Packet forwarding method, network node, and storage medium

Abstract

The present application provides a packet forwarding method, a network node, and a storage medium. The packet forwarding method applied to a first network node comprises: configuring an end-side shaping latency budget for a target service flow accessed from a source client (S110); on the basis of the end-side shaping latency budget and a head node shaping latency of each packet in the target service flow, determining a tail node damping latency budget of the corresponding packet (S120), wherein the target service flow comprises one or more packets; and sending each packet in the target service flow to a second network node on the basis of a predetermined target path, so that the second network node forwards the corresponding packet in the target service flow to a destination client on the basis of the tail node damping latency budget (S130).

Description

Message forwarding method, network node and storage medium Technical Field

[0001] The present application relates to the field of communication technology, for example, to a message forwarding method, a network node and a storage medium. Background Art

[0002] In a deterministic network architecture, the Quality of Service (QoS) objectives for deterministic service forwarding include: minimum and maximum latency from source to destination, bounded latency jitter, a permissible packet loss rate, and an upper bound on out-of-order packet delivery. To achieve these goals, deterministic networks employ resource reservation, explicit routing, and service protection. Resource reservation refers to the exclusive or shared allocation of resources, such as physical links, link bandwidth, and queue resources, by service traffic. Explicit routing involves pre-selecting the network transmission path for service flows to ensure routing stability and invariance to real-time changes in the network topology. This allows for the precise calculation of end-to-end latency and jitter bounds. Service protection involves sending multiple service flows simultaneously along multiple, non-intersecting paths to reduce packet loss. Generally, a deterministic path is a strictly explicit path calculated by a centralized controller, with resources reserved at nodes along the path to meet the Service Level Agreement (SLA) requirements of the deterministic service.

[0003] In order to meet the QoS goals of the above-mentioned deterministic services, the following three packet scheduling mechanisms are proposed: Packet Timeslot scheduling mechanism, Deadline scheduling mechanism and multi-CQF (multi-Cyclic Queuing and Forwarding) scheduling mechanism.

[0004] However, these scheduling mechanisms only guarantee the latency and jitter performance of the transmission paths within the network. They fail to consider the shaping delays caused by traffic policing when network ingress nodes receive service flows. Traffic policing involves the network ingress node limiting and shaping incoming service flows so that they conform to the service's traffic specification (TSpec). If the shaping delays caused by traffic policing are not addressed, some packets within the same service flow may experience less shaping delay, while others may experience more. This results in significant delay jitter and does not meet the requirements of deterministic services.

[0005] Summary of the Invention

[0006] In view of this, an embodiment of the present application provides a message forwarding method, a network node and a storage medium, so that each message in the target service flow can eliminate delay jitter on the end side, thereby ensuring the business requirements of deterministic services.

[0007] An embodiment of the present application provides a message forwarding method, applied to a first network node, comprising:

[0008] Configure the end-side shaping delay budget for the target service flow accessed from the source client.

[0009] Determining a tail node damping delay budget for a corresponding message based on the end-side shaping delay budget and the head node shaping delay of each message in the target service flow; wherein the target service flow includes one or more messages;

[0010] Each message in the target service flow is sent to the second network node according to a predetermined target path, so that the second network node forwards the corresponding message in the target service flow to the destination client according to the tail node damping delay budget.

[0011] An embodiment of the present application provides a message forwarding method, applied to a second network node, including:

[0012] Receiving a target service flow sent by a first network node according to a predetermined target path; wherein the target path is determined according to an end-to-end delay requirement of the target service flow and a path delay requirement determined by an end-side shaping delay budget;

[0013] The corresponding message is forwarded to the destination client according to the tail node damping delay budget of each message in the target service flow; wherein the target service flow includes one or more messages.

[0014] An embodiment of the present application provides a first network node, comprising: a memory, and one or more processors;

[0015] The memory is configured to store one or more programs;

[0016] When the one or more programs are executed by the one or more processors, the one or more processors implement the message forwarding method as described in any of the above embodiments.

[0017] An embodiment of the present application provides a second network node, comprising: a memory, and one or more processors;

[0018] The memory is configured to store one or more programs;

[0019] When the one or more programs are executed by the one or more processors, the one or more processors implement the message forwarding method described in any of the above embodiments.

