Search

CN-120342952-B - VXLAN-based data transmission method and device, storage medium and electronic equipment

CN120342952BCN 120342952 BCN120342952 BCN 120342952BCN-120342952-B

Abstract

The application discloses a data transmission method, a device, a storage medium and electronic equipment based on VXLAN, wherein the method comprises the steps of dynamically adjusting priorities of a plurality of physical links through a dynamic routing protocol after virtualizing the physical links between two user terminals into one virtual link through a VXLAN technology, enabling the physical links to be identified as equivalent paths, dispersing service flow to the physical links through a load sharing algorithm based on the equivalent paths for transmission, monitoring the physical link state in real time, and switching the service flow to an available target physical link through the load sharing algorithm when any physical link is detected to be faulty. The scheme breaks through the limitation that the traditional routing protocol only supports dual-link load, so that a plurality of physical links work together logically, the utilization rate of link resources is improved, automatic switching in fault is realized through dynamic priority adjustment, and the reliability of the network is enhanced.

Inventors

  • Jin Fanglong
  • JIANG ZHANGJIAN
  • YANG GANG
  • DUAN LIMIN
  • YUE CHENHUI

Assignees

  • 北京联广通网络科技有限公司

Dates

Publication Date
20260512
Application Date
20250425

Claims (7)

