other interface in the equalization group where the D-P1 interface is located, and the acl node forwards the ARP request packet to all other interfaces (U-P1 and U-P2).

Step 905: The agl node and the ag2 node respectively receive the packet from the acl node through the interface D-P1;

Step 906: The agl node analyzes the source MAC information and the destination MAC information carried in the received message, and the interface number D-P1 of the received message;

Step 907: The agl node learns the source MAC information and the information of the interface D-P1, and writes the information to the MAC table. In the application example, the D-P1 interface learns the MAC address.

Step 908: The ag2 node learns the MAC address carried by the ARP packet on its D-P1 interface according to the same procedure.

Step 909: Because the EQ group where the D-P1 interface is located has no other interfaces, the agl node forwards the packet to all other interfaces (D-P2, U-P1, and U-P2). The cl, c2, and ac2 nodes receive the forwarded ARP request.

Step 910: After receiving the ARP request, the ac2 node analyzes the MAC information and the interface information of the received packet.

Step 911: The U-P1 interface on the ac2 node is an uplink interface. The MAC learning process is performed according to the network node learning MAC process. In this application example, the U-P1 interface learns.

Step 912: Since U-P2 and U-P1 belong to the same equalization group, the ac2 node is no longer forwarded to other uplink interfaces U-P2.

Understandably, if the ac2 node has a downlink interface, it also needs to forward the "^ text" to the downlink interface.

Step 913: After the D-P1 interface of the cl-node receives the ARP request packet, the learning process is similar to the acl and _ag l nodes, and the learning process is similar to the acl and _ag l nodes. Step 914: Repeat the foregoing steps. The ARP request packet arrives at the destination server B, and each network node completes the learning of the MAC of the source server A. The destination server B responds to the request of the A, thereby forming a Layer 2 forwarding path between the ABs. Application example 2

FIG. 10 shows an application example 2, which mainly illustrates a detailed process of performing packet forwarding and MAC learning under the non-standard fat tree structure in the embodiment of the present invention;

As shown in FIG. 10, this is a process diagram of forwarding and MAC learning in a non-standard fat tree structure according to an embodiment of the present invention. The MAC learning process is as follows:

Step 1001: The AC1 node receives the free ARP packet sent by the virtual machine VM1 in the directly connected server, and the interface that receives the packet is D-P1.

Step 1002: The AC1 node analyzes the source MAC address carried by the received packet, and the interface number D-P1 of the received packet.

Step 1003: The AC1 node learns the source MAC information and the information of the interface D-P1, and writes the information to the MAC table. In the application example, the D-P1 interface learns the MAC address.

Step 1004: The AC1 node has no other interface in the EQ group where the D-P1 interface is located. The AC1 node forwards the gratuitous ARP packet to all other interfaces (U-P1, U-P2, and U-P3).

Step 1005: The AGG1 node, the AGG2 node, and the AGG3 node respectively receive the packet from the AC1 node through the interface D-P1.

Step 1006: The AGG1 node analyzes and obtains the source MAC information carried in the received packet, and the interface number D-P1 of the received packet.

Step 1007: The AGG1 node learns the source MAC information and the information of the interface D-P1, and writes the information to the MAC table. In the application example, the D-P1 interface learns the MAC address.

Step 1008: The AGG2 node and the AGG3 node learn the MAC address on the D-P1 interface according to the same procedure;

Step 1009: Because the equalization group in which the D-P1 interface of the AGG1 node is located has no other interfaces, the AGG1 node forwards all interfaces except the D-P1 interface (D-P2, D-P3, U-P1, and U-P2). The message. The Cl, C2, AC2, and AC3 nodes receive the free ARP packets forwarded.

Step 1010: After receiving the gratuitous ARP packet, the AC2 node analyzes the MAC information and the interface information of the received packet. Step 1011: The AC2 node performs MAC learning processing according to the MAC address learning process of the network node. In this application example, the U-P2 on the AC2 node learns the MAC address, and the U-P1 interface does not learn the MAC address.

Step 1012: U-P2 and U-P3 are in the same equalization group, and U-P2 and U-P3 on the uplink interface do not participate in forwarding.

Step 1013: After receiving the gratuitous ARP packet, the D-P1 interface on the C1 node has an equalization group configured on the interface. The ARP address carried in the learning packet of the interface in the equalization group is learned by the D-P1 in this embodiment.

Step 1014: The C1 node forwards the ARP packet to all interfaces except the equalization group where the interface that receives the ARP packet is located, because the C1 node is configured with multiple different equalization groups. In this application example, you need to forward to the U-P4, U-P5, and U-P6 interfaces.