[0020] An embodiment of the present application provides a storage medium storing a computer program. When the computer program is executed by a processor, the message forwarding method described in any of the above embodiments is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] FIG1 is a flow chart of a message forwarding method provided in an embodiment of the present application;

[0022] FIG2 is a flow chart of another message forwarding method provided in an embodiment of the present application;

[0023] FIG3 is a schematic diagram showing the relationship between various delay parameters in a deterministic network provided by an embodiment of the present application;

[0024] FIG4 is a schematic diagram of a configuration of a message header provided in an embodiment of the present application;

[0025] FIG5 is a schematic diagram of another configuration of a message header provided in an embodiment of the present application;

[0026] FIG6 is a schematic diagram of an implementation of message forwarding provided in an embodiment of the present application;

[0027] FIG7 is a structural block diagram of a message forwarding device provided in an embodiment of the present application;

[0028] FIG8 is a structural block diagram of another message forwarding device provided in an embodiment of the present application;

[0029] FIG9 is a schematic diagram of the structure of a network node provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] The following describes the embodiments of the present application in conjunction with the accompanying drawings. The following describes the present application in conjunction with the accompanying drawings. The examples are only used to explain the present application and are not used to limit the scope of the present application.

[0031] In order to solve the problem in related technical solutions that for the same business flow, some packets face less shaping delay, while some face more shaping delay, resulting in large delay jitter, which does not meet the deterministic business requirements.

[0032] In view of this, the present application proposes a message forwarding method, which configures an end-side shaping delay budget for the target business flow, and the end-side shaping delay budget is shared by the network ingress node (i.e., the head node of the deterministic path) and the network egress node (i.e., the tail node of the deterministic path). The end-to-end delay requirement of the target business flow is subtracted from the end-side shaping delay budget to obtain the path delay requirement of the deterministic path, and then the path that meets the path delay requirement is calculated in the network as the target path. The target path is used to provide bearer service for the target business flow. When the head node sends the target business flow, it carries the end-side shaping delay budget and the head node shaping delay in the encapsulated message header, or directly carries the tail node damping delay budget. The tail node obtains the tail node damping delay budget from the message header, and delays the delivery of the message to the destination client accordingly.

[0033] By excluding the head node shaping delay of the service flow during path calculation and carrying the tail node damping delay budget during forwarding, the target service flow can effectively eliminate delay jitter on the end side, which is very beneficial for meeting the needs of deterministic services. The embodiments of the present application can be applied to scenarios such as IP-based radio access networks (IPRAN) / slicing packet networks (SPN), metropolitan area networks / backbones, etc.

[0034] In one embodiment, Figure 1 is a flowchart of a message forwarding method provided by an embodiment of the present application. This embodiment is applied to eliminate latency jitter on the end side of a deterministic service flow. This embodiment can be executed by a first network node. In this example, the first network node can be the head node of a deterministic path. As shown in Figure 1, this embodiment includes: S110-S130.

[0035] S110: Configure a terminal-side shaping delay budget for a target service flow accessed from a source client.

[0036] The source client refers to the client that provides service flows to the deterministic network. In other words, the deterministic network provides deterministic forwarding services for the target service flows accessed from the source client. In this embodiment, the edge-side shaping delay budget is shared by the ingress node (i.e., the head node of the deterministic path) and the egress node (i.e., the tail node of the deterministic path) in the deterministic network.

[0037] S120 : Determine a tail node damping delay budget for the corresponding message based on the end-side shaping delay budget and the head node shaping delay of each message in the target service flow.

[0038] Among them, the head node shaping delay refers to the actual shaping delay caused by traffic supervision of the target business flow at the head node. The target business flow may include one or more packets, and the head node shaping delay of each two packets may be different, and the damping delay calculation of each two tail nodes may be different, but the end-side shaping delay budget of each packet in the same target business flow is the same. The maximum shaping delay faced by different target business flows at the head node may be different, which is related to the traffic specification of the target business flow, the actual arrival curve, and the shaping parameters configured by the head node for the target business flow. Similarly, the end-side shaping delay budget of different target business flows may also be different, which is related to the traffic specification of the target business flow, the actual arrival curve, and the shaping parameters configured by the head node for the target business flow.

[0039] In the embodiment, the tail node damping delay budget of the corresponding message may be obtained by subtracting the head node shaping delay from the end-side shaping delay budget.

[0040] S130: Send each packet in the target service flow to the second network node according to a predetermined target path, so that the second network node forwards the corresponding packet in the target service flow to the destination client according to the tail node damping delay budget.

