CN111654437A - Data center-based packet forwarding method and device - Google Patents

Abstract

The invention discloses a message forwarding method and device based on a data center. The method includes: determining a first shared risk link group to which a receiving interface of a message belongs; searching a route forwarding table for the destination IP of the message The first routing forwarding table entry corresponding to the address; if the first routing forwarding table entry is found in the routing forwarding table, the first shared risk link group is searched in the first routing forwarding table entry The corresponding first set equal-cost multi-path group; if the first set equal-cost multi-path group is found in the first routing forwarding entry, then according to the first set equal-cost multi-path group forwarding the packet; if the first set equal-cost multi-path group is not found in the routing and forwarding entry, then according to the first original equal-cost multi-path group in the first routing and forwarding entry forward the message. This solution can avoid the occurrence of Layer 3 loops, which can also avoid packet loss and ensure normal forwarding of service packets.

Description

Data center-based packet forwarding method and device

technical field

The present invention relates to the technical field of communications, and in particular, to a data center-based packet forwarding method and device.

Background technique

In the data center shown in Figure 1, the MAN switches will advertise default routes to the core switches, aggregation switches, and access switches for access to the external network and across data centers, and the access switches to the aggregation switches and access switches. The core switch advertises the host route of the downlink host, which is used to access the downlink host of the access switch. Suppose that the link between aggregation switch 1 and access switch 1 is faulty, and aggregation switch 1 preferentially deletes the host route from access switch 1. At this time, packets from external access switches to hosts connected to access switch 1 are sent from core switch 1. , the core switch 2 forwards the packet to the aggregation switch 1 and the aggregation switch 2. The aggregation switch 1 will match the default route according to the longest matching principle, and forward the packet to the core switch 1 and core switch 2; The packet is forwarded to aggregation switch 1 and aggregation switch 2, which will cause a brief Layer 3 loop between core switch 1, core switch 2, and aggregation switch 1, until aggregation switch 1 sends core switch 1 and core switch 1 to core switch 1. 2 Announce the deletion of the host route from access switch 1; when core switch 1 and core switch 2 delete the next hop of the host route with aggregation switch 1 as access switch 1, only aggregation switch 2 is retained as access switch 1 Only after the next hop of the host route is the next hop, the packet will be forwarded to the aggregation switch 2, and the Layer 3 loop will be eliminated.

In the above packet forwarding method, a Layer 3 loop will occur, and this short-term Layer 3 loop will cause some packets to be lost to the host connected to the access switch 1; and will cause core switch 1, core switch 2 and The link between aggregation switches 1 is congested, which affects the normal forwarding of other service packets.

SUMMARY OF THE INVENTION

Embodiments of the present invention provide a data center-based packet forwarding method and device, which are used to solve the problem of a three-layer loop existing in the prior art.

According to an embodiment of the present invention, a data center-based packet forwarding method is provided, which is applied to a core switch included in the data center, including:

determining a first shared risk link group to which the receiving interface of the message belongs, where the first shared risk link group includes each interface connected between the switch connected to the receiving interface and the core switch;

Find the first routing and forwarding table entry corresponding to the destination Internet Protocol IP address of the packet in the routing and forwarding table;

If the first routing and forwarding table entry is found in the routing and forwarding table, the first set equal-cost multi-path corresponding to the first shared risk link group is searched in the first routing and forwarding table entry Group;

If the first set equal-cost multi-path group is found in the first route forwarding entry, the packet is forwarded according to the first set equal-cost multi-path group; If the first set equal-cost multi-path group is not found in the entry, the packet is forwarded according to the first original equal-cost multi-path group in the first routing forwarding entry; wherein the first The interfaces included in the equal-cost multi-path group are set to be the interfaces included in the first original equal-cost multi-path group except the interfaces included in the first shared risk link group.

Optionally, also include:

Setting the interface connected to the switch with the same networking role among all the interfaces of the core switch as a load sharing interface group;

The interfaces connected to the same switch among all the interfaces of the core switch are set as a shared risk link group.

Optionally, also include:

After learning the second routing and forwarding entry, determine whether each interface included in the second original equal-cost multi-path group in the second routing and forwarding entry belongs to the same load sharing interface group;

If it is determined that each interface included in the second original equal-cost multi-path group belongs to the same load sharing interface group, then determine the shared risk link risk group to which each interface included in the second original E-C multi-path group belongs;

A set equal-cost multi-path group corresponding to each of the determined shared risk link groups is added to the second routing and forwarding entry, wherein the interface included in each added set-equal-cost multi-path group is the The interfaces included in the second original equal-cost multi-path group are excluding the interfaces included in the corresponding shared risk link group.

