CN117201407B - IPv6 network rapid congestion detection and avoidance method adopting perception - Google Patents
IPv6 network rapid congestion detection and avoidance method adopting perception Download PDFInfo
- Publication number
- CN117201407B CN117201407B CN202311471401.0A CN202311471401A CN117201407B CN 117201407 B CN117201407 B CN 117201407B CN 202311471401 A CN202311471401 A CN 202311471401A CN 117201407 B CN117201407 B CN 117201407B
- Authority
- CN
- China
- Prior art keywords
- application
- sla
- path
- srv
- flow
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 230000008447 perception Effects 0.000 title abstract description 7
- 238000001514 detection method Methods 0.000 title description 7
- 230000009191 jumping Effects 0.000 claims description 15
- 230000005856 abnormality Effects 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000002829 reductive effect Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000000593 degrading effect Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Abstract
The invention discloses a method for detecting and avoiding IPv6 network rapid congestion by using perception, which comprises the following steps: 1. carrying application information of the application in an application flow and transmitting the application information into a network; 2. establishing a positive selection path and an alternative path for the application meeting the SLA requirement; 3. forwarding the application flow according to the forward path; 4. the end point node on the forward path checks for congestion; 5. the endpoint node screens out an application stream with the lowest SLA service level according to the condition of the application stream and records the application stream as a stream Fi; 6. the SRv source node of the notification flow Fi starts a backup path to serve as a positive selection path, and the original positive selection path serves as an alternative path; 7. recording delay information from a source node to a local endpoint node; 8. and forwarding the last data packet to the source node, and collecting delay information by the source node so as to conveniently establish a forwarding path. When the network is congested, the invention adjusts the forwarding path of the low-priority traffic, and ensures that the high-priority traffic arrives with low delay.
Description
Technical Field
The invention relates to the technical field of communication, in particular to a method for detecting and avoiding IPv6 network rapid congestion by using perception.
Background
The requirements of network applications on quality of service, such as network bandwidth, delay, jitter, packet loss rate, etc., are not the same, but even very different. Applications such as interactive multimedia services place extremely high demands on network latency, while the demands of applications such as text are easily met. However, current networks and applications are decoupled, the network cannot sense the application requirements in fine granularity, when the network encounters congestion, the traditional network congestion control method only starts from best effort service and fairness of traffic scheduling, and does not perform traffic scheduling according to different application requirements, so that the traffic scheduling meets the fairness requirements and ignores the application requirements, thereby causing the overall quality of service (QoS, quality of Service) level of the network to be reduced.
Disclosure of Invention
Aiming at the problem that the prior art is difficult to provide corresponding service quality SLA guarantee for the application when the network encounters congestion, the invention provides an IPv6 network rapid congestion detection and avoidance method with application perception, which comprises the following steps:
step 1, acquiring application information carried by an application flow, and determining an SLA (service level agreement) corresponding to the application flow according to the application information;
step 2, when the application flow enters a network, according to the SLA requirement, when the controller establishes a forward selection SRv path for the application flow, simultaneously establishing another alternative SRv path meeting the SLA requirement at the source node;
step 3, forwarding the application flow according to a forward path SRv, and if the current forwarding is the last data packet of the application flow, turning to step 7;
step 4, checking equipment conditions and message queue conditions of the Endpoint nodes on the forward path SRv, if congestion or traffic abnormality of the Endpoint nodes on the forward path SRv is checked, jumping to step 5, otherwise jumping to step 3;
step 5, the Endpoint node on the forward selection SRv path sorts the passed application flows according to the SLA service level according to the condition of the application flows, and the application flow with the lowest SLA service level is screened out and recorded as flow Fi;
step 6, informing SRv source nodes of the flow Fi to start backup SRv paths as forward selection SRv6 paths, and jumping to step 3 by using the forward selection SRv paths as alternative SRv paths;
step 7, recording delay information from the source node to the Endpoint node;
and step 8, forwarding the last data packet to the source node, and collecting delay information by the source node so as to conveniently establish a forwarding path.