[0041] The second network node may be the tail node of the deterministic path; the destination client refers to the receiving end of the target service flow; and the target path refers to the deterministic path used to transmit the target service flow. In this embodiment, after determining the target path of the target service flow, the first network node sends each packet in the target service flow to the second network node along the target path, so that the second network node forwards the corresponding packet to the destination client according to the tail node damping delay budget. This ensures that packets in the target service flow with different head node delay shaping arrive at the destination client at the same time as much as possible, eliminating delay jitter of the target service flow on the end side.

[0042] In one embodiment, a message forwarding method applied to a first network node further includes: determining a path delay requirement for a target service flow based on the end-to-end delay requirement and the end-side shaping delay budget of the target service flow; and determining a target path for the target service flow based on the path delay requirement. In this embodiment, the path delay requirement of a deterministic path used to carry the target service flow is determined based on the end-to-end delay requirement and the end-side shaping delay budget of the target service flow. The end-to-end delay requirement can be subtracted from the end-to-end shaping delay budget to obtain the path delay requirement of the deterministic path. A path that meets the path delay requirement is then calculated in the network as a target path, and the target path is used to provide transmission services for the target service flow.

[0043] In one embodiment, a message forwarding method applied to a first network node further includes: obtaining the actual path delay of each message in a target service flow on a target path; determining a delay deviation value for the corresponding message based on the path delay requirement and the actual path delay; and sending the delay deviation value to a second network node. When the target service flow is transmitted along the target path, different scheduling mechanisms may be employed for message forwarding. Accordingly, when different scheduling mechanisms are employed, a delay deviation value may occur, i.e., the deviation between the actual path delay and the path delay requirement when the message arrives at the tail node. The corresponding delay deviation value can be obtained by subtracting the actual path delay from the path delay requirement of the target path. For example, when the target path employs the deadline scheduling mechanism, a delay deviation value may also appear in the message. In this case, the delay deviation value can be sent to the second network node so that the second network node can forward the corresponding message in the target service flow to the destination client according to the sum of the delay deviation value and the tail node damping delay budget, thereby ensuring that the deviation between the end-to-end service delay requirement and the actual end-to-end service delay is zero, thereby achieving zero-delay jitter service delivery.

[0044] In one embodiment, the packet header encapsulating the target service flow carries the end-side shaping delay budget and the corresponding packet's head node shaping delay; alternatively, the packet header encapsulating the target service flow carries the corresponding packet's tail node damping delay budget. Upon receiving the target service flow from the source client, the first network node on the target path encapsulates the target service flow with the end-side shaping delay budget and the corresponding packet's head node shaping delay in the packet header, or directly carries the corresponding packet's tail node damping delay budget, and then forwards the corresponding packet along the target path to the second network node.

[0045] In one embodiment, the header of the packet encapsulating the target service flow also carries the delay deviation value of the corresponding packet. During the forwarding process of the target service flow, if the delay deviation value occurs, the first network node also sends the delay deviation value to the second network node via the packet header of the corresponding packet in the target service flow.

[0046] In one embodiment, the end-side shaping delay budget is greater than or equal to the maximum head node shaping delay corresponding to the target service flow. In this embodiment, the end-side shaping delay budget is shared by the head node and the tail node, that is, the sum of the head node shaping delay and the tail node damping delay budget. To ensure the accuracy of the path delay requirements of the deterministic path of the target service flow, the end-side shaping delay budget configured for the target service flow is greater than or equal to the maximum head node shaping delay corresponding to all packets in the target service flow.

[0047] In one embodiment, Figure 2 is a flowchart of another message forwarding method provided by an embodiment of the present application. This embodiment is applied to eliminate latency jitter of a deterministic service flow on the end side. This embodiment can be executed by a second network node. As shown in Figure 2, this embodiment includes: S210-S220.

[0048] S210: Receive a target service flow sent by a first network node according to a predetermined target path.

[0049] The target path is determined based on the end-to-end delay requirement of the target service flow and the path delay requirement determined by the end-side shaping delay budget.

[0050] S220 : Forward the corresponding message to the destination client according to the tail node damping delay budget of each message in the target service flow.

[0051] In an embodiment, after the second network node receives the target service flow sent by the first network node according to the predetermined target path, the second network node forwards the corresponding message to the destination client according to the tail node damping delay budget of each message in the target service flow.