  1. 1. A VXLAN-based data transmission method, the method comprising: After virtualizing a plurality of physical links between two user terminals into a virtual link through a virtual extended local area network (VXLAN) technology, dynamically adjusting the priority of the plurality of physical links through a dynamic routing protocol so that the plurality of physical links are identified as equivalent paths; based on the equivalent path, distributing the service flow to the plurality of physical links for transmission through a load sharing algorithm; Monitoring the physical link state in real time, and switching the service flow to an available target physical link through the load sharing algorithm when any physical link is detected to be faulty; dispersing the service traffic to the plurality of physical links for transmission by a load sharing algorithm, including: Acquiring link weights allocated to each of the plurality of physical links based on a weight allocation model, wherein the link weights comprise current link state indexes of each of the plurality of physical links and service characteristics of the service flow, the current link state indexes of each physical link and the service characteristics of the service flow are input into the weight allocation model, the link weights allocated to each of the plurality of physical links are acquired, the link state indexes comprise at least one of bandwidth utilization rate, delay time length, packet loss rate and jitter degree, and the service characteristics of the service flow comprise flow types and priority labels; Calculating the minimum integer ratio of all link weights in the plurality of physical links, and calculating the sum of all values in the minimum integer ratio as the total weight; Configuring a corresponding weight interval for the link weight of each physical link according to the total weight and the minimum integer ratio, so that the length of the weight interval is equal to the corresponding integer in the minimum integer ratio; Respectively calculating hash values of target information in each message in the service flow, and carrying out normalization processing on each hash value to obtain a hash value after normalization; Determining a weight interval in which each normalized hash value is located, and distributing a corresponding message to a physical link corresponding to the weight interval for transmission; the loss function of the weight distribution model is as follows: Wherein L represents a loss value, N represents the number of physical links, K represents the number of traffic types, omega i represents the link weight distributed by a weight distribution model for the ith physical link, omega i,k represents the weight of the kth service on the ith physical link, U i represents the bandwidth utilization rate of the ith physical link, D i represents the delay time of the ith physical link, L i represents the packet loss rate of the ith physical link, J i represents the jitter degree of the ith physical link, priority k represents the Priority of the kth service, alpha, beta, gamma, delta and epsilon are respectively super-parameters, the importance of each sub-term is controlled, var (U i ) represents the variance of the bandwidth utilization rate of all links, alpha Var (U i ) represents a bandwidth balance term for avoiding a certain physical link and promoting the bandwidth utilization rate, Representing a delay penalty term, for high delay links should be assigned a lower weight, Represents a packet loss penalty term for reducing the weight of high packet loss links, Represents a jitter penalty term, for reducing path jitter of jitter-sensitive traffic, And representing service characteristic matching items, wherein the service characteristic matching items are used for the high-priority service to avoid high-delay and high-packet-loss links, and calculating the weighted sum of delay and packet loss of an allocation path of each type of service, wherein the higher the priority is, the more sensitive the service characteristic matching items are to the service characteristic matching items.
  2. 2. The method of claim 1, wherein dynamically adjusting the priorities of the plurality of physical links via a dynamic routing protocol to identify the plurality of physical links as equivalent paths comprises: And setting cost values of the plurality of physical links to the same value based on an Open Shortest Path First (OSPF) protocol, and starting an equal cost multi-path routing (ECMP) function of the OSPF protocol so that the plurality of physical links are identified as equal cost paths.
  3. 3. The method according to any of claims 1-2, wherein switching the traffic to an available target physical link by the load sharing algorithm when a failure of any physical link is detected comprises: When any physical link is detected to be faulty, carrying out fault prediction on the remaining physical links based on a fault prediction model to obtain a fault prediction result of each remaining physical link in a preset time length in the future, wherein the remaining physical links are other physical links except the faulty physical links; Taking all the physical links with failure prediction results without failure risk in the rest physical links as available target physical links; And switching the service flow to an available target physical link through the load sharing algorithm.
  4. 4. A VXLAN-based data transmission apparatus, the apparatus comprising: The adjusting unit is used for dynamically adjusting the priority of a plurality of physical links through a dynamic routing protocol after virtualizing the physical links between two user terminals into one virtual link through a virtual extended local area network (VXLAN) technology, so that the physical links are identified as equivalent paths; The load distribution unit is used for distributing the service flow to the plurality of physical links for transmission through a load sharing algorithm based on the equivalent paths; The switching unit is used for monitoring the physical link state in real time, and switching the service flow to an available target physical link through the load sharing algorithm when any physical link is detected to be faulty; the load distribution unit includes: The acquisition module is used for acquiring link weights allocated to each physical link in the plurality of physical links based on a weight allocation model, and comprises the steps of acquiring a current link state index of each physical link in the plurality of physical links and a service characteristic of the service flow, inputting the current link state index of each physical link and the service characteristic of the service flow into the weight allocation model, and acquiring the link weights allocated to each physical link in the plurality of physical links, wherein the link state index comprises at least one of a bandwidth utilization rate, a delay time length, a packet loss rate and a jitter degree, and the service characteristic of the service flow comprises a flow type and a priority label; The calculation module is used for calculating the minimum integer ratio of all link weights in the plurality of physical links and calculating the sum of all values in the minimum integer ratio as the total weight; The configuration module is used for configuring a corresponding weight interval for the link weight of each physical link according to the total weight and the minimum integer ratio, so that the length of the weight interval is equal to the corresponding integer in the minimum integer ratio; The calculation module is further configured to calculate hash values of the target information in each packet in the service flow, and normalize each hash value to obtain a normalized hash value; the determining module is used for determining a weight interval in which each normalized hash value is located; the distribution module is used for distributing the corresponding message to the physical link corresponding to the weight interval for transmission; the loss function of the weight distribution model is as follows: Wherein L represents a loss value, N represents the number of physical links, K represents the number of traffic types, omega i represents the link weight distributed by a weight distribution model for the ith physical link, omega i,k represents the weight of the kth service on the ith physical link, U i represents the bandwidth utilization rate of the ith physical link, D i represents the delay time of the ith physical link, L i represents the packet loss rate of the ith physical link, J i represents the jitter degree of the ith physical link, priority k represents the Priority of the kth service, alpha, beta, gamma, delta and epsilon are respectively super-parameters, the importance of each sub-term is controlled, var (U i ) represents the variance of the bandwidth utilization rate of all links, alpha Var (U i ) represents a bandwidth balance term for avoiding a certain physical link and promoting the bandwidth utilization rate, Representing a delay penalty term, for high delay links should be assigned a lower weight, Represents a packet loss penalty term for reducing the weight of high packet loss links, Represents a jitter penalty term, for reducing path jitter of jitter-sensitive traffic, And representing service characteristic matching items, wherein the service characteristic matching items are used for the high-priority service to avoid high-delay and high-packet-loss links, and calculating the weighted sum of delay and packet loss of an allocation path of each type of service, wherein the higher the priority is, the more sensitive the service characteristic matching items are to the service characteristic matching items.
  5. 5. The apparatus of claim 4 wherein the adjustment unit is configured to set cost values of the plurality of physical links to a same value based on an open shortest path first OSPF protocol and enable an equal cost multi path routing ECMP function of the OSPF protocol such that the plurality of physical links are identified as equal cost paths.
  6. 6. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any of claims 1-3.
  7. 7. An electronic device, the electronic device comprising: one or more processors; the processor is coupled with a storage device for storing one or more programs; The one or more programs, when executed by the one or more processors, cause the electronic device to implement the method of any of claims 1-3.