Optionally, also include:

If the first routing and forwarding table entry is not found in the routing and forwarding table, the packet is discarded.

According to an embodiment of the present invention, a data center-based packet forwarding device is also provided, which is applied to a core switch included in the data center, including:

A first determining module, configured to determine a first shared risk link group to which the receiving interface of the packet belongs, where the first shared risk link group includes each of the switches connected to the receiving interface and the core switch. interface;

a first lookup module, configured to look up the first routing and forwarding table entry corresponding to the destination IP address of the message in the routing and forwarding table;

A second search module, configured to search for the first route and forwarding entry corresponding to the first shared risk link group in the first route and forwarding entry if the first route and forwarding entry is found in the route and forwarding table. 1. Setting up an equal-cost multipath group;

a forwarding module, configured to forward the packet according to the first set equal-cost multi-path group if the first set equal-cost multi-path group is found in the first routing forwarding entry; if If the first set equal-cost multi-path group is not found in the routing and forwarding entry, the packet is forwarded according to the first original equal-cost multi-path group in the first routing and forwarding entry; wherein , the interfaces included in the first set equal-cost multi-path group are the interfaces included in the first original equal-cost multi-path group except the interfaces included in the first shared risk link group.

Optionally, also includes a settings module for:

Setting the interface connected to the switch with the same networking role among all the interfaces of the core switch as a load sharing interface group;

The interfaces connected to the same switch among all the interfaces of the core switch are set as a shared risk link group.

Optionally, it also includes a second determining module for:

After learning the second routing and forwarding entry, determine whether each interface included in the second original equal-cost multi-path group in the second routing and forwarding entry belongs to the same load sharing interface group;

If it is determined that each interface included in the second original equal-cost multi-path group belongs to the same load sharing interface group, then determine the shared risk link risk group to which each interface included in the second original E-C multi-path group belongs;

A set equal-cost multi-path group corresponding to each of the determined shared risk link groups is added to the second routing and forwarding entry, wherein the interface included in each added set-equal-cost multi-path group is the The interfaces included in the second original equal-cost multi-path group are excluding the interfaces included in the corresponding shared risk link group.

Optionally, a discard module is also included to:

If the first routing and forwarding table entry is not found in the routing and forwarding table, the packet is discarded.

According to an embodiment of the present invention, an electronic device is also provided, the electronic device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

memory for storing computer programs;

The processor is configured to implement the above method steps when executing the program stored in the memory.

According to an embodiment of the present invention, a computer-readable storage medium is further provided, where a computer program is stored in the computer-readable storage medium, and the computer program implements the above method steps when executed by a processor.

The beneficial effects of the present invention are as follows:

Embodiments of the present invention provide a data center-based packet forwarding method and device, by determining a first shared risk link group to which a receiving interface of a packet belongs, where the first shared risk link group includes the receiving interface connection Each interface connected between the switch and the core switch; find the first routing forwarding table entry corresponding to the destination Internet Protocol IP address of the message in the routing forwarding table; the first routing and forwarding table entry, look up the first set equal-cost multi-path group corresponding to the first shared risk link group in the first routing and forwarding table entry; if in the first routing and forwarding table If the first set equal-cost multi-path group is found in the routing entry, the packet is forwarded according to the first set equal-cost multi-path group; if the first set equal-cost multi-path group is not found in the routing forwarding entry Once an equal-cost multi-path group is set, the packet is forwarded according to the first original equal-cost multi-path group in the first routing forwarding entry; wherein the first set equal-cost multi-path group includes The interface is the interface included in the first original equal-cost multi-path group except the interface included in the first shared risk link group. In this solution, after receiving the message, the core switch searches the first routing and forwarding entry for the first set equal-cost multipath group corresponding to the first shared risk link group to which the receiving interface of the message belongs. The packets are forwarded through the first set equal-cost path group, because the interfaces included in the first set equal-cost multi-path group are the interfaces included in the first original equal-cost multi-path group, except those included in the first shared risk link group The interface other than the interface, and the interface of the first shared risk link group is connected to the same device. Therefore, the packet will not be forwarded through the interface included in the first shared risk link group to which the receiving interface of the packet belongs. It can also ensure that the packet will not be forwarded to the switch that sent the packet; if it is not found, it means that the interfaces included in the first original equal-cost multipath group do not include the interfaces included in the first shared risk link group. , the packet can be forwarded according to the first original equal-cost multi-path group in the first routing forwarding entry, which ensures that the packet will not be forwarded to the switch that sent the packet. Setting an equal-cost multipath group can ensure that the packet will not be returned to the sending switch, thereby avoiding the occurrence of Layer 3 loops, and thus avoiding packet loss and ensuring normal forwarding of service packets.