[0052] In one embodiment, when a packet header encapsulating a target service flow carries an end-side shaping delay budget and a head node shaping delay of the corresponding packet, the packet forwarding method applied to the second network node further includes: determining an end node damping delay budget for the corresponding packet in the target service flow based on the end-side shaping delay budget and the head node shaping delay. When a packet encapsulating the target service flow carries the end-side shaping delay budget and the head node shaping delay of the corresponding packet, the second network node needs to calculate the end node damping delay budget for the corresponding packet based on the end-side shaping delay budget and the head node shaping delay.

[0053] In one embodiment, a buffer or queue is created for the target service flow on the second network node, and the target service flow is temporarily stored in the buffer or queue. In this embodiment, the second network node needs to forward the corresponding message to the destination client based on the tail node damping delay budget of the message in the target service flow. That is, at least part of the message in the target service flow needs to be temporarily stored in the second network node until it reaches the tail node damping delay budget. To this end, the second network node needs to create a buffer or queue for the target service flow so that the target service flow waits in the buffer or queue for the time required by the tail node damping delay budget before being sent to the destination client.

[0054] In one embodiment, the message forwarding method applied to the second network node further includes: receiving a delay deviation value sent by the first network node; wherein the delay deviation value is determined based on the path delay requirement and the actual path delay of the corresponding message in the target service flow; and forwarding the corresponding message to the destination client according to the delay deviation value and the tail node damping delay budget of each message in the target service flow. In an embodiment, the second network node is able to obtain the delay deviation value of the message in the target service flow on the target path. The second network node can use the sum of the tail node damping delay budget and the delay deviation value of the target path as the waiting time of the target service flow in the buffer or queue, and then send it to the destination client, so that the deviation between the end-to-end delay requirement and the end-to-end actual delay of the target service flow is 0, thereby achieving zero-delay jitter service delivery.

[0055] In one embodiment, message forwarding of a target service flow from a source client to a destination client includes three processes: calculating a deterministic path for the target service flow; a head node sending processing related to the target service flow; and a tail node receiving processing related to the target service flow.

[0056] The first process is to calculate a deterministic path for the target service flow, which includes the following implementation processes:

[0057] First, configure an edge-side shaping delay budget for the target service flow. This delay budget is shared between the deterministic network ingress node (i.e., the head node of the deterministic path) and the deterministic network egress node (i.e., the tail node of the deterministic path). The following applies: Edge-side shaping delay budget = head node shaping delay + tail node damping delay budget.

[0058] The headnode shaping delay is the actual shaping delay incurred when policing the target service flow at the headnode. The tailnode damping delay budget can be obtained by subtracting the headnode shaping delay from the edge-side shaping delay budget.

[0059] Note that the edge-side shaping delay budget configured for a target service flow cannot be less than the maximum possible headnode shaping delay. Also note that different target service flows may experience different maximum headnode shaping delays at the headnode. This is related to the target service flow's own traffic specification (TSpec), the actual arrival curve, and the shaping parameters configured for the target service flow at the headnode.

[0060] Then, based on the end-to-end delay requirement of the target service flow and the end-side shaping delay budget, the delay requirement of the deterministic path used to carry the target service flow is determined. That is, the path delay requirement is equal to the difference between the end-to-end delay requirement of the service flow and the end-side shaping delay budget.

[0061] A deterministic path that meets the path delay requirements is calculated in the network as the target path, and the target path is used to provide transmission services for the target business flow.

[0062] Figure 3 is a schematic diagram illustrating the relationship between various delay parameters in a deterministic network provided by an embodiment of the present application. As shown in Figure 3, the source client is CE1, the destination client is CE2, the first network node is PE1, and the second network node is PE2. The end-to-end service delay requirement is the sum of the end-side shaping delay budget and the path delay requirement. The end-side shaping delay budget is the sum of the head node shaping delay and the tail node damping delay budget.

[0063] In addition, the process of calculating the target path based on the path delay requirement depends on the message scheduling mechanism used by each network node in the deterministic network. Different message scheduling mechanisms correspond to different deterministic path calculation processes. In the embodiments of this application, the calculation process of the target path corresponding to several typical message scheduling mechanisms is briefly described as follows:

[0064] The first method uses the Packet Timeslot scheduling mechanism. For any candidate path, the path delay requirement is subtracted from the sum of the propagation delays of all links on the candidate path to obtain the total residence delay budget for all nodes on the candidate path. Outbound time slots are then reserved on each link on the candidate path so that the sum of the residence delay estimates generated at all nodes matches the total residence delay budget.

