WO2022110948A1

WO2022110948A1 - Path weight allocation method and device

Info

Publication number: WO2022110948A1
Application number: PCT/CN2021/115465
Authority: WO
Inventors: 王贵; 姚俊达; 汪祖亮; 胡志波
Original assignee: 华为技术有限公司
Priority date: 2020-11-25
Filing date: 2021-08-30
Publication date: 2022-06-02
Also published as: CN114553760A; CN114553760B

Abstract

The present application discloses a path weight allocation method and device, belonging to the field of communication technology. In said method, an ingress node acquires transmission features of a first forwarding path, wherein the transmission features of the first forwarding path are used for indicating transmission characteristics of the first forwarding path when transmitting a segment routing (SR)-based message; and the ingress node allocates, on the basis of the transmission features of the first forwarding path, a first target weight to the first forwarding path, the first target weight being used for indicating a load sharing state of the first forwarding path. In said method, an ingress node allocates a weight to each forwarding path, without the need for a control node to allocate a weight to each forwarding path, thereby reducing calculation overheads of the control node.

Description

Path weight allocation method and device

This application claims the priority of the Chinese patent application with the application number 202011339362.5 and the invention title "Path Weight Assignment Method and Device" filed on November 25, 2020, the entire contents of which are incorporated herein by reference.

technical field

The present application relates to the field of communication technologies, and in particular, to a method and device for assigning path weights.

Background technique

At present, for a certain service, the control node determines the forwarding node in the forwarding network that is used to receive the data stream from the user side as the ingress node of the service, and uses the forwarding network to send the data stream to the user side. The forwarding node is determined as the egress node of the service. The control node may also allocate segment routing (SR)-multiprotocol label switching (MPLS) traffic engineering (TE) for the service based on the positions of the ingress node and the egress node in the forwarding network. Policy, SR-MPLS TE Policy is used to indicate multiple candidate paths (candidate paths) with the ingress node as the source node and the egress node as the tail node, each candidate path includes at least one sub-path, SR-MPLS TE Policy Specifically, it includes the priority of multiple candidate paths, the weight of each subpath in each candidate path, and the segment list identity (ID) of the segment list of each subpath, wherein the priority among the multiple candidate paths is the highest. The candidate path is the primary candidate path, and the other candidate paths are backup paths.

The control node can deliver the SR-MPLS TE Policy to the ingress node. After the ingress node receives the data flow of the service from a user side, the ingress node passes the primary candidate path indicated by the SR-MPLS TE Policy. , and transmit the received data stream to the egress node, so that the egress node outputs the data stream to another user side.

When the transmission characteristics of the main candidate path do not meet the requirements of the service-level agreement (SLA) of the service, the control node updates the priority of each candidate path in the SR-MPLS TE Policy, and updates the current main candidate path as The candidate path is selected, and the updated SR-MPLS TE Policy is delivered to the ingress node, and the ingress node transmits the data stream based on the main candidate path in the updated SR-MPLS TE Policy.

When the scale of the forwarding network is large, the control node provides more control services. If the control node also provides the service of updating the SR-MPLS TE Policy for each service, the calculation overhead of the control node will be further increased.

SUMMARY OF THE INVENTION

The embodiments of the present application provide a method and device for allocating path weights, which can reduce the computational overhead of a control node. The technical solution is as follows:

In a first aspect, a method for assigning path weights is provided, which is applied to an entry node, and the method includes:

Acquire transmission characteristics of the first forwarding path; based on the transmission characteristics of the first forwarding path, assign a first target weight to the first forwarding path, where the first target weight is used to represent the load of the first forwarding path share status.

The transmission characteristic of the first forwarding path is used to indicate the transmission characteristic of the first forwarding path when transmitting the SR-based message. Optionally, the transmission characteristic is an indicator value related to a drive test event (cause), or an indicator value related to an SLA, such as at least one of transmission delay, delay jitter value, and packet loss rate.

In the method, the weight is allocated to each forwarding path through the entry node, and the control node does not need to allocate the weight to each forwarding path, thereby saving the calculation overhead of the control node.

In a possible implementation, the transmission characteristic includes index values of N types of transmission indexes, where N is an integer greater than or equal to 1, and any transmission index is used to represent a transmission performance index.

In a possible implementation, the assigning the first target weight to the first forwarding path based on the transmission characteristics of the first forwarding path includes:

Based on the service level agreement SLA of the target service, assign the i-th weight to the i-th transmission indicator among the N-type transmission indicators, and the i-th weight of the i-th transmission indicator is used to represent the i-th transmission indicator pair The importance of the target business, the i is an integer greater than or equal to 1 and less than or equal to N;

The first target weight is obtained based on a weight corresponding to each of the N types of transmission indicators and an indicator value of each of the transmission indicators.

For the i-th transmission indicator among the N types of transmission indicators, the i-th weight is assigned to the indicator value of the i-th transmission indicator of the first forwarding path, and the i-th weight of the indicator value of the i-th transmission indicator is It is used to indicate the pros and cons of the first forwarding path relative to the k forwarding paths under the i-th transmission index, where i is an integer greater than or equal to 1 and less than or equal to N, and k is greater than or equal to 1 the integer;

The first target weight is determined based on the weight of the index value of each transmission index of the first forwarding path in the N kinds of transmission indexes.

In a possible implementation, the assigning the i-th weight to the indicator value of the i-th transmission indicator of the first forwarding path includes:

Sorting the index values of the i-th transmission index in the transmission characteristics of the k forwarding paths, to obtain an index value sequence corresponding to the i-th transmission index;

Based on the ranking of the index values of the i-th transmission index of the first forwarding path in the index value sequence, the i-th weight of the index value of the i-th transmission index of the first forwarding path is obtained.

determining the first target weight based on the weight corresponding to each transmission indicator in the N types of transmission indicators, and the weight of the indicator value of the each transmission indicator of the first forwarding path;

Wherein, the weight corresponding to any one of the transmission indicators is used to represent the importance of the any one of the transmission indicators to the target service, and the weight of the indicator value of the any one of the transmission indicators of the first forwarding path is used to represent the The degree of pros and cons of the first forwarding path relative to the k forwarding paths under any of the transmission indicators, where k is an integer greater than or equal to 1.

In a possible implementation, the first forwarding path belongs to a first candidate forwarding path; the method further includes:

For the i-th transmission indicator among the N types of transmission indicators, based on the indicator value of the i-th transmission indicator of the first forwarding path, assign the i-th transmission indicator to the first forwarding path The second target weight of the first forwarding path under the i-th transmission indicator is used to indicate that the first forwarding path is relative to m candidates under the i-th transmission indicator The pros and cons of each forwarding path in the path, the i is an integer greater than or equal to 1 and less than or equal to N, and the m is an integer greater than or equal to 1;

The third target weight of the first candidate forwarding path is determined based on the second target weight of the first forwarding path relative to the m candidate paths under each of the N kinds of transmission metrics, and the The third target weight is used to indicate the priority of the first candidate forwarding path among the m candidate forwarding paths.

In a possible implementation, before allocating a first target weight to the first forwarding path based on the transmission characteristics of the first forwarding path, the method further includes:

Based on the transmission characteristics of the first forwarding path, it is determined that the first forwarding path satisfies the SLA of the target service.

In a possible implementation, obtaining the transmission characteristics of the first forwarding path includes at least one of the following:

When the transmission characteristic includes a transmission time delay, the time length for transmitting a test packet to the egress node through the first forwarding path is determined as the transmission delay;

When the transmission characteristic includes a transmission jitter value, obtain the transmission jitter value based on the transmission delay determined by two adjacent test packets;

When the transmission characteristic includes a packet loss rate, the packet loss rate is determined based on the number of target transmissions and the number of target receptions, and the target number of transmissions is within a time window, and the entry node passes the A forwarding path sends the total number of the test packets to the egress node, and the target received number is the number of the test packets received by the egress node through the first forwarding path within the time window by the ingress node The total number of the test packets sent.

In a possible implementation, the test packet includes the segment list identifier of the first forwarding path, the candidate identifier of the first forwarding path, the sending time of the test packet sent by the ingress node, the at least one of the identifiers of the time window.

In a possible implementation, the test packet is a seamless bidirection forwarding detection (SBFD) packet, a two-way active measurement pootocol (TWAMP) packet, or a path-by-path detection. (in-situ information telemetry, iFIT) message.

In a second aspect, a path weight allocation apparatus is provided for executing the above path weight allocation method. Specifically, the path weight assignment device includes a functional module for executing the path weight assignment method provided in the first aspect or any optional manner of the first aspect.