Specifically, the application information includes a user name, an application type, a time delay, a broadband, and a Color value.
Specifically, the determining the SLA corresponding to the application flow according to the application information, specifically, determining the Color value corresponding to the application flow according to the application information.
Specifically, the step 2 of meeting the SLA requirement is specifically to query from an application SLA database according to the application information of the application flow, if the application information of the application flow exists in the SLA database, determining that the application meets the SLA requirement, otherwise, not meeting the SLA requirement.
Specifically, the application SLA database is established according to the signed SLA, and the database stores the mapping relation among the user name, the application type, the SLA service quality and the Color value, the priority of the applied SLA service quality requirement is inversely proportional to the size of the Color value, and the smaller the Color value is, the higher the applied SLA service quality requirement is, the larger the Color is, and the lower the applied SLA service quality requirement is.
Specifically, in step 2, the source node adopts TI-LFA algorithm when establishing another alternative SRv path meeting the SLA requirement.
Specifically, in step 5, the Endpoint node sorts the sizes of Color values in the application information of the passed application flows, so as to obtain an application flow sequence with the Color value from low to high or from high to low, and the application flow with the largest Color value is recorded as a flow Fi.
The invention discloses a method for detecting and avoiding IPv6 network rapid congestion by using perception, which comprises the following steps: step 1, acquiring application information carried by an application flow, and determining an SLA (service level agreement) corresponding to the application flow according to the application information; step 2, when the application flow enters a network, according to the SLA requirement, when the controller establishes a forward selection SRv path for the application flow, simultaneously establishing another alternative SRv path meeting the SLA requirement at the source node; step 3, forwarding the application flow according to a forward path SRv, and if the current forwarding is the last data packet of the application flow, turning to step 7; step 4, checking equipment conditions and message queue conditions of the Endpoint nodes on the forward path SRv, if congestion or traffic abnormality of the Endpoint nodes on the forward path SRv is checked, jumping to step 5, otherwise jumping to step 3; step 5, the Endpoint node on the forward selection SRv path sorts the passed application flows according to the SLA service level according to the condition of the application flows, and the application flow with the lowest SLA service level is screened out and recorded as flow Fi; step 6, informing SRv source nodes of the flow Fi to start backup SRv paths as forward selection SRv6 paths, and jumping to step 3 by using the forward selection SRv paths as alternative SRv paths; step 7, recording delay information from the source node to the Endpoint node; and step 8, forwarding the last data packet to the source node, and collecting delay information by the source node so as to conveniently establish a forwarding path. The invention separates the flow with different priority levels in the space domain and the time domain, improves the utilization rate of the link, encounters network congestion, adjusts the forwarding path of the flow with low priority level, and preferentially ensures that the flow with high priority level arrives with low delay.
Furthermore, the invention designs a network layer perception application type, and realizes routing by SRv6 (Segment Routing for IPv, SRv 6), and the Endpoint node on each Srv6 path backfills the transmission delay after successful forwarding of the message into the segment routing message at intervals of a period of time, so as to be beneficial to the SRv source node to establish forward selection forwarding paths and alternative forwarding paths; when SRv establishes a source-destination forwarding path, an alternative path is established for a specific application type, and when SRv an original path fails to meet transmission service quality, a node with congestion rapidly informs SRv6 of switching traffic to the alternative forwarding path, so as to achieve the purpose of avoiding network congestion.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of an application aware IPv6 network fast congestion detection and avoidance method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of Endpoint congestion detection provided in accordance with an embodiment of the present invention;
fig. 3 is a schematic diagram of rapid network traffic adjustment when congestion occurs according to an embodiment of the present invention;
fig. 4 is a schematic diagram of network congestion path switching provided according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a SRv SRH format provided in accordance with an embodiment of the present invention;
fig. 6 is a schematic diagram of an APN6 application information format provided according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which are derived by a person skilled in the art based on the embodiments of the invention, fall within the scope of protection of the invention.
Some terms involved in the present application are explained below.