[0065] The second method: When using the deadline scheduling mechanism, for any candidate path, the path delay requirement is subtracted from the sum of the propagation delays of all links in the candidate path to obtain the total residence delay budget for all nodes in the candidate path. This is then divided by the number of hops in the path to obtain the planned residence time for each node. Delay resources of a delay level corresponding to the planned residence time are then reserved on each link in the candidate path.

[0066] The third method: When using the multi-CQF scheduling mechanism, for any candidate path, the path delay requirement is subtracted from the sum of the propagation delays of all links on the candidate path to obtain the total residence delay budget for all nodes on the candidate path. The appropriate cycle level is then selected and bandwidth resources at that cycle level are reserved so that the sum of the residence delay evaluation values ​​generated at all nodes matches the total residence delay budget.

[0067] The second process is the processing related to sending the target business flow by the head node, which includes the following implementation processes:

[0068] When the head node of the target path receives the target service flow from the source client, it carries the end-side shaping delay budget and the head node shaping delay in the packet header encapsulating the target service flow, or directly carries the tail node damping delay budget, and then sends the packet along the target path to the tail node.

[0069] Figure 4 is a schematic diagram of a packet header configuration provided by an embodiment of the present application. As shown in Figure 4, the packet header (i.e., the packet header) carries the end-side shaping delay budget and the head node shaping delay.

[0070] Figure 5 is a schematic diagram of another packet header configuration provided by an embodiment of the present application. As shown in Figure 5, the tail node damping delay budget is directly carried in the packet header (ie, Packet Header).

[0071] The packet header may be any L2 or L3 packet header, such as an Ethernet header, an IPv4 header, an IPv6 header, or an MPLS header.

[0072] Of course, the head node also carries metadata related to the scheduling mechanism used by the target path in the encapsulated message header to guide the message to use the corresponding scheduling mechanism on each node and access deterministic forwarding resources.

[0073] The third process is the processing related to the tail node receiving the target service flow, which includes the following implementation process:

[0074] After the egress node on the target path receives a packet, it obtains the egress node damping delay budget for the packet from the packet header. If the received packet header contains both the edge-side shaping delay budget and the headend shaping delay, the egress node damping delay budget is calculated as the difference between the edge-side shaping delay budget and the headend shaping delay.

[0075] The egress node delays delivery of packets to the destination client based on the egress node's damping delay budget. To do this, the egress node establishes a buffer or queue for the target traffic flow, allowing the traffic flow to wait in the buffer or queue for the required amount of time before being sent to the destination client.

[0076] Optionally, if the egress node can obtain the delay deviation value of the message on the target path (for example, when the target path uses the deadline scheduling mechanism, the message will also carry the delay deviation value, which reflects the deviation between the actual path delay and the path delay requirement when the message reaches the egress node, that is, the difference between the path delay requirement and the actual path delay), the egress node can use the sum of the egress node damping delay budget and the target path delay deviation value as the waiting time of the service flow in the buffer or queue, and then send it to the destination client. This can make the deviation between the end-to-end delay requirement and the end-to-end actual delay of the target service flow zero, achieving zero-delay jitter service delivery. However, not all scheduling mechanisms carry the delay deviation value in the forwarded message, so this operation is optional.

[0077] Figure 6 is a schematic diagram of an implementation of message forwarding provided by an embodiment of the present application. As shown in Figure 6, on the ingress node PE1 of the deterministic network, a deterministic forwarding service is provided for the target service flow accessed from the source client CE1, the destination client is CE2, and the egress node of the deterministic forwarding path is PE2. The traffic specification (TSpec) of the target service flow has a periodic characteristic. Assuming that its service burst interval (Service Burst Interval) is 100us, it will periodically send three messages p1, p2, and p3 every 100us (for simplicity, it is assumed that there are 3 messages of equal length, each of 1000 bits). It can be seen that the bandwidth resources required for the target service flow are 30M bps.

[0078] Assume that the ingress node PE1 of the network configures leaky bucket shaping parameters for the target service flow, with a bucket depth of 1000 bits and a bucket rate of 30 Mbps.

[0079] Assume that the arrival curve of the target traffic flow at ingress node PE1 is as shown in Figure 6, with p1, p2, and p3 closely spaced. After leaky bucket shaping, p1, p2, and p3 face shaping delays of shaping_delay_1, shaping_delay_2, and shaping_delay_3, respectively. P1 faces shaping_delay_1, which is 0 because the leaky bucket is full when p1 arrives at ingress node PE1. However, shaping_delay_2 and shaping_delay_3 face non-zero delays, meaning they must wait for sufficient tokens to accumulate in the leaky bucket before they can be sent. Assume shaping_delay_2 is 28µs and shaping_delay_3 is 51µs. After shaping, p1, p2, and p3 are evenly distributed within the traffic burst interval.