A third aspect provides a network device, the network device includes a processor and a memory, the memory stores at least one piece of program code, the program code is loaded and executed by the processor to implement the first aspect or the first aspect as described above The operations performed by the methods provided in the various alternative implementations of .

In a fourth aspect, a computer-readable storage medium is provided, and at least one piece of program code is stored in the storage medium, and the program code is loaded and executed by a processor to implement the operations performed by the above path weight allocation method.

In a fifth aspect, a computer program product or computer program is provided, the computer program product or computer program includes program code, the program code is stored in a computer-readable storage medium, and the processor of the network device reads from the computer-readable storage medium. Taking the program code, the processor executes the program code, so that the computer device executes the method provided in the first aspect or various optional implementation manners of the first aspect.

In a sixth aspect, a system is provided, the system includes the path weight distribution apparatus provided in the second aspect or any optional manner of the second aspect, or includes the third aspect or any optional manner of the third aspect provided network equipment.

The solutions provided in the second aspect to the fifth aspect can be used to implement the path weight allocation method provided in the first aspect or any optional manner of the first aspect. Any optional manner of the aspect achieves the same beneficial effect, which will not be repeated here.

Description of drawings

FIG. 1 is a schematic diagram of a network scenario provided by an embodiment of the present application;

2 is a flowchart of a method for assigning path weights provided by an embodiment of the present application;

3 is a schematic diagram of an encapsulation format of a test message provided by an embodiment of the present application;

4 is a schematic structural diagram of a path weight allocation device provided by an embodiment of the present application;

FIG. 5 is a schematic structural diagram of a network device provided by an embodiment of the present application.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

FIG. 1 is a schematic diagram of a network scenario provided by an embodiment of the present application. Referring to FIG. 1 , the network 100 includes multiple forwarding nodes 101 . The plurality of forwarding nodes 101 can be divided into ingress nodes 1011 , interior nodes 1012 and egress nodes 1013 according to their positions or functions in the network 100 .

The ingress node 1011 is an edge device of the network 100 and is connected to a customer edge (CE) device. The ingress node 1011 is used to receive data streams from the user side and pass the received data streams through the network 100. The forwarding path is sent to the egress node 1013 , and the egress node 1013 forwards the data flow received from the forwarding path to another user side, so as to output the data flow to the network 100 . A forwarding path includes multiple forwarding nodes 101, the entry node 1011 is the first forwarding node of the forwarding path, that is, the source node; the exit node 1013 is the last forwarding node of the forwarding path, that is, the tail node ; Other nodes on the forwarding path except the ingress node 1011 and the egress node 1013 are all intermediate nodes 1012 , and the intermediate nodes 1012 are used to forward data streams to other forwarding nodes 101 .

For example, the ingress node 1011 and the egress node 1013 are provider edge (PE) devices. In FIG. 1, PE1 and PE2 are the ingress nodes 1011, both connected to CE1, and PE3 and PE4 are egress nodes 1013, both connected to CE2 PE1 receives the data stream sent by CE1, and transmits the received data stream to PE3 through the forwarding path between PE1 and PE3, and then PE3 forwards the received data stream to CE2, thereby realizing the data stream output from CE1. Sent to CE2.

The entry node 1011 is also used to obtain the SRPolicy (such as the SR-MPLS TE Policy) of the service corresponding to the data stream before forwarding the data stream, and then determine the candidate path with the highest priority indicated by the SR Policy. As the main candidate path for forwarding the data flow, the ingress node 1011 and based on the weight of each sub-path in the main candidate path, the weight of a sub-path is used to represent the load sharing state of the sub-path. The data stream is distributed and transmitted on each sub-path in the main candidate path, so that each sub-path can share the load, the data stream transmitted on each sub-path is converged at the egress node 1103 and forwarded out of the network by the egress node 1103 100. For example, the main candidate path includes 2 sub-paths 1 and 2, the weight of sub-path 1 is 0.3, the weight of sub-path 2 is 0.7, the ingress node 1011 transmits 30% of the data in the received data stream to the egress through sub-path 1 Node 1013, the ingress node 1011 transmits 70% of the data in the received data stream to the egress node 1013 through sub-path 2.

The entry node 1011 is further configured to, after acquiring the SRPolicy, acquire the transmission characteristic of each subpath in each candidate path indicated by the SRPolicy, and update the weight of each subpath according to the transmission characteristic of each subpath, thereby avoiding control node to update the weight of each sub-path in the SRPolicy to reduce the computational cost of the control node.

In a possible implementation manner, when updating the weight of each sub-path according to the transmission characteristics of each sub-path in a candidate path, the entry node 1011 takes the SLA of the service as a condition, and the transmission characteristics of the candidate path do not meet the SLA The entry node 1011 resets the weight of the sub-path to 0, so as to avoid the subsequent transmission of the data flow of the service on the sub-path. For the target sub-path whose transmission characteristics satisfy the SLA in the candidate path, the entry node 1011 updates the weight of the target sub-path according to the transmission characteristics of the target sub-path. When each target sub-path of a path transmits a data stream, it can not only ensure that the transmission characteristics of the data stream meet the SLA, but also ensure that the data stream is transmitted on each target sub-path in an optimal split manner.

In a possible implementation manner, the entry node 1011 only updates the weight of the sub-paths in the primary candidate path indicated by SRPolicy, but does not update the weight of the sub-paths in the backup path indicated by SRPolicy, when each sub-path in the primary candidate path When none of the transmission characteristics of the node satisfies the SLA, the ingress node 1011 requests the control node to re-issue the SRPolicy.

In a possible implementation manner, in addition to updating the weight of each subpath in each candidate path indicated by SRPolicy, the entry node 1011 can also update the priority of each candidate path based on the weight of each subpath in each candidate path , to re-determine the new primary candidate path.

For example, the candidate forwarding path and the sub-paths of the candidate forwarding path in the embodiment of the present application are both forwarding paths composed of multiple forwarding nodes. When there is no fork node in the candidate forwarding path, the candidate forwarding path is a forwarding path, or in other words, a candidate forwarding path in SRPolicy corresponds to only one segment list, and a forwarding path indicated by the segment list is also That is, the candidate forwarding path. When there is a fork node in the candidate forwarding path, the candidate forwarding path is a mesh forwarding path composed of multiple sub-paths, each sub-path is a branch of the mesh forwarding path, and each branch takes the ingress node as each branch The first forwarding node of each branch takes the exit node as the last forwarding node of each branch. The fork node is a forwarding node that has a connection relationship with at least two forwarding nodes in the candidate forwarding path. For example, an exit node is connected to two intermediate nodes in the candidate forwarding path, and the exit node is a fork node. For example, If one intermediate node in the candidate forwarding path is connected to the other three intermediate nodes in the candidate forwarding path, the one intermediate node is a fork node. In other words, a candidate forwarding path in SRPolicy corresponds to at least two segment lists, and a forwarding path indicated by each segment list in the at least two segment lists is a sub-path of the candidate forwarding path, and the at least two segment lists are The mesh forwarding path formed by the indicated at least two sub-paths is also a candidate forwarding path.

In order to further embody the process of updating the weight of each sub-path in the candidate forwarding path by the egress node, refer to the flowchart of a path weight allocation method provided by an embodiment of the present application as shown in FIG. 2 .

201. The egress node obtains the SRPolicy of the target service.

The target service is any service served by the forwarding network, such as video service, game service, and the like. The SRPolicy is used to indicate m candidate forwarding paths for forwarding the data flow of the target service, where m is an integer greater than or equal to 1. Optionally, the SRPolicy is applied to segment routing (segment routing using Ipv6 data plane, SRv6) using the Internet Protocol version 6 (Internet protocol version 6, IPv6) data plane, or, applied to the data plane using the Internet Protocol version 4 segment routing using Ipv4 data plane (SRv4).

The SRPolicy includes a candidate identifier (candidate identity, candidate ID) of each candidate forwarding path in the m candidate forwarding paths, a fourth target weight of each candidate forwarding path, and segment list information of each candidate forwarding path. The fourth target weight of a candidate forwarding path is used to indicate the priority of the candidate forwarding path among the m candidate forwarding paths, and the candidate forwarding path with the largest fourth target weight among the m candidate forwarding paths is the target service The primary candidate path of the m candidate forwarding path, that is, the candidate forwarding path with the highest priority, and the forwarding paths other than the primary candidate forwarding path among the m candidate forwarding paths are all candidate paths of the target service. The segment list information of a candidate forwarding path includes segment list identifiers of the k segment lists and a fifth target weight of the k segment lists, where k is an integer greater than or equal to 1. The segment list identifier of a segment list is used for the segment list, and the segment list is used to indicate a forwarding path. Optionally, the segment list includes address information of multiple forwarding nodes on the forwarding path, for example, the Internet protocol IP) address. The fifth target weight of the segment list is the weight of the forwarding path indicated by the segment list, and is used to indicate the load sharing state of the forwarding path. When the segment list information of a candidate forwarding path includes a segment list identifier of a segment list, the forwarding path indicated by the segment list in the segment list information is also the candidate forwarding path; when the segment list information of the candidate forwarding path includes When the segment lists of multiple segment lists are identified, the forwarding paths indicated by each segment list in the segment list information are respectively a sub-path of the candidate forwarding path.