(1)SLA
The SLA is a service level agreement (Service Level Agreement), which is an agreement or contract agreed between the business and the customer providing the service in terms of quality, level, performance, etc. of the service, and is a basic service in communication services, and in general, is an agreement for a service provider to determine what level to achieve in the provided service. But not every product has an SLA. And the parameters required in the different products are not exactly the same.
(2)QoS
QoS (Quality of Service) is a key parameter that needs to be met in an SLA, and can be specifically quantified as performance indexes such as bandwidth, delay, jitter, packet loss rate, throughput, and the like. Reflecting the overall end-to-end or edge-to-edge performance and the network's ability to guarantee information transfer and meet business requirements.
(3) Network congestion
Too much data transmitted by the network can cause delays and losses, degrading transmission performance, which is known as network congestion. Network congestion will cause network QoS to drop and the network layer and transport layer together take responsibility for handling the congestion. The common network layer congestion control method comprises the following steps: admission control, flow regulation, load shedding, etc.
The admission control checks whether the newly added traffic brings network congestion at the traffic inlet, if so, the newly added traffic is not allowed to enter the network; after congestion occurs, the flow regulation informs the source host to reduce the sending rate through various means; load shedding is to discard the data packet directly.
(4) Explicit congestion control
Explicit congestion control is a congestion control method of traffic regulation and when congestion is found to occur, the network device signals any packet it forwards (called ECN, explicit Congestion Notification, explicit congestion notification) with a flag indicating that it is congested. The data receiver notices congestion occurrence and informs the sender when it sends a reply packet, and the sender can reduce the sending rate to relieve congestion. The ECN mode response period is long because the congestion occurs without sending the information directly to the sender.
(5)SR（Segment Routing）
Segment Routing (SR) is a Segment Routing technique, where a source node designates a path for an application message, converts the path into an ordered Segment list, encapsulates the ordered Segment list into a header, and an intermediate node of the path only needs to forward according to the path designated in the header. Segment Routing can make the network more simplified and has good scalability.
(6)SRv6
SRv6 is an internet protocol version 6segment routing (internet protocol version 6 for segment routing), SRv6 is a method designed based on the concept of Source Routing (SR) to forward packets over a network. SRv6Segment is in the form of an IPv6 address, which may also be commonly referred to as SRv6 SID (Segment Identifier). SRv6 SIDs are of many types, with different types of SRv SIDs representing different functions. For example, the End SID represents an End SID, which identifies a certain destination node (node) in the network. The end.x SID represents an end SID of a three-layer cross-connect, identifying a link in the network.
(7) SRv6 node role
In the SRv network there are three types of node roles including source node, transit node, endPoint node (EndPoint node).
Source node: the source node generating SRv message directs the packet into SRv Segment List, and if SRv Segment List contains only a single SID and no information or TLV is required to be added to SRv message, the destination address field of SRv message is set to the SID, and SRH may not be encapsulated. The source node may be a host that generates an IPv6 message and supports SRv6, or may be an edge device of SRv domain.
Transfer node: and the IPv6 node which does not participate in SRv processing on the SRv message forwarding path, namely the transit node only executes common IPv6 message forwarding. After the node receives the SRv message, it parses the IPv6 DA (Destination Address ) field of the message. If the IPv6 destination address is neither the SRv SID nor the local interface address which are locally configured, the node takes the SRv message as a common IPv6 message, searches the IPv6 routing table according to the longest matching principle, processes and forwards, and does not process SRH, and the node is a transit node. The transit node may be a general IPv6 node or a node supporting SRv 6.
Endpoint node: in the SRv message forwarding process, the node receives a message whose IPv6 destination address is a locally configured SID, and is referred to as an endpoint node. The node needs to process SRv SID and SRH, the format of SRH is shown in fig. 5.