Description of drawings

1 is an architecture diagram of a data center in the prior art;

2 is a flowchart of a data center-based packet forwarding method in an embodiment of the present invention;

3 is a schematic structural diagram of a data center-based message forwarding device in an embodiment of the present invention;

FIG. 4 is a schematic structural diagram of an electronic device shown in this application.

Detailed ways

Aiming at the problem of Layer 3 loops in the prior art, an embodiment of the present invention provides a data center-based packet forwarding method, which is applied to a core switch included in the data center. The flow of the method is shown in FIG. 2 . The execution steps are as follows:

S21: Determine the first shared risk link group to which the receiving interface of the packet belongs.

The first shared risk link group includes each interface connected between the switch receiving the interface connection and the core switch, that is to say, the interfaces connected to the same switch can be set as a shared risk link group.

S22: Find the first routing forwarding entry corresponding to the destination Internet Protocol (Internet Protocol, IP) address of the message in the routing forwarding table, and if the first routing forwarding entry is found in the routing forwarding table, perform S23; If the first routing and forwarding table entry is not found in the routing and forwarding table, S26 is executed.

S23: Search the first routing and forwarding entry for the first set equal-cost multi-path group corresponding to the first shared risk link group, if the first set equal-cost multi-path group is found in the first routing and forwarding entry , then execute S24; if the first set equal-cost multi-path group is not found in the routing forwarding entry, execute S25.

If the first routing and forwarding entry is found in the routing and forwarding table, the packet can be processed according to the first routing and forwarding entry. Specifically, the first routing and forwarding entry can be searched for the corresponding A set equal-cost multi-path group, the set-equal-cost multi-path group can be defined as the first set equal-cost multi-path group.

S24: Forward the packet according to the first set equal-cost multi-path group.

S25: Forward the packet according to the first original equal-cost multi-path group in the first route forwarding entry.

The interfaces included in the first set equal-cost multi-path group are the interfaces included in the first original equal-cost multi-path group except the interfaces included in the first shared risk link group.

S26: Discard the packet.

If the destination IP address of the packet is not found in the routing and forwarding table, the packet cannot be forwarded and can be discarded directly.

In this solution, after receiving the message, the core switch searches the first routing and forwarding entry for the first set equal-cost multipath group corresponding to the first shared risk link group to which the receiving interface of the message belongs. The packets are forwarded through the first set equal-cost path group, because the interfaces included in the first set equal-cost multi-path group are the interfaces included in the first original equal-cost multi-path group, except those included in the first shared risk link group The interface other than the interface, and the interface of the first shared risk link group is connected to the same device. Therefore, the packet will not be forwarded through the interface included in the first shared risk link group to which the receiving interface of the packet belongs. It can also ensure that the packet will not be forwarded to the switch that sends the packet; if it is not found, it means that the interfaces included in the first original equal-cost multipath group do not include the interfaces included in the first shared risk link group, then The packet can be forwarded according to the first original equal-cost multi-path group in the first routing and forwarding entry, which ensures that the packet will not be forwarded to the switch that sends the packet. It can be seen that no matter whether the first setting is found or not Equal-cost multipath groups can ensure that the packet will not be returned to the sending switch, thereby avoiding the occurrence of Layer 3 loops, and thus avoiding packet loss and ensuring normal forwarding of service packets.

Optionally, the above method further includes:

Set the interfaces connected to the switches with the same networking role among all the interfaces of the core switch as a load balancing interface group;

Set all interfaces of the core switch that are connected to the same switch as a shared risk link group.