[0080] Assuming the arrival curve of the target service flow on ingress node PE1 is stable, shaping_delay_3 is the maximum headend shaping delay the target service flow can experience. In this case, configure the edge-side shaping delay budget edge_shaping_delay_budgt to shaping_delay_3.

[0081] Then the tail node damping delay budget damping_delay_1 of p1 is shaping_delay_3=51 us, the tail node damping delay budget damping_delay_2 of p2 is shaping_delay_3-shaping_delay_2=23 us, and the tail node damping delay budget damping_delay_3 of p3 is 0.

[0082] When the target service flow is encapsulated at the network ingress node PE1 and sent along the deterministic forwarding path, the encapsulated packet header can carry the edge-side shaping delay budget and the head node shaping delay, or directly carry the egress node damping delay budget. For example, the packet header encapsulated for packet p1 can carry the edge-side shaping delay budget (i.e., 51) and the head node shaping delay (i.e., 0), or directly carry the egress node damping delay budget (i.e., 51); the packet header encapsulated for packet p2 can carry the edge-side shaping delay budget (i.e., 51) and the head node shaping delay (i.e., 28), or directly carry the egress node damping delay budget (i.e., 23); the packet header encapsulated for packet p3 can carry the edge-side shaping delay budget (i.e., 51) and the head node shaping delay (i.e., 51), or directly carry the egress node damping delay budget (i.e., 0).

[0083] Assuming the deterministic forwarding path employs a scheduling mechanism that guarantees delay jitter (e.g., Multi-CQF, Deadline, or Packet Timeslot), at the egress node PE2 of the deterministic forwarding path, the distribution of packets of the target service flow leaving the corresponding scheduler within the service burst interval will remain somewhat consistent with the shaping results at the ingress node PE1 (for example, the Deadline scheduler maintains consistency based on the perceived delay deviation, while Multi-CQF or Packet Timeslot introduces jitter related to the cyle length or slot length). Regardless, egress node PE2 can obtain the tail node damping delay budget from the packet header and wait the packet in the buffer or queue for an additional amount of time based on the tail node damping delay budget before sending it to the destination client CE2. Alternatively, egress node PE2 can combine the delay deviation (if any) provided by the scheduling mechanism and the tail node damping delay budget into a single step, waiting in the buffer or queue for the combined duration before sending the packet to the destination client CE2.

[0084] In one embodiment, FIG7 is a block diagram of a message forwarding device provided in an embodiment of the present application. This embodiment is applied to a first network node. As shown in FIG7 , the message forwarding device in this embodiment includes: a configuration module 710, a determination module 720, and a sending module 730.

[0085] The configuration module 710 is configured to configure a terminal-side shaping delay budget for a target service flow accessed from a source client.

[0086] The determination module 720 is configured to determine the tail node damping delay budget of the corresponding message according to the end-side shaping delay budget and the head node shaping delay of each message in the target service flow.

[0087] The sending module 730 is configured to send each message in the target service flow to the second network node according to the predetermined target path, so that the second network node forwards the corresponding message in the target service flow to the destination client according to the tail node damping delay budget.

[0088] In one embodiment, the message forwarding device applied to the first network node further includes:

[0089] The determination module is further configured to determine the path delay requirement of the target service flow based on the end-to-end delay requirement of the target service flow and the end-side shaping delay budget;

[0090] The determination module is further configured to determine the target path of the target service flow based on the path delay requirement.

[0091] In one embodiment, the message forwarding device applied to the first network node further includes:

[0092] an acquisition module configured to acquire an actual path delay of each packet in a target service flow on a target path;

[0093] The determination module is further configured to determine a delay deviation value of a corresponding message based on a path delay requirement and an actual path delay;

[0094] The sending module is further configured to send the delay deviation value to the second network node.

[0095] In one embodiment, the packet header encapsulating the target service flow carries the end-side shaping delay budget and the head node shaping delay of the corresponding packet; or, the packet header of the target service flow carries the tail node damping delay budget of the corresponding packet.

[0096] In one embodiment, the message header encapsulating the target service flow also carries the delay deviation value of the corresponding message.

[0097] In one embodiment, the edge-side shaping delay budget is greater than or equal to the maximum head node shaping delay corresponding to the target service flow.