In a possible implementation manner, the entry node obtains the SR Policy from the control node.

In another possible implementation manner, the entry node does not need to obtain the SR Policy from the control node, but the entry node directly generates the SR Policy. Optionally, the ingress node determines, according to the location information of the destination device of the target service, an egress node in the forwarding network for forwarding the data flow to the destination device, and the ingress node is the ingress node and the egress node in the forwarding network. At least one candidate forwarding path between them is respectively assigned a fourth target weight to indicate the priority of each candidate forwarding path, and a fifth target weight is assigned to each sub-path of each candidate forwarding path, the entry node is based on each The fourth target weight of each candidate forwarding path and the fifth target weight of each subpath in each candidate forwarding path are used to generate the SR Policy.

Wherein, the target device is a user-side device used to receive the data stream of the target service forwarded by the forwarding network, optionally, the target device is a user-edge device connected to the egress node, or a user-edge device connected to the user-edge device connected terminal equipment.

202. Based on the SR Policy, the entry node determines a first forwarding path to be tested.

The entry node determines any sub-path in any candidate forwarding path among the m candidate forwarding paths indicated by the SR Policy as the first forwarding path.

203. The ingress node acquires the transmission characteristic of the first forwarding path, where the transmission characteristic of the first forwarding path is used to indicate the transmission characteristic of the first forwarding path when transmitting the SR-based message.

SR-based packets are packets transmitted by using segment routing, such as SRv6 packets and SRv4 packets. The transmission feature includes index values of N types of transmission indexes, where N is an integer greater than or equal to 1, and any transmission index is used to represent a transmission performance index. Optionally, the transmission feature is an index value related to a drive test event, or an index value related to an SLA, such as at least one of transmission delay, delay jitter value, and packet loss rate.

The entry node detects the transmission characteristics of the first forwarding path based on a test packet, wherein the test packet is a seamless bidirection forwarding detection (SBFD) packet, a two-way active detection protocol (tow-way active detection protocol) measurement pootocol, TWAMP) message or in-situ information telemetry (iFIT) message.

In a possible implementation manner, the process shown in this step 203 is implemented by at least one of the following steps 2031-2033.

Step 2031 : When the transmission characteristic includes a transmission delay, the time duration for the ingress node to transmit a test packet to the egress node through the first forwarding path is determined as the transmission delay.

Before executing this step 2031, the ingress node first obtains the duration of the transmission of the test packet to the egress node through the first forwarding path. Wherein, the process for the ingress node to acquire the duration of the transmission of the test packet to the egress node through the first forwarding path includes the following steps A-E.

Step A, the entry node generates a test packet.

The test packet includes at least one of a segment list identifier of the first forwarding path, a candidate identifier of the first forwarding path, a sending time (senttime) of the test packet, and an identifier of a time window to which the sending time belongs. Wherein, the candidate identifier of the first forwarding path is the candidate identifier corresponding to the segment list identifier in the SR Policy, that is, the candidate identifier of the candidate forwarding path to which the first forwarding path belongs. The sending time of the test packet is the time when the ingress node sends the test packet. In some embodiments, the ingress node tests the transmission characteristics of the first forwarding path in real time in a plurality of test cycles, each test cycle is also a time window, and the ingress node is in the time window of each test cycle, Send multiple test packets to the egress node through the first forwarding path, so as to test the transmission characteristics of the first forwarding path in real time through the multiple test packets.

When the test packet is an SBFD packet or a TWAMP packet, for any packet in the SBFD packet and the TWAMP packet, the ingress node adds the first forwarding path in the extension field of the any packet The identifier of the segment list, the candidate identifier of the first forwarding path, the sending time of the test packet, and the identifier of the time window to which the sending time belongs to obtain the test packet.

Wherein, the extension field includes a stain identification field, a candidate identification field, a segment list identification field, and a sending time field. The dyeing identification field is used to store the identification of the time window to which the sending time belongs, the candidate identification field is used to store the candidate identification of the first forwarding path, and the segment list identification field is used to store the segment list identification of the first forwarding path , the sending time field is used to store the sending time of the test packet. In some embodiments, the test packet further includes at least one of a reception time (receivetime) field and a reserved (reserved) field, wherein the reception time field is used to store the reception time when the ingress node receives the test packet, This reserved field is reserved so that information can be added later according to the application scenario. The fields other than the extension field in any of the packets are the existing fields of the any of the packets. For example, as shown in FIG. The test packet is an SBFD packet, and the existing fields of the SBFD packet include the version (Vers) field, the diagnostic word (diagnostic, Diag) field, the state (state, Sta) field, and the polling (poll, P) field , final (final, F) field, forwarding / control separation (controlplane independent, C) field, authentication identification (authenticationpresent, A) field, demand (demand, D) field, multipoint (multipoint, M) field, detection timeout multiple ( detectmult) field, length (length) field, local identifier (mydiscriminator) field, remote identifier (yourdiscriminator) field, required minimum transmit extended specification interval (desired minimumtransmit extended specification interval, desired min TXinterval) field (referred to as "all" Minimum required sending interval field"), required minimum receiving extended specification interval (requiredminimumreceiveextended specification interval, requiredminreceiveRXinterval) field (referred to as "required minimum receiving interval field"), required minimum echo message receiving interval field (required min Echo RXinterval) field. Among them, the Vers field is used to store the SBFD protocol version number; the Diag field is used to store the diagnostic word to indicate the reason for the last session state transmission change of the local SBFD system; the P field is used to store the P flag. The P flag is set in the SBFD message, and the receiver must respond to the SBFD message; the F field is used to store the F flag, and whether to respond to the response message with the P flag set is determined by the setting state of the F flag; the C field is used to store C flag, once the C flag is set to 1, the service state change of the control plane does not affect SBFD detection; the A field is used to store the authentication flag to indicate whether the session needs to be authenticated; the D field is used to store the D flag to indicate whether the system wants to work In query mode; the M field is a reserved bit for SBFD to support multi-point expansion in the future; the detection timeout multiple stored in the detection timeout multiple field is used for the detection party to calculate the detection timeout time; the length field is used to store the length of the SBFD message ;The local identifier field is used to store the local identifier of the SBFD session connection, and a unique, non-zero discriminant value generated by the sending system is used to distinguish multiple SBFD sessions of the system; the remote identifier field is used to store the remote identifier of the SBFD session connection. Terminal identifier; the required minimum sending interval field is used to store the locally supported minimum SBFD packet sending interval, in milliseconds; the required minimum receiving interval field is used to store the locally supported minimum SBFD packet receiving interval, in milliseconds; The required minimum echo packet receiving interval field is used to store the locally supported minimum echo packet receiving interval, in milliseconds.

When the test packet is an iFIT packet, and the first forwarding path belongs to the primary candidate path, after the ingress node receives the data flow of the target service, within a time window, the ingress node is in any position of the data flow. An iFIT header is added to a service packet, and the segment list identifier of the first forwarding path, the candidate identifier of the first forwarding path, the sending time of the test packet, and the time window to which the sending time belongs are added to the iFIT header. ID to get the test message.

For example, since SBFD packets and TWAMP packets have nothing to do with the data flow of the target service, the ingress node can test the first forwarding path in real time based on test packets whose packet types are SBFD packets or TWAMP packets. transfer characteristics. For example, before receiving the data flow, the ingress node tests the transmission characteristics of the first forwarding path in real time based on the test message whose message type is SBFD message or TWAMP message. For another example, the ingress node is in the process of forwarding the data flow. , and test the transmission characteristics of the first forwarding path in real time based on the test message whose message type is the SBFD message or the TWAMP message. The test packet whose packet type is iFIT packet is generated based on the service packets in the data flow. Therefore, the test packet must be sent along with the data flow, and the ingress node only transmits data on the main candidate path. Therefore, when the ingress node uses the service packet carrying the iFIT header as the test packet, it can only test the main candidate path in the process of forwarding the data flow.

Step B: The ingress node sends the test packet to the egress node through the first forwarding path.