Example 1
Referring to fig. 1, according to the present embodiment, an application aware IPv6 network rapid congestion detection and avoidance method is disclosed, which includes the following steps:
step 1, acquiring application information carried by an application flow, and determining an SLA service level corresponding to the application flow according to the application information;
the embodiment adopts the design framework of APN6, and utilizes the programmable space of the IPv6 data message to carry the application information of the application in the IPv6 data message of the application flow and transmit the application information into the network;
the format of the application information of the APN6 is shown in fig. 6, and specifically, the application information comprises a user name, an application type, time delay and a broadband;
determining an SLA corresponding to the application flow according to the application information, specifically determining a Color value corresponding to the application flow according to the application information; the present embodiment uses Color values to represent SLA service levels of application flows.
Specifically, the priority of the service quality requirement of the application is inversely proportional to the size of the Color value, and the smaller the Color value is, the higher the service quality requirement of the application is, and the larger the Color is, the lower the service quality requirement of the application is.
The embodiment may establish a correspondence between the user information and the Color value in advance, for example, a database is used to store the mapping relationship between the user information and the Color value.
The implementation can extract user information from the user stream and search Color values corresponding to the user information from a database according to the user information.
The service provider of this embodiment may sign an SLA service commitment with a user, and after signing an SLA service commitment, the Color value of the SLA service application should be relatively fixed, and the smaller the Color value, the higher the priority of the service quality requirement of the application. The Color value reflects the time delay requirement, is approximately proportional to the time delay, and is also related to the user level, the application type and the service quality commitment.
Specifically, the application SLA database is established according to the signed SLA, and the database stores the mapping relationship among the user name, the application type, the service quality and the Color value, and the mapping relationship is shown in table 1:
the service provider makes service commitments with the user, and the service provider can charge fees according to different quality of service levels.
Specifically, when determining the corresponding Color value according to the user information, multiple information such as a user name, an application type, a time delay, a bandwidth and the like can be comprehensively adopted to determine the corresponding Color value. The corresponding Color value may also be determined from a combination of one or more of these. In one embodiment, if only the corresponding user name can be matched, the Color value of the corresponding user name is employed. The corresponding relation between the user name and the Color value is signed by the user and the service provider, and the smaller the Color value is, the higher the charge is.
To reduce the implementation complexity of the present invention, the present embodiment uses Color to prioritize different application traffic, and the smaller the Color value, the higher its priority. The Color value may be a Color value in SRv6 Policy (SRv Policy has a Color value of 32 bits and only 16 bits are taken), but the smaller the Color value, the higher priority is, and the comparison is facilitated during traffic scheduling.
As shown in fig. 3, in this embodiment, a plurality of applications are running between an originating node t1 and a destination node t2, S1 is used as a source node of SRv, and 4 applications with a quality of service requirement are set for each application, which are respectively a data transmission application F1, a video interaction application F2, an AI training application F3, and a Web browsing application F4;
step 2, when the application flow enters a network, according to the SLA requirement, when the controller establishes a forward selection SRv path for the application flow, simultaneously establishing another alternative SRv path meeting the SLA requirement at the source node;
specifically, the requirement of meeting the SLA is specifically that the application is queried from an application SLA database according to the application information of the application flow, if the application information of the application flow exists in the SLA database, the application is judged to meet the requirement of the SLA, otherwise, the application is judged not to meet the requirement;
specifically, the application SLA database is established according to the signed SLA, and the database stores the mapping relation among the user name, the application type, the SLA service quality and the Color value, the priority of the applied SLA service quality requirement is inversely proportional to the size of the Color value, and the smaller the Color value is, the higher the applied SLA service quality requirement is, the larger the Color is, and the lower the applied SLA service quality requirement is.
Specifically, the source node adopts the TI-LFA algorithm when establishing another alternative SRv path meeting the SLA requirement.
For the application needing to meet the SLA requirement, when the SRv path is created, another alternative path meeting the SLA requirement is simultaneously established at the source node, and the alternative path can be established by adopting a TI-LFA algorithm.
The alternative path nodes and the positive path nodes are not overlapped as far as possible, and partial nodes can be overlapped under the condition that all the alternative path nodes cannot be met and the alternative paths with less overlapping are prioritized;
in this embodiment, no limitation is made on what kind of database is used for the application SLA database, how to build the database, and how to query the database, which is the prior art, and will not be described here again.