As shown in Figure 1, for core switch 1 and core switch 2, the interface connected to the MAN switch can be set as a load sharing group, and the networking roles of aggregation switch 1 and aggregation switch 2 in the data center are both aggregation switch, so you can set the interface connected to aggregation switch 1 and aggregation switch 2 as another load balancing group, and then set the interface connected to aggregation switch 1 as a shared risk link group, and set the interface connected to aggregation switch 2 as a shared risk link group. The interface is set to another shared risk link group.

Correspondingly, the above method also includes:

After learning the second routing and forwarding entry, determine whether each interface included in the second original equal-cost multi-path group in the second routing and forwarding entry belongs to the same load balancing interface group;

If it is determined that each interface included in the second original equal-cost multi-path group belongs to the same load balancing interface group, then determine the shared risk link risk group to which each interface included in the second original E-multi-path group belongs;

A set equal-cost multi-path group corresponding to each of the determined shared risk link groups is added to the second routing and forwarding entry, wherein the interface included in each added set-equal-cost multi-path group is the second original etc. The interfaces included in the valence multipath group are excluding the interfaces included in the corresponding shared risk link group.

The core switch will continuously learn the routing and forwarding entry. The routing and forwarding entry can be defined as the second routing and forwarding entry, and the equal-cost multi-path group included in the second routing and forwarding entry can be defined as the second original equal-cost multi-path group. Path group, it can be determined whether each interface included in the second original equal-cost multi-path group belongs to the same load balancing interface group. When a Layer 3 loop is generated, it is necessary to further determine the shared risk link risk group to which each interface included in the second original equal-cost multipath group belongs, and then add each of the determined shared risk link groups to the second routing forwarding entry. The corresponding set equal-cost multi-path group, wherein, the interface included in each added set equal-cost multi-path group is the interface included in the second original equal-cost multi-path group except the interface included in the corresponding shared risk link group This ensures that the received packet will not be forwarded to the switch that sent the packet.

It should be noted that the second routing and forwarding entry and the first routing and forwarding entry may be the same or different.

The following takes the core switch 1 shown in FIG. 1 as an example to introduce the specific implementation of the above method. It is assumed that the interfaces connecting the core switch 1 and the aggregation switch 1 are Gi0/0 and Gi0/1, and the next hop addresses are 10.1 respectively. .0.1, 10.1.1.1, the interfaces connecting core switch 1 and aggregation switch 2 are Gi0/2 and Gi0/3, and the next hop addresses are 10.1.2.1 and 10.1.3.1 respectively. Core switch 1 is connected to the MAN switch. The interfaces are Gi0/4 and Gi0/5, and the next hop addresses are 10.1.4.1 and 10.1.5.1 respectively. You can configure Gi0/0, Gi0/1, Gi0/2, and Gi0/3 as load balancing interface group 1. Gi0/4 and Gi0/5 are configured as load balancing interface group 2, Gi0/0 and Gi0/1 can also be configured as shared risk link group 1, and Gi0/2 and Gi0/3 can be configured as shared risk link group 2 , and configure Gi0/4 and Gi0/5 as shared risk link group 3.

If the routing table entry 100.1.1.1/32 from access switch 1 is learned, its next hop and outgoing interface are <10.1.0.1, Gi0/0>, <10.1.1.1, Gi0/1>, <10.1 respectively .2.1, Gi0/2>, <10.1.3.1, Gi0/3>. All outgoing interfaces of route 100.1.1.1/32 are in load balancing interface group 1, among which outgoing interfaces Gi0/0, Gi0/1, Gi0/2, and Gi0/3 belong to different sharing risk link groups. The set equivalent multipath groups corresponding to the risk link group settings are:

A) With {<10.1.0.1, Gi0/0>, <10.1.1.1, Gi0/1>, <10.1.2.1, Gi0/2>, <10.1.3.1, Gi0/3>} as the default primitive equivalent Path groups, marked with EP-0.

B) The set of forwarding paths {<10.1.2.1, Gi0/2>, <10.1.3.1, Gi0/3>} that excludes the shared risk link group 1 as a set equal-cost multi-path group, marked with EP-1 .

C) The set of forwarding paths {<10.1.0.1, Gi0/0>, <10.1.1.1, Gi0/1>} that excludes the shared risk link group 2 as a set equal-cost multi-path group, marked with EP-2 .

The routing table entry 100.1.1.1/32 may be associated with EP-0, EP-1 and EP-2.

For external access to the packet of access switch 1 downlink server 100.1.1.1, it reaches the core switch 1 through the MAN switch; the core switch 1 receives the packet from Gi0/4 or Gi0/5 between the MAN switch and the MAN switch, Determine the shared risk link group 3 to which the receiving interface of the packet belongs, and then look up the routing forwarding table according to the destination IP address 100.1.1.1 of the packet, find the routing table entry with the prefix 100.1.1.1/32, and then enter the routing table entry in the routing table entry. In 100.1.1.1/32, the set ECM corresponding to the shared risk link group 3 is searched, and the set ECM is not found. In this case, the forwarding can be based on the original ECP group EP-0. The packets are sent to aggregation switch 1 or aggregation switch 2; if the link between aggregation switch 1, access switch 1, and access switch 2 fails, the packets accessing the 100.1.1.1 server are re-forwarded to aggregation switch 1 according to the default route. Core switch 1, core switch 2; the core switch 1 receives the packet from the interface Gi0/0 or Gi0/1 between the core switch 1 and the aggregation switch 1, determines the shared risk link group 1 to which the interface receiving the packet belongs, and then According to the destination IP address 100.1.1.1 of the packet, the route forwarding table is searched, the routing table entry with the prefix 100.1.1.1/32 is found, and then the device corresponding to the shared risk link group 1 is found in the routing table entry 100.1.1.1/32. Determines an equal-cost multipath group, finds EP-1, and forwards packets to aggregation switch 2 according to EP-1 (the forwarding path of EP-1 does not exist to reach aggregation switch 1); aggregation switch 2 receives the message forwarded by core switch 1 message, and then forward the modified message to access switch 1. Thus, the generation of a three-layer loop can be avoided.

Based on the same inventive concept, an embodiment of the present invention provides a data center-based packet forwarding device, which is applied to a core switch included in a data center. The structure of the device is shown in FIG. 3 , including:

The first determination module 31 is configured to determine the first shared risk link group to which the receiving interface of the message belongs, and the first shared risk link group includes each interface connected between the switch connected to the receiving interface and the core switch;

The first search module 32 is used for searching the first routing and forwarding table entry corresponding to the destination IP address of the message in the routing and forwarding table;

The second search module 33 is configured to search for the first set equal-cost multipath corresponding to the first shared risk link group in the first routing and forwarding entry if the first routing and forwarding entry is found in the routing and forwarding table Group;

The forwarding module 34 is configured to forward the packet according to the first set equal-cost multi-path group if the first set equal-cost multi-path group is found in the first routing and forwarding entry; If the first set equal-cost multi-path group is found, the packet is forwarded according to the first original equal-cost multi-path group in the first routing forwarding entry; wherein, the interface included in the first set equal-cost multi-path group is the first The interfaces included in an original equal-cost multipath group are excluding the interfaces included in the first shared risk link group.

In this solution, after receiving the message, the core switch searches the first routing and forwarding entry for the first set equal-cost multipath group corresponding to the first shared risk link group to which the receiving interface of the message belongs. The packets are forwarded through the first set equal-cost path group, because the interfaces included in the first set equal-cost multi-path group are the interfaces included in the first original equal-cost multi-path group, except those included in the first shared risk link group The interface other than the interface, and the interface of the first shared risk link group is connected to the same device. Therefore, the packet will not be forwarded through the interface included in the first shared risk link group to which the receiving interface of the packet belongs. It can also ensure that the packet will not be forwarded to the switch that sends the packet; if it is not found, it means that the interfaces included in the first original equal-cost multipath group do not include the interfaces included in the first shared risk link group, then The packet can be forwarded according to the first original equal-cost multi-path group in the first routing and forwarding entry, which ensures that the packet will not be forwarded to the switch that sends the packet. It can be seen that no matter whether the first setting is found or not Equal-cost multipath groups can ensure that the packet will not be returned to the sending switch, thereby avoiding the occurrence of Layer 3 loops, and thus avoiding packet loss and ensuring normal forwarding of service packets.

Optionally, the above device further includes a setting module for:

Set the interfaces connected to the switches with the same networking role among all the interfaces of the core switch as a load balancing interface group;

Set all interfaces of the core switch that are connected to the same switch as a shared risk link group.