The entry node determines the next hop node of the entry node on the first forwarding path based on the segment list indicated by the segment list identifier of the first forwarding path; at the sending time of the test packet, the entry node sends the next hop to the entry node. The one-hop node sends the test packet; for any intermediate node on the first forwarding path, after receiving the test packet from the previous hop node, the intermediate node identifies the test packet based on the segment list in the test packet. the indicated segment list, and send the test packet to the next hop node of any intermediate node on the first forwarding path.

Step C, the exit node receives the test message.

The egress node receives the test packet from the previous hop node of the egress node on the first forwarding path.

Step D: The egress node sends a response message of the test message to the ingress node.

The response message includes the segment list identifier of the first forwarding path, the candidate identifier of the first forwarding path, the sending time of the test packet, the identifier of the time window to which the sending time belongs, and the receiving time of the test packet, The receiving time of the test packet is the time when the egress node receives the test packet.

The egress node obtains the segment list identifier of the first forwarding path, the candidate identifier of the first forwarding path, the sending time of the test packet, and the identifier of the time window to which the sending time belongs from the test packet, and converts the The reception time and the acquired segment list identifier of the first forwarding path, the candidate identifier of the first forwarding path, the sending time of the test packet, and the identifier of the time window to which the sending time belongs are encapsulated into a response packet.

In some embodiments, if the test packet is an SBFD packet and a TWAMP packet, the egress node adds the reception time in the reception time field of the test packet to obtain the response packet.

After the egress node acquires the response message, the egress node sends the response message to the ingress node. In a possible implementation manner, the egress node outputs the response packet to the ingress node through the first forwarding path. In another possible implementation manner, a control signal channel exists between the egress node and the ingress node, the egress node transmits the response message to the ingress node through the control signal channel, and the control signal channel is used to transmit the ingress node A control signal between a node and an exit node, wherein the response message is a type of control signal.

Step E, after receiving the response message, the entry node obtains the difference between the receiving time of the test message in the response message and the sending time of the test message as the test message passing through the first forwarding The length of time for the route to travel to the exit node.

After acquiring the duration, the ingress node uses the duration as the transmission delay of the first forwarding path at the current moment. The transmission delay Delay is shown in the following formula, where t1 is the sending time of the test packet, and t2 is the receiving time of the test packet.

Delay=t2-t1

If the ingress node sends multiple test packets to the egress node through the first forwarding path, the ingress node executes step 2031 each time it receives a response packet, so that the ingress node can obtain the first forwarding path The transmission delay at different times, therefore, the ingress node can test the transmission delay of the first forwarding path in real time by testing the packet.

Step 2032: When the transmission characteristic includes a transmission jitter value, the ingress node acquires the transmission jitter value based on the transmission delay determined by two adjacent test packets.

The two adjacent test packets are test packets corresponding to any two adjacent response packets received by the ingress node, or, two adjacent valid test packets, whether one test packet is valid Depends on whether the ingress node can receive the response message of the test message. If the entry node can receive the response packet of the test packet, the test packet is a valid test packet. If the entry node does not receive the response packet of the test packet, the test packet may be in the If it is lost during transmission, the test packet is an invalid test packet.

For example, the ingress node sends test message 1, test message 2, and test message 3 to the egress node sequentially through the first forwarding path. If the ingress node receives the response message 1 of the test message 1, the The response packet 2 of the test packet 2 and the response packet 3 of the test packet 3, the test packets 1-3 are all valid test packets, wherein the test packet 1 and the test packet 2 are adjacent two. test packets, test packet 2 and test packet 3 are two adjacent test packets; if the entry node receives response packet 1 and response packet 3, but does not receive response packet 2, the test packet The message 2 is an invalid test message, and the test message 1 and the test message 3 are two adjacent test messages.

The ingress node performs the above step 2031 on both the adjacent two test packets, so that the ingress node can obtain the two transmission delays determined based on the two adjacent test packets, and the ingress node uses the two adjacent test packets to obtain the two transmission delays. The absolute value of the difference between the transmission delays is determined as the delay jitter value of the first forwarding path at the current moment. The delay jitter value Jitter is shown in the following formula, where Delay1 is the transmission delay determined based on the first test packet in the two adjacent test packets, and Delay2 is based on the two adjacent test packets. Transmission delay determined by the second test packet in the test packet.

Jitter=|Delay2-Delay1|

Step 2033, when the transmission characteristic includes a packet loss rate, the ingress node determines the packet loss rate based on the number of target transmissions and the number of target receptions, and the target number of transmissions is within a time window, and the ingress node passes the The total number of the test packets sent by the first forwarding path to the egress node, and the target received number is the test packets received by the egress node and sent by the ingress node through the first forwarding path within the time window the total number of.

Within the time window, the ingress node sends a plurality of test packets to the egress node through the first forwarding path, and each test packet carries an identifier of the time window, and the ingress node counts the data of the plurality of test packets. The total number, get the number of the target sent.

Each time the exit node receives a test packet, it returns a response packet of the test packet to the entry node, and the response packet carries the identifier of the time window to which the sending time of the test packet belongs, then the entry node The total number of response packets carrying the identifier of the time window is counted to obtain the number of received packets by the target.

After obtaining the number of targets sent and received, the entry node determines the difference between the number of targets sent and the number of targets received as the number of lost targets, and the number of lost targets is the number of lost targets. The total number of test packets lost when a forwarding path transmits the plurality of test packets; the ingress node determines the ratio between the number of lost targets and the number of targets sent as the first forwarding path in This loss rate for this time window. The loss rate Loss is shown in the following formula, where S1 is the number of target transmissions, and S2 is the number of target receptions.

Loss=(S1-S2)/S1

In some embodiments, if the transmission characteristic includes a loss rate, the ingress node performs step 2033 in each time window, so that the ingress node can obtain the loss rate of the first forwarding path in each time window. In other embodiments, if the transmission characteristic does not include the loss rate, the ingress node does not perform this step 2033, and the test message and the response message do not need to carry the identifier of the time window.

204. The ingress node assigns a first target weight to the first forwarding path based on the transmission characteristic of the first forwarding path, where the first target weight of the forwarding path is used to indicate a load sharing state of the first forwarding path.

The transmission characteristics of the first forwarding path include index values of N types of transmission indicators, for example, the N types of transmission indicators include at least one of a delay index, a delay jitter index, and a packet loss index, and the transmission delay is the index value of the delay index , the delay jitter value is the index value of the delay jitter index, and the packet loss rate is the index value of the packet loss index. The embodiments of the present application are described by taking the transmission characteristics including transmission delay, delay jitter value, and packet loss ratio as an example.

In some embodiments, the ingress node first assigns a weight to each transmission index, and then assigns a first target weight to the first forwarding path based on the weight corresponding to each transmission index. In a possible implementation manner, this step 204 is implemented by the processes shown in the following steps 2041-2042.

Step 2041: Based on the SLA of the target service, the ingress node allocates the i-th weight to the i-th transmission indicator in the N-type transmission indicators, and the i-th weight of the i-th transmission indicator is used to represent the i-th transmission indicator pair The importance of the target service, where i is an integer greater than or equal to 1 and less than or equal to N.

Wherein, the i-th weight of the i-th transmission indicator is also the weight corresponding to the i-th transmission indicator. The SLA of the target service requires different priorities for different transmission indicators, and the priority of one transmission indicator is used to indicate that the SLA requires the forwarding path to satisfy the priority of the transmission indicator. The forwarding path first meets the SLA requirements for high-priority transmission indicators, and then satisfies the SLA requirements for low-priority transmission indicators.

The ingress node assigns different weights to each transmission indicator based on the priorities of the N types of transmission indicators specified by the SLA, and the change trend of the priorities of the N types of transmission indicators is proportional to the weights corresponding to the N types of transmission indicators. The change trend is the same. For example, if the change trend of the priority of the N kinds of transmission indicators is gradually increasing, the change trend of the N weights corresponding to the N kinds of transmission indicators is also gradually increased. If the priority of the N kinds of transmission indicators The change trend of the level is gradually reduced, and the change trend of the N weights corresponding to the N kinds of transmission indicators is also gradually reduced.

For another example, the delay index is at the first priority, the delay jitter index is at the second priority, and the packet loss index is at the third priority, where the first priority is higher than the second priority, and the second priority is higher than For the third priority, the weights assigned by the entry node to the delay index, delay jitter index, and packet loss index are 0.6, 0.3, and 0.1, respectively.

Step 2042: The ingress node obtains the first target weight of the first forwarding path based on the weight corresponding to each of the N types of transmission indicators and the index value of each of the transmission indicators.