Specifically, initially, the controller calculates a routing policy for t1 through t2, with path 1 and path 2, respectively, and F1 and F2 being arranged in path 1: on S1- > S4- > S6- > S7- > t2, F3 and F4 are arranged in path 2: on the S1- > S3- > S5- > S7- > t2, a backup path is established for each path, and path 1 and the backup paths thereof are shown in FIG. 4.
Step 3, forwarding the application flow according to a forward path SRv, and if the current forwarding is the last data packet of the application flow, turning to step 7;
step 4, checking equipment conditions and message queue conditions of the Endpoint nodes on the forward path SRv, if congestion or traffic abnormality of the Endpoint nodes on the forward path SRv is checked, jumping to step 5, otherwise jumping to step 3;
specifically, as shown in fig. 3, when congestion occurs at the Endpoint node S6, the Endpoint node S6 sends a congestion notification message to the source node S1 of SRv to inform the Endpoint node S6 of the congestion;
step 5, the Endpoint node on the forward selection SRv path sorts the passed application flows according to the SLA service level according to the condition of the application flows, and the application flow with the lowest SLA service level is screened out and recorded as flow Fi;
specifically, in step 5, the Endpoint node sorts the sizes of Color values in the application information of the passed application flows, so as to obtain an application flow sequence with the Color value from low to high or from high to low, and the application flow with the largest Color value is recorded as a flow Fi.
The traffic scheduling is mainly based on Color values, and the smaller the Color is, the earlier the application flow is forwarded; if the same Color value appears, the smaller the delay, the higher the priority. The SRV6 message may not carry other SLA information of the application, but must carry Color information.
Step 6, informing SRv source nodes of the flow Fi to start backup SRv paths as forward selection SRv6 paths, and jumping to step 3 by using the forward selection SRv paths as alternative SRv paths;
after receiving the congestion message, the source node S1 selects 1 flow with the lowest service quality requirement, that is, the flow with the largest Color value from the application flows passing through the path 1, and in this embodiment, the Color value of the data transmission application F1 is 200 flows with the lowest service level for the SLA, so that the forwarding path of the data transmission application F1 is adjusted to the backup path, and the purpose of alleviating the congestion problem of the Endpoint node S6 is achieved.
Step 7, recording delay information from the source node to the Endpoint node;
step 8, forwarding the last data packet to the source node, and collecting delay information by the source node so as to conveniently establish a forwarding path;
the embodiment discloses a fast congestion detection and avoidance method for an IPv6 network by applying awareness, which firstly checks whether congestion or traffic abnormality occurs at an Endpoint node on a SRv path, but not detects congestion or traffic abnormality by a data receiver, so that network congestion can be found as soon as possible and traffic with low priority of a scheduling part can be adopted, thereby reducing the probability of network jitter and network service quality degradation caused by random packet discarding. Further, in the method of this embodiment, when traffic is switched, according to the SLA service level in the application information, the application flow with a lower service level is first switched to the alternative SRv path, and the traffic is not switched all, so that normal forwarding of data of the main SRv path can be ensured, and compared with the situation that all traffic is switched in a congestion control manner, the method can better satisfy the overall QoS requirement, and because part of the application flows with lower service levels are switched, congestion does not occur in the main SRv path at this time, the corresponding QoS requirement can be satisfied, and because time delay required by a client is less, the influence on the service quality is less when the past application flows are switched. According to the embodiment, on one hand, congestion can be timely processed by timely detecting congestion through an Endpoint node on an SRV6 path, and on the other hand, a switched application flow is determined according to SLA requirements of the application flow, so that the overall QoS is improved. In summary, the present application performs path switching only for a small amount of traffic with low priority, and no abrupt change of traffic is caused; the application types and the service quality grades of the traffic are distinguished, so that the traffic can be determined to be subjected to path switching, and adverse effects on the application caused by traffic adjustment are reduced.