Step 1015: The AGG4, AGG5, and AGG6 nodes receive the free forwarding by the C1 node.

ARP packet, and analyzes the information carried in the packet and the information about the receiving interface; processing according to the foregoing steps and forwarding in sequence;

Step 1016: The free ARP is forwarded to all the network nodes of the entire network, and each network node completes learning the MAC of the virtual machine VM1 on the source server, so that each node has the MAC address of forwarding the MAC address of the destination MAC to VM1. Publish the item.

Application example 3

FIG. 11 is a flowchart showing an application process example 3, which mainly illustrates a detailed process of packet forwarding and MAC learning in the case of a multicast service according to an embodiment of the present invention;

As shown in FIG. 11, this is a process diagram of a tree forwarding and MAC learning process in a multicast case according to an embodiment of the present invention. A router node is a router that controls network multicast, and the MAC learning process is as follows:

Step 1101: The router sends a multicast query message to all interfaces of the router; the packet type is a broadcast packet.

Step 1102: After receiving the multicast query message, the cl, c2, c3, and c4 network nodes learn the MAC according to the foregoing MAC learning process; the following process uses the cl network node as an example for description; Step 1103: The interface for receiving the multicast query message is U-P1, and the equalization group where the U-P1 interface is located has no other interface, and the cl will forward the multicast query message to all interfaces except the U-P1 interface. Forward

Step 1104: The agl, ag3, and ag5 network nodes receive the multicast query message forwarded by the cl node. The agl network node is used as an example for description.

Step 1105: The interface of the agl network node to obtain the received multicast query message and receive the message is U-P1;

Step 1106: The agl network node performs MAC learning processing according to the network node MAC learning process. In this embodiment, the U-P1 interface learns; and forwards to all interfaces except the equalization group where the U-P1 is located;

Step 1107: The acl and ac2 network nodes receive the packet forwarded by the agl network node; and the acl network node is used as an example for description;

Step 1108: The acl network node learns that the MAC and forwarding process is similar to agl, and the process class synchronization step 1105-step 1106 is not described;

Step 1109: Server A receives the multicast query message from the acl network node, and server A responds to the multicast query message; thus, a multicast branch path is formed; the formation process of other multicast branch paths is the same as this. No longer described;

Step 1110: When all servers respond, the multicast path is formed.

Compared with the related art, the method and the network node in the embodiment of the present invention configure an equalization group for the network node according to the network architecture in advance to avoid the broadcast storm. When the packet is forwarded, the preset equalization group is located to the receiving interface. All the other interfaces except the equalization group can forward the packets to avoid broadcast storms. The solution of the embodiment of the present invention only needs to be set, and the requirements for the node devices are low and easy to implement. In addition, when MAC address learning and updating are required, the interface of the same equalization group implements the sharing of MAC address learning according to the equalization policy, which improves the performance of the system.

One of ordinary skill in the art will appreciate that all or a portion of the above steps may be performed by a program to instruct the associated hardware, such as a read only memory, a magnetic disk, or an optical disk. Alternatively, all or part of the steps of the above embodiments may also be implemented using one or more integrated circuits. Correspondingly, each module/unit in the above embodiment can be used The form of hardware implementation can also be implemented in the form of software function modules. The invention is not limited to any specific form of combination of hardware and software.

The modules in the system/device/device described in the embodiments of the present invention are only an example according to their functions. It is understood that, in the case that the system/device/device implements the same function, those skilled in the art may One or more other functional division modes are given, and any one or more of the functional modules may be implemented by one functional entity device or unit in a specific application, and undeniably, the above transformation manners are all within the protection scope of the present application. Inside.

It is apparent that the described embodiments are only a part of the embodiments of the invention, and not all of them. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present invention without creative efforts are within the scope of the present invention.

Industrial applicability

The method and the network node in the embodiment of the present invention configure the equalization group for the network node according to the network architecture in advance to avoid the broadcast storm. When the packet is forwarded, all the other groups except the equalization group where the receiving interface is located according to the preset equalization group are performed. The interface can forward the packet to avoid broadcast storms. The solution of the embodiment of the present invention only needs to be set, and the requirements on the node device are low and easy to implement. In addition, when MAC address learning and update are required, the interface of the same equalization group implements the sharing of MAC address learning according to the equalization policy, which improves the performance of the system.

Claims

claims

1. A layer 2 network data transmission method, including:

Configure a balancing group for network nodes based on the network architecture to avoid broadcast storms. A balancing group includes one or more interfaces;

The network node receives the text from the receiving interface; and

The network node forwards the message to an interface outside the balancing group where the receiving interface is located.

2. The method of claim 1, wherein: the interfaces in the balancing group are all uplink interfaces used to interact with upper-layer network equipment or are all downlink interfaces used to interact with lower-layer network equipment.

3. The method of claim 1, wherein: after the network node receives the message, the method further includes:

The network node queries the local MAC address table according to the media access control MAC information carried in the message;

If no matching address entry is found, the network node performs MAC address learning; if a matching address entry is found, the network node determines whether the MAC address update condition is met; and

When it is determined that the MAC address update conditions are met, the network node updates the MAC address.

4. The method of claim 3, wherein: the network node performs MAC address learning, including: determining whether the balancing group where the receiving interface is located has other interfaces;

If there are no other interfaces, the receiving interface performs MAC address learning; and

If there are other interfaces, the interface in the balancing group where the receiving interface is located is selected according to the load balancing policy to perform the MAC address learning.

5. The method of claim 4, wherein: the conditions for updating the MAC address include: the interface in the matching address entry is in the same balancing group as the receiving interface;

The interface in the matching address entry and the receiving interface are in different balancing groups and are not interfaces of the same type; or The interface in the matching address table entry and the receiving interface are in different balancing groups, but belong to the same type of interface, and the network node supports virtual machine migration.

6. The method of claim 5, wherein,

When the interface in the matching address entry that meets the MAC address update condition is in the same balancing group as the receiving interface, the network node selects the interface in the balancing group where the receiving interface is located to perform MAC address update according to the load balancing policy. ; as well as

The MAC address update condition is that the interface in the matching address entry and the receiving interface are in different balancing groups and are not interfaces of the same type; or the interface in the matching address entry and the receiving interface are in different balancing groups , but belong to the same type of interface, and the network node supports virtual machine migration, the receiving interface of the network node performs MAC address update.

7. The method of claim 1, wherein: when an interface of a network node fails, the network node transfers the MAC address table of the failed interface to the interface of the balancing group where the failed interface is located according to the load balancing policy.

8. A network node, including:

several interfaces;

A balancing group configuration unit, which is configured to configure a balancing group for network nodes based on the principle of network architecture to avoid broadcast storms, and a balancing group includes one or more interfaces; and

The message forwarding control module, when receiving a message from a receiving interface, is configured to forward the message to an interface outside the balancing group where the receiving interface is located.

9. The network node according to claim 8, wherein: the interfaces in the balancing group are all uplink interfaces used to interact with upper-layer network equipment or are all downlink interfaces used to interact with lower-layer network equipment.

10. The network node according to claim 8, wherein: the network node further includes: a medium access control MAC address query unit, which is configured to query the local MAC address table according to the MAC information carried in the message;

A MAC address management unit, which is configured to control the corresponding interface to perform MAC address learning when no matching address entry is found, and to control the corresponding interface to perform MAC address updating when it is determined that the MAC address update conditions are met; and The MAC address update judgment unit is configured to judge whether the MAC address update condition is met when a matching address entry is found.

11. The network node according to claim 10, wherein: the network node further includes a balancing group policy control unit configured to balance interfaces in the balancing group based on a load balancing policy according to the balancing group configured by the balancing group configuration unit. For control, the MAC address management unit determines whether there are other interfaces in the balancing group where the receiving interface is located. If there are no other interfaces, control the receiving interface to perform MAC address learning; if there are other interfaces, control the balancing The interface selected by the Group Policy Control Unit performs MAC address learning.

12. The network node according to claim 11, wherein: the conditions for updating the MAC address include:

The interface in the matching address entry is in the same balancing group as the receiving interface;

The interface in the matching address entry and the receiving interface are in different balancing groups and are not interfaces of the same type; or

The interface in the matching address table entry and the receiving interface are in different balancing groups, but belong to the same type of interface, and the network node supports virtual machine migration.

13. The network node as claimed in claim 12, wherein,

When the interface in the matching address entry that meets the MAC address update condition is located in the same balancing group as the receiving interface, the MAC address management unit controls the balancing group where the receiving interface is located selected by the balancing group policy control unit. The interfaces in the group perform MAC address update; and the interface in the matching address entry that meets the MAC address update condition and the receiving interface are in different balancing groups and are not interfaces of the same type; or the interface in the matching address entry When the receiving interface is in a different balancing group but belongs to the same type of interface, and the network node supports virtual machine migration, the MAC address management unit controls the receiving interface to perform MAC address update.

14. The network node according to claim 8, wherein: the network node further includes a balancing group fault processing unit configured to detect interfaces in the balancing group according to the balancing group configured by the balancing group configuration unit, and in balancing When an interface in the group fails, the MAC address management unit is notified to transfer the MAC address table of the failed interface to other interfaces in the balancing group where the receiving interface is located.