For the i-th transmission indicator among the N types of transmission indicators, the ingress node obtains the i-th weight corresponding to the indicator value of the i-th transmission indicator in the transmission feature, and the indicator of the i-th transmission indicator of the first forwarding path The i-th weight corresponding to the value is used to indicate the degree of pros and cons of the first forwarding path under the j-th transmission index, where i is an integer greater than or equal to 1 and less than or equal to N.

The manner in which the entry node obtains the i th weight corresponding to the index value of the i th transmission index in the transmission characteristic includes the following manners 1 and 2.

Manner 1: The ingress node determines the weight corresponding to the index interval to which the index value of the i-th transmission index of the first forwarding path belongs to the i-th weight corresponding to the index value of the i-th transmission index.

The entry node sets a plurality of indicator intervals for the i-th transmission indicator, each indicator interval includes a plurality of indicator values, and each indicator interval corresponds to a weight. There is an inverse relationship between the index value in any index interval and the corresponding weight, that is, the larger the index value in any index interval, the smaller the corresponding weight, and vice versa, the greater the corresponding weight. For example, the i-th transmission indicator is a delay indicator, and the multiple indicator intervals under the delay indicator include a delay indicator interval 1 [0, 20ms], a delay indicator interval 2 (20ms, 1000us], and a delay indicator interval 3 ( 1000ms, ∞), the weight corresponding to the delay indicator interval 1 is 0.5, the weight corresponding to the delay indicator interval 2 is 0.2, and the weight corresponding to the delay indicator interval 3 is 0.3.

In a possible implementation manner, the entry node sets an index threshold for the i-th transmission index, and if the minimum index value in any index interval under the i-th transmission index is greater than the index threshold, the entry node sets the index threshold for the i-th transmission index. The weight corresponding to any indicator interval is set to 0.

Optionally, the indicator threshold of the i-th transmission indicator is specified by the SLA. Optionally, the indicator threshold of the i-th transmission indicator may be different under different actual network environments, and the embodiment of the present application does not specifically limit the indicator threshold set by the ingress node for the i-th transmission indicator. .

Mode 2: For the index value of the ith transmission index in the transmission feature, the entry node determines the ratio of the index threshold of the ith transmission index to the index value as the ith weight corresponding to the index value.

After the entry node obtains the weight corresponding to the index value of each transmission index in the transmission characteristics of the first forwarding path, the entry node corresponds to the weight corresponding to the index value of each transmission index among the N types of transmission index , The weight corresponding to each kind of transmission index is input into the following formula, and the first target weight W _x of the first forwarding path is calculated and obtained, wherein, w _i is the i-th weight corresponding to the i-th transmission index in the N kinds of transmission indicators , w _{0, i} is the ith weight corresponding to the index value of the ith transmission index in the transmission characteristics of the first forwarding path.

In some embodiments, the ingress node does not need to determine the first target weight of the first forwarding path based on the weight corresponding to each transmission index, but directly determines the value of each index in the transmission characteristic to determine the first target weight. The first target weight of the first forwarding path. In a possible implementation manner, this step 204 is implemented by the process shown in the following steps 204A-204B.

Step 204A: For the i-th transmission indicator among the N transmission indicators, assign the i-th weight to the indicator value of the i-th transmission indicator of the first forwarding path, and the i-th weight of the indicator value of the i-th transmission indicator It is used to indicate the pros and cons of the first forwarding path relative to the k forwarding paths under the i-th transmission index, where i is an integer greater than or equal to 1 and less than or equal to N, and k is an integer greater than or equal to 1.

The i-th weight of the index value of the i-th transmission index is the weight corresponding to the index value of the i-th transmission index of the first forwarding path. The k forwarding paths are sub-paths in the candidate forwarding paths to which the first forwarding path belongs, and the first forwarding path is any one of the k forwarding paths. For the convenience of expressing the candidate forwarding paths to which the first forwarding path belongs The path is denoted as "the first candidate forwarding path".

For the i-th transmission indicator among the N types of transmission indicators, the ingress node sorts the indicator values of the i-th transmission indicator in the transmission characteristics of the k forwarding paths, and obtains the indicator value corresponding to the i-th transmission indicator sequence. In a possible implementation manner, in an ascending order, the entry node sorts the index values of the i-th transmission indicator in the transmission characteristics of the k forwarding paths, wherein the i-th transmission indicator is The smaller the index value of the forwarding path, the better the performance of the i-th transmission index.

After obtaining the index value sequence, the entry node assigns the ith weight to the index value of the ith transmission index of the first forwarding path based on the index value sequence. In a possible implementation manner, the ingress node obtains the i-th transmission index of the first forwarding path based on the order of the index values of the i-th transmission index of the first forwarding path in the index value sequence The ith weight of the index value, where the smaller the index value of the ith type of transmission index is, the larger the ith weight is assigned to the forwarding path, and vice versa, the smaller the ith weight is assigned.

Optionally, the i-th weight w _{1, i} of the indicator value of the i-th transmission indicator of the first forwarding path includes any of the following forms, where R is the indicator value sequence of the first forwarding path. , where a and b are both integers greater than or equal to 1.

w _1,i =NR,w _1,i =a*(NR),w _1,i =N-R+b or w _1,i =a*(NR)+b

Step 204B, the ingress node determines a first target weight of the first forwarding path based on the weight of the index value of each transmission index among the N kinds of transmission indexes of the first forwarding path.

The entry node determines the sum of the weights of the index values of each transmission index of the first forwarding path in the N kinds of transmission indexes as the first target weight of the first forwarding path.

In some embodiments, the ingress node determines the first forwarding path's first forwarding path based on a weight corresponding to each of the N types of transmission metrics and the weight of the index value of each of the transmission metrics of the first forwarding path. a target weight. Optionally, the entry node inputs the weight corresponding to each of the N types of transmission indicators and the weight of the index value of each of the N types of transmission indicators of the first forwarding path into the following formula: , the first target weight W _x of the first forwarding path is obtained by calculation, wherein w _{1, i} is the ith weight of the index value of the ith transmission index of the first forwarding path.

After the ingress node obtains the first target weight of the first forwarding path through this step 204, the ingress node updates the fifth target weight of the first forwarding path in the SR Policy to the first target weight of the first forwarding path target weight.

The entry node may assign a first target weight to each sub-path of each candidate forwarding path indicated by the SR Policy according to the process shown in the above steps 201-204, and assign the fifth target weight of each sub-path in the SR Policy The goal weight update becomes the first goal weight assigned to each subpath.

205. If the first candidate forwarding path to which the first forwarding path belongs is the primary candidate path of the data flow, the ingress node passes the k forwarding paths based on the first target weights of the k forwarding paths in the first candidate forwarding path. The forwarding path sends the data stream to the exit node.

After the ingress node receives the data stream, for the first forwarding path in the k forwarding paths, the ingress node sends the first forwarding path in the data stream to the egress node through the first forwarding path. A target weight proportion of data. For example, if the first target weight of the first forwarding path is 0.3, the ingress node transmits 30% of the data in the data stream to the egress node through the first forwarding path.

In some embodiments, after acquiring the transmission characteristics of the first forwarding path, the ingress node determines whether the first forwarding path satisfies the SLA based on the transmission characteristics of the first forwarding path and the SLA of the target service. Optionally, if at least one indicator value in the transmission characteristics of the first forwarding path satisfies the indicator threshold specified by the SLA, the ingress node determines that the first forwarding path satisfies the SLA; otherwise, the ingress node determines that the first forwarding path satisfies the SLA. The forwarding path does not meet this SLA. For example, the transmission delay of the first forwarding path is less than or equal to the index threshold of the delay index specified by the SLA, and the first forwarding path satisfies the SLA.

If the first forwarding path satisfies the SLA, the ingress node assigns a first target weight to the first forwarding path based on transmission characteristics of the first forwarding path. If the first forwarding path does not meet the SLA, the ingress node sets the first target weight of the first forwarding path to 0, so as to avoid using the first forwarding path to forward the data flow of the target service subsequently.

The process shown in the above steps 203-204 is a process in which the entry node assigns a weight to each sub-path in each candidate path. In some embodiments, the ingress node can further assign a third target weight to the m candidate forwarding paths indicated by the SR Policy, wherein the third target weight of a candidate forwarding path is used to indicate that the candidate forwarding path is among the m candidate forwarding paths Priority in candidate forwarding paths.

In a possible implementation manner, for the first candidate forwarding path to which the first forwarding path belongs, the ingress node assigns a third target weight to the first candidate forwarding path according to the process shown in the foregoing steps 203-204.

In another possible implementation manner, the ingress node assigns a third target weight to the first candidate forwarding path through the process shown in the following steps A-B.

Step A, for the i-th transmission index in the N kinds of transmission indicators, the entry node allocates the i-th transmission index for the first forwarding path based on the index value of the i-th transmission index of the first forwarding path. The second target weight under the indicator, the second target weight of the first forwarding path under the i-th transmission indicator is used to indicate that the first forwarding path is relative to each of the m candidate paths under the i-th transmission indicator. The pros and cons of the forwarding path.

The entry node first sorts the index value of the i-th transmission index in the transmission characteristics of each forwarding path among the m candidate forwarding paths, and then, based on the sorting result, assigns each forwarding path among the m candidate forwarding paths an The second target weight under the i-th transmission index. In a possible implementation manner, for the i-th transmission indicator among the N types of transmission indicators, in an order from small to large, the ingress node compares the i-th transmission indicator of each forwarding path among the m candidate forwarding paths The index values are sorted, and the target index sequence corresponding to the i-th transmission index is obtained. The entry node determines the weight corresponding to the index value of the i-th transmission index of the first forwarding path according to the order of the index values of the i-th transmission index of the first forwarding path in the target index sequence, wherein the target index sequence in A smaller index value corresponds to a larger weight, and a larger index value corresponds to a smaller weight. The ingress node determines the weight corresponding to the index value of the i-th transmission index of the first forwarding path as the second target weight of the first forwarding path under the i-th transmission index.

Step B, the ingress node determines the third target weight of the first candidate forwarding path based on the second target weight of the first forwarding path relative to the m candidate paths under each of the N kinds of transmission indicators, The third target weight is used to indicate the priority of the first candidate forwarding path among the m candidate forwarding paths.

In a possible implementation manner, the ingress node includes a weight corresponding to each of the N types of transmission indicators, and the first forwarding path relative to the m candidate paths in each of the N types of transmission indicators. The following formula is input to the second target weight of the first candidate forwarding path, and the third target weight W _y of the first candidate forwarding path is obtained by calculation. Wherein, the w _2,s,i is the second target weight of the s-th forwarding path in the first candidate forwarding path under the i-th transmission characteristic, and the s is an integer greater than or equal to 1 and less than or equal to m.

In some embodiments, the ingress node assigns a third target weight to the first candidate forwarding path based on the number of forwarding paths in the first candidate forwarding path that satisfy the SLA. In a possible implementation manner, the entry node is set with multiple target number intervals, each target number interval includes multiple target numbers, and the multiple target number intervals correspond to a weight, wherein the multiple target number intervals correspond to a weight. In the target number interval, the target number interval with the larger target number corresponds to the larger weight, and vice versa, the corresponding weight is smaller. The entry node determines a weight corresponding to a target number interval to which the number of forwarding paths satisfying the SLA in the first candidate path belongs to a third target weight of the first candidate forwarding path. For example, the weight corresponding to the target number interval 1 [1, 3] is 0.4, and the weight corresponding to the target number interval 2 [4, 7] is 0.6. If the first candidate forwarding path has the number of forwarding paths that satisfy the SLA is 6, the ingress node takes the weight 0.6 as the third target weight of the first candidate forwarding path.

For example, after the ingress node determines the third target weight of the first candidate forwarding path, the ingress node updates the fourth target weight of the first candidate forwarding path in the SR Policy to the value of the first candidate forwarding path. The third target weight. The ingress node may assign the third target weight to each candidate forwarding path indicated by the SR Policy in the manner of allocating the third target weight to the first candidate forwarding path, and assign the fourth target weight of each candidate forwarding path in the SR Policy The update becomes its assigned third target weight. When the entry node receives the data stream of the target service, it determines the candidate forwarding path with the third largest target weight in the updated SR Policy as the main candidate path of the data stream. If the first candidate node is the main candidate path, then The ingress node sends the data stream to the egress node through the m forwarding paths based on the first target weights of the m forwarding paths in the first candidate path.

In the method provided by the embodiment of the present application, the weight is allocated to each forwarding path through the entry node, and the control node does not need to allocate the weight to each forwarding path, thereby saving the calculation overhead of the control node. Moreover, based on the SLA of the target service, weights are assigned to each forwarding path, so that subsequent ingress nodes preferentially use forwarding paths that meet the SLA to transmit data streams. In addition, the ingress node determines the first target weight of each forwarding path based on the weight corresponding to each of the N kinds of transmission indicators and the corresponding weight of each forwarding path under each transmission indicator, so that the assigned weight of each forwarding path is The first target weight is more reasonable. In addition, the ingress node can acquire the transmission characteristics of each forwarding path by transmitting test packets on each forwarding path, so that the ingress node can assign weights to each forwarding path based on the transmission characteristics of each forwarding path.

The methods of the embodiments of the present application are described above, and the devices of the embodiments of the present application are described below. The apparatus described below has any of the functions of the entry node in the above method.

FIG. 4 is a schematic structural diagram of an apparatus for allocating path weights provided by an embodiment of the present application. The apparatus 400 includes:

an acquisition module 401, configured to perform the above step 203;

The allocation module 402 is configured to perform the above step 204 .

Optionally, the allocation module is configured to perform the above steps 2041-4042.

Optionally, the distribution module includes:

The first allocation unit is used to perform the above steps 204A-404B.

Optionally, the first allocating unit is configured to: sort the index values of the i-th transmission index in the transmission characteristics of the k forwarding paths, and obtain an index value sequence corresponding to the i-th transmission index. ; Based on the ordering of the index values of the i-th transmission index of the first forwarding path in the index value sequence, obtain the i-th weight of the index value of the i-th transmission index of the first forwarding path.

Optionally, the allocating module is configured to: based on the weight corresponding to each transmission indicator in the N types of transmission indicators, and the weight of the indicator value of the each transmission indicator of the first forwarding path, determine the The first target weight; wherein the weight corresponding to any one of the transmission indicators is used to indicate the importance of the any one of the transmission indicators to the target service, and the indicator of the any one of the transmission indicators of the first forwarding path The weight of the value is used to indicate the degree of pros and cons of the first forwarding path relative to the k forwarding paths under any one of the transmission metrics, where k is an integer greater than or equal to 1.

Optionally, the distribution module includes:

a second allocating unit, configured to, for the i-th transmission indicator among the N types of transmission indicators, allocate the first forwarding path to the first forwarding path based on the indicator value of the i-th transmission indicator of the first forwarding path The second target weight under the i-th transmission indicator, and the second target weight of the first forwarding path under the i-th transmission indicator is used to indicate that the first forwarding path is in the i-th transmission Under the indicator, relative to the pros and cons of each forwarding path among the m candidate paths, the i is an integer greater than or equal to 1 and less than or equal to N, and the m is an integer greater than or equal to 1;

a second determining unit, configured to determine the first candidate forwarding path based on a second target weight of the first forwarding path relative to the m candidate paths under each of the N types of transmission metrics The third target weight is used to indicate the priority of the first candidate forwarding path among the m candidate forwarding paths.

Optionally, the device further includes:

A determining module, configured to determine that the first forwarding path satisfies the SLA of the target service based on the transmission characteristics of the first forwarding path.

Optionally, the obtaining module is configured to perform at least one of the above steps 2031-2033.

Optionally, the apparatus 400 further includes a sending module, configured to perform the above step 205 .

By way of example, the apparatus 400 corresponds to the entry node in the above method embodiments, and each module in the apparatus 300 and the above other operations and/or functions are respectively implemented to implement various steps and methods for the entry node in the method embodiments. For details, reference may be made to the foregoing method embodiments, which are not repeated here for brevity.

For example, when the apparatus 400 generates the weights for the forwarding paths, only the division of the above-mentioned functional modules is used as an example. The structure is divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus 400 provided in the foregoing embodiment and the foregoing method embodiment belong to the same concept, and the specific implementation process thereof is detailed in the foregoing method embodiment, which will not be repeated here.

For example, the device 400 may be disposed at the ingress node 1011 in the network 100 .

Corresponding to the method embodiments and the virtual apparatus embodiments provided in the present application, the embodiments of the present application further provide a network device, and the hardware structure of the network device is introduced below.

The network device 500 corresponds to the ingress node in the foregoing method embodiments, and each hardware, module, and the foregoing other operations and/or functions in the network device 500 are respectively implemented to implement various steps and methods performed by the ingress node in the method embodiments, For the detailed process of how the network device 500 allocates the weight of the forwarding path, the specific details can be found in the foregoing method embodiments, which are not repeated here for brevity. Wherein, each step of the above method embodiment is completed by an integrated logic circuit of hardware in the processor of the network device 500 or an instruction in the form of software. The steps of the methods disclosed in conjunction with the embodiments of the present application may be directly embodied as executed by a hardware processor, or executed by a combination of hardware and software modules in the processor. The software modules may be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other storage media mature in the art. The storage medium is located in the memory, and the processor reads the information in the memory, and completes the steps of the above method in combination with its hardware. To avoid repetition, detailed description is omitted here.

The network device 500 corresponds to the device 400 in the above virtual device embodiment, and each functional module in the device 400 is implemented by the software of the network device 500 . In other words, the functional modules included in the apparatus 400 are generated after the processor of the network device 500 reads the program codes stored in the memory.

Referring to FIG. 5 , FIG. 5 is a schematic structural diagram of a network device provided by an embodiment of the present application. The network device 500 may be configured as an entry node.

Network device 500 includes at least one processor 501 , communication bus 502 , memory 503 , and at least one physical interface 504 .

The processor 501 may be a general-purpose central processing unit (CPU), a network processor (NP), a microprocessor, or may be one or more integrated circuits for implementing the solution of the present application, such as , an application-specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof. The above-mentioned PLD can be a complex programmable logic device (complex programmable logic device, CPLD), a field-programmable gate array (field-programmable gate array, FPGA), a general array logic (generic array logic, GAL) or any combination thereof.

The communication bus 502 is used to transfer information between the aforementioned components. The communication bus 502 can be divided into an address bus, a data bus, a control bus, and the like. For ease of presentation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

The memory 503 can be read-only memory (ROM) or other types of static storage devices that can store static information and instructions, or can be random access memory (random access memory, RAM) or can store information and instructions. Other types of dynamic storage devices, it can also be electrically erasable programmable read-only memory (electrically erasable programmable read-only memory, EEPROM), compact disc read-only memory (CD-ROM) or other optical disk storage , optical disc storage (including compact disc, laser disc, optical disc, digital versatile disc, blu-ray disc, etc.), magnetic disk storage medium or other magnetic storage device, or can be used to carry or store desired program code in the form of instructions or data structures and any other medium that can be accessed by a computer, but is not limited thereto. The memory 503 may exist independently and be connected to the processor 501 through the communication bus 502 . The memory 503 may also be integrated with the processor 501 .

Physical interface 504 uses any transceiver-like device for communicating with other devices or communication networks. The physical interface 504 includes a wired communication interface and may also include a wireless communication interface. Wherein, the wired communication interface may be, for example, an Ethernet interface. The Ethernet interface can be an optical interface, an electrical interface or a combination thereof. The wireless communication interface may be a wireless local area network (wireless local area networks, WLAN) interface, a cellular network communication interface or a combination thereof, and the like. The physical interface 504 is also referred to as a physical port.

In a specific implementation, as an embodiment, the processor 501 may include one or more CPUs, such as CPU0 and CPU1 as shown in FIG. 5 .

In a specific implementation, as an embodiment, the network device 500 may include multiple processors, such as the processor 501 and the processor 505 shown in FIG. 5 . Each of these processors can be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). A processor herein may refer to one or more devices, circuits, and/or processing cores for processing data (eg, computer program instructions).

In a specific implementation, as an embodiment, the network device 500 may further include an output device 506 and an input device 507 . The output device 506 is in communication with the processor 501 and can display information in a variety of ways. For example, the output device 506 may be a liquid crystal display (LCD), a light emitting diode (LED) display device, a cathode ray tube (CRT) display device, a projector, or the like . Input device 507 is in communication with processor 501 and can receive user input in a variety of ways. For example, the input device 507 may be a mouse, a keyboard, a touch screen device, a sensor device, or the like.

In some embodiments, the memory 503 is used to store the program code 510 for executing the solutions of the present application, and the processor 501 can execute the program code 510 stored in the memory 503 . That is, the network device 500 can implement the method provided by the method embodiment through the processor 501 and the program code 510 in the memory 503 .

The network device 500 in this embodiment of the present application may correspond to the entry node in each of the foregoing method embodiments, and the processor 501, the physical interface 504, and the like in the network device 500 may implement the features of the entry node in each of the foregoing method embodiments. functions and/or the various steps and methods implemented. For brevity, details are not repeated here.

For example, the allocation module 402 in the apparatus 400 may be equivalent to the processor 501 in the network device 500 ; the acquiring module 401 and the sending module in the apparatus 400 are equivalent to the physical interface 504 in the network device 500 .

In some possible embodiments, the above-mentioned entry node may be implemented as a virtualized device. For example, the virtualization device may be a virtual machine (virtual machine, VM) running a program for sending a message, and the virtual machine is deployed on a hardware device (eg, a physical server). A virtual machine refers to a complete computer system with complete hardware system functions simulated by software and running in a completely isolated environment. A virtual machine can be configured as an entry node. For example, the entry node can be implemented based on a general-purpose physical server combined with network functions virtualization (NFV) technology. Ingress nodes are virtual hosts, virtual routers, or virtual switches. By reading this application, those skilled in the art can virtualize an entry node with the above functions on a general physical server in combination with the NFV technology. It will not be repeated here.

For example, the network devices in the above-mentioned various product forms respectively have any functions of the ingress nodes in the above-mentioned method embodiments, which will not be repeated here.

Embodiments of the present application also provide a computer program product or computer program, where the computer program product or computer program includes computer instructions, where the computer instructions are stored in a computer-readable storage medium, and the processor of the network device is obtained from the computer-readable storage medium. The computer instruction is read, and the processor executes the computer instruction, so that the path weight assignment executes the above path weight assignment method.

The embodiment of the present application further provides a chip, including a processor and an interface circuit, the interface circuit is used to receive instructions and transmit them to the processor; the processor can be used to execute the above method for assigning execution path weights applied to an instruction entry node. The processor is coupled to a memory, and the memory is used to store programs or instructions, and when the programs or instructions are executed by the processor, the chip system enables the method in any of the foregoing method embodiments. Optionally, the number of processors in the chip system may be one or more. The processor can be implemented by hardware or by software. When implemented in hardware, the processor may be a logic circuit, an integrated circuit, or the like. When implemented in software, the processor may be a general-purpose processor implemented by reading software codes stored in memory. Optionally, there may also be one or more memories in the chip system. The memory may be integrated with the processor, or may be provided separately from the processor, which is not limited in this application. Exemplarily, the memory can be a non-transitory processor, such as a read-only memory ROM, which can be integrated with the processor on the same chip, or can be provided on different chips. The setting method of the processor is not particularly limited. For example, the chip system may be a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on chip (SoC), or a system on chip (SoC). It can be CPU, NP, digital signal processing circuit (digital signal processor, DSP), microcontroller unit (MCU), programmable logic device (programmable logic device, PLD) or other integrated chips.

An embodiment of the present application provides a system, where the system includes the foregoing apparatus 400 or the foregoing network device 500 .

All the above-mentioned optional technical solutions can be combined arbitrarily to form optional embodiments of the present disclosure, which will not be repeated here. Those of ordinary skill in the art can understand that all or part of the steps of implementing the above embodiments can be completed by hardware, or can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. The storage medium mentioned may be a read-only memory, a magnetic disk or an optical disk, etc. The above are only optional embodiments of the present application, and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the protection of the present application. within the range.

Claims

A path weight allocation method, characterized in that, applied to an entry node, the method comprising:

acquiring transmission characteristics of the first forwarding path, where the transmission characteristics of the first forwarding path are used to indicate the transmission characteristics of the first forwarding path when transmitting segment-based routing SR packets;

Based on the transmission characteristics of the first forwarding path, a first target weight is allocated to the first forwarding path, where the first target weight is used to indicate a load sharing state of the first forwarding path.
The method according to claim 1, wherein the transmission characteristics include index values of N types of transmission indicators, where N is an integer greater than or equal to 1, and any transmission index is used to represent a transmission performance index .
The method according to claim 2, wherein the assigning the first target weight to the first forwarding path based on the transmission characteristics of the first forwarding path comprises:

Based on the service level agreement SLA of the target service, assign the i-th weight to the i-th transmission indicator among the N-type transmission indicators, and the i-th weight of the i-th transmission indicator is used to represent the i-th transmission indicator pair The importance of the target business, the i is an integer greater than or equal to 1 and less than or equal to N;

The first target weight is obtained based on a weight corresponding to each of the N types of transmission indicators and an indicator value of each of the transmission indicators.
The method according to claim 2, wherein the assigning the first target weight to the first forwarding path based on the transmission characteristics of the first forwarding path comprises:

For the i-th transmission indicator among the N types of transmission indicators, the i-th weight is assigned to the indicator value of the i-th transmission indicator of the first forwarding path, and the i-th weight of the indicator value of the i-th transmission indicator is It is used to indicate the pros and cons of the first forwarding path relative to the k forwarding paths under the i-th transmission index, where i is an integer greater than or equal to 1 and less than or equal to N, and k is greater than or equal to 1 the integer;

The first target weight is determined based on the weight of the index value of each transmission index of the first forwarding path in the N kinds of transmission indexes.
The method according to claim 4, wherein the assigning the i-th weight to the indicator value of the i-th transmission indicator of the first forwarding path comprises:

Sorting the index values of the i-th transmission index in the transmission characteristics of the k forwarding paths, to obtain an index value sequence corresponding to the i-th transmission index;

Based on the ranking of the index values of the i-th transmission index of the first forwarding path in the index value sequence, the i-th weight of the index value of the i-th transmission index of the first forwarding path is obtained.
The method according to claim 2, wherein the assigning the first target weight to the first forwarding path based on the transmission characteristics of the first forwarding path comprises:

Determine the first target weight based on the weight corresponding to each transmission index in the N kinds of transmission indicators, and the weight of the index value of the each transmission index of the first forwarding path;

Wherein, the weight corresponding to any one of the transmission indicators is used to represent the importance of the any one of the transmission indicators to the target service, and the weight of the indicator value of the any one of the transmission indicators of the first forwarding path is used to represent the The degree of pros and cons of the first forwarding path relative to the k forwarding paths under any of the transmission indicators, where k is an integer greater than or equal to 1.
The method according to any one of claims 2-6, wherein the first forwarding path belongs to a first candidate forwarding path; the method further comprises:

For the i-th transmission indicator among the N types of transmission indicators, based on the indicator value of the i-th transmission indicator of the first forwarding path, assign the i-th transmission indicator to the first forwarding path The second target weight of the first forwarding path under the i-th transmission indicator is used to indicate that the first forwarding path is relative to m candidates under the i-th transmission indicator The pros and cons of each forwarding path in the path, the i is an integer greater than or equal to 1 and less than or equal to N, and the m is an integer greater than or equal to 1;

The third target weight of the first candidate forwarding path is determined based on the second target weight of the first forwarding path relative to the m candidate paths under each of the N kinds of transmission metrics, and the The third target weight is used to indicate the priority of the first candidate forwarding path among the m candidate forwarding paths.
The method according to any one of claims 1-7, wherein before the first target weight is assigned to the first forwarding path based on the transmission characteristics of the first forwarding path, the method Also includes:

Based on the transmission characteristics of the first forwarding path, it is determined that the first forwarding path satisfies the SLA of the target service.
The method according to any one of claims 1-8, wherein the acquiring the transmission characteristic of the first forwarding path comprises at least one of the following:

When the transmission characteristic includes a transmission time delay, the time length for transmitting a test packet to the egress node through the first forwarding path is determined as the transmission delay;

When the transmission characteristic includes a transmission jitter value, obtain the transmission jitter value based on the transmission delay determined by two adjacent test packets;

When the transmission characteristic includes a packet loss rate, the packet loss rate is determined based on the number of target transmissions and the number of target receptions, and the target number of transmissions is within a time window, and the entry node passes the A forwarding path sends the total number of the test packets to the egress node, and the target received number is the number of the test packets received by the egress node through the first forwarding path within the time window by the ingress node The total number of the test packets sent.
The method according to claim 9, wherein the test packet includes a segment list identifier of the first forwarding path, a candidate identifier of the first forwarding path, and the test packet sent by the ingress node at least one of the sending time and the identifier of the time window.
The method according to claim 9 or 10, wherein the test message is a seamless bidirectional forwarding check SBFD message, a bidirectional active measurement protocol TWAMP message, or an iFIT message with a path.
A path weight allocation device, characterized in that the device comprises:

an acquisition module, configured to acquire the transmission characteristics of the first forwarding path, where the transmission characteristics of the first forwarding path are used to indicate the transmission characteristics of the first forwarding path when transmitting the segment routing-based SR message;

an allocation module, configured to allocate a first target weight to the first forwarding path based on the transmission characteristics of the first forwarding path, where the first target weight is used to indicate a load sharing state of the first forwarding path.
The device according to claim 12, wherein the transmission characteristic includes index values of N kinds of transmission indexes, where N is an integer greater than or equal to 1, and any transmission index is used to represent a transmission performance index .
The apparatus according to claim 13, wherein the distribution module is used for:

Based on the service level agreement SLA of the target service, assign the i-th weight to the i-th transmission indicator among the N-type transmission indicators, and the i-th weight of the i-th transmission indicator is used to represent the i-th transmission indicator pair The importance of the target business, the i is an integer greater than or equal to 1 and less than or equal to N;

The first target weight is obtained based on a weight corresponding to each of the N types of transmission indicators and an indicator value of each of the transmission indicators.
The apparatus of claim 13, wherein the distribution module comprises:

a first allocating unit, configured to assign the i-th weight to the index value of the i-th transmission indicator of the first forwarding path for the i-th transmission indicator among the N types of transmission indicators, and the i-th transmission indicator The ith weight of the index value is used to indicate the degree of pros and cons of the first forwarding path relative to the k forwarding paths under the ith transmission index, where i is an integer greater than or equal to 1 and less than or equal to N, The k is an integer greater than or equal to 1;

A first determining unit, configured to determine the first target weight based on the weight of the index value of each transmission index among the N kinds of transmission indexes of the first forwarding path.
The apparatus according to claim 15, wherein the first distribution unit is used for:

Sorting the index values of the i-th transmission index in the transmission characteristics of the k forwarding paths, to obtain an index value sequence corresponding to the i-th transmission index;

Based on the ranking of the index values of the i-th transmission index of the first forwarding path in the index value sequence, the i-th weight of the index value of the i-th transmission index of the first forwarding path is obtained.
The apparatus according to claim 13, wherein the distribution module is used for:

determining the first target weight based on the weight corresponding to each transmission indicator in the N types of transmission indicators, and the weight of the indicator value of the each transmission indicator of the first forwarding path;

Wherein, the weight corresponding to any one of the transmission indicators is used to represent the importance of the any one of the transmission indicators to the target service, and the weight of the indicator value of the any one of the transmission indicators of the first forwarding path is used to represent the The degree of pros and cons of the first forwarding path relative to the k forwarding paths under any of the transmission indicators, where k is an integer greater than or equal to 1.
The device according to any one of claims 12-17, wherein the distribution module comprises:

a second allocating unit, configured to, for the i-th transmission indicator among the N types of transmission indicators, allocate the first forwarding path to the first forwarding path based on the indicator value of the i-th transmission indicator of the first forwarding path The second target weight under the i-th transmission indicator, and the second target weight of the first forwarding path under the i-th transmission indicator is used to indicate that the first forwarding path is in the i-th transmission Under the indicator, relative to the pros and cons of each forwarding path among the m candidate paths, the i is an integer greater than or equal to 1 and less than or equal to N, and the m is an integer greater than or equal to 1;

a second determining unit, configured to determine the first candidate forwarding path based on a second target weight of the first forwarding path relative to the m candidate paths under each of the N types of transmission metrics The third target weight is used to indicate the priority of the first candidate forwarding path among the m candidate forwarding paths.
The device according to any one of claims 12-17, wherein the device further comprises:

A determining module, configured to determine that the first forwarding path satisfies the SLA of the target service based on the transmission characteristics of the first forwarding path.
The device according to any one of claims 12-19, wherein the obtaining module is configured to execute at least one of the following:

When the transmission characteristic includes a transmission time delay, the time length for transmitting a test packet to the egress node through the first forwarding path is determined as the transmission delay;

When the transmission characteristic includes a transmission jitter value, obtain the transmission jitter value based on the transmission delay determined by two adjacent test packets;

When the transmission characteristic includes a packet loss rate, the packet loss rate is determined based on the number of target transmissions and the number of target receptions, and the target number of transmissions is within a time window, and the entry node passes the The total number of test packets sent by a forwarding path to the egress node, and the target received number is the number of test packets received by the egress node and sent by the ingress node through the forwarding path within the time window. The total number of the test packets.
The apparatus according to claim 20, wherein the test packet includes a segment list identifier of the first forwarding path, a candidate identifier of the first forwarding path, and the test packet sent by the ingress node at least one of the sending time and the identifier of the time window.
The apparatus according to claim 20 or 21, wherein the test message is a seamless bidirectional forwarding check SBFD message, a bidirectional active measurement protocol TWAMP message, or an iFIT message with a path.