The method comprises the following steps: step 1, acquiring application information carried by an application flow, and determining an SLA (service level agreement) corresponding to the application flow according to the application information; step 2, when the application flow enters a network, according to the SLA requirement, when the controller establishes a forward selection SRv path for the application flow, simultaneously establishing another alternative SRv path meeting the SLA requirement at the source node; step 3, forwarding the application flow according to a forward path SRv, and if the current forwarding is the last data packet of the application flow, turning to step 7; step 4, checking equipment conditions and message queue conditions of the Endpoint nodes on the forward path SRv, if congestion or traffic abnormality of the Endpoint nodes on the forward path SRv is checked, jumping to step 5, otherwise jumping to step 3; step 5, the Endpoint node on the forward selection SRv path sorts the passed application flows according to the SLA service level according to the condition of the application flows, and the application flow with the lowest SLA service level is screened out and recorded as flow Fi; step 6, informing SRv source nodes of the flow Fi to start backup SRv paths as forward selection SRv6 paths, and jumping to step 3 by using the forward selection SRv paths as alternative SRv paths; step 7, recording delay information from the source node to the Endpoint node; and step 8, forwarding the last data packet to the source node, and collecting delay information by the source node so as to conveniently establish a forwarding path. The invention separates the flow with different priority levels in the space domain and the time domain, improves the utilization rate of the link, encounters network congestion, adjusts the forwarding path of the flow with low priority level, and preferentially ensures that the flow with high priority level arrives with low delay.
Furthermore, the embodiment designs a network layer aware application type, and realizes routing by SRv6 (Segment Routing for IPv6, SRv 6), and the Endpoint node on each Srv6 path backfills the transmission delay after successful forwarding of the message into the segment routing message at intervals of a period of time, so as to be beneficial to the SRv source node to establish forward selection forwarding paths and alternative forwarding paths; when SRv establishes a source-destination forwarding path, an alternative path is established for a specific application type, and when SRv an original path fails to meet transmission service quality, a node with congestion rapidly informs SRv6 of switching traffic to the alternative forwarding path, so as to achieve the purpose of avoiding network congestion.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (4)
1. The method for detecting and avoiding the rapid congestion of the IPv6 network by using the awareness is characterized by comprising the following steps:
step 1, acquiring application information carried by an application flow, and determining an SLA (service level agreement) corresponding to the application flow according to the application information;
step 2, when the application flow enters a network, according to the SLA requirement, when the controller establishes a forward selection SRv path for the application flow, simultaneously establishing another alternative SRv path meeting the SLA requirement at the source node;
step 3, forwarding the application flow according to a forward path SRv, and if the last data packet of the application flow is forwarded currently, turning to a step 7;
step 4, checking equipment conditions and message queue conditions of the Endpoint nodes on the forward path SRv, if congestion or traffic abnormality of the Endpoint nodes on the forward path SRv is checked, jumping to step 5, otherwise jumping to step 3;
step 5, the Endpoint node on the forward selection SRv path sorts the passed application flows according to the SLA service level according to the condition of the application flows, and the application flow with the lowest SLA service level is screened out and recorded as flow Fi;
step 6, informing SRv source nodes of the flow Fi to start backup SRv paths as forward selection SRv6 paths, and jumping to step 3 by using the forward selection SRv paths as alternative SRv paths;
step 7, recording delay information from the source node to the Endpoint node;
step 8, forwarding the last data packet to the source node, and collecting delay information by the source node so as to conveniently establish a forwarding path;
the application information comprises a user name, an application type, time delay, a broadband and Color values;
determining an SLA corresponding to the application flow according to the application information, specifically determining a Color value corresponding to the application flow according to the application information;
and step 2, the requirement of the SLA is met specifically, query is carried out from an application SLA database according to the application information of the application flow, if the application information of the application flow exists in the SLA database, the application is judged to meet the requirement of the SLA, otherwise, the application is judged not to meet the requirement of the SLA.
2. The method of claim 1, wherein the application SLA database is established according to an signed SLA, the database stores a mapping relationship among a user name, an application type, SLA service quality and a Color value, the priority of the application SLA service quality requirement is inversely proportional to the size of the Color value, and the smaller the Color value is, the higher the application SLA service quality requirement is, the larger the Color is, and the lower the application SLA service quality requirement is.