Description

VXLAN-based data transmission method and device, storage medium and electronic equipment Technical Field The present application relates to the field of computer communications, and in particular, to a VXLAN-based data transmission method, apparatus, storage medium, and electronic device. Background In the traditional network architecture, the common dynamic routing protocols such as OSPF and BGP are mainly designed for small and medium-scale network scenarios. Under the condition of double-link configuration, the protocols can better realize link load sharing and redundancy protection, can distribute flow to two physical links, and can also switch and ensure continuous operation of service when the links fail. The limitations of existing protocols are emphasized when there are three or more physical links in the network. The underlying algorithms of these protocols typically only support a fixed number of transmission paths, typically two by default, and the redundant physical links cannot be treated as valid transmission paths by the dynamic routing protocol. This is because the protocol simplifies the design of path computation and state synchronization, such as the SPF algorithm of OSPF, is more prone to selecting the optimal path. This results in a significant amount of physical link resources being idle and the weights cannot be allocated or dynamically adjusted as needed. This not only reduces bandwidth utilization, but may also cause congestion due to traffic concentration on a few links. This problem is more pronounced in link-intensive scenarios such as cloud computing, multi-data center interconnection, etc., so technological innovations are urgently needed to break the path capacity limitations of traditional routing protocols. Disclosure of Invention The application provides a data transmission method, a device, a storage medium and electronic equipment based on VXLAN, which can solve the problem that a plurality of physical links are idle due to the fact that only dual-link load is supported. The specific technical scheme is as follows: in a first aspect, an embodiment of the present application provides a VXLAN-based data transmission method, where the method includes: After virtualizing a plurality of physical links between two user terminals into a virtual link through a virtual extended local area network (VXLAN) technology, dynamically adjusting the priority of the plurality of physical links through a dynamic routing protocol so that the plurality of physical links are identified as equivalent paths; based on the equivalent path, distributing the service flow to the plurality of physical links for transmission through a load sharing algorithm; And monitoring the physical link state in real time, and switching the service flow to an available target physical link through the load sharing algorithm when any physical link is detected to be faulty. In one possible implementation, the distributing the traffic flow over the plurality of physical links for transmission by a load sharing algorithm includes: Acquiring link weights distributed to each physical link in the plurality of physical links based on a weight distribution model; Calculating the minimum integer ratio of all link weights in the plurality of physical links, and calculating the sum of all values in the minimum integer ratio as the total weight; Configuring a corresponding weight interval for the link weight of each physical link according to the total weight and the minimum integer ratio, so that the length of the weight interval is equal to the corresponding integer in the minimum integer ratio; Respectively calculating hash values of target information in each message in the service flow, and carrying out normalization processing on each hash value to obtain a hash value after normalization; and determining a weight interval in which each normalized hash value is located, and distributing the corresponding message to a physical link corresponding to the weight interval for transmission. In one possible implementation, the method for assigning link weights to each of the plurality of physical links based on a weight assignment model includes: acquiring a current link state index of each physical link in the plurality of physical links and service characteristics of the service flow; and inputting the current link state index of each physical link and the service characteristics of the service flow into the weight distribution model to obtain the distribution link weight of each physical link in the plurality of physical links. In one possible implementation, dynamically adjusting the priorities of the plurality of physical links by a dynamic routing protocol, so that the plurality of physical links are identified as equivalent paths includes: And setting cost values of the plurality of physical links to the same value based on an Open Shortest Path First (OSPF) protocol, and starting an equal cost multi-path routing (ECMP) fu