Optionally, the above-mentioned device further includes a second determination module for:

After learning the second routing and forwarding entry, determine whether each interface included in the second original equal-cost multi-path group in the second routing and forwarding entry belongs to the same load balancing interface group;

If it is determined that each interface included in the second original equal-cost multi-path group belongs to the same load balancing interface group, then determine the shared risk link risk group to which each interface included in the second original E-multi-path group belongs;

A set equal-cost multi-path group corresponding to each of the determined shared risk link groups is added to the second routing and forwarding entry, wherein the interface included in each added set-equal-cost multi-path group is the second original etc. The interfaces included in the valence multipath group are excluding the interfaces included in the corresponding shared risk link group.

Optionally, the above device further includes a discarding module for:

If the first routing forwarding table entry is not found in the routing forwarding table, the packet is discarded.

An embodiment of the present application further provides an electronic device, as shown in FIG. 4 , including a processor 410, a communication interface 420, a memory 430, and a communication bus 440, wherein the processor 410, the communication interface 420, and the memory 430 pass through the communication bus 440 completes the mutual communication.

a memory 430 for storing computer programs;

The processor 410 is configured to implement the data center-based packet forwarding method described in any of the foregoing embodiments when executing the program stored in the memory 430 .

The communication interface 420 is used for communication between the above electronic device and other devices.

The memory may include random access memory (Random Access Memory, RAM), and may also include non-volatile memory (Non-Volatile Memory, NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

The above-mentioned processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; may also be a digital signal processor (Digital Signal Processing, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

In this solution, after receiving the message, the core switch searches the first routing and forwarding entry for the first set equal-cost multipath group corresponding to the first shared risk link group to which the receiving interface of the message belongs. The packets are forwarded through the first set equal-cost path group, because the interfaces included in the first set equal-cost multi-path group are the interfaces included in the first original equal-cost multi-path group, except those included in the first shared risk link group The interface other than the interface, and the interface of the first shared risk link group is connected to the same device. Therefore, the packet will not be forwarded through the interface included in the first shared risk link group to which the receiving interface of the packet belongs. It can also ensure that the packet will not be forwarded to the switch that sent the packet; if it is not found, it means that the interfaces included in the first original equal-cost multipath group do not include the interfaces included in the first shared risk link group. , the packet can be forwarded according to the first original equal-cost multi-path group in the first routing forwarding entry, which ensures that the packet will not be forwarded to the switch that sent the packet. Setting an equal-cost multipath group can ensure that the packet will not be returned to the sending switch, thereby avoiding the occurrence of Layer 3 loops, and thus avoiding packet loss and ensuring normal forwarding of service packets.

Correspondingly, an embodiment of the present application further provides a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the computer-readable storage medium is run on a computer, the computer is made to execute the data-based storage medium described in any of the foregoing embodiments. The center's packet forwarding method.

In this solution, after receiving the message, the core switch searches the first routing and forwarding entry for the first set equal-cost multipath group corresponding to the first shared risk link group to which the receiving interface of the message belongs. The packets are forwarded through the first set equal-cost path group, because the interfaces included in the first set equal-cost multi-path group are the interfaces included in the first original equal-cost multi-path group, except those included in the first shared risk link group The interface other than the interface, and the interface of the first shared risk link group is connected to the same device. Therefore, the packet will not be forwarded through the interface included in the first shared risk link group to which the receiving interface of the packet belongs. It can also ensure that the packet will not be forwarded to the switch that sent the packet; if it is not found, it means that the interfaces included in the first original equal-cost multipath group do not include the interfaces included in the first shared risk link group. , the packet can be forwarded according to the first original equal-cost multi-path group in the first routing forwarding entry, which ensures that the packet will not be forwarded to the switch that sent the packet. Setting an equal-cost multipath group can ensure that the packet will not be returned to the sending switch, thereby avoiding the occurrence of Layer 3 loops, and thus avoiding packet loss and ensuring normal forwarding of service packets.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in a flow or flow of a flowchart and/or a block or blocks of a block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions The apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.

Although alternative embodiments of the present invention have been described, additional changes and modifications to these embodiments may occur to those skilled in the art once the basic inventive concepts are known. Therefore, the appended claims are intended to be construed to include alternative embodiments and all changes and modifications that fall within the scope of the present invention.