3. The method of claim 1, wherein the source node in step 2 employs a TI-LFA algorithm when establishing another alternative SRv6 path that meets SLA requirements.
4. The method of claim 2, wherein step 5 is specifically that the Endpoint node sorts the sizes of Color values in the application information of the passed application flows, so as to obtain an application flow sequence with the Color value from low to high or from high to low, and the application flow with the largest Color value is recorded as flow Fi.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311471401.0A CN117201407B (en) | 2023-11-07 | 2023-11-07 | IPv6 network rapid congestion detection and avoidance method adopting perception |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311471401.0A CN117201407B (en) | 2023-11-07 | 2023-11-07 | IPv6 network rapid congestion detection and avoidance method adopting perception |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117201407A CN117201407A (en) | 2023-12-08 |
| CN117201407B true CN117201407B (en) | 2024-01-05 |
Family
ID=88998360
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311471401.0A Active CN117201407B (en) | 2023-11-07 | 2023-11-07 | IPv6 network rapid congestion detection and avoidance method adopting perception |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117201407B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117596204A (en) * | 2024-01-19 | 2024-02-23 | 杭州网鼎科技有限公司 | Dynamic acceleration method under SRv6 network |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008055548A1 (en) * | 2006-11-09 | 2008-05-15 | Telefonaktiebolaget Lm Ericsson (Publ) | Congestion control in stateless domains |
| CN111865810A (en) * | 2019-04-30 | 2020-10-30 | 华为技术有限公司 | Congestion information acquisition method, system, related equipment and computer storage medium |
| CN112019371A (en) * | 2019-05-31 | 2020-12-01 | 瞻博网络公司 | Dynamic application SLA metric generation, distribution and intent-based SD-WAN link selection |
| WO2021169258A1 (en) * | 2020-02-24 | 2021-09-02 | 华为技术有限公司 | Message forwarding method, routing information publishing method, apparatus and system |
| CN113364677A (en) * | 2021-06-07 | 2021-09-07 | 北京工业大学 | SRv6Endpoint fault protection method |
| WO2022117092A1 (en) * | 2020-12-04 | 2022-06-09 | 苏州盛科通信股份有限公司 | Time delay measurement method and apparatus based on srv6 sid |
| WO2022127698A1 (en) * | 2020-12-15 | 2022-06-23 | 华为技术有限公司 | Congestion control method and network device |
| CN115460150A (en) * | 2021-05-21 | 2022-12-09 | 华为技术有限公司 | Communication method, device and system |
| CN115473825A (en) * | 2022-09-14 | 2022-12-13 | 中国电信股份有限公司 | Business service level agreement guarantee method and system, controller and storage medium |
| CN115604724A (en) * | 2022-10-18 | 2023-01-13 | 江苏省未来网络创新研究院（Cn） | SRv6 method for evaluating risk of congestion of backbone network flow |
| WO2023011149A1 (en) * | 2021-07-31 | 2023-02-09 | 华为技术有限公司 | Communication method based on segment routing over internet protocol version 6 (srv6) |
| CN115766219A (en) * | 2022-11-15 | 2023-03-07 | 中盈优创资讯科技有限公司 | Method and device for monitoring abnormal flow of SRv6 tunnel based on flowspec technology |
| WO2023069757A1 (en) * | 2021-10-22 | 2023-04-27 | Intel Corporation | Traffic engineering in fabric topologies with deterministic services |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11398958B2 (en) * | 2020-08-19 | 2022-07-26 | Cisco Technology, Inc. | Reverting routing decisions made based on incorrect network predictions |
-
2023
- 2023-11-07 CN CN202311471401.0A patent/CN117201407B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008055548A1 (en) * | 2006-11-09 | 2008-05-15 | Telefonaktiebolaget Lm Ericsson (Publ) | Congestion control in stateless domains |
| CN111865810A (en) * | 2019-04-30 | 2020-10-30 | 华为技术有限公司 | Congestion information acquisition method, system, related equipment and computer storage medium |