[0098] The message forwarding device provided in this embodiment is configured to implement the message forwarding method applied to the first network node of the embodiment shown in FIG1 . The implementation principle and technical effects of the message forwarding device provided in this embodiment are similar and will not be described in detail here.

[0099] In one embodiment, FIG8 is a block diagram of another message forwarding device provided in an embodiment of the present application. This embodiment can be executed by a second network node. As shown in FIG8 , the message forwarding device in this embodiment includes: a receiving module 810 and a forwarding module 820.

[0100] The receiving module 810 is configured to receive a target service flow sent by the first network node according to a predetermined target path; wherein the target path is determined according to the end-to-end delay requirement of the target service flow and the path delay requirement determined by the end-side shaping delay budget.

[0101] The forwarding module 820 is configured to forward the corresponding message to the destination client according to the tail node damping delay budget of each message in the target service flow.

[0102] In one embodiment, when the packet header encapsulating the target service flow carries the end-side shaping delay budget and the head node shaping delay of the corresponding packet, the packet forwarding device applied to the second network node further includes:

[0103] The determination module is configured to determine the tail node damping delay budget of the corresponding message in the target service flow according to the end-side shaping delay budget and the head node shaping delay.

[0104] In one embodiment, a buffer or queue is created for the target service flow on the second network node, and the target service flow is temporarily stored in the buffer or queue.

[0105] In one embodiment, the message forwarding device applied to the second network node further includes:

[0106] The receiving module is further configured to receive a delay deviation value sent by the first network node; wherein the delay deviation value is determined based on the path delay requirement and the actual path delay of the corresponding message in the target service flow;

[0107] The forwarding module is further configured to forward the corresponding message to the destination client according to the delay deviation value and the tail node damping delay budget of each message in the target service flow.

[0108] The message forwarding device provided in this embodiment is configured to implement the message forwarding method applied to the second network node of the embodiment shown in FIG2 . The implementation principle and technical effects of the message forwarding device provided in this embodiment are similar and will not be described in detail here.

[0109] In one embodiment, Figure 9 is a schematic diagram of the structure of a network node provided by an embodiment of the present application. As shown in Figure 9, the network node provided by the present application (which may also be referred to as a communication device, network device or communication node) includes: a processor 910, a memory 920 and a communication interface 930. The number of processors 910 in the network node may be one or more, and Figure 9 takes one processor 910 as an example. The number of memories 920 in the network node may be one or more, and Figure 9 takes one memory 920 as an example. The processor 910, memory 920 and communication interface 930 of the network node may be connected via a bus or other means, and Figure 9 takes connection via a bus as an example. In this embodiment, the network node may be a first network node.

[0110] The memory 920, as a computer-readable storage medium, can be configured to store software programs, computer executable programs, and modules, such as program instructions / modules corresponding to the network nodes of any embodiment of the present application (for example, the configuration module 710, the determination module 720, and the sending module 730 in the message forwarding device). The memory 920 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created based on the use of the device, etc. In addition, the memory 920 may include a high-speed random access memory and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 920 may further include a memory remotely located relative to the processor 910, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof. Among them, the communication interface 930 is used to enable the first network node to establish a communication connection with other network nodes (for example, the second network node).

[0111] In the case where the network node is the first network node, the above-provided device can be configured to execute the message forwarding method applied to the first network node provided in any of the above-mentioned embodiments, and have corresponding functions and effects.

[0112] In the case where the network node is a second network node, the above-provided device may be configured to execute the message forwarding method applied to the second network node provided in any of the above-mentioned embodiments, and have corresponding functions and effects.

[0113] An embodiment of the present application also provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to execute a message forwarding method applied to a first network node, the method comprising: configuring an end-side shaping delay budget for a target service flow accessed from a source client; determining a tail node damping delay budget for the corresponding message based on the end-side shaping delay budget and the head node shaping delay of each message in the target service flow; and sending each message in the target service flow to a second network node according to a predetermined target path, so that the second network node forwards the corresponding message in the target service flow to the destination client according to the tail node damping delay budget.

[0114] An embodiment of the present application also provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to execute a message forwarding method applied to a second network node, the method comprising: receiving a target service flow sent by a first network node according to a predetermined target path; wherein the target path is determined based on the end-to-end delay requirement of the target service flow and the path delay requirement determined by the end-side shaping delay budget; and forwarding the corresponding message to the destination client according to the tail node damping delay budget of each message in the target service flow.

[0115] It will be appreciated by those skilled in the art that the term user equipment encompasses any suitable type of wireless user equipment, such as a mobile phone, a portable data processing device, a portable web browser or a car-mounted mobile station.

[0116] In general, various embodiments of the present application may be implemented in hardware or dedicated circuits, software, logic, or any combination thereof. For example, some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that can be executed by a controller, microprocessor, or other computing device, although the present application is not limited thereto.

[0117] Embodiments of the present application may be implemented by executing computer program instructions by a data processor of a mobile device, for example, in a processor entity, or by hardware, or by a combination of software and hardware. The computer program instructions may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages.

[0118] The block diagram of any logical flow in the drawings of the present application may represent program steps, or may represent interconnected logical circuits, modules and functions, or may represent a combination of program steps and logical circuits, modules and functions. A computer program may be stored on a memory. The memory may be of any type suitable for the local technical environment and may be implemented using any suitable data storage technology, such as, but not limited to, a read-only memory (ROM), a random access memory (RAM), an optical storage device and system (a digital versatile disc (DVD) or a compact disk (CD)). Computer-readable media may include non-transient storage media. A data processor may be of any type suitable for the local technical environment, such as, but not limited to, a general-purpose computer, a special-purpose computer, a microprocessor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), and a processor based on a multi-core processor architecture.

Claims

1. A message forwarding method, applied to a first network node, comprising: Configure the end-side shaping delay budget for the target service flow accessed from the source client; Determine the tail node damping delay budget of the corresponding message according to the end-side shaping delay budget and the head node shaping delay of each message in the target service flow; wherein the target service flow includes one or more messages; Each message in the target service flow is sent to the second network node according to a predetermined target path, so that the second network node forwards the corresponding message in the target service flow to the destination client according to the tail node damping delay budget.

2. The method according to claim 1, further comprising: Determining the path delay requirement of the target service flow according to the end-to-end delay requirement of the target service flow and the end-side shaping delay budget; A target path for the target service flow is determined based on the path delay requirement.

3. The method according to claim 2, further comprising: Obtaining an actual path delay of each message in the target service flow on the target path; Determine a delay deviation value of a corresponding message based on the path delay requirement and the path actual delay; The delay deviation value is sent to the second network node.

4. The method according to any one of claims 1 to 3, wherein: The end-side shaping delay budget and the head node shaping delay of the corresponding message are carried in the message header of each message in the target service flow encapsulation; or, the tail node damping delay budget of the corresponding message is carried in the message header of each message in the target service flow.

5. The method according to any one of claims 1 to 3, wherein: The message header of each message in the target service flow encapsulated also carries the delay deviation value of the corresponding message.

6. The method according to any one of claims 1 to 3, wherein: The end-side shaping delay budget is greater than or equal to the maximum head node shaping delay corresponding to the target service flow.

7. A message forwarding method, applied to a second network node, comprising: Receiving a target service flow sent by a first network node according to a predetermined target path; wherein the target path is determined according to the end-to-end delay requirement of the target service flow and the path delay requirement determined by the end-side shaping delay budget; The corresponding message is forwarded to the destination client according to the tail node damping delay budget of each message in the target service flow; wherein the target service flow includes one or more messages.

8. The method according to claim 7, in the case where the packet header encapsulating each packet in the target service flow carries the end-side shaping delay budget and the head node shaping delay of the corresponding packet, the method further comprises: Determine the tail node damping delay budget of the corresponding message in the target service flow according to the end-side shaping delay budget and the head node shaping delay.

9. The method according to claim 7, wherein: A buffer or a queue is created for the target service flow on the second network node, and the target service flow is temporarily stored in the buffer or the queue.

10. The method according to claim 7, further comprising: receiving a delay deviation value sent by the first network node; wherein the delay deviation value is based on the path delay requirement The actual path delay of the corresponding message in the target service flow is determined by summing up; The corresponding message is forwarded to the destination client according to the delay deviation value and the tail node damping delay budget of each message in the target service flow.

11. A first network node, comprising: memory, and one or more processors; The memory is configured to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the message forwarding method as described in any one of claims 1 to 6.

12. A second network node, comprising: memory, and one or more processors; The memory is configured to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the message forwarding method as described in any one of claims 7 to 10.

13. A storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the message forwarding method as described in any one of claims 1 to 6, or implements the message forwarding method as described in any one of claims 7 to 10.

Images