Obviously, those skilled in the art can make various changes and modifications to the embodiments of the present invention without departing from the spirit and scope of the embodiments of the present invention. Thus, provided that these modifications and variations of the embodiments of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims (10)

1. A message forwarding method based on a data center is applied to a core switch included in the data center, and is characterized by comprising the following steps:

determining a first shared risk link group to which a receiving interface of a message belongs, wherein the first shared risk link group comprises each interface connected between a switch connected with the receiving interface and the core switch;

searching a first route forwarding table item corresponding to a destination Internet Protocol (IP) address of the message in a route forwarding table;

if the first route forwarding table entry is found in the route forwarding table, finding a first set equal-cost multi-path group corresponding to the first shared risk link group in the first route forwarding table entry;

if the first set equal cost multi-path group is found in the first route forwarding table entry, forwarding the message according to the first set equal cost multi-path group; if the first set equal cost multi-path group is not found in the route forwarding table entry, forwarding the message according to a first original equal cost multi-path group in the first route forwarding table entry; the interfaces included in the first set equal cost multi-path group are interfaces except the interfaces belonging to the first shared risk link group in the interfaces included in the first original equal cost multi-path group.

2. The method of claim 1, further comprising:

setting interfaces connected with the switches with the same networking role in all the interfaces of the core switch as a load sharing interface group;

and setting the interfaces connected with the same switch in all the interfaces of the core switch as a shared risk link group.

3. The method of claim 2, further comprising:

after learning a second route forwarding table entry, determining whether each interface included in a second original equivalent multipath group in the second route forwarding table entry belongs to the same load sharing interface group;

if it is determined that each interface included in the second original equal-cost multi-path group belongs to the same load sharing interface group, determining a shared risk link risk group to which each interface included in the second original equal-cost multi-path group belongs;

and adding a set equal cost multi-path group corresponding to each determined shared risk link group in the second route forwarding table entry, wherein an interface included in each added set equal cost multi-path group is an interface except for an interface included in the corresponding shared risk link group in the interfaces included in the second original equal cost multi-path group.

4. The method of any of claims 1-3, further comprising:

and if the first route forwarding table entry is not found in the route forwarding table, discarding the message.

5. A message forwarding device based on a data center is applied to a core switch included in the data center, and is characterized by comprising:

a first determining module, configured to determine a first shared risk link group to which a receiving interface of a packet belongs, where the first shared risk link group includes interfaces connected between a switch connected to the receiving interface and the core switch;

the first searching module is used for searching a first route forwarding table item corresponding to the destination IP address of the message in a route forwarding table;

a second searching module, configured to search a first set equal-cost multipath group corresponding to the first shared risk link group in the first route forwarding table entry if the first route forwarding table entry is found in the route forwarding table;

a forwarding module, configured to forward the packet according to the first set equal cost multipath group if the first set equal cost multipath group is found in the first route forwarding entry; if the first set equal cost multi-path group is not found in the route forwarding table entry, forwarding the message according to a first original equal cost multi-path group in the first route forwarding table entry; the interfaces included in the first set equal cost multi-path group are interfaces except the interfaces belonging to the first shared risk link group in the interfaces included in the first original equal cost multi-path group.

6. The apparatus of claim 5, further comprising a setup module to:

setting interfaces connected with the switches with the same networking role in all the interfaces of the core switch as a load sharing interface group;

and setting the interfaces connected with the same switch in all the interfaces of the core switch as a shared risk link group.

7. The apparatus of claim 6, further comprising a second determination module to:

after learning a second route forwarding table entry, determining whether each interface included in a second original equivalent multipath group in the second route forwarding table entry belongs to the same load sharing interface group;

if it is determined that each interface included in the second original equal-cost multi-path group belongs to the same load sharing interface group, determining a shared risk link risk group to which each interface included in the second original equal-cost multi-path group belongs;

and adding a set equal cost multi-path group corresponding to each determined shared risk link group in the second route forwarding table entry, wherein an interface included in each added set equal cost multi-path group is an interface except for an interface included in the corresponding shared risk link group in the interfaces included in the second original equal cost multi-path group.

8. The apparatus of any of claims 5-7, further comprising a discard module to:

and if the first route forwarding table entry is not found in the route forwarding table, discarding the message.

9. An electronic device, characterized in that the electronic device comprises a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;

a memory for storing a computer program;

a processor for implementing the method steps of any of claims 1-4 when executing a program stored on a memory.

10. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of claims 1 to 4.

Images