| CN112019371A (en) * | 2019-05-31 | 2020-12-01 | 瞻博网络公司 | Dynamic application SLA metric generation, distribution and intent-based SD-WAN link selection |
| WO2021169258A1 (en) * | 2020-02-24 | 2021-09-02 | 华为技术有限公司 | Message forwarding method, routing information publishing method, apparatus and system |
| WO2022117092A1 (en) * | 2020-12-04 | 2022-06-09 | 苏州盛科通信股份有限公司 | Time delay measurement method and apparatus based on srv6 sid |
| WO2022127698A1 (en) * | 2020-12-15 | 2022-06-23 | 华为技术有限公司 | Congestion control method and network device |
| CN115460150A (en) * | 2021-05-21 | 2022-12-09 | 华为技术有限公司 | Communication method, device and system |
| CN113364677A (en) * | 2021-06-07 | 2021-09-07 | 北京工业大学 | SRv6Endpoint fault protection method |
| WO2023011149A1 (en) * | 2021-07-31 | 2023-02-09 | 华为技术有限公司 | Communication method based on segment routing over internet protocol version 6 (srv6) |
| WO2023069757A1 (en) * | 2021-10-22 | 2023-04-27 | Intel Corporation | Traffic engineering in fabric topologies with deterministic services |
| CN115473825A (en) * | 2022-09-14 | 2022-12-13 | 中国电信股份有限公司 | Business service level agreement guarantee method and system, controller and storage medium |
| CN115604724A (en) * | 2022-10-18 | 2023-01-13 | 江苏省未来网络创新研究院（Cn） | SRv6 method for evaluating risk of congestion of backbone network flow |
| CN115766219A (en) * | 2022-11-15 | 2023-03-07 | 中盈优创资讯科技有限公司 | Method and device for monitoring abnormal flow of SRv6 tunnel based on flowspec technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117201407A (en) | 2023-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5016033B2 (en) | Content-based differentiation and sequencing for prioritization | |
| CN113395210B (en) | Method for calculating forwarding path and network equipment | |
| JP4814376B2 (en) | Method and system for fault tolerant QoS | |
| Kumar et al. | Beyond best effort: Router architectures for the differentiated services of tomorrow's internet | |
| EP1705845B1 (en) | Load distributing method | |
| US7107344B2 (en) | Connection allocation technology | |
| US10659343B2 (en) | Method and system for gateway selection in inter-region communication on IP networks | |
| US6418139B1 (en) | Mechanism to guarantee quality of service to real-time traffic on IP networks | |
| US6058113A (en) | Method for enhancing resource reservation communication | |
| US7702816B2 (en) | Facilitating application synchronization with a reservation protocol at a sender without application receiver participation | |
| US20070183332A1 (en) | System and method for backward congestion notification in network | |
| JP2012075172A (en) | Systems and methods for adaptive throughput management for event-driven message-based data | |
| WO2008037187A1 (en) | A method and device for processing the border gateway protocol routes | |
| CN117201407B (en) | IPv6 network rapid congestion detection and avoidance method adopting perception | |
| JP2003078556A (en) | Network system, network repeater system, network relay monitoring device and network operating method | |
| JP2012075173A (en) | Systems and methods for dynamic mode-driven link management | |
| CN107454000B (en) | Network data transmission device and method | |
| US20220124040A1 (en) | Traffic sending method and apparatus | |
| US7079491B2 (en) | Method and node apparatus for filtering ICMP data frame | |
| US20050138038A1 (en) | Dynamic links in content-based networks | |
| CN115412482B (en) | Calculation force routing method and device, electronic equipment and storage medium | |
| US8554860B1 (en) | Traffic segmentation | |
| US20150055471A1 (en) | System and method for quality-based optimization of network traffic | |
| WO2007045163A1 (en) | Method for realizing end-to-end stream transmission and the node equipment | |
| CN111953598B (en) | Distributed traffic forwarding method, device and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |